Leveraging AI chatbots in supporting breast and ovarian cancer patients: A scoping review

Abstract

Objective

Individuals who are at risk of or diagnosed with breast and ovarian cancer often face barriers in seeking help due to embarrassment, complex information needs, and limited access to timely support. Chatbots provide a private, non-judgmental communication interface that may help overcome these barriers. This scoping review systematically examines chatbot applications in breast and ovarian cancer care, focusing on their design, functionalities, evaluation outcomes, and implementation barriers and facilitators.

Methods

A comprehensive search was conducted through PubMed, Medline, Embase, CINAHL, Cochrane Library, and Web of Science databases using keywords related to chatbots, breast cancer, and ovarian cancer. Studies were screened and reviewed following PRISMA-ScR guidelines.

Results

Nineteen studies met the inclusion criteria, covering educational support (n=16), clinical support (n=14), and psychosocial support (n=11). NLP served as the primary technical foundation (n=12), with rule-based and retrieval-based approaches equally represented (n=7 each) and a growing adoption of LLM-driven approaches (n=5). Studies reported consistently high user satisfaction, though RCT evidence on clinical efficacy showed mixed results with benefits varying by patient subgroups. Qualitative studies identified adoption barriers including data privacy concerns and patient expectations exceeding chatbot scope. While breast cancer applications showed promising outcomes, research on diagnosed ovarian cancer patients remains limited.

Conclusions

Chatbots show potential as complementary tools in breast and ovarian cancer care. Future development should focus on standardised evaluation frameworks, specialized ovarian cancer applications, and optimizing the balance between automation and human oversight in clinical settings.

Keywords

AI chatbots large language models patient education breast cancer ovarian cancer generative AI

Introduction

Breast and ovarian cancers are major malignancies with profound impacts on global health that are frequently studied together due to their shared risk factors and similar treatment approaches. According to the World Health Organization,¹ breast cancer ranks as the most prevalent cancer among females in 157 out of 185 countries, with an annual incidence of 2.3 million diagnoses, while ovarian cancer accounts for around 313,959 new cases annually.² These cancers share key risk factors including advanced age, hormonal factors, family history, more specifically, the hereditary breast and ovarian cancer (HBOC) syndrome characterized by BRCA1 and BRCA2 gene mutations.³ Despite advances in cancer screening and diagnosis, many patients continue to face substantial challenges in navigating the complexities of treatment, care coordination, and psychosocial support throughout their cancer journey. Studies indicated that approximately 20-50% of breast cancer patients experienced treatment non-adherence due to psychosocial factors, financial barriers, and difficulty managing complex treatment regimens.^4–7 Additionally, rising patient volumes have overwhelmed oncology services, leading to prolonged wait times and communication challenges.^8,9 Traditional care approaches often fall short in providing personalised care coordination, real-time monitoring, and timely intervention.¹⁰ Many patients face significant information needs regarding diagnostic procedures, treatment options, side effects, and self-management strategies, with limited access to reliable and personalised resources between diagnosis and follow-up visits.¹¹ These challenges underscore the need for innovative healthcare solutions to support patients with knowledge acquisition and enhance their overall treatment experience through personalised emotional support and resources tailored to individual needs.

Chatbots, or conversational agents, are defined as computer programs designed to simulate conversation with human users.¹² The emergence of chatbots has revolutionized health information dissemination and access. Initially, chatbots relied on basic keyword-matching techniques, which restricted their abilities to comprehend variations in language and context.¹³ With advancements in artificial intelligence (AI), and large language models (LLMs), chatbots evolved to incorporate more sophisticated response generation methods, such as rule-based systems utilizing predefined patterns, retrieval-based systems selecting responses from existing databases, and generative models creating dynamic responses through machine learning (ML) algorithms.^14–16 This evolution has significantly enhanced chatbots’ ability to process complex medical information and maintain context-aware conversations, particularly valuable in healthcare settings requiring effective communication and support efficiently.¹⁷

Currently, the integration of chatbots into oncology has significantly enhances patient care in multiple ways. For example, in prostate and lung cancer care, chatbots have helped patients and caregivers understand complex health information and manage treatment expectations.^18,19 In colorectal cancer management, chatbots collect family history for risk assessment and educate at-risk individuals about inherited cancer syndromes before clinical visits.²⁰ Some applications in head and neck cancer have also addressed caregiver needs and optimized communication pathways.²¹ Moreover, healthcare professionals reported improved workflow efficiency as chatbots handle routine inquiries and preliminary assessments, allowing them to focus on complex cases and specialized care.²² More importantly, chatbots’ ability to facilitate anonymous interactions has led to increased disclosure of sensitive health information compared to traditional clinical consultations.^23,24 These benefits position chatbots as valuable tools for personalizing cancer care delivery.²⁵

Despite this emerging evidence, few studies have specifically examined chatbot applications tailored to breast and ovarian cancer alone.^26–28 There is one review exploring chatbot applications in breast cancer care, but it was limited to patient education, leaving other potential functions in breast cancer management unexplored.²⁹ Considering that both breast and ovarian cancers share genetic predispositions (e.g., BRCA1/2 mutations), exhibit similar pathophysiological processes, and have similar treatment modalities (e.g., PARP inhibitors), we review them together to provide a comprehensive understanding of chatbot applications in oncology.

This scoping review aims to address the current gap by systematically mapping chatbot applications across populations at risk of, experiencing, and recovered from breast and ovarian cancer. It aims to synthesize current evidence on chatbot characteristics, functions, outcomes, and implementation considerations, providing insights for future development and integration into clinical workflows. Specifically, the research questions are as follows:

(1) What chatbot applications have been developed for breast and ovarian cancer care; (2) What are the technical approaches and functions of these chatbots; (3) What evaluation outcomes have been reported; (4) What implementation facilitators and barriers have been identified?

Materials and methods

This scoping review was conducted following the five-stage methodological framework proposed by Arksey and O'Malley³⁰ and enhanced by Levac et al.³¹ The study adheres to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews (PRISMA-ScR),³² with the detailed checklist provided in Supplementary Material (S1 Table). This study was registered in the Open Science Framework (https://doi.org/10.17605/OSF.IO/P26Z3).

Search strategies

An extensive search strategy was formulated in consultation with a research librarian for six academic databases, including PubMed, Medline, Embase, CINAHL, Cochrane Library, Web of Science. For this review, we operationalized chatbots as computer programs that simulate human conversation through text or voice interactions, encompassing various terms such as conversational agents and dialogue systems. Additionally, artificial intelligence was considered as the underlying technology that enables natural language processing (NLP) and ML capabilities in these systems. Based on these operational definitions, the search strategy included three groups of search terms: (1) Breast cancer (e.g., “Breast Neoplasms”, “Breast Cancer Lymphedema”, “Unilateral Breast Neoplasms”); (2) Ovarian cancer (e.g., “Ovarian neoplasm”, “Epithelial Carcinoma”, “Ovarian tumour”); (3) Chatbot (e.g., “Chatbot”, “Artificial intelligence”, “Conversational agent”). The full search syntax for each database, including all Boolean operators and controlled vocabulary is provided in Supplementary Material (S2 Table). The search was limited to English-language peer-reviewed articles published between 01 January 2015 and 01 January 2025, spanning a 10-year period, to incorporate the early evolution of chatbot technology. This timeframe was selected as Agarwal et al.³³ identified post-2015 as the period when chatbots began to be widely utilized for health-related purposes. Additionally, a second-round search covering 01 January 2025 to 26 February 2026 was performed using the same databases and syntax to ensure this review reflects the most recent literature.

Eligibility criteria

Studies were considered eligible for inclusion if they met the following criteria: (1) investigated chatbot applications in populations at risk of, experiencing, or recovered from breast or ovarian cancer; (2) published in peer-reviewed journals; (3) written in English; (4) published between January 1, 2015, and February 26, 2026; and (5) available in full-text. Exclusion criteria included: (1) studies focusing on cancers other than breast or ovarian cancer; (2) review articles, protocols, commentaries, or viewpoint pieces; (3) experimental research without human subject testing.

Data extraction and review process

The selection process was performed using EndNote 21, through separate screening of titles and abstracts for relevance. Data were extracted independently by two authors using a standardised data extraction form developed in Microsoft Excel. The extracted data were categorized into four main domains: (1) study characteristics (including year of publication, study design, country of origin, age group, population, and sample size); (2) chatbot characteristics (including name of chatbots, AI techniques, Dialogue system methods, launch methods, and functions); (3) chatbot evaluation outcomes (including user satisfaction, usability, and information quality); and (4) reported limitations (both chatbot-related and research methodology limitations). The detailed data extraction framework is presented in Supplementary Material (S3 Table). Subsequently, full-text documents were retrieved and subjected to comprehensive qualitative review, guided by the above-mentioned inclusion criteria. Prior to screening, a calibration exercise was conducted where two independent reviewers each evaluated a subset of 100 articles independently. A 72% inter-rater agreement was obtained on the initial set. Discrepancies were discussed to refine the eligibility criteria and improve screening consistency before moving to the formal screening. In the formal screening process, two independent reviewers assessed the titles and abstracts of the articles and manually annotated them as “included,” “excluded” or “uncertain” based on the definition and eligibility criteria defined. Articles marked as “uncertain” or with conflicting decisions were flagged for further review. Any disagreements were resolved through discussion between the two reviewers, and a third reviewer was consulted when consensus could not be reached. In accordance with scoping review methodology, no quality appraisal was conducted,³⁴ as the primary aim was to map the breadth of chatbot applications in breast and ovarian cancer care.

Results

The search was conducted in two rounds across six academic databases. The initial search yielded 5761 articles, while the second-round update search identified an additional 1118 articles, resulting in a combined total of 6879 records. After eliminating 2539 duplicate records, 4340 articles remained for titles and abstracts screening. Of these, 4082 records were excluded based on the inclusion criteria, leaving 258 full-text articles retrieved for further review. Following full-text screening, 239 studies were excluded due to other cancer types, non-English language, non-human studies, and review or commentary articles. 19 studies were ultimately included in this review (Figure 1).

Figure 1.

PRISMA Flow diagram of the study selection process.

Characteristics of the included studies

This review examined 19 studies published between 2019 and 2026, with more than 60% published in 2023 or later. The geographical breakdown shows a predominance of research from Western countries, with 26.3% (n=5) from the United States and 47.4% (n=9) from European nations, including Germany, Norway and France. Contributions from Asia accounted for 21.1% (n=4), with studies from Taiwan, Japan, and South Korea, while African contributions accounted for 5.3% (n=1).

In terms of study design, we classified the studies based on the hierarchy of evidence-based medicine.³⁵ Randomised controlled trials (RCT) represented 21.1% (n=4) of the studies.^36–39 Cohort studies made up 10.5% (n=2), including one prospective⁴⁰ and one retrospective cohort study.⁴¹ Cross-sectional studies accounted for 5.3% (n=1),⁴² while pilot and feasibility studies formed the largest proportion at 26.3% (n=5). Additionally, there were 3 development and evaluation studies with user testing,^22,43,44 and 3 qualitative interview studies.^45–47 Sample sizes ranged from 11 to 61,070 participants, with the research predominantly focused on middle-aged women, whose mean ages varied from 38.7 to 52.9 years, spanning an overall age range of 20 to 82 years. The included studies focused on four groups: diagnosed breast cancer patients (n=9), individuals at risk of HBOC (n=7), diagnosed ovarian cancer patients (n=2), and individuals with suspected breast cancer (n=2). Siglen et al.⁴⁷ focused on both diagnosed breast and ovarian cancer patients. Although 7 studies were designed for individuals at risk for ovarian cancer due to HBOC, only two specifically targeted diagnosed ovarian cancer patients. The detailed characteristics of included studies are presented in Table 1.

Table 1.

Characteristics of included studies.

Author/Year	Country of origin	Study design	Objective(s)	Age group (mean age)	Population	Sample size	Findings
Al-Hilli et al., 2023³⁶	US	RCT	To compare patient satisfaction, knowledge comprehension, genetic testing uptake, and treatment timing between chatbot and physician committee counselling	48-82	Breast cancer patients	37	(1) Comparable satisfaction (30 vs. 30, p=0.19) and knowledge scores (11 vs. 12, p=0.09) between chatbot and physician groups;
Al-Hilli et al., 2023³⁶	US	RCT		48-82	Breast cancer patients	37	(2) Both groups showed 100% genetic testing uptake, with pathogenic variants detected in 13.5% of all participants, and no genetic testing-related treatment delays observed.
Bibault et al., 2019³⁷	France	RCT	To determine whether an artificial conversational agent could provide answers to patients with satisfaction levels similar to physicians	42	Breast cancer patients	142	Success rates (score >3) were 69% in chatbot group versus 64% in physicians’ group, demonstrating noninferiority of chatbot responses (P<.001). Patient satisfaction was comparable between groups, with 83.1% finding answers helpful.
Chaix et al., 2019⁴⁰	France	Prospective cohort study	To analyse chatbot interactions with patients and evaluate whether it could improve medication adherence through prescription reminders	48	Breast cancer patients	958	(1) Chatbot interactions averaged 132,970 messages per month with 93.95% user satisfaction rate and 88% reporting effective support and treatment tracking (n=958)
Chaix et al., 2019⁴⁰	France	Prospective cohort study		48	Breast cancer patients	958	(2) Treatment reminder function showed improvement in adherence from 51% in week 1 to 76% in week 5 (20% improvement, p=0.04)
Chen et al., 2021²²	Taiwan	Development and evaluation study	To develop a symptomatic assessment AI chatbot to prescreen women for breast cancer symptoms and facilitate timely medical consultation	NR	Individuals with suspected breast cancer	135	The chatbot achieved 95.4% scoring accuracy against specialist doctors’ benchmark scores across 135 anonymized patient cases, and was subsequently approved for clinical trial by the IRB.
Chetlen et al., 2019⁴⁸	US	Pilot study	To create and evaluate a chatbot providing evidence-based answers to frequently asked questions for patients scheduled for breast biopsies	NR	Individuals with suspected breast cancer	55	The chatbot enhanced patient understanding of their upcoming breast biopsy procedure, with 87% reporting that it made the process easier to comprehend, regardless of their perceived technology proficiency. Additionally, 74.5% of participants felt that the chatbot helped improve the quality of their care.
Griewing et al., 2023⁴²	Germany	Cross-sectional study	To assess the concordance between treatment recommendations made by ChatGPT 3.5 and those of a multidisciplinary tumour board for breast cancer patients	51	Breast cancer patients	20	ChatGPT 3.5 can provide treatment recommendations for breast cancer patients that are consistent with multidisciplinary tumour board decision making of a gynaecologic oncology centre in Germany. The congruence of chatbot’s recommendations with those of the specific tumour board amounted to 70%
Lukac et al., 2023⁴⁹	Germany	Pilot study	To evaluate ChatGPT’s potential as a supplementary tool for decision-making in multidisciplinary tumour boards for primary breast cancer diagnosis	NR	Breast cancer patients	10	ChatGPT provided mostly general treatment recommendations and showed limited concordance with MDT decisions, achieving a 16.05% congruence. It identified some risk factors and suggested treatments but lacked specificity in certain areas, such as neoadjuvant treatments and lifestyle interventions.
Nazareth et al., 2021⁴¹	US	Retrospective cohort study	To examine user experience with a clinical chatbot that automates hereditary cancer risk triage and provides genetic testing education	NR	Individuals at risk of HBOC	61,070	High engagement with the chatbot, with 64.2% of invited patients participating. The average satisfaction score among users is 4.6 (min. 1, max. 5). Additionally, 89.4% completed the cancer risk assessment, and 71.4% completed the genetic testing education section. One in four patients met criteria for genetic testing based on National Comprehensive Cancer Network guidelines.
Siglen et al., 2022⁴³	Norway	Pilot study	To design and develop a chatbot for digital conversations with breast or ovarian cancer patients about genetic BRCA testing	NR	Individuals at risk of HBOC	58	The development process revealed challenges in AI-based matching of user questions with predefined information, leading to improvements in reducing language ambiguities. Users found the chatbot trustworthy and reader-friendly, and expressed willingness to use it in real-life settings if recommended by healthcare personnel.
Siglen et al., 2023⁴⁵	Norway	Qualitative (Interview)	To explore patients’ perceived utility of and trust in chatbot technology for providing information about hereditary cancer	20-55	Individuals at risk of HBOC	16	Participants highly valued the 24/7 accessibility of Rosa and considered it a reliable source of genetic information. They appreciated having the chatbot as a complement to genetic counselling rather than a replacement. None of the participants reported increased anxiety from using Rosa, and many found it helpful for preparing for counselling sessions and reinforcing information afterward.
Tawfik et al., 2023³⁸	Egypt	RCT	To compare the effects of a chatbot versus nurse-led education on self-care behaviors and chemotherapy side effects in women with breast cancer	>20	Breast cancer patients	150	Participants stated that the replies from chatbot are useful, appropriate and informative, and the chatbot was user-friendly. Frequency and severity of physical and psychological symptoms decreased in the 3 groups
Sato et al., 2024⁵⁰	Japan	Pilot study	To validate the feasibility of an AI chatbot for preliminary HBOC screening in a clinical setting	35-67 (52)	Individuals at risk of HBOC	11	All participants completed the chatbot operation with average time of 18.0 minutes (SD 5.44). The chatbot’s determinations of BRCA1/2 testing criteria were consistent with certified genetic counsellors’ evaluations. The system demonstrated high usability and acceptability among participants.
Wollney et al., 2025⁴⁶	US	Qualitative (Interview)	To identify women’s perceived facilitators and barriers to adopting a chatbot for HBOC genetic screening in a rural obstetrics and gynaecology setting	31–64 (50.6)	Individuals at risk of HBOC	17	Six facilitators and barriers to Gia chatbot adoption were identified: cancer risk perception, clinician communication, screening feasibility, fiscal concerns, technology trust/distrust, and previous genetic testing experience. Clinician explanation of Gia’s relevance and 24/7 accessibility facilitated adoption, while data privacy concerns and lack of perceived personal risk were the primary barriers.
Chou et al., 2025⁵¹	Taiwan	Development and evaluation study	To evaluate the correctness and completeness of responses to ovarian cancer-related questions from chatbot compared with healthcare professionals in gynaecologic oncology	50.9	Ovarian cancer patients	31	LilyBot significantly outperformed healthcare professionals in both correctness (5.31 vs. 5.07, p=0.017) and completeness (2.66 vs. 2.36, p<0.001) across 150 ovarian cancer-related questions, achieving perfect scores in immunotherapy and gene therapy categories. Usability testing among 31 ovarian cancer patients yielded a mean satisfaction score of 5.43 out of 7.
Siglen et al., 2025⁴⁷	Norway	Qualitative (Interview)	To explore how newly diagnosed patients with breast or ovarian cancer patients’ experience of using the chatbot in mainstream genetic testing, and to identify potential barriers to its implementation	28–57	Breast and ovarian cancer patients	7	Patients valued Rosa as a trustworthy and an accessible supplement to mainstream genetic testing. However, they feared missing out on human interaction, expressing concerns about misunderstandings and reduced patient-provider contact. Chatbot accuracy was also lower in this population (80.1%) compared to healthy at-risk individuals (88.7%), as patients frequently asked questions beyond Rosa’s scope regarding treatment and prognosis.
Wolff et al., 2025⁵²	Germany	Pilot study	To evaluate the usability and content quality of a chatbot-based mobile app designed to provide personalised support to HBOC patients in the post-genetic counselling phase	25–48 (38.7)	Individuals at risk of HBOC	6	GENIE achieved a mean System Usability Score of 75.33, with 5 of 6 participants using the app daily. Participants rated content as credible, clear, and relevant, and all would recommend it to others. However, the layout was perceived as moderately professional and slightly uninspiring, indicating a need for interface redesign.
Lee et al., 2025³⁹	South Korea	RCT	To evaluate the effectiveness of chatbot and video education in reducing anxiety among breast cancer patients undergoing radiation therapy	20–75	Breast cancer patients	145	No significant difference in anxiety reduction was found across all groups overall. However, among patients aged ≤50 years, the video and chatbot group showed a significant reduction in anxiety (APAIS score decreased from 3.06 to 1.88), suggesting that digital education tools may be more effective for younger, digitally literate patients. Skin irritation, diet and exercise, and nausea were the most frequently queried topics via the chatbot.
Boie et al., 2025⁵³	Germany	Pilot study	To evaluate the potential of a AI-driven chatbot to provide personalised, accurate answers to breast cancer-related questions in German	NR	Breast cancer patients	NR	The chatbot achieved 87.5% correctness, 85.6% comprehensibility, and 89.4% non-harmful responses across 104 breast cancer questions in German, though completeness was notably lower at 69.2%. Performance was strongest in bone health and nutrition categories, while 6 responses (5.8%) were flagged as potentially harmful due to outdated source information or retrieval failures involving tabular data.
Coen et al., 2025⁴⁴	US	Development and evaluation study	To design, implement, and evaluate a chatbot to support the return of positive genomic screening results in the context of a population-wide genetic screening program	NR	Individuals at risk of HBOC	NR	The chatbot for returning positive hereditary cancer screening results achieved an overall expert rating of 3.86/5 (SD 0.89) across 8 criteria. Tone (4.25) and usability (4.25) scored highest, followed by boundary management (4.0) and efficiency (3.88), while program accuracy received the lowest score (3.25), indicating difficulty delivering program-specific details despite RAG integration.

Note. RCT: randomized controlled trial; NR: not reported; HBOC: hereditary breast and ovarian cancer; MDT: multidisciplinary team; BRCA: breast cancer gene; RAG: retrieval-augmented generation; APAIS: Amsterdam Preoperative Anxiety and Information Scale.

Technical and functional characteristics of chatbots applications

Technical characteristics

The technical implementation of chatbots demonstrated diverse approaches in AI techniques. Rule-based and retrieval-based approaches were equally represented (n=7 each), followed by generative methods (n=5). NLP served as the primary technical foundation (n=12), frequently combined with ML (n=7). A notable example is Gia,^36,41,46 a HIPAA-compliant chatbot leveraging NLP exclusively for predefined conversation pathways. Several chatbots augmented NLP with ML techniques for enhanced intent recognition and semantic matching. For instance, Rosa employed semantic similarity matching,^43,45,47 Vik applied supervised learning for intent classification and entity recognition,^37,40 and ChemoFreeBot utilized Azure QnA Maker for knowledge retrieval.³⁸ A more recent development saw the adoption of LLMs in 5 studies, featuring ChatGPT 3.5^42,49 and GPT-4.^44,51,53 Early implementations using LLMs without structured input demonstrated limited output consistency,⁴⁹ whereas later studies introduced structured data input⁴² and prompt engineering with differentiated interaction modes tailored to varied patient needs.⁵¹ The most advanced design adopted Retrieval-Augmented Generation (RAG), a technique that retrieves relevant documents from an external knowledge base before generating responses. For example, Boie et al.⁵³ leveraged a 3,110-page clinical database to ground LLM outputs in verified sources, aiming to mitigate hallucination and knowledge obsolescence. Regarding deployment platforms, mobile applications predominated (n=9), encompassing native mobile apps and phone-based interfaces such as iOS, Android, and Facebook Messenger. Web-based platforms (n=7) were also commonly used. One study utilized a tablet-based interface via a password-protected, university-owned internet program.⁴⁸ Table 2 displays the features of chatbot applications.

Table 2.

Technical characteristics of chatbots applications.

Author/Year	Name of the chatbot	Technical characteristics
Author/Year	Name of the chatbot	AI techniques	Dialogue system methods	Launch method
Al-Hilli et al., 2023³⁶	Gia	NLP	Rule-based	Web-based platform
Bibault et al., 2019³⁷	Vik	NLP + ML	Retrieval-based	1. Web
Bibault et al., 2019³⁷	Vik	NLP + ML	Retrieval-based	2. Mobile phones (iOS/Android/Facebook Messenger)
Chaix et al., 2019⁴⁰	Vik	NLP + ML	Retrieval-based	1. Web
Chaix et al., 2019⁴⁰	Vik	NLP + ML	Retrieval-based	2. Mobile phones (iOS/Android/Facebook Messenger)
Chen et al., 2021²²	SAC	NLP + ML + CWS	Rule-based	1. Web (via PC)
Chen et al., 2021²²	SAC	NLP + ML + CWS	Rule-based	2. Mobile phone (iOS front-end chat interface)
Chetlen et al., 2019⁴⁸	Breast center chatbot	NLP	Rule-based	Internet-based chatbot program on tablet (with university-owned password protected)
Griewing et al., 2023⁴²	ChatGPT3.5	LLMs	Generative	Web
Lukac et al., 2023⁴⁹	ChatGPT3.5	LLMs	Generative	Web
Nazareth et al., 2021⁴¹	Gia	NLP	Rule-based	Web-based platform
Siglen et al., 2022⁴³	Rosa	NLP + ML	Retrieval-based	Mobile app
Siglen et al., 2023⁴⁵	Rosa	NLP + ML	Retrieval-based	Mobile app
Tawfik et al., 2023³⁸	ChemoFreeBot	NLP+ML	Retrieval-based	Mobile Phones (WhatsApp)
Sato et al., 2024⁵⁰	NR	NLP	Rule-based	Mobile Phones (LINE app)
Wollney et al., 2025⁴⁶	Gia	NLP	Rule-based	Web-based platform
Chou et al., 2025⁵¹	Lilybot	LLMs	Generative	Mobile-based platform (LINE app)
Siglen et al., 2025⁴⁷	Rosa	NLP + ML	Retrieval-based	Mobile app
Wolff et al., 2025⁵²	GENIE	NR	Retrieval-based	Mobile app
Lee et al., 2025³⁹	KakaoTalk	ML	Rule-based	Mobile app
Boie et al., 2025⁵³	ChatGPT 4.0	LLMs + RAG	Generative	NR
Coen et al., 2025⁴⁴	ChatGPT4.0	LLMs + RAG	Generative	Web-based platform

Notes. RAG: retrieval-augmented generation; NR: not reported; LLMs: large language models; ML: machine learning; NLP: natural language processing; CWS: Chinese word segmentation.

Functional characteristics

Three functional domains were consistently represented, including clinical support, educational support, and psychosocial support. Most studies incorporated more than one domain. Educational support was the most prevalent (n=16), closely followed by clinical support (n=14), with psychosocial support appearing less frequently (n=11). Figure 2 illustrates the subcategories within each domain and the number of studies addressing each. Detailed chatbot functionalities for each study are provided in Supplementary Material (S4 Table).

Figure 2.

Distribution of chatbot functionalities used in breast and ovarian cancer care.

Clinical functionalities comprised risk assessment, genetic counseling, symptom monitoring, risk triage and referral, patient medical history collection, and clinical decision-making assistance. Risk assessment (n=5) and genetic counseling (n=5) played a central role. These applications were designed to support hereditary cancer risk evaluation, with one system successfully identifying 27% of participants as high-risk HBOC candidates.⁴¹ Genetic counseling chatbots primarily served as digital pre-consultation tools, guiding patients through pre-test guidance and preliminary interpretation of results before directing them to in-person genetic counseling.⁴⁷ Clinical decision-making assistance specifically focused on tumour board decision-making, with one chatbot achieving 70% congruence with multidisciplinary tumour board recommendations.⁴² Symptom monitoring capabilities were also implemented, with Chen et al.²² developing a system that demonstrated high correlation accuracy in breast cancer assessment scoring compared to specialist evaluations.

Educational functions included disease knowledge, treatment procedures, genetic testing information, medication side effects, rehabilitation and lifestyle, and financial and legal information. Disease knowledge was a foundational component across multiple applications, with chatbots providing information about breast cancer epidemiology, symptoms, and prognosis.^37,40,53 Treatment procedures were addressed in chatbots explaining radiotherapy protocols³⁹ and breast biopsy processes, where 87% of patients reported improved understanding after use.⁴⁸ Genetic testing information constituted a major focus, with several systems educating patients about BRCA1/2 mutations, hereditary cancer syndromes, and testing implications.^36,41,45,50 Rehabilitation and lifestyle guidance was integrated into chatbots offering advice on post-treatment recovery, exercise, diet, and daily activities during radiotherapy.^37,39 Financial and legal information, including reimbursement processes and patients’ rights, was incorporated into comprehensive support chatbots like Vik.^40,41

Psychosocial support functions, while less commonly emphasized, were nonetheless integral to user experience in several applications. These included anxiety management that helped users cope with procedure-related distress,^39,50 fertility-related emotional support addressing concerns about reproductive capacity and family planning following cancer treatment.^37,40 Family communication support guiding patients in discussing genetic risks with relatives and children,^37,40,43,47 coping strategies providing practical approaches to managing the psychological impact of diagnosis and treatment,^38,45 and body image and sexuality support helping patients navigate changes in self-perception and intimate relationships post-treatment.^37,51 These support functions showed preliminary positive signals in user-reported psychological wellbeing, with users developing emotional engagement with chatbots,^45,50 reducing chemotherapy-related symptoms,³⁸ and improving medication adherence from 51% in week 1 to 76% in week 5⁴⁰. An emerging trend toward personalised support features was identified, with 5 chatbots incorporating individualized guidance based on patient-specific factors and clinical contexts. Users particularly valued the 24/7 accessibility of these systems, considering them reliable complementary sources of information rather than replacements for healthcare provider interactions.⁴⁵

Evaluation outcomes of chatbot applications

Satisfaction, usability, feasibility, and efficacy

Chatbots in breast and ovarian cancer care have been evaluated across satisfaction, usability, feasibility, and efficacy. 5 studies quantitatively assessed satisfaction. In the pilot and RCT studies, Al-Hilli et al.³⁶ compared Gia with face-to-face genetic counseling among 37 newly diagnosed breast cancer patients, finding no significant difference in median satisfaction scores between groups (30 vs. 30, p=0.19). Chou et al.⁵¹ recorded a mean satisfaction score of 5.43/7 regarding the ovarian cancer-related information provided by the chatbot in a study with 31 ovarian cancer patients. High satisfaction levels were similarly observed in larger cohort studies. Chaix et al.⁴⁰ reported a satisfaction rate of 93.95% among 958 breast cancer patients, with 88% acknowledging effective support from the chatbot. Nazareth et al.⁴¹ reported a mean satisfaction score of 4.6/5 across 61,070 users undergoing hereditary cancer risk assessment. Bibault et al.³⁷ also reported that 83.1% of 142 breast cancer patients found the chatbot’s responses helpful when compared to a multidisciplinary board comprising surgical, medical, and radiation oncologists. Regarding usability, 4 studies reported that patients found the chatbot interface intuitive and easy to use, regardless of their technological literacy.^38,43,45,48 Even those with minimal exposure to digital tools reported being able to navigate the systems successfully, with many completing their engagements without issues. For instance, in the study by Chetlen et al.,⁴⁸ 74.5% of users indicated a better understanding of medical procedures through chatbot interaction. Regarding feasibility, Sato et al.⁵⁰ conducted a pilot study to evaluate the feasibility of using chatbots to collect family history information for HBOC, finding a high 100% completion rate and an average task time of 18 minutes.

Efficacy was evaluated across four RCTs, with two focusing on clinical outcomes and two employing non-inferiority trials. Tawfik et al.³⁸ assessed the chatbot’s impact on chemotherapy-related side effects among breast cancer patients, finding significant reductions in the frequency, severity, and distress associated with physical and psychological symptoms, alongside notably higher self-care efficacy compared to the control group. In contrast, Lee et al.³⁹ enrolled breast cancer patients undergoing radiotherapy and found no significant improvement in overall anxiety levels. However, their subgroup analysis revealed younger patients (aged ≤50) showed significantly reduced anxiety, suggesting age-related differential effects. The remaining two studies employed non-inferiority designs to evaluate chatbots against conventional clinical consultation. Al-Hilli et al.³⁶ found patients receiving genetic counseling via chatbot demonstrated no significant differences in knowledge comprehension compared to those counseled in person by a genetic counselor, with a genetic testing uptake rate of 100% in both groups. Similarly, Bibault et al.³⁷ demonstrated that chatbot was non-inferior to a multidisciplinary oncology board in delivering breast cancer-related information, with comparable success rates (69% vs. 64%, p<0.001).

Performance and information quality

Information quality was formally assessed in 8 studies. High concordance was demonstrated in genetic counseling applications^36,50 and screening assessments,²² while treatment planning applications showed variable results with congruence rates ranging from 70%⁴² to 16.05%⁴⁹ when compared with professional team recommendations. The evaluation methods for information quality varied considerably across studies, with few reporting validated measurement tools. Only a small number of studies employed standardised assessment instruments, such as 5-point satisfaction rating scales³⁷ and knowledge assessment questionnaires.³⁶ Most studies relied on custom evaluation frameworks, including specialist comparison protocols,²² tumour board decision concordance metrics,^42,49 genetic counselor validation protocols,⁵⁰ and technical performance indicators such as fallback rates.^43,45

Challenges in chatbot implementation

Technical challenges were identified in 9 studies, primarily concerning chatbot comprehension abilities and language accessibility. Two studies specifically noted that similar wordings could lead to misinterpretation of essential information.^22,43 Language accessibility emerged as another significant barrier, particularly evident in one U.S. study where English-only support limited effectiveness in Spanish-speaking populations.⁴¹ Two studies reported insufficient database support in recognizing specific medical terms,^37,49 while three studies noted limitations in accurate diagnosis and screening due to incomplete patient information collection through conversations.^42,49,50 Additionally, clinical integration challenges focused on human-chatbot interaction limitations. Studies identified insufficient capabilities in establishing emotional connections with patients⁴⁵ and addressing complex, personalised issues.³⁸ Multiple studies emphasized that current chatbot systems should complement rather than replace healthcare professionals.^37,38,50 Methodological constraints were also noted, including small sample sizes and the need for standardised evaluation frameworks,^36,37 suggesting opportunities for more robust research designs in future studies.

Additionally, two qualitative studies provided insight into patient perspectives on chatbot adoption. Wollney et al.⁴⁶ interviewed breast cancer patients and found that clinician endorsement of the chatbot’s relevance during genetic counseling sessions served as a key facilitator. Similarly, Siglen et al.⁴⁷ conducted qualitative interviews with 7 breast and ovarian cancer patients and identified perceived accessibility as the primary driver of willingness to use the chatbot. However, both studies revealed several barriers. Patients expressed concerns regarding the privacy and security of genetic information, particularly the risk of data misuse or unauthorized disclosure.⁴⁶ A lack of personal risk perception also emerged as a significant barrier, as individuals who did not consider themselves at high risk found it difficult to recognize the tool’s relevance to their own circumstances.⁴⁶ Information clarity represented another prominent concern, with patients worried both about misinterpreting chatbot-generated information and about the chatbot’s limited capacity to comprehend the complexity of their individual queries.⁴⁷ Notably, patients frequently posed questions beyond the chatbot’s intended scope, such as those related to treatment and prognosis, resulting in lower response accuracy. This finding underscores the importance of clearly communicating the chatbot’s functional boundaries to patients prior to implementation, so that expectations are appropriately managed from the outset.

Discussion

Principal findings

This scoping review identified 19 studies that investigated the use of chatbots in breast and ovarian cancer care. The majority of chatbot applications targeted breast cancer and addressed three functional domains: clinical support, educational support, and psychosocial support. NLP remained the primary technical foundation, with a growing adoption of LLM-driven and RAG-based approaches. Our analysis revealed consistently high user satisfaction and usability across studies, while RCT evidence on clinical efficacy showed mixed results. The studies also highlighted important limitations in chatbot capabilities, adoption barriers identified through qualitative research, and gaps in implementation evidence.

This review found that current chatbots incorporate clinical, educational, and psychosocial support functions. Early healthcare chatbots were predominantly single-function tools focused on basic patient education, symptom checking, and health information delivery.^29,54 Current systems showcase comprehensive integration of multiple care domains. This integration particularly excelled in high-stakes clinical domains, such as genetic counseling and risk assessment, where chatbots showed potential in identifying high-risk HBOC populations.⁴¹ Furthermore, the reviewed cancer-specific chatbots exhibited advanced personalization capabilities, incorporating context-aware support features that adapt to individual patient circumstances and clinical requirements. This evolution towards complex, multi-functional systems represents a notable trend in chatbot applications, though it also highlights the need for more robust evaluation frameworks to assess the feasibility and efficacy of these integrated functions in real-world clinical settings.

Importantly, while breast cancer chatbots show diverse applications, there is a notable absence of chatbots specifically designed for ovarian cancer care, revealing a significant gap in the field. This finding is consistent with Cheung et al.,⁵⁵ who also found that AI and ML technologies for ovarian cancer care significantly lag behind other oncology areas. This gap may be explained by two key challenges. On one hand, the majority of patients are diagnosed at an advanced stage, with approximately 75% presenting at stage III or IV.⁵⁶ At this point, patients face urgent surgical decisions, complex chemotherapy regimens, and palliative care needs that go far beyond what a general health education chatbot can offer. On the other hand, ovarian cancer’s high molecular and histological heterogeneity, both across subtypes and within individual tumours, makes it exceptionally difficult to build a unified information framework or a consistent conversational pathway for patients.⁵⁷ This complexity also severely limits the availability of early-stage training data for AI development. Despite these challenges, the unmet need for digital support among ovarian cancer patients should not be overlooked. Compared to other cancer types, ovarian cancer patients report a higher proportion of unmet psychological and systemic support needs,⁵⁸ and face unique demands such as managing treatment-induced symptoms, making fertility preservation decisions, and navigating complex surgical options. Future chatbot research could therefore focus on guiding patients through post-treatment recovery, supporting health literacy and follow-up understanding, and raising awareness of early symptoms such as persistent bloating and pelvic pain, which are frequently overlooked and contribute to diagnostic delay. Developing specialized ovarian cancer chatbots represents a critical opportunity to address these specific care gaps and enhance patient outcomes.

The dialogue system and AI techniques used in chatbots varied across different care tasks, with rule-based and retrieval-based chatbots predominating in clinical tasks and generative chatbots in patient educational and psychosocial support. Fujihara and Sone⁵⁹ observed similar patterns in diabetes care, where deterministic algorithms and rule-based systems were preferred in medication decisions and risk assessment, while ML and neural network approaches were more commonly applied in patient self-management tools and continuous monitoring. Gupta et al.⁶⁰ further noted this differentiation, finding that while NLP-enhanced systems excel in processing unstructured clinical data and facilitating patient-provider communication, rule-based systems with clear decision trees are often favored for critical clinical decisions due to their predictability. Rule-based systems excel in providing the transparency and reliability needed for high-stakes clinical decisions, particularly in areas like genetic counseling and risk assessment, where clear and predictable pathways are essential. In contrast, more sophisticated AI technologies are increasingly utilized in patient psychosocial support, where the ability to handle natural language and adapt to contextual nuances enhances the patient experience. For instance, generative AI could play a transformative role in personalised health education or emotional support during critical phases of cancer care, including treatment decisions, perioperative periods, and remission. More importantly, the latest development of digital twins and multimodal chatbot driven by predictive analytics could revolutionize patient care by developing real-time virtual models of patients/caregivers. Ultimately, these advancements could further provide 24/7 continuous information or emotional support across the entire oncology patient journey, bridging the gaps in patient care delivery and improving long-term survivorship outcomes.

The RCT evidence in this review revealed mixed efficacy outcomes. While some trials demonstrated significant reductions in symptom burden⁴⁰ and non-inferiority to conventional counseling,^36,37 others found no overall improvement in anxiety levels, with benefits limited to specific subgroups such as younger patients.³⁹ These inconsistent findings suggest that chatbot effectiveness may be moderated by patient characteristics, and highlight the need for larger, well-powered trials with stratified analyses.

Beyond technological considerations, the implementation of chatbots in cancer care presents distinct ethical challenges. Privacy protection in genetic counseling applications and the handling of sensitive cancer-related data require particular attention. The limited geographical diversity in current research, with predominant representation from Western countries, raises concerns about potential algorithmic bias when these systems are deployed across different populations with diverse cultural backgrounds. This underrepresentation is particularly concerning as cultural factors significantly influence both healthcare communication preferences and cancer care approaches. Additionally, the emergence of LLM-driven chatbots introduces specific risks related to misinformation and hallucination, where the system may generate plausible but clinically inaccurate responses.⁶¹ In oncology settings, such errors could directly influence patient decision-making regarding treatment or genetic testing, potentially leading to delayed diagnoses or the pursuit of clinically inappropriate interventions. While RAG-based approaches have been proposed to mitigate hallucination by grounding responses in verified sources,^44,53 their reliability in high-stakes clinical contexts remains insufficiently validated. RAG systems in oncology also risk exposing sensitive patient data through external knowledge retrieval unless privacy-preserving mechanisms such as differential privacy or on-premise architectures are adopted.⁶² Furthermore, integrating large external knowledge bases introduces latency that can impede real-time clinical use, while retrieval quality across heterogeneous data sources remains inconsistent, undermining accuracy and governance in oncology applications.⁶³ Moreover, health equity concerns also warrant further attention, as current chatbot implementations predominantly serve English-speaking populations in high-income countries, potentially widening existing disparities in cancer care access for underserved communities. The digital divide and limited AI literacy act as compounding determinants of this inequity, as restricted broadband access, low device ownership, and unfamiliarity with AI-driven tools can systematically exclude vulnerable patients from the benefits of these technologies.⁶⁴Moreover, although high satisfaction levels were reported in both small-scale pilot studies and large-scale implementations, it is important to note that these results may not be directly comparable. Small-scale studies often have limited generalisability, and future research involving broader populations or larger sample sizes is needed to confirm the consistency of these findings. Furthermore, chatbots’ limitations in handling complex emotional support highlight the critical need to maintain appropriate boundaries between automated and human-delivered care. These ethical considerations underscore the importance of developing clear guidelines for chatbot implementation in clinical oncology care, particularly regarding data privacy, algorithmic fairness, and the scope of automation in personalizing patient support.

Limitations

This review has several limitations worth noting. First, although we conducted a comprehensive search across multiple databases, we only included English-language publications, which may have led to the exclusion of relevant studies published in other languages. Second, the geographical distribution of included studies showed a predominance from Western countries, with limited representation from Asian and African regions. This geographical disparity may stem partially from our English-language inclusion criterion. Third, the heterogeneity in outcome measures and evaluation methods across studies made it challenging to directly compare effectiveness across different chatbot implementations. Fourth, in line with scoping review methodology, no formal quality appraisal was performed. This may limit the ability to evaluate the reliability and validity of the reported findings. Future systematic reviews and meta-analyses are warranted to further validate the effectiveness of these findings.

Future directions

Based on our review findings, several key areas warrant further investigation. Future research should prioritize the development of more sophisticated chatbot designs that can better handle complex clinical scenarios and emotional support needs, particularly in genetic counseling and treatment decision-making processes.⁶⁵ Standardised evaluation frameworks need to be established to enable meaningful comparisons across different chatbot implementations and to assess their long-term impact on patient outcomes. More rigorous study designs, particularly RCT with larger sample sizes and longer follow-up periods, are needed to establish the clinical effectiveness of chatbot interventions.⁶⁶ Future studies should also focus on implementing chatbots across larger and more diverse geographical samples to enhance the applicability and generalisability of research outcomes.⁴¹ Additionally, there is a need to develop and validate multilingual chatbot systems that can serve diverse patient populations and address cultural-specific needs in cancer care. Importantly, future research should explore the optimal balance between chatbot automation and human oversight to ensure safe and effective deployment in clinical settings.

Conclusion

This scoping review mapped the landscape of chatbot applications in breast and ovarian cancer care, revealing integration of clinical, educational, and support functions with generally favorable user satisfaction. The implementation pattern shows rule-based systems dominating critical decision-making areas while advanced AI approaches serve patient support roles. Despite promising breast cancer applications, a notable absence exists in ovarian cancer-specific chatbots. Key future priorities should include developing specialized applications for ovarian cancer care, establishing standardised evaluation frameworks, enhancing geographical research diversity, and optimizing the balance between chatbot automation and human oversight in clinical settings. Ultimately, although chatbots show promise as supportive tools, they should be viewed as augmenting rather than replacing human healthcare providers, and integrated with appropriate human oversight to ensure patient safety and care quality.

Supplemental material

Supplemental material - Leveraging AI chatbots in supporting breast and ovarian cancer patients: A scoping review

Supplemental material for Leveraging AI chatbots in supporting breast and ovarian cancer patients: A scoping review by Vivian Hui, Lidan Tian, Xinyu Feng, Xiaoling Yuan, Janelle Yorke and Young Ji Lee in Digital Health.

Footnotes

Acknowledgements

The authors acknowledge the support of the Hong Kong Jockey Club STEM Lab for Digital Oncology Care Enhancement (DOCE).

ORCID iDs

Vivian Hui

Lidan Tian

Xinyu Feng

Janelle Yorke

Ethical considerations

Ethical approval was not required for this scoping review as it analyzed only publicly available published literature and did not involve human participants.

Consent to participate

This scoping review did not involve human participants.

Consent for publication

This scoping review does not contain any individual person’s data, images, or videos.

Author contributions

VH: Conceptualization, Methodology, Formal analysis, Writing – original draft, Writing – review & editing, Supervision, Project administration. LT: Conceptualization, Data curation, Formal analysis, Investigation, Writing – original draft, Writing – review & editing. XF: Data curation, Investigation, Validation, Writing – review & editing. XY: Methodology, Data curation, Writing – review & editing. JY: Supervision, Writing – review & editing, Funding acquisition. YJL: Methodology, Supervision, Writing – review & editing.

Funding

The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Hong Kong Jockey Club STEM Lab for Digital Oncology Care Enhancement (DOCE).

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Data Availability Statement

All data generated or analyzed during this study are included in this published article and its supplementary information files.*

Supplemental material

Supplemental material for this article is available online.

References

World Health Organization . Breast cancer. https://www.who.int/news-room/fact-sheets/detail/breast-cancer Published 2024. Accessed April 7, 2026.

Huang

Chan

Ngai

, et al. Worldwide Burden, Risk Factors, and Temporal Trends of Ovarian Cancer: A Global Study. Cancers (Basel) 2022; 14(9): 2230. https://doi.org/10.3390/cancers14092230

Sun

Meng

Yao

, et al. Germline Mutations in Cancer Susceptibility Genes in a Large Series of Unselected Breast Cancer Patients. Clinical Cancer Research 2017; 23(20): 6113–6119. https://doi.org/10.1158/1078-0432.CCR-16-3227

Rinder

Marcille

Sinel-Boucher

, et al. Dynamic Projection of Medication Nonpersistence and Nonadherence Among Patients With Early Breast Cancer. JAMA Netw Open 2024; 7(5): E2411909. https://doi.org/10.1001/JAMANETWORKOPEN.2024.11909

Bouwman

Eeltink

Visser

, et al. Prevalence and associated factors of medication non-adherence in hematological-oncological patients in their home situation. BMC Cancer 2017; 17(1): 739. https://doi.org/10.1186/s12885-017-3735-1

Lin

Clark

, et al. Breast cancer oral anti-cancer medication adherence: a systematic review of psychosocial motivators and barriers. Breast Cancer Res Treat 2017; 165(2): 247–260. https://doi.org/10.1007/S10549-017-4317-2

Zheng

Chagpar

. Contribution of cost to treatment nonadherence in the US breast cancer survivors: a population-based analysis. Breast Cancer Res Treat 2022; 192(2): 369–373. https://doi.org/10.1007/S10549-022-06510-W

Solbjør

Sand

Ervik

, et al. Patient experiences of waiting times in standardised cancer patient pathways in Norway – a qualitative interview study. BMC Health Serv Res 2021; 21(1): 651. https://doi.org/10.1186/s12913-021-06679-8

Arogyaswamy

Vukovic

Keniston

, et al. The Impact of Hospital Capacity Strain: a Qualitative Analysis of Experience and Solutions at 13 Academic Medical Centers. J Gen Intern Med 2022; 37(6): 1463–1474. https://doi.org/10.1007/s11606-021-07106-8

10.

Springer

Mehnert-Theuerkauf

Gebhardt

, et al. Unmet supportive care needs among cancer patients: exploring cancer entity-specific needs and associated factors. J Cancer Res Clin Oncol 2024; 150(4): 190. https://doi.org/10.1007/s00432-024-05715-4

11.

Davis

O’Malley

Bator

, et al. Rationale and design of extended cancer education for longer term survivors (EXCELS): a randomized control trial of ‘high touch’ vs. ‘high tech’ cancer survivorship self-management tools in primary care. BMC Cancer 2019; 19(1): 340. https://doi.org/10.1186/s12885-019-5531-6

12.

Hussain

Ameri Sianaki

Ababneh

. A Survey on Conversational Agents/Chatbots Classification and Design Techniques. In: Web, Artificial Intelligence and Network Applications. WAINA, 2019, pp. 946–956. https://doi.org/10.1007/978-3-030-15035-8_93

13.

Aslam

. The Impact of Artificial Intelligence on Chatbot Technology: A Study on the Current Advancements and Leading Innovations. European Journal of Technology 2023; 7(3): 62–72. https://doi.org/10.47672/ejt.1561

14.

Adamopoulou

Moussiades

. Chatbots: History, technology, and applications. Machine Learning with Applications 2020; 2: 100006. https://doi.org/10.1016/j.mlwa.2020.100006

15.

Xing

, et al. Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), July 30–August 4, Vancouver, Canada, 2017; 1: 496–505. https://doi.org/10.18653/V1/P17-1046

16.

Hien

Cuong

Nam

LNH

, et al. Intelligent assistants in higher-education environments: The FIT-EBOt, a chatbot for administrative and learning support. ACM International Conference Proceeding Series, December 6–7, 2018, Danang City, Viet Nam, 2018: 69–76. https://doi.org/10.1145/3287921.3287937

17.

Huang

Hew

Fryer

. Chatbots for language learning—Are they really useful? A systematic review of chatbot supported language learning. J Comput Assist Learn 2022; 38(1): 237–257. https://doi.org/10.1111/jcal.12610

18.

Görtz

Baumgärtner

Schmid

, et al. An artificial intelligence-based chatbot for prostate cancer education: Design and patient evaluation study. Digit Health 2023; 9: 20552076231173304. https://doi.org/10.1177/20552076231173304

19.

Kataoka

Takemura

Sasajima

, et al. Development and Early Feasibility of Chatbots for Educating Patients With Lung Cancer and Their Caregivers in Japan: Mixed Methods Study. JMIR Cancer 2021; 7(1): e26911. https://doi.org/10.2196/26911

20.

Schmidlen

Jones

Campbell Salome

, et al. Use of a chatbot to increase uptake of cascade genetic testing. J Genet Couns 2022; 31(5): 1219–1230. https://doi.org/10.1002/jgc4.1592

21.

Ahmad

Premanandan

Cajander

, et al. A Qualitative Study with Informal Caregivers and Healthcare Professionals for Individuals with Head and Neck Cancer on the Usage of AI Chatbots. Stud Health Technol Inform, Digital Health and Informatics Innovations for Sustainable Health Care Systems 2024; 316:751–755. https://doi.org/10.3233/SHTI240522

22.

Chen

Agbodike

Kuo

, et al. Online Textual Symptomatic Assessment Chatbot Based on Q& A Weighted Scoring for Female Breast Cancer Prescreening. Applied Sciences 2021; 11(11): 5079. https://doi.org/10.3390/app11115079

23.

Lucas

Gratch

King

, et al. It’s only a computer: Virtual humans increase willingness to disclose. Comput Human Behav 2014; 37: 94–100. https://doi.org/10.1016/J.CHB.2014.04.043

24.

Miner

Milstein

Schueller

, et al. Smartphone-Based Conversational Agents and Responses to Questions About Mental Health, Interpersonal Violence, and Physical Health. JAMA Intern Med 2016; 176(5): 619–625. https://doi.org/10.1001/JAMAINTERNMED.2016.0400

25.

Wang

Ding

Luo

. Future of ChatGPT in Pharmacovigilance. Drug Saf 2023; 46(8): 711–713. https://doi.org/10.1007/s40264-023-01315-2

26.

Sanders

, et al. Chatbot for Health Care and Oncology Applications Using Artificial Intelligence and Machine Learning: Systematic Review. JMIR Cancer 2021; 7(4): e27850. https://doi.org/10.2196/27850

27.

Wang

Qian

Briggs

, et al. The Use of Chatbots in Oncological Care: A Narrative Review. Int J Gen Med 2023; 16: 1591–1602. https://doi.org/10.2147/IJGM.S408208

28.

Goumas

Dardavesis

Syrigos

, et al. Chatbots in Cancer Applications, Advantages and Disadvantages: All that Glitters Is Not Gold. J Pers Med 2024; 14(8): 877. https://doi.org/10.3390/jpm14080877

29.

Lin

Sun

Chen

, et al. Chatbots for breast cancer education: a systematic review and meta-analysis. Supportive Care in Cancer 2025; 33(1): 55. https://doi.org/10.1007/s00520-024-09096-9

30.

Arksey

O’Malley

. Scoping studies: towards a methodological framework. Int J Soc Res Methodol 2005; 8(1): 19–32. https://doi.org/10.1080/1364557032000119616

31.

Levac

Colquhoun

O’Brien

. Scoping studies: advancing the methodology. Implementation Science 2010; 5(1): 69. https://doi.org/10.1186/1748-5908-5-69

32.

Tricco

Lillie

Zarin

, et al. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med 2018; 169(7): 467–473. https://doi.org/10.7326/M18-0850

33.

Agarwal

Gupta

. Chatbots and virtual assistants: a bibliometric analysis. Library Hi Tech 2022; 40(4): 1013–1030. https://doi.org/10.1108/LHT-09-2021-0330

34.

Pham

Rajić

Greig

, et al. A scoping review of scoping reviews: advancing the approach and enhancing the consistency. Res Synth Methods 2014; 5(4): 371–385. https://doi.org/10.1002/jrsm.1123

35.

. Evidence-Based Medicine Must Be. Journal of Medicine and Philosophy 2009; 34(5): 509–527. https://doi.org/10.1093/jmp/jhp034

36.

Al-Hilli

Noss

Dickard

, et al. A Randomized Trial Comparing the Effectiveness of Pre-test Genetic Counseling Using an Artificial Intelligence Automated Chatbot and Traditional In-person Genetic Counseling in Women Newly Diagnosed with Breast Cancer. Ann Surg Oncol 2023; 30(10): 5990–5996. https://doi.org/10.1245/s10434-023-13888-4

37.

Bibault

Chaix

Guillemassé

, et al. A Chatbot Versus Physicians to Provide Information for Patients With Breast Cancer: Blind, Randomized Controlled Noninferiority Trial. J Med Internet Res 2019; 21(11): e15787. https://doi.org/10.2196/15787

38.

Tawfik

Ghallab

Moustafa

. A nurse versus a chatbot ‒ the effect of an empowerment program on chemotherapy-related side effects and the self-care behaviors of women living with breast Cancer: a randomized controlled trial. BMC Nurs 2023; 22(1): 102. https://doi.org/10.1186/s12912-023-01243-7

39.

Lee

Byun

Kim

, et al. A Study on Breast Cancer Patient Care Using Chatbot and Video Education for Radiation Therapy: A Randomized Controlled Trial. Int J Radiat Oncol Biol Phys 2025; 122(1): 84–92. https://doi.org/10.1016/j.ijrobp.2024.12.012

40.

Chaix

Bibault

Pienkowski

, et al. When Chatbots Meet Patients: One-Year Prospective Study of Conversations Between Patients With Breast Cancer and a Chatbot. JMIR Cancer 2019; 5(1): e12856. https://doi.org/10.2196/12856

41.

Nazareth

Hayward

Simmons

, et al. Hereditary Cancer Risk Using a Genetic Chatbot Before Routine Care Visits. Obstetrics & Gynecology 2021; 138(6): 860–870. https://doi.org/10.1097/AOG.0000000000004596

42.

Griewing

Gremke

Wagner

, et al. Challenging ChatGPT 3.5 in Senology—An Assessment of Concordance with Breast Cancer Tumor Board Decision Making. J Pers Med 2023; 13(10): 1502. https://doi.org/10.3390/jpm13101502

43.

Siglen

Vetti

Lunde

ABF

, et al. Ask Rosa – The making of a digital genetic conversation tool, a chatbot, about hereditary breast and ovarian cancer. Patient Educ Couns 2022; 105(6): 1488–1494. https://doi.org/10.1016/j.pec.2021.09.027

44.

Coen

Del Fiol

Kaphingst

, et al. Chatbot for the Return of Positive Genetic Screening Results for Hereditary Cancer Syndromes: Prompt Engineering Project. JMIR Cancer 2025; 11: e65848. https://doi.org/10.2196/65848

45.

Siglen

Vetti

Augestad

, et al. Evaluation of the Rosa Chatbot Providing Genetic Information to Patients at Risk of Hereditary Breast and Ovarian Cancer: Qualitative Interview Study. J Med Internet Res 2023; 25: e46571. https://doi.org/10.2196/46571

46.

Wollney

Sims

Ricks-Santi

, et al. Implementing a chatbot to promote hereditary breast & ovarian cancer genetic screening in women’s health: identifying barriers and facilitators to screening adoption. BMC Public Health 2025; 25(1): 2516. https://doi.org/10.1186/s12889-025-23488-4

47.

Siglen

Vetti

Lyssand

, et al. Patients’ and healthcare professionals’ experiences with implementing the Rosa chatbot in mainstream genetic testing for hereditary breast and ovarian cancer. J Genet Couns 2025; 34(5): e70119. https://doi.org/10.1002/jgc4.70119

48.

Chetlen

Artrip

Drury

, et al. Novel Use of Chatbot Technology to Educate Patients Before Breast Biopsy. Journal of the American College of Radiology 2019; 16(9): 1305–1308. https://doi.org/10.1016/j.jacr.2019.05.050

49.

Lukac

Dayan

Fink

, et al. Evaluating ChatGPT as an adjunct for the multidisciplinary tumor board decision-making in primary breast cancer cases. Arch Gynecol Obstet 2023; 308(6): 1831–1844. https://doi.org/10.1007/s00404-023-07130-5

50.

Sato

Haneda

Hiroshima

, et al. Preliminary Screening for Hereditary Breast and Ovarian Cancer Using an AI Chatbot as a Genetic Counselor: Clinical Study. J Med Internet Res 2024; 26: e48914. https://doi.org/10.2196/48914

51.

Chou

Chen

Lin

, et al. AI-driven patient support: Evaluating the effectiveness of ChatGPT-4 in addressing queries about ovarian cancer compared with healthcare professionals in gynecologic oncology. Supportive Care in Cancer 2025; 33(4): 337. https://doi.org/10.1007/s00520-025-09389-7

52.

Wolff

Kupka

Reichert

, et al. Personalized Support in Hereditary Breast and Ovarian Cancer After Genetic Counseling by the Chatbot-Based GENIE Mobile App: Proof-of-Concept Wizard of Oz Study. JMIR Form Res 2025; 9: e69115. https://doi.org/10.2196/69115

53.

Boie

Glastetter

Lux

, et al. Evaluating a Chatbot as a Companion for Patients With Breast Cancer: Collaborative Pilot Study. JMIR Cancer 2025; 11: e68426. https://doi.org/10.2196/68426

54.

Karuna

Reddy

Sushmitha

, et al. Helpi – An Automated Healthcare Chatbot. E3S Web of Conferences, 5–8 September 2023, Newcastle, England, 2023; 430: 01040. https://doi.org/10.1051/E3SCONF/202343001040

55.

Ashley Cheung

. ST. Literary Review of Artificial Intelligence in Ovarian Cancer: Transforming Diagnosis, Treatment, and Future Advancements. OxJournal 2024. https://www.oxjournal.org/literary-review-of-artificial-intelligence-in-ovarian-cancer/ (Accessed 7 April 2026).

56.

Hong

Ding

. Early Diagnosis of Ovarian Cancer: A Comprehensive Review of the Advances, Challenges, and Future Directions. Diagnostics 2025; 15(4): 406. https://doi.org/10.3390/diagnostics15040406

57.

Sebastian

Peter

. Artificial Intelligence in Cancer Research: Trends. Challenges and Future Directions 2022; 12(12): 1991. https://doi.org/10.3390/life12121991

58.

Beesley

Price

Webb

, et al. Changes in supportive care needs after first line treatment for ovarian cancer: identifying care priorities and risk factors for future unmet needs. Psychooncology 2013; 22(7): 1565–1571. https://doi.org/10.1002/pon.3169

59.

Fujihara

Sone

. Machine Learning Approach to Drug Treatment Strategy for Diabetes Care. Diabetes Metab J 2023; 47(3): 325–332. https://doi.org/10.4093/DMJ.2022.0349

60.

Gupta

Viciano

Wormer

, et al. Exploring Unsupervised Semantic Similarity Methods for Claim Verification in Health Care News Articles. In: Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing. Varna: INCOMA Ltd., 2023, pp. 440–447. https://aclanthology.org/2023.ranlp-1.49/ (Accessed 7 April 2026).

61.

Huang

, et al. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. ACM Trans Inf Syst 2025; 43(2): 1–55. https://doi.org/10.1145/3703155

62.

Takamura

Umezawa

. Privacy-Preserving Retrieval-Augmented Generation on Local Devices for Regenerative Medicine Applications. medRxiv 2025; [preprint]. https://doi.org/10.1101/2025.10.20.25337146

63.

Zhang

Rouhizadeh

, et al. Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications [preprint]. ArXiv 2025; https://doi.org/10.21203/rs.3.rs-8330917/v1

64.

Jakobsen

. Reconceptualizing the Digital Divide as Digital Disability: Implications for Health Equity. OSF Preprints 2024; https://doi.org/10.31235/osf.io/93kwp

65.

Safi

Abd-Alrazaq

Khalifa

, et al. Technical Aspects of Developing Chatbots for Medical Applications: Scoping Review. J Med Internet Res 2020; 22(12): e19127. https://doi.org/10.2196/19127

66.

Hindelang

Sitaru

Zink

. Transforming Health Care Through Chatbots for Medical History-Taking and Future Directions: Comprehensive Systematic Review. JMIR Med Inform 2024; 12: e56628. https://doi.org/10.2196/56628

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.14 MB