Enhancing Aviation Safety through AI-Driven Mental Health Management for Pilots and Air Traffic Controllers

Abstract

This article provides an overview of the mental health challenges faced by pilots and air traffic controllers (ATCs), whose stressful professional lives may negatively impact global flight safety and security. The adverse effects of mental health disorders on their flight performance pose a particular safety risk, especially in sudden unexpected startle situations. Therefore, the early detection, prediction and prevention of mental health deterioration in pilots and ATCs, particularly among those at high risk, are crucial to minimize potential air crash incidents caused by human factors. Recent research in artificial intelligence (AI) demonstrates the potential of machine and deep learning, edge and cloud computing, virtual reality and wearable multimodal physiological sensors for monitoring and predicting mental health disorders. Longitudinal monitoring and analysis of pilots’ and ATCs physiological, cognitive and behavioral states could help predict individuals at risk of undisclosed or emerging mental health disorders. Utilizing AI tools and methodologies to identify and select these individuals for preventive mental health training and interventions could be a promising and effective approach to preventing potential air crash accidents attributed to human factors and related mental health problems. Based on these insights, the article advocates for the design of a multidisciplinary mental healthcare ecosystem in modern aviation using AI tools and technologies, to foster more efficient and effective mental health management, thereby enhancing flight safety and security standards. This proposed ecosystem requires the collaboration of multidisciplinary experts, including psychologists, neuroscientists, physiologists, psychiatrists, etc. to address these challenges in modern aviation.

Introduction

It is widely recognized that human factors account for approximately 80 percent of all accidents in modern civil and military aviation.^1–4 Within this context, the issue of human mental health is often not sufficiently addressed as a significant risk factor for safety, with the bulk of responsibility for managing mental health falling on the shoulders of the pilots themselves.⁵ A 2023 study published in the Journal of Occupational and Environmental Medicine revealed that 72 percent of pilots admitted to avoiding health care for fear of jeopardizing their employment.⁶ Such barriers and stigma around mental health, combined with the inherently stressful lifestyles of pilots and air traffic controllers (ATCs) pose significant challenges to the safety and security of global aviation. This concern has motivated entities such as the United States National Transportation Safety Board and the Federal Aviation Administration (FAA) to address these issues in the recent “Navigating Mental Health in Aviation” summit.⁷

The unregulated use of certain psychopharmacological medications to manage anxiety or depression can lead to undesirable mental health conditions, posing additional risks to flight safety and security. Acknowledging the undeniable importance of evidence-based pharmacotherapy and psychotherapy for treating conditions such as depression and anxiety,^8–10 it is critical to consider that certain medications can impair cognitive functions^11,12 such as attention, situational awareness and decision-making abilities, potentially leading to catastrophic outcomes. These medications are often incompatible with the duties of the pilots and ATCs or require careful monitoring by healthcare professionals to mitigate flight safety risks.^13–15 According to official reports, the unreported use of psychopharmacological and psychoactive medications has been causally linked to 4–5 percent of fatal aviation accidents in the official accident reports.¹⁶

Thus, a thorough and cutting-edge assessment of the mental health and readiness of pilots and ATCs in their high-stress professional environments is imperative. The introduction of an overloaded, stressful professional lifestyle, jet lag, and inadequate rest can disrupt circadian rhythms, leading to fatigue, burnout, anxiety, depression, chronic stress and potentially posttraumatic stress disorder (PTSD), culminating in poor collaboration both with systems and fellow humans. Numerous issues related to these conditions have been explored within the Human Factors Analysis and Classification System⁴ framework. Mental health disorders among pilots and ATCs can significantly impact their functional performance, manifesting as decreased situational awareness, reduced workload capacity, diminished attention focus, slower visuomotor responses, and mind wandering, among others. The long-term consequences of such states can adversely affect overall performance, behavior, and decision-making processes, potentially leading to tragic accidents and loss of life. The early identification and timely intervention for these vulnerable individuals are therefore of paramount importance.

Mental Health Disorders as Security Challenges in Civil Aviation

In 2015, following the tragic Germanwings Flight 9525 incident where a co-pilot deliberately crashed a passenger plane into the French Alps, killing all 150 people on board, the FAA established the Pilot Fitness Aviation Rulemaking Committee.¹⁷ This committee was tasked with evaluating pilot mental health to address such catastrophic incidents head-on. In addition, suicidal tendencies and actions by pilots or co-pilots have been implicated in the mysterious disappearance of Malaysia Flight 370, which resulted in the loss of all 239 passengers. Despite these high-profile cases, research and development aimed at predicting and preventing mental health deterioration among civil aviation pilots and ATCs is still in its infancy.

Research shows that the prevalence of mental health disorders within the pilot population is between 6.7 percent and 12 percent, with pilots under higher workloads experiencing an increased prevalence of 23.7 percent.¹⁸ Rates of depression and suicidal ideation, standing at 12–13 percent and 4 percent, respectively, pose significant safety risks.¹⁹ These rates, largely in line with the general population,¹⁹ suggest that the pilot population is more resilient, considering the pressures of their profession. However, the negative impact of acute and chronic mental health disorders, such as anxiety, depression, burnout, PTSD etc. on pilots’ and ATCs’ functional performance represents a unique safety risk, as shown in Figure 1, especially in the face of sudden unexpected startle situations, which are well-known precursors^20,21 to various commercial aviation accidents.

FIG. 1.

Adverse impact of mental health disorders on pilots’/ATCs’ functional performance. ATC, air traffic controllers.

Mental health disorders are one of the most common reasons, after cardiovascular diseases, for the revocation of an aviation license,²² leading pilots to conceal symptoms and medication usage from aviation authorities due to fear of job loss. Pilots are also reluctant to seek mental health support from aeromedical professionals, who are tasked by regulatory authorities to conduct regular aeromedical assessments,²³ or from mental health professionals, who may lack familiarity with aviation treatment protocols²⁴ and are viewed with skepticism by pilots.²² The challenge of mitigating mental health related flight safety risks through personality questionnaires during the selection process is further complicated by the pressure on individuals to provide socially desirable answers due to stigma.^25,26

Safety management programs mandated by the aviation regulators have a limited focus on pilot mental health and wellbeing,^23,27 overlooking several relevant mental health-related safety risks. As a result, the comprehensive monitoring of mental health, though critical, is viewed as both expensive and sensitive by airlines and is unlikely to be undertaken without specific governmental guidelines.²⁶

Potential of Digital Psychiatry and Cyberpsychology in Prediction and Prevention of Mental Health Disorders

The application of advanced tools for the prevention and treatment of stress-related disorders^28–35 holds significant promise to improve the mental health and readiness of pilots and ATCs in the future. A preventive approach, translatable to their selection, training and education, and based on cutting-edge artificial intelligence (AI) tools and processes using multimodal adaptive stimulation and multimodal real-time neuro-psycho-physiological feedback, has been explored in research. This includes virtual reality-enhanced cognitive behavioral exposure therapy, stress inoculation training, and similar stress management techniques.^{29,30,34–45} Psychological interventions adapted from clinical settings to resilience programs for professionals in high-stress jobs have been grounded in cognitive-behavioral exposure therapy,⁴⁶ stress inoculation training,⁴⁷ stress exposure training,⁴⁸ mental readiness training,⁴⁹ emotion regulation frameworks,^50,51 cognitive restructuring,⁵² and mindfulness training.^53,54 There are several research studies related to the application of these approaches in the aviation domain.^55–60

Research integrating these approaches with digital technologies such as virtual and mixed reality, physiological monitoring and AI in contexts such as astronaut training, stress, burnout and PTSD prevention, and treatment of phobias and anxiety disorders shows their potential.^{28–30,34,35,38,61–71} These technologies could provide valuable longitudinal data on the pilots’ and ATCs’ states throughout their professional life cycle,^72–80 helping to predict those at risk of acute and chronic mental health disorders. The use of AI and machine learning (ML) is critical for efficient and effective mental health management in the increasingly stressful aviation industry. Predictive AI-based methods^81–94 can identify patterns of potential chronic psychopathology early enough to prevent severe mental illnesses among highly stressed employees and improve their mental health with appropriate training techniques. Evaluation of ML model performance in detecting broad stress-related responses in aviation (e.g., levels of workload, mental fatigue, etc.) has been done in a variety of studies, with accuracies ranging from 0.61 to 0.94,⁹⁵ up to maximum 0.97.⁹⁶ Similar evaluations of ML models are also discussed in the context of detection of mental health problems in different populations, using metrics such as accuracy, precision, recall and/or F1 score, with results up to 0.96.⁹⁷ Table 1 illustrates a fraction of research literature evaluating ML model performance in the detection and prediction of various mental health disorders.

Table 1.

Performance of Selected ML Models in the Detection and Prediction of Various Mental Health Disorders

Research article	Subjects and goals	ML model evaluation results
(Schultebraucks et al., 2022, Psychological Medicine)⁸⁶	n = 81 emergency department patients, assessed 1-month posttrauma Classify PTSD status vs. no PTSD Classify depression status vs. no depression	PTSD: 0.90 AUC, 0.83 precision, 0.84 recall, 0.83 F1 score Depression: 0.86 AUC, 0.83 precision, 0.82 recall, 0.82 F1 score
(Li et al., 2022, Journal of Affective Disorders)⁸⁷	n = 1107 Chinese firefighters Classify PTSD-positive vs. PTSD-negative firefighters	0.93 AUC, 0.85+ sensitivity, 0.85+ specificity
(Schultebraucks et al., 2020, Nature Medicine)⁸⁵	n = 377 emergency department patients for model development n = 221 emergency department patients at different site, for model external validation Predict PTSD status at 12 months vs. no PTSD	External validation: 0.87 AUC, 0.76 sensitivity, 0.91 specificity
(Karstoft et al., 2015, BMC Psychiatry)⁸³	n = 957 trauma survivors admitted to emergency department Predict nonremitting PTSD trajectory vs. other trajectories over the following 15 months	0.75 mean AUC (95% range: 0.67–0.80)
(Cai et al., 2018, Complexity)⁸⁸	n = 213 (92 depressed, 121 controls) Classify depressed vs. control	0.79 accuracy
(Liu et al., 2022, Brain Sciences)⁸⁹	n = 53, public dataset (24 depressed, 29 controls) n = 32, private dataset (16 depressed, 16 controls) Classify depressed vs. control	Public dataset: 0.89 accuracy Private dataset: 0.88 accuracy
(Shah et al., 2021, Translational Psychiatry)⁹⁰	n = 14 adults experiencing moderate depression symptoms Predict individualized depressed mood over 1 month on a 7-point Likert scale	0.77 ± 0.27 average maximum absolute error, across all subjects and models
(Pang et al., 2022, Pacific-Asia Conference on Knowledge Discovery and Data Mining)⁹¹	n = 4983 children Predict depression 2–4 years before the illness occurs vs. no depression	0.82 AUC, 0.70 precision, 0.80 recall, 0.74 F1 score
(Kinreich et al., 2021, Molecular Psychiatry)⁹²	n = 656 children Predict who will develop alcohol use disorder years later vs. who will not	European American ancestry: 0.69 specificity, 0.75 sensitivity African American ancestry: 0.74 specificity, 0.78 sensitivity
(dos Santos Machado et al., 2022, Psychological Medicine)⁹⁸	n = 32700, general United States population Predict who will attempt suicide over the next 3 years vs. who will not	0.89 AUC, 0.89 specificity, 0.74 sensitivity

AUC, area under receiver operating characteristic (ROC) curve; ML, machine learning; PTSD, posttraumatic stress disorder.

However, there are significant challenges in the clinical use of ML for predicting, preventing, diagnosing, and treating mental health disorders,^99,100 especially concerning the prediction of rare events such as suicides, which could lead to a high number of false positives.^98,101–103 Despite these challenges, the potential of predictive technologies warrants further AI-based research to enhance the safety and security of the modern aviation industry. Moreover, explainable AI could serve as a self-explanatory digital assistant to flight management personnel, identifying specific patterns and hidden warning signs of mental deterioration, enabling timely prevention and intervention.

A variety of multimodal neuro-psycho-physiological response features obtained by longitudinal tracking and monitoring may be valuable discriminators and predictors of pilot’s/ATCs’ stress resilience, mental health disorders, and functional performance under stress, as different cognitive, emotional and behavioral conditions relevant for flight safety and security:^80,104–108

resting heart rate variability and respiratory sinus arrhythmia;

features of psychophysiological allostasis, for example, heart rate reaction to stress and poststress heart rate recovery;

features of phasic and tonic components of skin conductance signal;

electromyogram and electrodermal activity (EDA) based acoustic startle response features, such as startle habituation, fear-potentiated startle response, and prepulse inhibited startle response;

electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) features computed from the brain activity;

oculometric features, for example, eye blinking patterns, saccadic velocity, saccade length, fixation duration, movement dynamics, and pupil dilation and constriction;

prosodic features of the voice, for example, fundamental frequency, energy, jitter, shimmer, formants, zero-crossing rate, and cepstral coefficients.

In previous studies, we have successfully proven that fusing multiple dynamic physiological signals can determine the unique physiology of an individual under stress versus that same individual while not under stress.¹⁰⁹ This could allow for earlier, more personalized interventions.

Multimodal sensing of the pilot’s physiological, cognitive, and behavioral states during operational flights and their after-action review may help to predict individuals with potential acute or chronic mental health disorders (Figure 2). Comprehensive post-flight analysis of their multimodal features based on AI and ML tools and means can assist in early identification of individuals with potential or emerging mental health problems and select them for preventive mental health training or early treatments.^111–114 This might be a valuable contribution to existing methods of preventing potential unexplainable air crash accidents caused by human factors and related mental health problems. Continuous tracking, monitoring, and gathering of pilots’ vital multimodal physiological features and preventive computerized cognitive behavioral therapy, stress inoculation training, mindfulness training, etc. should be the key components of mental health preventive strategies to avoid previously mysterious and unexplainable air crash accidents. Therefore, in the near future, we can expect newly designed aircraft capabilities related to the extension of existing flight data and cockpit voice recorders merged with a pilot’s multimodal physiological flight recorder. Early detection of individuals who may have chronic stress or are at higher risk of stress vulnerability may enable proactive mental health management strategies, including psychological assessment and timely preventive cognitive-behavioral interventions, if necessary. This proposal is in line with similar initiatives for prediction and prevention of mental health disorders,^81,115 as well as with comprehensive proposals for the mental health management of commercial pilots.²⁷

FIG. 2.

Integration of multimodal sensors with AI tools and methods opens up new possibilities in pilot and ATC selection, training and operational monitoring, including improved detection, prediction, and prevention of mental health disorders (right photo, by NASA, is in the public domain¹¹⁰). AI, artificial intelligence; ATC, air traffic controllers.

Developing AI-Based Mental Healthcare Ecosystem in Civil Aviation

A new organizational culture related to mental healthcare management in the modern aviation industry is essential to prevent further degradation of human functional performance due to ever-increasing task overload, which significantly impacts the mental health of pilots and ATCs. In this context, the design, development, and establishment of a multidisciplinary digital mental healthcare ecosystem in civil aviation, focused on the prediction and prevention of mental health disorders, warrants heightened attention. Timely and appropriate preventive interventions among high-risk individuals before the onset of serious psychopathology are of paramount interest. The proposed AI-based predictive and preventive approach should be viewed as part of a comprehensive array of measures focusing on the protection of individual mental health among stressful aviation occupations. Early prediction, prevention, and treatment of mental health disorders in individuals at increased risk as soon as possible is extremely important^81,115 because delayed care of chronic mental health disorders is often less efficient and effective. New wearable disruptive technologies available today offer a tremendous opportunity to improve mental healthcare ecosystems in modern aviation, creating breakthrough solutions, which will improve mental healthcare and well-being outcomes on a greater scale than ever before. However, these new tools and means require clinical validation and trust to meet these challenges effectively. AI-based tools of unsupervised ML methods, such as multivariate correlation analyses, clustering, and principal component analysis, as well as a range of traditional supervised ML methods, such as artificial neural networks, support vector machines, and contemporary deep learning-supervised approaches, can significantly improve the prediction reliability and accuracy of potential mental health degradation within these stressful occupations.

Disruptive technology based on wearable digital sensors, digital therapeutic apps, and new AI and ML tools may provide tremendous opportunities to improve a continuum of mental health and well-being in our modern aviation industry, encompassing stress inoculation training, prediction, prevention and treatment. A variety of wearable devices, such as smart watches, wristwatches, armbands, wristbands, chest straps, shoes, helmets, glasses, lenses, rings, textiles, and hearing aids can collect huge amounts of data which might be used by a variety of ML methods, such as deep neural networks for training and predictive modeling of human mental states. The complexity of these applications may require high computational power, particularly with an increased number of customized multisensory inputs and modalities, numerous neuro-psycho-physiological features, and sophisticated ML training algorithms. Therefore, these applications will necessitate sufficient distributed processing power, an adequate amount of memory, high-speed interfaces capable of moving large amounts of data, multisensory and multimodal input-output interaction devices, etc. Such applications require immediate analysis and processing of large datasets, timely decisions, and accurate decision-making.

Usage of distributed architectures and cloud computing related to analysis of big data sets on multiple hierarchical levels, as along with advanced ML algorithms and advanced analytics, may provide accurate and insightful identification of individuals with compromised mental health. While cloud computing offers the flexibility of storage and computational resources on-demand, it comes with compromises in higher costs, power consumption, latency, and challenges for preserving the privacy of both the data and ML model. If the sensor data are stored on centralized servers with personally identifiable information about an individual’s mental health, and if that information is hacked, the individual’s privacy might be compromised. Therefore, acquiring and processing sensory data on local devices keeps the data private and decreases the latency for the prediction/classification, because there is no need to transmit large amounts of data from edge devices to the cloud outside of the user’s control. However, this cloud-edge computing architecture (Figure 3) depends on specific applications, the size of the data streams, and ML models to be used in training and testing.

FIG. 3.

Proposed airline’s AI-based mental healthcare ecosystem (figure includes fragments from public domain and Creative Commons Attribution (CC-BY) sources^116–121). AI, artificial intelligence; CC-BY.

The proposed new AI-based ecosystem for mental health monitoring and management of aviation staff might include, for example, an AI assistant for recommendations of mental-health checkups and mental health screening and evaluation in specialized clinics, when necessary. However, a well-balanced organizational approach to design and building this ecosystem requires a multidisciplinary team of psychologists, neuroscientists, physiologists, psychiatrists, sociologists, aeromedical personnel, policy and legal experts, aviation industry regulators, governmental authorities, as well as representatives of airline companies and aviation professionals’ associations. Additional expertise related to ethical considerations,¹²² data protection and privacy,¹²³ trustworthiness,¹²⁴ explainable AI,^125,126 as well as cost-efficiency and scalability,¹²⁷ is also important. Therefore, leaders of proposed changes related to an AI-based mental healthcare ecosystem in the modern aviation industry require additional education and training to avoid any potential misuse of uncontrollable technological changes related to machine and deep learning, big data, wearable and wireless sensors, edge and cloud computing, virtual and augmented reality etc., because of their potential immaturity in transitional times. Furthermore, building the culture of more transparency and tolerance regarding mental health challenges is critically important, as well as avoiding any hasty premature technology deployment that might have unintended adverse consequences, as witnessed in the past.¹²⁸ All these multidisciplinary and multidimensional issues should be also put in the broader context of Safety I, II, and III.¹²⁹ Such a holistic and more balanced integrative approach has potential to provide higher levels of flight safety and security.

Conclusions

An April 2024 article by the Royal Aeronautical Society on “Psychosocial Risk Management and Mental Health”¹³⁰ emphasizes the importance of managing psychosocial risks within the aviation industry to enhance safety and operational efficiency. Overall, it calls for the aviation industry to acknowledge and address these risks with the same rigor as physical safety risks, recognizing the profound impact they may have on overall safety and efficiency. Building on this foundational understanding, the advancement of AI-based research in predicting, preventing, and treating serious mental health disorders among aviation employees may play an important role in maintaining the safety and security of the modern aviation industry.

Continuous and comprehensive monitoring of complex human physiological parameters using a wide range of wearable sensors enables the early identification of compromised physiological and cognitive states. This approach has the potential to offer several advantages, such as improved safety and security, better healthcare management in aviation, and an enhancement in performance quality, life satisfaction, and overall well-being.

Enhancements of mental health care and safety management in aviation proposed in the recent literature,^27,131 augmented by new AI-based tools and methodologies, should be a cornerstone of an improved prevention strategy aimed at circumventing the dire consequences of mental health deterioration within aviation organizations. The ability to make reliable predictions more quickly and accurately is essential for preventing the transition from acute stress to more severe chronic mental health disorders, such as PTSD or burnout. This is particularly crucial for individuals at high risk due to their stressful job conditions and constant cognitive overload. Timely predictive modeling might therefore be lifesaving, especially for employees facing severe mental health challenges.

Relatively lower classification or prediction accuracy in some published articles^89–92,98 can be significantly improved by multimodal measurements, based on data fusion of EEG, fNIRS, ECG, EDA, and electromyography (EMG) features, as well as with comprehensive oculometric and speech/acoustic features. Such state-of-the-art multimodal approach enhanced with new deep learning algorithms can substantially improve classification or prediction accuracy, in general. Such tools and means as new assistive technology in modern mental health management can help in early identification and prevention of serious mental health disorders in modern overburdened civil aviation today.

By monitoring vital physiological signs and managing stress levels while adhering to ethical guidelines and data privacy,^131,132 proactive stress management can significantly enhance safety and security within the aviation industry. As technology continues to advance, bringing more processing power, larger data storage capacities, a wider range of sensors, more sophisticated AI and ML algorithms, and improved prediction accuracy, we have the opportunity to design, develop, and validate more advanced multi-purpose, cost-effective capabilities. These capabilities can facilitate immediate alerting, stress detection, and stress management in modern aviation, positively impacting the lives of millions worldwide.

Footnotes

Author Disclosure Statement

No competing financial interests exist.

Funding Information

No funding was received for this article.

References

de Hoyos

. Human Factor in Military Aviation Accidents II: A Summary of 21 USAF Accidents Extracted from Accident Investigation Board (AIB) Public Reports. 2023. Available from: https://www.amazon.com/Human-Factor-Military-Aviation-Accidents-ebook/dp/B0BTB46WVY

National Commission for Military Aviation Safety (NCMAS). Military Aviation Losses FY2013-2020. Report to the President and the Congress of the United States. 2020. Available from: https://www.globalsecurity.org/military/library/report/2020/ncmas_final_report_20201201.pdf

Rankin

. MEdA investigation process. Boeing Commercial Aero. Available from: https://www.boeing.com/commercial/aeromagazine/articles/qtr_2_07/AERO_Q207_article3.pdf

Shappell

, Wiegmann

. The Human Factors Analysis and Classification System: HFACS. Civil Aeromedical Institute. United States. Office of Aviation Medicine; DOT/FAA/AM-00/7. 2000. Available from: https://rosap.ntl.bts.gov/view/dot/21482/dot_21482_DS1.pdf

Silva

, Santos

, Melicio

, et al. Aviation’s approach towards pilots’ mental health: A review. Int Rev Aerosp Eng, 2022; 15(6):294–307; doi: 10.15866/irease.v15i6.22645

Patel

, Hoffman

, Aden

, et al. Health care avoidance among Canadian pilots due to fear of medical certificate loss: A National Cross-Sectional Survey Study. J Occup Environ Med, 2023; 65(6):e413–e417; doi: 10.1097/JOM.0000000000002838

National Transportation Safety Board. NTSB to Hold Summit on Pilot Mental Health. 2023 Nov 30. Available from: https://www.ntsb.gov/news/press-releases/Pages/NR20231130A.aspx

Cuijpers

, Sijbrandij

, Koole

, et al. The efficacy of psychotherapy and pharmacotherapy in treating depressive and anxiety disorders: A meta‐analysis of direct comparisons. World Psychiatry, 2013; 12(2):137–148; doi: 10.1002/wps.20038

Cuijpers

, van Straten

, Warmerdam

, et al. Psychotherapy versus the combination of psychotherapy and pharmacotherapy in the treatment of depression: A meta‐analysis. Depress Anxiety, 2009; 26(3):279–288; doi: 10.1002/da.20519

10.

Kamenov

, Twomey

, Cabello

, et al. The efficacy of psychotherapy, pharmacotherapy and their combination on functioning and quality of life in depression: A meta-analysis. Psychol Med, 2017; 47(3):414–425; doi: 10.1017/S0033291716002774

11.

Meador

. Cognitive side effects of medications. Neurol Clin, 1998; 16(1):141–155; doi: 10.1016/s0733-8619(05)70371-6

12.

Stein

, Strickland

. A review of the neuropsychological effects of commonly used prescription medications. Arch Clin Neuropsychol, 1998; 13(3):259–284; doi: 10.1016/S0887-6177(97)00027-9

13.

Federal Aviation Administration. Does the FAA Have a List of Prescription and Over-The-Counter Drugs that Pilots Can and Cannot Take while Flying? Available from: https://www.faa.gov/faq/does-faa-have-list-prescription-and-over-counter-drugs-pilots-can-and-cannot-take-while-flying [Last accessed: May 3, 2024].

14.

Federal Aviation Administration. Guide for Aviation Medical Examiners. Decision Considerations - Aerospace Medical Dispositions. Item 47. Psychiatric Conditions. 2023 Mar 10. Available from: https://www.faa.gov/ame_guide/app_process/exam_tech/item47/amd#:∼:text=The%20use%20of%20a%20psychotropic,analeptics%2C%20anxiolytics%2C%20and%20hallucinogens [Last accessed: May 3, 2024].

15.

European Union Aviation Safety Agency. Use of Medication in Aviation – Advice for Aeromedical Examiners. Available from: https://www.easa.europa.eu/en/use-medication-aviation-advice-aeromedical-examiners [Last accessed: May 3, 2024].

16.

Vuorio

, Budowle

, Sajantila

, et al. Duty of notification and aviation safety—a study of fatal aviation accidents in the United States in 2015. Int J Environ Res Public Health, 2018; 15(6):1258; doi: 10.3390/ijerph15061258

17.

Federal Aviation Administration. Pilot Fitness Aviation Rulemaking Committee Report. 2015 Nov 18. Available from: https://www.faa.gov/regulations_policies/rulemaking/committees/documents/media/pilot%20fitness%20arc%20report.11302015.pdf

18.

Feijó

, Luiz

, Camara

. Common mental disorders among civil aviation pilots. Aviat Space Environ Med, 2012; 83(5):509–513; doi: 10.3357/asem.3185.2012

19.

DeHoff

, Cusick

. Mental health in commercial aviation - depression & anxiety of pilots. Int J Aviat Aeronaut Aerosp, 2018; 5(5):5; doi: 10.58940/2374-6793.1287

20.

Landman

, Groen

, Van Paassen

, et al. Dealing with unexpected events on the flight deck: A conceptual model of startle and surprise. Hum Factors, 2017; 59(8):1161–1172; doi: 10.1177/0018720817723428

21.

Martin

, Murray

, Bates

. The effects of startle on pilots during critical events: A case study analysis. In: Proceedings of 30th EAAP Conference: Aviation Psychology & Applied Human Factors; 2012; pp. 387–394.

22.

Bor

. Psychological factors in airline passenger and crew behaviour: A clinical overview. Travel Med Infect Dis, 2007; 5(4):207–216; doi: 10.1016/j.tmaid.2007.03.003

23.

Cahill

, Cullen

, Anwer

, et al. Pilot work related stress (WRS), effects on wellbeing and mental health, and coping methods. Int J Aerosp Psychol, 2021; 31(2):87–109; doi: 10.1080/24721840.2020.1858714

24.

Vuorio

, Laukkala

, Navathe

. Major depression and fitness to fly by different aviation authorities. Aviat Space Environ Med, 2012; 83(9):909–911; doi: 10.3357/asem.3363.2012

25.

Butcher

. Psychological assessment of airline pilot applicants with the MMPI-2. J Pers Assess, 1994; 62(1):31–44; doi: 10.1207/s15327752jpa6201_4

26.

Butcher

. Assessing pilots with ‘the wrong stuff’: A call for research on emotional health factors in commercial aviators. Int J Selection Assessment, 2002; 10(1-2):168–184; doi: 10.1111/1468-2389.00204

27.

Cahill

, Cullen

, Gaynor

. Interventions to support the management of work-related stress (WRS) and wellbeing/mental health issues for commercial pilots. Cogn Tech Work, 2020; 22(3):517–547; doi: 10.1007/s10111-019-00586-z

28.

Ćosić

, Popović

, Jovanovic

, et al. Physiology-driven adaptive VR system: Technology and rationale for PTSD treatment. Annu Rev CyberTherapy Telemed, 2007; 5:179–191.

29.

Ćosić

, Popović

, Kukolja

, et al. Physiology-driven adaptive virtual reality stimulation for prevention and treatment of stress related disorders. Cyberpsychol Behav Soc Netw, 2010; 13(1):73–78; doi: 10.1089/cyber.2009.0260

30.

Ćosić

, Popović

, Horvat

, et al. Computer-aided psychotherapy based on multimodal elicitation, estimation and regulation of emotion. Psychiatr Danub, 2013; 25(3):340–346.

31.

Dropuljić

, Mijić

, Petrinović

, et al. Vocal analysis of acoustic startle responses. IEEE ACM Trans Audio Speech Lang Process, 2018; 26(2):318–329; doi: 10.1109/TASLP.2017.2775742

32.

Horvat

, Bogunović

, Ćosić

. STIMONT: A core ontology for multimedia stimuli description. Multimed Tools Appl, 2014; 73(3):1103–1127; doi: 10.1007/s11042-013-1624-4

33.

Kukolja

, Popović

, Horvat

, et al. Comparative analysis of emotion estimation methods based on physiological measurements for real-time applications. Int J Hum Comput Stud, 2014; 72(10-11):717–727; doi: 10.1016/j.ijhcs.2014.05.006

34.

Popovic

, Slamic

, Cosic

. scenario self-adaptation in virtual reality exposure therapy of posttraumatic stress disorder. In: Proceedings of the NATO Advanced Research Workshop on Novel Approaches to the Diagnosis and Treatment of Posttraumatic Stress Disorder. (Roy M, ed.) 2005 Jun 13–16; Cavtat-Dubrovnik, Croatia. NATO Security through Science Series E Human and Societal Dynamics. IOS Press: Amsterdam; 2006; pp. 135–147.

35.

Popovic

, Horvat

, Kukolja

, et al. Stress inoculation training supported by physiology-driven adaptive virtual reality stimulation. Annu Rev CyberTherapy Telemed, 2009:50–54.

36.

de Visser

, Dorfman

, Chartrand

, et al. Building resilience with the stress resilience training system: Design validation and applications. Work, 2016; 54(2):351–366; doi: 10.3233/WOR-162295

37.

Gaggioli

, Gorini

, Wiederhold

, et al. Interreality in the treatment of psychological stress in soldiers: rationale and protocol of the INTERSTRESS project. In: Coping with Posttraumatic Stress Disorders in Returning Troops. ( Wiederhold

, ed.) NATO Science for Peace and Security Series—E: Human and Societal Dynamics; IOS Press: Amsterdam; 2010; pp. 221–234.

38.

Gaggioli

, Pallavicini

, Morganti

, et al. Experiential virtual scenarios with real-time monitoring (interreality) for the management of psychological stress: A block randomized controlled trial. J Med Internet Res, 2014; 16(7):e3235; doi: 10.2196/jmir.3235

39.

Hourani

, Tueller

, Kizakevich

, et al. Toward preventing post-traumatic stress disorder: Development and testing of a pilot predeployment stress inoculation training program. Mil Med, 2016; 181(9):1151–1160; doi: 10.7205/MILMED-D-15-00192

40.

Hourani

, Tueller

, Kizakevich

, et al. Effect of stress inoculation training with relaxation breathing on perceived stress and posttraumatic stress disorder in the military: A longitudinal study. Int J Stress Manag, 2018; 25(S1):124–136; doi: 10.1037/str0000082

41.

Pallavicini

, Argenton

, Toniazzi

, et al. Virtual reality applications for stress management training in the military. Aerosp Med Hum Perform, 2016; 87(12):1021–1030; doi: 10.3357/AMHP.4596.2016

42.

Pyne

, Constans

, Nanney

, et al. Heart rate variability and cognitive bias feedback interventions to prevent post-deployment PTSD: Results from a randomized controlled trial. Mil Med, 2019; 184(1-2):e124–e132; doi: 10.1093/milmed/usy171

43.

Serino

, Triberti

, Villani

, et al. Toward a validation of cyber-interventions for stress disorders based on stress inoculation training: A systematic review. Virtual Reality, 2014; 18(1):73–87; doi: 10.1007/s10055-013-0237-6

44.

Vakili

, Brinkman

, Morina

, et al. Characteristics of successful technological interventions in mental resilience training. J Med Syst, 2014; 38(9):113–114; doi: 10.1007/s10916-014-0113-2

45.

Wiederhold

, Wiederhold

. A continuum of care: Pre-deployment medical and tactical stress inoculation training using virtual reality. Int Rev Armed Forces Med Services, 2014; 87(3):39–45.

46.

Wiederhold

, Wiederhold

. Pre-Deployment Stress Inoculation Training. In: Stress Management and Peace Soldiering. ( Ebner

, Golth

, eds.) National Defence Academy: Vienna, Austria; 2010; pp. 55–91.

47.

Meichenbaum

. Stress inoculation training: A preventative and treatment approach. In: The Evolution of Cognitive Behavior Therapy. Routledge; 2017; pp. 101–124.

48.

Driskell

, Salas

, Johnston

, et al. Stress Exposure Training: An Event-Based Approach. In: Performance under Stress. CRC Press; 2018; pp. 287–302.

49.

Thompson

, McCreary

. Enhancing mental readiness in military personnel. In: RTO Meeting Proceedings MP-HFM-134 on Human Dimensions in Military Operations – Military Leaders’ Strategies for Addressing Stress and Psychological Support; 2006 Apr 24–26; Brussels, Belgium. RTO/NATO: Neuilly-sur-Seine, France; 2006. pp. 4–1–4-12.

50.

Braunstein

, Gross

, Ochsner

. Explicit and implicit emotion regulation: A multi-level framework. Soc Cogn Affect Neurosci, 2017; 12(10):1545–1557; doi: 10.1093/scan/nsx096

51.

Renna

, Quintero

, Fresco

, et al. Emotion regulation therapy: A mechanism-targeted treatment for disorders of distress. Front Psychol, 2017; 8:98; doi: 10.3389/fpsyg.2017.00098

52.

Clark

. Cognitive restructuring. In: The Wiley Handbook of Cognitive Behavioral Therapy. Wiley; 2013: pp. 1–22; doi: 10.1002/9781118528563.wbcbt02

53.

Baer

. Mindfulness training as a clinical intervention: A conceptual and empirical review. Clinical Psychology: Science and Practice, 2003; 10(2):125–143; doi: 10.1093/clipsy.bpg015

54.

Stanley

. Mindfulness‐based mind fitness training: An approach for enhancing performance and building resilience in high‐stress contexts. The Wiley Blackwell Handbook of Mindfulness, 2014:964–985; doi: 10.1002/9781118294895.ch50

55.

Robson

, Manacapilli

. Enhancing Performance under Stress: Stress Inoculation Training for Battlefield Airmen. RAND Corporation: Santa Monica, CA; 2014.

56.

Scott

. Initial Stress Inoculation Program: A Critical Incident Stress Debriefing Training Module for American Airlines Flight Attendants. Carlos Albizu University: Miami, Florida; 2000.

57.

McClernon

, McCauley

, O’Connor

, et al. Stress training improves performance during a stressful flight. Hum Factors, 2011; 53(3):207–218; doi: 10.1177/0018720811405317

58.

Darses

, Bernier

, Berthelot

, et al. Effects of mindfulness training on decision-making in critical and high-demand situations: A pilot study in combat aviation. Safety Science, 2023; 166:106204; doi: 10.1016/j.ssci.2023.106204

59.

Meland

, Fonne

, Wagstaff

, et al. Mindfulness-based mental training in a high-performance combat aviation population: A one-year intervention study and two-year follow-up. Int J Aviat Psychol, 2015; 25(1):48–61; doi: 10.1080/10508414.2015.995572

60.

Fornette

, Bardel

, Lefrançois

, et al. Cognitive-adaptation training for improving performance and stress management of air force pilots. Int J Aviat Psychol, 2012; 22(3):203–223; doi: 10.1080/10508414.2012.689208

61.

Maciolek

, Ilnicki

, Wiederhold

, et al. The influence of pre-deployment VR computer-assisted stress inoculation training on the anxiety level in the polish ISAF soldiers. In: New Tools to Enhance Posttraumatic Stress Disorder Diagnosis and Treatment. IOS Press: Amsterdam; 2013; pp. 161–171.

62.

Stetz

, Wildzunas

, Wiederhold

, et al. The usefulness of virtual reality stress inoculation training for military medical females: A Pilot Study. In: Annual Review of CyberTherapy and Telemedicine, Vol. 4. ( Wiederhold

, Bouchard

, Riva

, eds.) Interactive Media Institute: San Diego; 2006; pp. 51–58.

63.

Wiederhold

, Salva

, Sotomayor

, et al. Next generation stress inoculation training for life saving skills using prosthetics. In: Annual Review of CyberTherapy and Telemedicine, Vol. 7. ( Wiederhold

, Riva

, eds.) Interactive Media Institute: San Diego; 2009; pp. 116–121.

64.

Wiederhold

, Wiederhold

. Using advanced prosthetics for stress inoculation training and to teach life saving skills. In: RTO Meeting Proceedings MP-HFM-182 on Use of Advanced Technologies and New Procedures in Medical Field Operations. RTO/NATO: Brussels; 2010.

65.

Wiederhold

, Wiederhold

. Pre-deployment stress inoculation training. In: Stress Management and Peace Soldiering. ( Ebner

, Golth

, eds.) National Defence Academy: Vienna; 2011; pp. 67–124.

66.

Wiederhold

, Wiederhold

. Virtual Reality Therapy for Anxiety Disorders: Advances in Education and Treatment. American Psychological Association Press: New York; 2004.

67.

Wiederhold

, Wiederhold

. Three-year follow-up for virtual reality exposure for fear of flying. Cyberpsychol Behav, 2003; 6(4):441–445; doi: 10.1089/109493103322278844

68.

Bălan

, Moise

, Moldoveanu

, et al. An investigation of various machine and deep learning techniques applied in automatic fear level detection and acrophobia virtual therapy. Sensors, 2020; 20(2):496; doi: 10.3390/s20020496

69.

Kritikos

, Alevizopoulos

, Koutsouris

. Personalized virtual reality human-computer interaction for psychiatric and neurological illnesses: A dynamically adaptive virtual reality environment that changes according to real-time feedback from electrophysiological signal responses. Front Hum Neurosci, 2021; 15:596980; doi: 10.3389/fnhum.2021.596980

70.

Finseth

, Dorneich

, Keren

, et al. The effectiveness of adaptive training for stress inoculation in a simulated astronaut task. In: Proceedings of the Human Factors and Ergonomics Society Annual Meeting (Vol. 65, No. 1). SAGE Publications: Los Angeles, CA; 2021; pp. 1541–1545.

71.

I Badia

, Quintero

, Cameirao

, et al. Toward emotionally adaptive virtual reality for mental health applications. IEEE J Biomed Health Inform, 2018; 23(5):1877–1887.doi: 10.1109/JBHI.2018.2878846

72.

, Zhang

, He

, et al. Pilot selection in the era of virtual reality: Algorithms for accurate and interpretable machine learning models. Aerospace, 2023; 10(5):394; doi: 10.3390/aerospace10050394

73.

Matton

, Paubel

, Puma

. Toward the use of pupillary responses for pilot selection. Hum Factors, 2022; 64(3):555–567; doi: 10.1177/0018720820945163

74.

Cao

, MacNaughton

, Cadet

, et al. Heart rate variability and performance of commercial airline pilots during flight simulations. Int J Environ Res Public Health, 2019; 16(2):237; doi: 10.3390/ijerph16020237

75.

Hoke

, Reuter

, Romeas

, et al. Perceptual-cognitive & physiological assessment of training effectiveness. In: Interservice/Industry Training, Simulation, and Education Conference. Orlando, FL; 2017.

76.

Labedan

, Darodes-de-Tailly

, Dehais

, et al. Virtual reality for pilot training: Study of cardiac activity. In: Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021)—Volume 2: HUCAPP. SCITEPRESS; 2021; pp. 81–88.

77.

Landman

, Groen

, Van Paassen

, et al. The influence of surprise on upset recovery performance in airline pilots. Int J Aerospace Psychol, 2017; 27(1-2):2–14; doi: 10.1080/10508414.2017.1365610

78.

Yang

, Yu

, Lammers

, et al. Artificial intelligence in pilot training and education–towards a machine learning aided instructor assistant for flight simulators. In: International Conference on Human-Computer Interaction. Springer International Publishing: Cham; 2021; pp. 581–587.

79.

Scannella

, Peysakhovich

, Ehrig

, et al. Assessment of ocular and physiological metrics to discriminate flight phases in real light aircraft. Hum Factors, 2018; 60(7):922–935; doi: 10.1177/0018720818787135

80.

Masi

, Amprimo

, Ferraris

, et al. Stress and workload assessment in aviation—A narrative review. Sensors, 2023; 23(7):3556; doi: 10.3390/s23073556

81.

Ćosić

, Popović

, Šarlija

, et al. AI-based prediction and prevention of psychological and behavioral changes in ex-COVID-19 patients. Front Psychol, 2021; 12:782866; doi: 10.3389/fpsyg.2021.782866

82.

Pyne

, Constans

, Wiederhold

, et al. Heart rate variability: Pre-deployment predictor of post-deployment PTSD symptoms. Biol Psychol, 2016; 121(Pt A):91–98; doi: 10.1016/j.biopsycho.2016.10.008

83.

Karstoft

, Galatzer-Levy

, Statnikov

, et al. Bridging a translational gap: Using machine learning to improve the prediction of PTSD. BMC Psychiatry, 2015; 15:30; doi: 10.1186/s12888-015-0399-8

84.

Priya

, Garg

, Tigga

. Predicting anxiety, depression and stress in modern life using machine learning algorithms. Procedia Computer Science, 2020; 167:1258–1267; doi: 10.1016/j.procs.2020.03.442

85.

Schultebraucks

, Shalev

, Michopoulos

, et al. A validated predictive algorithm of post-traumatic stress course following emergency department admission after a traumatic stressor. Nat Med, 2020; 26(7):1084–1088; doi: 10.1038/s41591-020-0951-z

86.

Schultebraucks

, Yadav

, Shalev

, et al. Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood. Psychol Med, 2022; 52(5):957–967; doi: 10.1017/S0033291720002718

87.

, Li

, Zhang

, et al. Predicting PTSD symptoms in firefighters using a fear-potentiated startle paradigm and machine learning. J Affect Disord, 2022; 319:294–299; doi: 10.1016/j.jad.2022.09.094

88.

Cai

, Han

, Chen

, et al. A pervasive approach to EEG-based depression detection. Complexity, 2018; 2018:1–13; doi: 10.1155/2018/5238028

89.

Liu

, Jia

, Wang

, et al. A depression prediction algorithm based on spatiotemporal feature of EEG signal. Brain Sci, 2022; 12(5):630; doi: 10.3390/brainsci12050630

90.

Shah

, Grennan

, Zafar-Khan

, et al. Personalized machine learning of depressed mood using wearables. Transl Psychiatry, 2021; 11(1):338; doi: 10.1038/s41398-021-01445-0

91.

Pang

, Pham

NTA

, Baker

, et al. Deep depression prediction on longitudinal data via joint anomaly ranking and classification. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer International Publishing: Cham; 2022; pp. 236–248.

92.

Kinreich

, Meyers

, Maron-Katz

, et al. Predicting risk for Alcohol Use Disorder using longitudinal data with multimodal biomarkers and family history: A machine learning study. Mol Psychiatry, 2021; 26(4):1133–1141; doi: 10.1038/s41380-019-0534-x

93.

Zulfiker

, Kabir

, Biswas

, et al. An in-depth analysis of machine learning approaches to predict depression. Curr Res Behav Sci, 2021; 2:100044; doi: 10.1016/j.crbeha.2021.100044

94.

Lou

, Liu

, Warner

, et al. Predicting physician burnout using clinical activity logs: Model performance and lessons learned. J Biomed Inform, 2022; 127:104015; doi: 10.1016/j.jbi.2022.104015

95.

van Weelden

, Alimardani

, Wiltshire

, et al. Aviation and neurophysiology: A systematic review. Appl Ergon, 2022; 105:103838; doi: 10.1016/j.apergo.2022.103838

96.

Alreshidi

, Moulitsas

, Jenkins

. Advancing aviation safety through machine learning and psychophysiological data: A systematic review. IEEE Access, 2024; 12:5132–5150; doi: 10.1109/ACCESS.2024.3349495

97.

Abd Rahman

, Omar

, Noah

SAM

, et al. Application of machine learning methods in mental health detection: A systematic review. IEEE Access, 2020; 8:183952–183964; doi: 10.1109/ACCESS.2020.3029154

98.

dos Santos Machado

, Ballester

, Cao

, et al. Prediction of suicide attempts in a prospective cohort study with a nationally representative sample of the US population. Psychol Med, 2022; 52(14):2985–2996; doi: 10.1017/S0033291720004997

99.

Graham

, Depp

, Lee

, et al. Artificial intelligence for mental health and mental illnesses: An overview. Curr Psychiatry Rep, 2019; 21(11):116; doi: 10.1007/s11920-019-1094-0

100.

Rainey

, Erden

. Correcting the brain? The convergence of neuroscience, neurotechnology, psychiatry, and artificial intelligence. Sci Eng Ethics, 2020; 26(5):2439–2454; doi: 10.1007/s11948-020-00240-2

101.

Belsher

, Smolenski

, Pruitt

, et al. Prediction models for suicide attempts and deaths: A systematic review and simulation. JAMA Psychiatry, 2019; 76(6):642–651; doi: 10.1001/jamapsychiatry.2019.0174

102.

Schafer

, Kennedy

, Gallyer

, et al. A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis. PLoS One, 2021; 16(4):e0249833; doi: 10.1371/journal.pone.0249833

103.

Jiang

, Gradus

, Rosellini

. Supervised machine learning: A brief primer. Behav Ther, 2020; 51(5):675–687; doi: 10.1016/j.beth.2020.05.002

104.

Ćosić

, Šarlija

, Ivkovic

, et al. Stress resilience assessment based on physiological features in selection of air traffic controllers. IEEE Access, 2019; 7:41989–42005; doi: 10.1109/ACCESS.2019.2907479

105.

Ćosić

, Popović

, Šarlija

, et al. New tools and methods in selection of air traffic controllers based on multimodal psychophysiological measurements. IEEE Access, 2019; 7:174873–174888; doi: 10.1109/ACCESS.2019.2957357

106.

Šarlija

, Popović

, Jagodić

, et al. Prediction of task performance from physiological features of stress resilience. IEEE J Biomed Health Inform, 2021; 25(6):2150–2161; doi: 10.1109/JBHI.2020.3041315

107.

Aricò

, Borghini

, Di Flumeri

, et al. Human factors and neurophysiological metrics in air traffic control: A critical review. IEEE Rev Biomed Eng, 2017; 10:250–263; doi: 10.1109/RBME.2017.2694142

108.

Ćosić

, Popović

, Šarlija

, et al. An approach to prediction of mental resilience in fighter pilot selection. In: Proceedings of the 1st International Conference on Cognitive Aircraft Systems (ICCAS). SciTePress; 2023; pp. 83–87.

109.

Israel

, Irvine

, Cheng

, et al. ECG to identify individuals. Pattern Recognit, 2005; 38(1):133–142; doi: 10.1016/j.patcog.2004.05.014

110.

National Aeronautics and Space Administration (NASA). NASA Langley 100: Innovation at 100. Photo: Aerospace research engineer Kyle Ellis uses computer-aided synthetic vision technology in a flight deck simulator. Available from: https://www.nasa.gov/centers-and-facilities/langley/nasalangley100-innovation-at-100/

111.

Cuijpers

, Van Straten

, Smit

, et al. Preventing the onset of depressive disorders: A meta-analytic review of psychological interventions. Am J Psychiatry, 2008; 165(10):1272–1280; doi: 10.1176/appi.ajp.2008.07091422

112.

Topper

, Emmelkamp

, Watkins

, et al. Prevention of anxiety disorders and depression by targeting excessive worry and rumination in adolescents and young adults: A Randomized Controlled Trial. Behav Res Ther, 2017; 90:123–136; doi: 10.1016/j.brat.2016.12.015

113.

Andrews

, Cuijpers

, Craske

, et al. Computer therapy for the anxiety and depressive disorders is effective, acceptable and practical health care: A meta-analysis. PLoS One, 2010; 5(10):e13196; doi: 10.1371/journal.pone.0013196

114.

McDermott

, Dozois

. A randomized controlled trial of Internet-delivered CBT and attention bias modification for early intervention of depression. J Exp Psychopathol, 2019; 10(2):204380871984250; doi: 10.1177/2043808719842502

115.

Schultebraucks

, Chang

. The opportunities and challenges of machine learning in the acute care setting for precision prevention of posttraumatic stress sequelae. Exp Neurol, 2021; 336:113526; doi: 10.1016/j.expneurol.2020.113526

116.

Huang

, Su

, Wu

, et al. Graphene-based sensors for human health monitoring. Front Chem, 2019; 7:399. https://www.frontiersin.org/articles/10.3389/fchem.2019.00399/full

117.

Peake

, Kerr

, Sullivan

. A critical review of consumer wearables, mobile applications, and equipment for providing biofeedback, monitoring stress, and sleep in physically active populations. Front Physiol, 2018; 9:743. https://www.frontiersin.org/articles/10.3389/fphys.2018.00743

118.

Wikimedia Commons. File:Smartphone - The Noun Project.svg. Available from: https://commons.wikimedia.org/wiki/File:Smartphone_-_The_Noun_Project.svg

119.

Public Domain Pictures. Photo: Laptop on white background. Available from: https://www.publicdomainpictures.net/en/view-image.php?image=910&picture=laptop

120.

Moore

. What’s inside the Computer. Photo: Desktop case. Available from: https://www.lions-wing.net/stem/computers/whatsinside.html

121.

Wired. Microsoft costruisce una centrale elettrica per alimentare i suoi data center. 2nd photo in the document. Available from: https://www.wired.it/economia/business/2017/09/19/microsoft-centrale-elettrica/

122.

Thieme

, Belgrave

, Doherty

. Machine learning in mental health: A systematic review of the HCI literature to support the development of effective and implementable ML systems. ACM Trans Comput-Hum Interact, 2020; 27(5):1–53; doi: 10.1145/3398069

123.

Mooney

, Pejaver

. Big data in public health: Terminology, machine learning, and privacy. Annu Rev Public Health, 2018; 39:95–112; doi: 10.1146/annurev-publhealth-040617-014208

124.

Chandler

, Foltz

, Elvevåg

. Using machine learning in psychiatry: The need to establish a framework that nurtures trustworthiness. Schizophr Bull, 2020; 46(1):11–14; doi: 10.1093/schbul/sbz105

125.

Tjoa

, Guan

. A survey on explainable artificial intelligence (XAI): Toward medical XAI. IEEE Trans Neural Netw Learn Syst, 2020; 32(11):4793–4813; doi: 10.1109/TNNLS.2020.3027314

126.

Roessner

, Rothe

, Kohls

, et al. Taming the chaos? Using eXplainable artificial intelligence (XAI) to tackle the complexity in mental health research. Eur Child Adolesc Psychiatry, 2021; 30(8):1143–1146; doi: 10.1007/s00787-021-01836-0

127.

Spira

, Johnston

, McLay

, et al. Expert panel: Future directions of technological advances in prevention, assessment, and treatment for military deployment mental health. Cyberpsychol Behav Soc Netw, 2010; 13(1):109–117; doi: 10.1089/cyber.2009.0370

128.

Growns

, Kukucka

, Moorhead

, et al. The Post Office Scandal in the United Kingdom: Mental health and social experiences of wrongly convicted and wrongly accused individuals. Legal Criminol Psychol, 2024; 29(1):17–31; doi: 10.1111/lcrp.12247

129.

Aven

. A risk science perspective on the discussion concerning Safety I, Safety II and Safety III. Reliab Eng Syst Saf, 2022; 217:108077; doi: 10.1016/j.ress.2021.108077

130.

Royal Aeronautical Society (RAeS), RAeS Human Factors Specialist Group. Psychosocial Risk Management and Mental Health: The Mental Health Challenge to Civil Aviation Safety in the 21st Century. 2024 Apr. Available from: https://www.aerosociety.com/media/23475/mental-health-and-wellbeing-raes-paper.pdf [Last accessed: May 19, 2024].

131.

Cahill

, Cullen

, Anwer

, et al. Using Emerging Technologies to Support Wellbeing and Resilience for Pilots and Enabling the Assessment of Wellbeing Risk in Airline Safety Management Systems. In: International Conference on Human-Computer Interaction. Springer Nature Switzerland: Cham; 2022; pp. 61–79.

132.

Gooding

, Kariotis

. Ethics and law in research on algorithmic and data-driven technology in mental health care: Scoping review. JMIR Ment Health, 2021; 8(6):e24668; doi: 10.2196/24668