Organizational considerations from HFE to speed up the adoption of AI-related technology in medical diagnostics

Abstract

Diagnostic errors contribute to hospital complications that can lead to death. It is essential to create a favorable environment for implementing AI-related technologies to improve medical diagnostics. This study aims to present the different categories of A.I. diagnostic applications, as well as the organizational factors and policies, inﬂuencing the best adoption and implementation of A.I. applications. We conducted an online database search to identify peer-reviewed papers published between Jan 2009 and May 2019 that were related to A.I. applications in medical diagnostics. Papers were included as indexed in database PubMed if they contain any one of the following: (1) the research used Artificial Intelligence or Machine Learning or Deep Learning to perform medical diagnostics, and (2) the research conducted validation analysis or clinical trial. Additionally, we explored whether the study can promisingly improve social welfare or achieve cost-savings by improving clinical outcomes. 197 selected papers were explored that covered the following topics: types of diagnostic technology, medical application scenario, clinical outcome measurement, potential beneﬁt, and how the AI-related diagnostics is improving the clinical outcome and produce economic value.

Keywords

Artiﬁcial Intelligence Clinical outcome Cost beneﬁt analysis Deep Learning Healthcare Machine learning technology imaging chatbots natural language processing precision medicine imaging reinforcement learning

References

Balogh

EP.

Miller

BT.

Ball

J.R.

Editors. (2015). Improving Diagnosis in Health Carne. Washington (D.C.): National Academies Press (U.S.). Overview of Diagnostic Error in Health Care. https://www.ncbi.nlm.nih.gov/books/NBK338594/

Barros

Morales

García

et al. (2020). Recognizing states of psychological vulnerability to suicidal behavior: a Bayesian network of artificial intelligence applied to a clinical sample. BMC Psychiatry 20, 138. https://doi.org/10.1186/s12888-020-02535-x.

Chen

Decary

(2020). Artiﬁcial intelligence in healthcare: An essential guide for health leaders. Healthc Manage Forum. 33(1):10-18. https://doi.org/10.1177/0840470419873123.

Davenport

Kalakota

(2019). The Future of Health and Healthcare in a World of Artiﬁcial Intelligence. (n.d.), 1(1), 7. Future Healthc J. 94–98. https://doi.org/10.7861/futurehosp.6-2-94.

Davenport

TH.

Glaser

(2002). Just-in-time delivery comes to knowledge management. Harvard Business Review 2002. https://hbr.org/2002/07/just-in-time-delivery-comes-oto- knowledge-management.

Scerri

Grech

(2020). Artiﬁcial intelligence in medicine. Early Human Development. Elsejier. https://doi.org/10.1016/j.earlhumdev.2020.105017.

Seetharam

Kagiyama

Sengupta

. (2019). Application of mobile health, telemedicine and artiﬁcial intelligence to echocardiography. https://doi.org/10.1530/ERP-18-0081.

Shekelle

Morton

SC.

Keeler

. (2006). Costs and Beneﬁts of Health Information Technology. Rockville (M.D.): Agency for Healthcare Research and Quality (U.S.). Evidence Reports/Technology Assessments, No. 132. https://www.ncbi.nlm.nih.gov/books/NBK37988/.

Sordo

(2002). Introduction to neural networks in healthcare. OpenClinical. www.openclinical.org/docs/int/neuralnetworks011.pdf

10.

Stacy

Carter

W.R.

Khin

T.W.

Frazer

Richards

Houssami

(2019). The ethical, legal and social implications of using artiﬁcial intelligence systems in breast cancer care. Open Access Published. https://doi.org/10.1016/j.breast.2019.10.001.

11.

Ting

DSW.

Pasquale

LR.

Peng

Campbell

JP.

Lee

AY.

Raman

Tan

GSW.

Schmetterer

Keane

PA.

Wong

TY.

(2019). Artificial intelligence and deep learning in ophthalmology. Br J Ophtalmol. 103(2): 167-175. https://doi.org/10.1136/bjophthalmol-2018-313173

12.

Vial

Stirling

Field

et al. (2018). The role of deep learning and radiomic feature extraction in cancer-specific predictive modelling: a review. Transl Cnacer Res. 7:803-16.