BE PART OF THE REVOLUTION TRANSFORMING HEALTHCARE WITH AI - PowerPoint PPT Presentation

BE PART OF THE REVOLUTION TRANSFORMING HEALTHCARE WITH AI CALIFORNIA — THE RITZ-CARLTON, LAGUNA NIGUEL 11–14 DECEMBER 2019 1000 ATTENDEES 80 SPEAKERS 10 WORKSHOPS www.aimed.events/northamerica-2019/ 2 SOCIAL EVENTS #AIMed19 1 AIMed19 Insert Logo, text, URLs, etc here

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Looking Look g Ah Ahea ead with Both Ca Caution and Eager r Insert Photo Here Anticipa An pation on Edward H. Shortliffe, MD, PhD; Professor (Adjunct, Retired) Columbia University Arizona State University Weill Cornell Medical College Senior Executive Consultant, IBM Watson Health www.aimed.events/northamerica-2019 tedshortliffe @tshortliffe

JAMA 2018;320(21):2199-2200 CDSS = Clinical Decision-Support System

Varying Models of Decision Support: Medical-Device Data Interpretation Decision-specific clinical data (e.g., Software produces from measurement interpretive report device) e.g. • Electrocardiogram Deliver to clinician • Electroencephologram • Radiologic images Clinician verifies interpretation and incorporates it into decision making process Well accepted: May be reviewed first by expert; clinician decides how to use result

AI & Machine Learning for Data Analytics JAMA. 2017;318(22):2211-2223

Varying Models of Decision Support: Event Monitoring and Alerts Repository for Knowledge Event clinical information base of what monitoring on a patient (e.g., to watch for software EHR) (e.g. rules) If: patient is receiving Decision support: digoxin and serum • Warnings potassium is low • Alerts Then: warn physician • Guidance that patient may require potassium Interface to clinician replacement for chart review and order entry

Two Major Consulting Questions for Medical AI to Address What does my patient have? (a question about what is true right now) What should I do for my patient? (a question about action-oriented decision making)

Varying Models of Decision Support: Direct Consultation with Clinical User “Greek Oracle” model Clinical Repository for advisory tool clinical information (typically for on a patient (e.g., diagnosis or EHR) treatment) Issues: • Transparency/explanation Analytical • Time requirements methods (e.g. • Usability and complexity rules, scoring • Relevance and insight function, • Respect for user statistical) Interface to clinician • Scientific foundation that integrates decision support with chart review and order entry Preferred model

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Wo Workf kflow • Black boxes are unacceptable: • A Clinical Decision-Support System (CDSS) requires transparency so that users can understand the basis for any advice or recommendations that are offered. www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Work orkflow ow • Time is a scarce resource: • A CDSS should be efficient in terms of time requirements and must blend into the workflow of the busy clinical environment. www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Work orkflow ow • Complexity and lack of usability thwart use: • A CDSS should be intuitive and simple to learn and use so that major training is not required and it is easy to obtain advice or analytic results. www.aimed.events/northamerica-2019/

Users vote with their feet….

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Work orkflow ow • Relevance and insight are essential: • A CDSS should reflect an understanding of the pertinent domain and the kinds of questions with which clinicians are likely to want assistance. www.aimed.events/northamerica-2019/

Rapid pulse, sweating, shallow breathing. According to the computer, you’ve got gallstones.

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Work orkflow ow • Delivery of knowledge and information must be respectful www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Work orkflow ow • Delivery of knowledge and information must be respectful: • A CDSS should offer advice in a way that recognizes the expertise of the user, making it clear that it is designed to inform and assist but not to replace a clinician. X www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Cr Criter eria for or CD CDSS Accept cceptance nce and nd Integ In egra ration on into o Work orkflow ow • Scientific foundation must be strong: • A CDSS should have rigorous, peer-reviewed scientific evidence establishing its safety, validity, reproducibility, usability, and reliability. www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 De Decisi sion Ma Making is s Not the Only Topic fo for E Eval valuati ations ns • Time requirements and impact on workflow • Usability and acceptability • Impact of system use on clinician’s subsequent decisions • Ultimate impact on patient outcomes • Cost-effectiveness of the introduction and use of the technology www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 So Some Im Implic licatio tions • Commercialization of clinical decision support systems requires a time-consuming staged evaluation plan that demonstrates more than quality of advice • Early adopters naturally become partners in evaluation studies, since many questions cannot be answered in the laboratory and must be assessed in actual clinical use environments www.aimed.events/northamerica-2019/

AIMed NORTH AMERICA, CALIFORNIA 11–14 DECEMBER 2019 Th The F Futu ture • Decision support evaluation partnerships similar to those that have long existed in pharmaceutical industry • Interactive medical AI systems and their promulgation will be highly dependent on success in standards setting, interoperability, and rigorous evaluations www.aimed.events/northamerica-2019/

Th Thank k You ted@shortliffe.net