66: Predicting Outcomes of Antidepressant Treatment in Community Practice Settings
Psychiatric Services From Pages to Practice
English - February 21, 2024 16:17 - 32 minutes - 44.4 MB - ★★★★★ - 26 ratingsSocial Sciences Science Health & Fitness Medicine criminaljustice dsm communitybasedtreatment depression journal medicine mentalhealth psychiatricservices psychiatry psychology Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Gregory E. Simon, M.D., M.P.H. (Kaiser Permanente Washington Health Research Institute, Seattle) join Dr. Dixon and Dr. Berezin to discuss the use of machine learning models to analyze electronic health records to predict antidepressant treatment response.
00:00 Introduction
02:31 Focus on practical research
04:55 Population studied
05:57 Predicting outcomes
07:20 Using diagnostic codes, not personalized notes
08:04 What three data items might be more helpful?
08:49 What key indicators are we missing in clinical care?
11:35 A billing tool, not a clinical tool
12:57 Is suicide a predictable event based on electronic health record data?
14:48 “Machine learning and artificial intelligence”
16:15 Methods
18:59 Can we do a better job clarifying what we mean by depression?
22:32 How can we use a predictive model in clinical practice?
28:20 Predictive models, probability, the weather, and communicating
Subscribe to the podcast here.
Check out Editor's Choice, a set of curated collections from the rich resource of articles published in the journal. Sign up to receive notification of new Editor's Choice collections.
Browse other articles on our website.
Be sure to let your colleagues know about the podcast, and please rate and review it wherever you listen to it.
Listen to other podcasts produced by the American Psychiatric Association.
Follow the journal on Twitter.
E-mail us at [email protected]