Dr. Roy Perlis (Mass General Bringham, Boston) joins AJP Audio to discuss a machine learning model to examine electronic health records in individuals who had recently given birth designed to detect those who might develop postpartum depression. Afterwards, AJP Editor-in-Chief Dr. Ned Kalin puts the rest of the June issue into context.

00:31 Perlis interview
02:56 Lack of validation in screening methods
04:03 Stumbling blocks on the road to validation
05:10 Synergy between screening scores and machine learning models
06:36 Issues with clinician adoption?
08:44 Administrative burden for running these models
10:38 Current clinical application
12:37 Screening without those with a history of depression
13:48 Limitations
15:30 Future research
17:26 Kalin interview
17:41 Clapp et al.
21:41 Kępińska et al.
25:19 Savitz et al.
25:25 Miller
28:38 Wall et al.

Transcript

Be sure to let your colleagues know about the podcast, and please rate and review it on Apple Podcasts, Google Podcasts, Spotify, or wherever you listen to it.

Subscribe to the podcast here.

Listen to other podcasts produced by the American Psychiatric Association.

Browse articles online.

How authors may submit their work.

Follow the journals of APA Publishing on Twitter.

E-mail us at ajp@psych.org

June 2025: Stratifying Risk for Postpartum Depression at Time of Hospital Discharge

American Journal of Psychiatry Audio