Back

A review of the application of digital phenotyping in predicting peripartum depressive symptoms

Kovacs, B. Z.; Schweitzer, S.; Papadopoulos, F. C.; Bauer, A.; Skalkidou, A.; Tu, H.-F.

2025-09-18 health informatics
10.1101/2025.09.17.25335179 medRxiv
Show abstract

Peripartum depression (PPD) affects 12 to 25% pregnant women worldwide, yet screening often misses real-time symptom changes. Digital phenotyping (DP) offers a promising support, using data like text entries or sleep tracking to detect PPD. This review (PROSPERO: CRD42023461325) evaluated 14 studies, highlighting the substantial potential of personal history and semi-random ecological-momentary data. Future work should focus on improving models and advancing their translation into clinical settings for broader impact.

Published in npj Digital Medicine (predicted rank #1) · training set

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.