Predicting first time depression onset in pregnancy: applying machine learning methods to patient-reported data
2024

Predicting Depression Onset in Pregnancy Using Machine Learning

Sample size: 944 publication Evidence: high

Author Information

Author(s): Krishnamurti Tamar, Rodriguez Samantha, Wilder Bryan, Gopalan Priya, Simhan Hyagriv N.

Primary Institution: University of Pittsburgh

Hypothesis

Can machine learning algorithms predict the onset of moderate-to-severe depression in pregnant individuals using early pregnancy data?

Conclusion

A small amount of self-reported data can accurately predict first-time depression among pregnant individuals.

Supporting Evidence

  • 78% of participants identified as white.
  • 61% had an income of $50,000 or more.
  • 70% had at least a college degree.
  • 14 questions were used to predict depression onset.

Takeaway

Researchers used a smartphone app to ask pregnant women questions and found a way to predict if they might get sad later on.

Methodology

Participants used a prenatal support app and self-reported data was analyzed using various machine learning algorithms.

Potential Biases

Potential bias due to self-selection of participants who were willing to engage with the app.

Limitations

The study may not represent all pregnant individuals due to participation bias and limited demographic diversity.

Participant Demographics

78% identified as white, average age 30, 61% had income ≥ $50,000, 70% had a college degree or higher.

Statistical Information

Confidence Interval

[0.84, 0.94]

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1007/s00737-024-01474-w

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication