Research on the construction of prediction model for depressive symptom in the second and third trimester of pregnancy based on artificial neural network - Takeaways - MDSpire

Research on the construction of prediction model for depressive symptom in the second and third trimester of pregnancy based on artificial neural network

  • By

  • Wang, Liuyue

  • Zhou, Dandan

  • Liu, Yanhui

  • Liu, Zhiqun

  • Wan, Huan

  • April 29, 2026

  • 0 min

Share

  • 1

    The study assessed depressive symptoms in 588 pregnant women during the second and third trimesters, revealing a 42.7% positive screening rate.

  • 2

    Factors such as social support and active coping were negatively correlated with depressive symptoms, while negative coping was positively correlated.

  • 3

    Binary logistic regression and an artificial neural network were used to create predictive models for depressive symptoms during pregnancy.

  • 4

    The logistic regression model achieved a prediction accuracy of 79.6%, while the artificial neural network model reached 86.9% accuracy.

  • 5

    The findings support early identification and targeted interventions for managing depressive symptoms in pregnant women.

Original Source(s)

Research on the construction of prediction model for depressive symptom in the second and third trimester of pregnancy based on artificial neural network

  • by Wang, Liuyue , Zhou, Dandan , Liu, Yanhui , Liu, Zhiqun , Wan, Huan

  • April 29, 2026

Related Content

Staffing, Flexibility Top Nurses' List to Return

Two-thirds of former hospital nurses would consider coming back if workplace conditions improved, survey finds

Side Effects: Nobody Trained for This

Chemsex at the pharmacy counter. Gut bacteria tracking helmet impacts. PMD predicting psychiatric illness bidirectionally. This week's research keeps landing in the same uncomfortable place: medicine is improvising.

AI Scribes Lag Clinicians on Note Quality

A VHA study across 11 vendors finds AI-generated primary care notes score lower than clinician-written notes, with the largest deficits in thoroughness, organization, and usefulness