Developing a machine learning prediction model for postpartum psychiatric admission: Findings from the born in Queensland study
Journal of Affective Disorders · 2026
DOI: 10.1016/j.jad.2025.120180 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026. Verfasst von Khushi Malani und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Population Health, Curtin University, Building 400, Kent Street, Bentley, WA, Australia. Electronic address: khushi.malani@postgrad.curtin.…. Hauptthemen laut MEDLINE: Machine Learning, Depression, Postpartum, Hospitalization, Mental Disorders. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Queensland Health.
Abstract (Originalsprache)
BACKGROUND: We utilised novel prenatal depression screening data in a population sample to develop a machine learning-based prediction model for postpartum psychiatric admissions. METHODS: We used health administrative data from Queensland, Australia, containing 945 clinical and demographic variables for 205,495 pregnancies between July 2015 and January 2021. Two machine learning algorithms, gradient-boosted trees and elastic net regularisation, were compared to predict postpartum psychiatric admissions occurring within 12 months of neonatal discharge. RESULTS: Gradient-boosted trees outperformed elastic net regularisation, achieving good discrimination in the test set [AUC = 0.79, 95 % CI = (0.76, 0.82)]. As expected, the inclusion of the Edinburgh Postnatal Depression Scale ascertained during pregnancy improved the model's predictive performance. Antenatal mental health diagnoses, being a single mother and smoking during pregnancy were also found to be strong risk factors. LIMITATIONS: This study contained no information on community or outpatient mental health visits and excluded private obstetrics patients. CONCLUSION: Our prediction model may enable early identification and timely intervention for at-risk women during pregnancy which, in turn, may reduce the severity of postpartum mental health problems or the need for postpartum psychiatric admissions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Population Health, Curtin University, Building 400, Kent Street, Bentley, WA, Australia. Electronic address: khushi.malani@postgrad.curtin.edu.au.
- School of Population Health, Curtin University, Building 400, Kent Street, Bentley, WA, Australia; School of Public Health, University of Queensland, Brisbane, QLD, Australia. Electronic address: rosa.alati@curtin.edu.a…
- School of Medicine, University of Queensland, Brisbane, QLD, Australia. Electronic address: s.kisely@uq.edu.au.
- School of Population Health, Curtin University, Building 400, Kent Street, Bentley, WA, Australia. Electronic address: kim.betts@curtin.edu.au.
Förderung
- Queensland Health
Zitieren
APA
Malani, K., Alati, R., Kisely, S., & Betts, K. (2026). Developing a machine learning prediction model for postpartum psychiatric admission: Findings from the born in Queensland study. Journal of Affective Disorders. https://doi.org/10.1016/j.jad.2025.120180
Vancouver
Malani K, Alati R, Kisely S, Betts K. Developing a machine learning prediction model for postpartum psychiatric admission: Findings from the born in Queensland study. Journal of Affective Disorders. 2026. doi:10.1016/j.jad.2025.120180
BibTeX
@article{Malani2026,
author = {Malani, Khushi and Alati, Rosa and Kisely, Steve and Betts, Kim},
title = {Developing a machine learning prediction model for postpartum psychiatric admission: Findings from the born in Queensland study},
journal = {Journal of Affective Disorders},
year = {2026},
doi = {10.1016/j.jad.2025.120180}
}
EUVIMED