Related Experiment Video
Updated: Apr 24, 2026
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
8.3K
Development and Validation of Machine Learning-Based Models for Predicting Postoperative Depression Risk in Patients
Jitong Zhao1,2, Kaige Pei1,2, Junhan Liu1,2
1Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, 610041 Chengdu, Sichuan, China.
Actas Espanolas De Psiquiatria
|April 23, 2026
Summary
Machine learning models can predict postoperative depression risk in ovarian cancer patients. The random forest model showed the best performance, aiding early intervention for high-risk individuals.
Area of Science:
- Oncology
- Psychiatry
- Data Science
Background:
- Ovarian cancer patients face a significant risk of postoperative depression.
- Early identification of at-risk patients is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To develop and validate machine learning models for predicting postoperative depression risk in ovarian cancer patients.
- To assess the clinical utility and performance of these predictive models.
Main Methods:
- Utilized machine learning algorithms to analyze data from 850 ovarian cancer patients.
- Feature selection identified 13 key predictive variables.
- Evaluated model performance using metrics like AUC, Brier score, sensitivity, and F1 score.
Main Results:
- 31.5% of patients were at risk for postoperative depression.
- The random forest model achieved the highest predictive performance (AUC 0.776).
- Key predictors included pain score, postoperative insomnia, albumin, and opioid use. A nomogram was developed for individual risk assessment.
Conclusions:
- Machine learning models demonstrate strong potential for predicting postoperative depression risk in ovarian cancer patients.
- The random forest model and clinical nomogram offer valuable tools for early risk identification and personalized intervention.
