Related Experiment Video
Updated: Jan 16, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Interpretable machine learning model to predict aggressive behavior in first-episode schizophrenia
Machine learning models can predict aggressive behavior in first-episode schizophrenia patients. The Random Survival Forest model showed high accuracy, identifying impulsivity and income as key risk factors.
Area of Science:
- Psychiatry
- Machine Learning
- Behavioral Science
Background:
- Schizophrenia is a complex mental disorder.
- Aggressive behavior is a significant concern in first-episode schizophrenia patients.
- Predicting aggressive behavior is crucial for timely intervention.
Purpose of the Study:
- To predict the risk of aggressive behavior in first-episode schizophrenia patients.
- To evaluate the performance of time-to-event machine learning models for this prediction.
- To identify key predictors of aggressive behavior in this population.
Main Methods:
- A cohort study design was employed with 216 first-episode schizophrenia patients.
- Patients were followed for 24 months to assess aggressive behavior.
- Three survival models were developed and evaluated using metrics like C-index, time-dependent AUC, and AUPRC. Shapley Additive Explanation (SHAP) was used for feature importance.
Main Results:
- Aggressive behavior was observed in 16.67% of patients during follow-up.
- The Random Survival Forest model exhibited the best performance (C-index=0.79, time-dependent AUC=0.91, AUPRC=0.59).
- High impulsivity, higher average monthly income, larger household size, unemployment, and lower EPQ-L scores were identified as significant predictors.
Conclusions:
- The Random Survival Forest model is effective in predicting aggressive behavior in first-episode schizophrenia.
- Impulsivity and average monthly income are the most significant factors influencing aggressive behavior.
- These findings can aid in developing targeted interventions for at-risk individuals.
More Related Videos
05:52Handwriting Analysis Indicates Spontaneous Dyskinesias in Neuroleptic Naïve Adolescents at High Risk for Psychosis
Published on: November 21, 2013
13:08Measurement of Fronto-limbic Activity Using an Emotional Oddball Task in Children with Familial High Risk for Schizophrenia
Published on: December 2, 2015
Related Concept Videos
Psychological and Sociocultural Causes of Schizophrenia
Biological Causes of Schizophrenia
Genetic Factors in Schizophrenia
The genetic basis of schizophrenia is strongly supported by family and twin...
Positive Symptoms of Schizophrenia: Hallucinations and Delusions
Thought Disorders
Disorganized and unusual thought processes mark thought disorders in schizophrenia. One key feature is disorganized speech, where an individual's conversation includes...
Psychosis and Antipsychotic Drugs: Overview
Aggression
Psychosis: Goals of Pharmacotherapy