What question did this study set out to answer?

To evaluate whether a machine learning model trained on routinely collected clinical and sociodemographic data can predict unplanned 90-day psychiatric readmission among adults with major depressive disorder.

September 17, 2026Journal of Affective DisordersOpen Access

Predicting early psychiatric readmission among people with major depressive disorder: A machine learning analysis from the prospective multicentre DEEP READ study

View Full Paper

Ask AI

Bookmark

Authors

FBFrancesco Bartoli MLMario Luciano CCCristina Crocamo

Discussion

Member takes

Overview

Prospective cohort study shows a machine learning model predicts 90-day psychiatric readmission in major depressive disorder, indicating routine clinical features can flag high-risk individuals.

Key Points

To evaluate whether a machine learning model trained on routinely collected clinical and sociodemographic data can predict unplanned 90-day psychiatric readmission among adults with major depressive disorder.
Prospective multicentre cohort study enrolled 322 adults aged 18–65 years with DSM-5-TR major depressive disorder across 13 Italian provinces between January 2024 and December 2025.
A Random Forest classifier evaluated 22 routinely recorded sociodemographic, clinical, and pharmacological predictors of unplanned 90-day psychiatric readmission using stratified 5-fold cross-validation.
Unplanned psychiatric readmission within 90 days occurred in 15.5% (n = 50/322) of the cohort.
The Random Forest model achieved a mean test area under the receiver operating characteristic curve (AUC) of 0.74 (range: 0.59–0.87).
Key predictors of readmission included prior suicide attempts, previous hospitalizations, anticonvulsant prescriptions, cluster B personality disorders, female sex, and anxious distress, whereas lithium prescriptions showed a protective pattern.

Cite This Study

Bartoli et al. (2026) studied this question.

synapsesocial.com/papers/6aabb6635f706d05830e4bfb https://doi.org/10.1016/j.jad.2026.122502

View Full Paper

Ask AI

Bookmark

September 17, 2026Journal of Affective DisordersOpen Access

Predicting early psychiatric readmission among people with major depressive disorder: A machine learning analysis from the prospective multicentre DEEP READ study

View Full Paper

Ask AI

Bookmark

Authors

FBFrancesco Bartoli MLMario Luciano CCCristina Crocamo

Discussion

Member takes

Overview

Prospective cohort study shows a machine learning model predicts 90-day psychiatric readmission in major depressive disorder, indicating routine clinical features can flag high-risk individuals.

Key Points

To evaluate whether a machine learning model trained on routinely collected clinical and sociodemographic data can predict unplanned 90-day psychiatric readmission among adults with major depressive disorder.
Prospective multicentre cohort study enrolled 322 adults aged 18–65 years with DSM-5-TR major depressive disorder across 13 Italian provinces between January 2024 and December 2025.
A Random Forest classifier evaluated 22 routinely recorded sociodemographic, clinical, and pharmacological predictors of unplanned 90-day psychiatric readmission using stratified 5-fold cross-validation.
Unplanned psychiatric readmission within 90 days occurred in 15.5% (n = 50/322) of the cohort.
The Random Forest model achieved a mean test area under the receiver operating characteristic curve (AUC) of 0.74 (range: 0.59–0.87).
Key predictors of readmission included prior suicide attempts, previous hospitalizations, anticonvulsant prescriptions, cluster B personality disorders, female sex, and anxious distress, whereas lithium prescriptions showed a protective pattern.

Cite This Study

Bartoli et al. (2026) studied this question.

synapsesocial.com/papers/6aabb6635f706d05830e4bfb https://doi.org/10.1016/j.jad.2026.122502

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark