An unsupervised machine learning analysis of biopsychosocial characteristics and treatment outcome of…

AI / informaticsJournal of addictive diseases· Aug 2026

An unsupervised machine learning analysis of biopsychosocial characteristics and treatment outcome of alcohol use disorder.

Aravind Karunakaran, Aparna Sasikumar, Jaimon Plathottathil Michael … Varghese Punnoose

Substance & AddictionAI / informaticsTreatmentQ3IF 1.6

Severe biopsychosocial profile linked to far lower abstinence at 3 months than other clusters

An unsupervised machine learning analysis of biopsychosocial characteristics and treatment outcome of alcohol use disorder.

Aravind Karunakaran … Varghese Punnoose

Journal of addictive diseases · Aug 2026 · Q3 in Psychiatry

Background

Alcohol Use Disorder is a heterogeneous condition where standard severity measures often fail to predict individual treatment responses.

Purpose

To identify clinically meaningful Alcohol Use Disorder profiles using k-means clustering based on eight baseline biopsychosocial variables and validate their prognostic utility by comparing treatment outcomes.

Methods

A retrospective observational study included 102 patients at a tertiary care center in India.

n = 102 patients

Results

severe-profile patients relapsed far more often, less than half stayed abstinent

Late-Onset

65.8%

Severe

36.7%

“

Conclusion · 1 of 2

Identifying three distinct Alcohol Use Disorder profiles through k-means cluster analysis advances precision medicine in substance use treatment. Return to use risk was driven by craving and co-occurring conditions rather than AUD severity.

Conclusion · 2 of 2

These findings support a stratified approach, where Severe profile group patients require immediate, intensive "front-loaded" intervention.

An unsupervised machine learning analysis of biopsychosocial characteristics and treatment outcome of alcohol use disorder.

An unsupervised machine learning analysis of biopsychosocial characteristics and treatment outcome of alcohol use disorder.

Related papers