acek-means clustering of AUD patients to predict 3-month abstinence
Source article: An unsupervised machine learning analysis of biopsychosocial characteristics and treatment outcome of alcohol use disorder
Abstract: Background: Alcohol Use Disorder is a heterogeneous condition where standard severity measures often fail to predict individual treatment responses. Precision medicine requires identifying distinct biopsychosocial profiles to guide targeted interventions.Objectives: 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 st…
Negative state: both sides are scored from claims and sources, not community votes.
Alcohol and birth defects : the fetal alcohol syndrome and related disorders by Petrakis, Peter L National Institute on Alcohol Abuse and Alcoholism (U.S.). Public domain
In a retrospective study of 102 patients at a tertiary care center in India, researchers used k-means clustering on eight biopsychosocial baseline variables to derive three AUD profiles. By the August 2026 publication date, they reported Late-Onset, High-Functioning, and Severe groups with differing 3-month abstinence rates corroborated by GGT levels and bootstrap-assessed cluster stability.
The stratification matters because it shows standard severity scores did not predict outcome while craving and co-occurring psychiatric conditions did, suggesting a need for front-loaded intensive care for the Severe group. Uncertainty remains about generalizability beyond a single tertiary center, stability in larger diverse cohorts, and whether prospective use of the profiles improves outcomes.
- Retrospective observational study of 102 patients at a tertiary care center in India using k-means clustering on eight baseline variables.
- Three profiles: Late-Onset n=38 older age lowest craving 65.8% abstinence; High-Functioning n=34 high socioeconomic status zero co-occurring disorders; Severe n=30 early onset 73.3% psychiatric comorbidity intense craving.
- Primary outcome was 3-month abstinence corroborated by GGT levels; Severe group had 36.7% abstinence p=0.004 despite similar alcohol severity scores p=0.215.
- Cluster stability was assessed via bootstrap resampling and return to use risk was driven by craving and co-occurring conditions rather than AUD severity.
K-means clustering of eight biopsychosocial variables identified three distinct AUD profiles that predicted 3-month abstinence, with Late-Onset achieving 65.8% abstinence, supporting stratified front-loaded intervention.
Patients classified as Severe profile with early onset, 73.3% co-occurring psychiatric conditions and intense craving had poorer 3-month outcomes with only 36.7% abstinence and steep return to use.
The rundown
Researchers applied k-means clustering to eight baseline variables including age, alcohol use duration, severity, craving, co-occurring psychiatric conditions, self-efficacy, education and occupation in 102 patients at a tertiary care center in India.
The three clusters showed divergent 3-month abstinence rates corroborated by GGT levels, with Late-Onset at 65.8% and Severe at 36.7% p=0.004, despite no significant difference in alcohol severity scores p=0.215, indicating craving and psychiatric comorbidity as drivers of return to use.
Single-center retrospective design with 102 patients at a tertiary care center in India limits generalizability and causal inference for broader AUD populations.
Sources
- Peer-reviewedJournal of Addictive Diseases2026-08-07
How should this claim be treated?
The debate