Cross-sectional Functional Stratification Based on Psychometric Profiling and Machine Learning in Patients With Substance Use Disorders (SUD)

NCT07590154 | Completed

• 1 other identifier: SISAP-TUS-EFTP-ML-2026
• Study Type: observational
• Target: 155
• Locations: 1 country
• Sites: 1

Brief Summary

Substance use disorders (SUDs) show considerable clinical heterogeneity that limits the usefulness of traditional categorical diagnoses. This observational, cross-sectional study aims to apply an unsupervised deep learning method - an autoencoder - to learn continuous latent representations from standardised psychometric data and to explore whether those representations can help stratify clinical subpopulations. The investigators will recruit 155 adults undergoing residential treatment for SUD. Participants will complete six validated instruments assessing impulsivity (BIS-11), anger regulation (STAXI-2), behavioural activation/avoidance (BADS), borderline symptomatology (BSL-23), generalised anxiety (GAD-7), and environmental reward (EROS). Demographic and clinical variables (age, sex, primary substance, years of use, prior treatments) will also be recorded. After data cleaning and standardisation (z-scores), a symmetric autoencoder with a 12-dimensional bottleneck (architecture 21-32-24-12-24-32-21) will be trained using mean squared error loss. Regularisation includes L2 weight decay and dropout. The model will be trained 30 times with different random seeds to assess stability; the five best models (by validation pseudo-R²) will be combined into a weighted ensemble. Five-fold cross-validation will evaluate generalisation. For comparison, principal component analysis (PCA) will be applied to the same data. Gaussian mixture models (GMM) will be fitted on the latent space to explore potential clinical subgroups. The primary outcome is the stability of the latent representation (coefficient of variation of validation MSE across runs). Secondary outcomes include reconstruction performance (pseudo-R²) of the ensemble, comparison with PCA, and the interpretability of latent dimensions via correlations with original variables. GMM results will be described using BIC, silhouette width, bootstrap stability, and clinical characterisation of clusters. This study does not involve any intervention. Results will be hypothesis-generating and require external validation. No automated clinical decisions will be made.

Conditions

Substance Abuse Disorder; Addiction; Clinical Stratification; Substance-related Disorders; Residential Treatment Program

Keywords

Transdiagnostic; Machine Learning; Psychometric Assessment; Dimensionality Reduction; RDoC

Outcome Measures

Primary Outcomes (1)

• Latent dimension scores

  Twelve continuous latent dimensions derived from the bottleneck layer of a symmetric autoencoder trained on 21 standardized clinical variables. Each dimension represents a compressed, nonlinear combination of the original psychometric indicators (impulsivity, emotion regulation, behavioral activation, borderline symptoms, anxiety, and environmental reward). The dimensions are extracted for each participant after averaging the predictions of an ensemble of the five best autoencoder runs. Unit of Measure: Standardized z-score (mean = 0, SD = 1 in the training sample)

  Baseline (single assessment, cross-sectional)

Secondary Outcomes (6)

• Gaussian mixture model cluster membership

  Baseline

• Autoencoder reconstruction pseudo-R²

  Baseline (computed on the validation split and on the full sample after training)

• Autoencoder reconstruction mean squared error

  Baseline

• Coefficient of variation of reconstruction MSE

  Baseline (after all runs are completed)

• Cross-validated reconstruction R²

  Baseline

Study Arms (1)

Total sample (residential treatment)

Adult patients (N=155) with DSM-5 TR substance use disorder receiving residential treatment. All participants completed six psychometric scales (BIS-11, STAXI-2, BADS, BSL-23, GAD-7, EROS) and provided demographic/clinical data in a single cross-sectional session. No intervention was administered.

Other: No intervention (observational only)

Interventions

No intervention (observational only) OTHER

This is a purely observational study. No drug, device, behavioral therapy, or other intervention was assigned. The study only involved standardized psychometric measurements.

Total sample (residential treatment)

Eligibility Criteria

• Age: 18 Years - 60 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients (≥18 years) with a diagnosis of Substance Use Disorder (SUD) admitted to a residential detoxification and rehabilitation center. Consecutive recruitment between February 2024 and March 2026. Estimated final sample size is 155 participants. No healthy volunteers are included.

You may qualify if:

• DSM-5 diagnosis of Substance Use Disorder (SUD), confirmed by a psychiatrist or clinical psychologist.
• Age ≥ 18 years.
• Currently admitted to a residential addiction treatment center at the time of assessment.
• Ability to complete the psychometric questionnaires independently.
• Written informed consent.

You may not qualify if:

• Active psychotic disorder (e.g., schizophrenia, delusional disorder) not stabilized pharmacologically.
• Severe cognitive impairment (dementia, severe brain injury) that prevents understanding the questionnaire items.
• Language barriers or illiteracy that prevent self-administration of the scales.
• Scheduled discharge from the center within 7 days of the assessment date.

Sponsors & Collaborators

• Lauro Gutiérrez Castro: lead

Study Sites (1)

Under The Tree

Ajijic, Jalisco, 45920, Mexico

Location

MeSH Terms

Conditions

Substance-Related Disorders; Behavior, Addictive

Condition Hierarchy (Ancestors)

Chemically-Induced Disorders; Mental Disorders; Compulsive Behavior; Impulsive Behavior; Behavior

Study Officials

• Lauro Gutiérrez Castro

  Under The Tree

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: CROSS SECTIONAL
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: May 9, 2026
• First Posted: May 15, 2026
• Study Start: March 25, 2024
• Primary Completion: February 18, 2026
• Study Completion: April 22, 2026
• Last Updated: May 18, 2026

Record last verified: 2026-05

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, CSR
• Time Frame: Beginning 9 months and ending 36 months after article publication
• Access Criteria: Data will be available to researchers who provide a methodologically sound proposal for purposes of replicating the results or conducting secondary analyses. Proposals should be directed to the corresponding author. Requestors will need to sign a data access agreement.

Locations

ME (1)