An Alternative Approach for Detecting Problematic Alcohol Use: Developing the Student Alcohol Risk Assessment Scale-15 Using AI-Assisted Machine Learning

IF 3.4 3区医学 Q2 PSYCHIATRY

International Journal of Methods in Psychiatric Research Pub Date : 2026-07-20 DOI:10.1002/mpr.70096

Şükrü Alperen Korkmaz, Pınar Mutlu, Sibel Oymak, Gamze Çan

{"title":"An Alternative Approach for Detecting Problematic Alcohol Use: Developing the Student Alcohol Risk Assessment Scale-15 Using AI-Assisted Machine Learning","authors":"Şükrü Alperen Korkmaz, Pınar Mutlu, Sibel Oymak, Gamze Çan","doi":"10.1002/mpr.70096","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background/Aim</h3>\n \n <p>Risky alcohol use is common among university students and negatively impacts physical and psychosocial health. Current screening instruments focus only on behavioral indicators, neglecting psychosocial factors. This study aimed to develop an AI-supported, brief student-focused tool for assessing alcohol-related risk and to evaluate its preliminary reliability and validity among university students.</p>\n </section>\n \n <section>\n \n <h3> Materials and Methods</h3>\n \n <p>A total of 599 university students participated in this cross-sectional study. From a pool of 59 items covering behavioral, psychological, social, and academic questions related to alcohol use, a new risk model was created using 15 items selected with ChatGPT-supported AI algorithms (SARAS-15). Risk scores ranged from 0 to 27, categorizing participants into low, medium, and high-risk groups. The model's performance was evaluated using machine learning methods such as Random Forest, Logistic Regression, SVM, and KNN, along with cross-validation and ROC analysis. We also analyzed its internal consistency and its correlations with screening instruments (AUDIT, RAPS4-QF, CAGE).</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>In machine learning analyses, the logistic regression model achieved the highest performance (93.5% accuracy, F1-score = 0.864, sensitivity = 0.826, specificity = 0.959). ROC analysis demonstrated excellent discrimination between low-risk (AUC = 0.96) and high-risk (AUC = 0.93) groups, with strong discrimination for the intermediate-risk group (AUC = 0.88). The Random Forest model achieved an overall accuracy of 87%, successfully differentiating between the low-risk group (F1 score = 0.91) and the high-risk group (F1 score = 1.00). The new model's Cronbach's alpha was 0.811, with strong convergent validity correlations with screening instruments (AUDIT, <i>r</i> = 0.861; RAPS4-QF, <i>r</i> = 0.793; CAGE, <i>r</i> = 0.631).</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>The developed artificial intelligence-supported 15-item new risk score model is valid and reliable in assessing risky alcohol use among university students. This scale demonstrates a high level of agreement with traditional tests and can accurately detect three risk levels. Due to its multi-domain content structure, which addresses both behavioral and psychosocial effects, it serves as a complementary screening tool for early risk identification and intervention planning.</p>\n </section>\n </div>","PeriodicalId":50310,"journal":{"name":"International Journal of Methods in Psychiatric Research","volume":"35 3","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13382531/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Methods in Psychiatric Research","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mpr.70096","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}

引用次数: 0

Abstract

Background/Aim

Risky alcohol use is common among university students and negatively impacts physical and psychosocial health. Current screening instruments focus only on behavioral indicators, neglecting psychosocial factors. This study aimed to develop an AI-supported, brief student-focused tool for assessing alcohol-related risk and to evaluate its preliminary reliability and validity among university students.

Materials and Methods

A total of 599 university students participated in this cross-sectional study. From a pool of 59 items covering behavioral, psychological, social, and academic questions related to alcohol use, a new risk model was created using 15 items selected with ChatGPT-supported AI algorithms (SARAS-15). Risk scores ranged from 0 to 27, categorizing participants into low, medium, and high-risk groups. The model's performance was evaluated using machine learning methods such as Random Forest, Logistic Regression, SVM, and KNN, along with cross-validation and ROC analysis. We also analyzed its internal consistency and its correlations with screening instruments (AUDIT, RAPS4-QF, CAGE).

Results

In machine learning analyses, the logistic regression model achieved the highest performance (93.5% accuracy, F1-score = 0.864, sensitivity = 0.826, specificity = 0.959). ROC analysis demonstrated excellent discrimination between low-risk (AUC = 0.96) and high-risk (AUC = 0.93) groups, with strong discrimination for the intermediate-risk group (AUC = 0.88). The Random Forest model achieved an overall accuracy of 87%, successfully differentiating between the low-risk group (F1 score = 0.91) and the high-risk group (F1 score = 1.00). The new model's Cronbach's alpha was 0.811, with strong convergent validity correlations with screening instruments (AUDIT, r = 0.861; RAPS4-QF, r = 0.793; CAGE, r = 0.631).

Conclusion

The developed artificial intelligence-supported 15-item new risk score model is valid and reliable in assessing risky alcohol use among university students. This scale demonstrates a high level of agreement with traditional tests and can accurately detect three risk levels. Due to its multi-domain content structure, which addresses both behavioral and psychosocial effects, it serves as a complementary screening tool for early risk identification and intervention planning.

Abstract Image

查看原文本刊更多论文

检测问题酒精使用的另一种方法：使用人工智能辅助机器学习开发学生酒精风险评估量表-15。

背景/目的：危险饮酒在大学生中很常见，并对身体和心理健康产生负面影响。目前的筛查手段只注重行为指标，忽视了心理社会因素。本研究旨在开发一种人工智能支持的、以学生为中心的简短工具，用于评估酒精相关风险，并评估其在大学生中的初步信度和效度。材料与方法：共有599名大学生参与了本横断面研究。从涉及与饮酒有关的行为、心理、社会和学术问题的59个项目中，使用chatgpt支持的人工智能算法（SARAS-15）选择的15个项目创建了一个新的风险模型。风险评分范围从0到27，将参与者分为低、中、高风险组。使用随机森林、逻辑回归、支持向量机和KNN等机器学习方法以及交叉验证和ROC分析来评估模型的性能。我们还分析了其内部一致性及其与筛选工具（AUDIT、RAPS4-QF、CAGE）的相关性。结果：在机器学习分析中，logistic回归模型的准确率最高（93.5%,F1-score = 0.864，灵敏度= 0.826，特异性= 0.959）。ROC分析显示，低危组（AUC = 0.96）和高危组（AUC = 0.93）之间具有很好的区分性，而中危组（AUC = 0.88）具有很强的区分性。随机森林模型的总体准确率达到87%，成功区分了低风险组（F1评分= 0.91）和高风险组（F1评分= 1.00）。新模型的Cronbach's alpha为0.811，与筛选工具具有较强的收敛效度相关（AUDIT, r = 0.861; RAPS4-QF, r = 0.793； CAGE, r = 0.631）。结论：建立的人工智能支持的15项风险评分模型可有效、可靠地评估大学生危险饮酒行为。该量表显示与传统测试高度一致，可以准确地检测出三个风险级别。由于其多领域内容结构，涉及行为和心理社会影响，它可以作为早期风险识别和干预计划的补充筛查工具。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Methods in Psychiatric Research 医学-精神病学

CiteScore

5.20

自引率

6.50%

发文量

审稿时长

>12 weeks

期刊介绍： The International Journal of Methods in Psychiatric Research (MPR) publishes high-standard original research of a technical, methodological, experimental and clinical nature, contributing to the theory, methodology, practice and evaluation of mental and behavioural disorders. The journal targets in particular detailed methodological and design papers from major national and international multicentre studies. There is a close working relationship with the US National Institute of Mental Health, the World Health Organisation (WHO) Diagnostic Instruments Committees, as well as several other European and international organisations. MPR aims to publish rapidly articles of highest methodological quality in such areas as epidemiology, biostatistics, generics, psychopharmacology, psychology and the neurosciences. Articles informing about innovative and critical methodological, statistical and clinical issues, including nosology, can be submitted as regular papers and brief reports. Reviews are only occasionally accepted. MPR seeks to monitor, discuss, influence and improve the standards of mental health and behavioral neuroscience research by providing a platform for rapid publication of outstanding contributions. As a quarterly journal MPR is a major source of information and ideas and is an important medium for students, clinicians and researchers in psychiatry, clinical psychology, epidemiology and the allied disciplines in the mental health field.