Kirsten Zantvoort, Barbara Nacke, Dennis Görlich, Silvan Hornstein, Corinna Jacobi, Burkhardt Funk
{"title":"Estimation of minimal data sets sizes for machine learning predictions in digital mental health interventions","authors":"Kirsten Zantvoort, Barbara Nacke, Dennis Görlich, Silvan Hornstein, Corinna Jacobi, Burkhardt Funk","doi":"10.1038/s41746-024-01360-w","DOIUrl":null,"url":null,"abstract":"<p>Artificial intelligence promises to revolutionize mental health care, but small dataset sizes and lack of robust methods raise concerns about result generalizability. To provide insights on minimal necessary data set sizes, we explore domain-specific learning curves for digital intervention dropout predictions based on 3654 users from a single study (ISRCTN13716228, 26/02/2016). Prediction performance is analyzed based on dataset size (<i>N</i> = 100–3654), feature groups (F = 2–129), and algorithm choice (from Naive Bayes to Neural Networks). The results substantiate the concern that small datasets (<i>N</i> ≤ 300) overestimate predictive power. For uninformative feature groups, in-sample prediction performance was negatively correlated with dataset size. Sophisticated models overfitted in small datasets but maximized holdout test results in larger datasets. While <i>N</i> = 500 mitigated overfitting, performance did not converge until <i>N</i> = 750–1500. Consequently, we propose minimum dataset sizes of <i>N</i> = 500–1000. As such, this study offers an empirical reference for researchers designing or interpreting AI studies on Digital Mental Health Intervention data.</p>","PeriodicalId":19349,"journal":{"name":"NPJ Digital Medicine","volume":"91 1","pages":""},"PeriodicalIF":12.4000,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"NPJ Digital Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1038/s41746-024-01360-w","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0
Abstract
Artificial intelligence promises to revolutionize mental health care, but small dataset sizes and lack of robust methods raise concerns about result generalizability. To provide insights on minimal necessary data set sizes, we explore domain-specific learning curves for digital intervention dropout predictions based on 3654 users from a single study (ISRCTN13716228, 26/02/2016). Prediction performance is analyzed based on dataset size (N = 100–3654), feature groups (F = 2–129), and algorithm choice (from Naive Bayes to Neural Networks). The results substantiate the concern that small datasets (N ≤ 300) overestimate predictive power. For uninformative feature groups, in-sample prediction performance was negatively correlated with dataset size. Sophisticated models overfitted in small datasets but maximized holdout test results in larger datasets. While N = 500 mitigated overfitting, performance did not converge until N = 750–1500. Consequently, we propose minimum dataset sizes of N = 500–1000. As such, this study offers an empirical reference for researchers designing or interpreting AI studies on Digital Mental Health Intervention data.
期刊介绍:
npj Digital Medicine is an online open-access journal that focuses on publishing peer-reviewed research in the field of digital medicine. The journal covers various aspects of digital medicine, including the application and implementation of digital and mobile technologies in clinical settings, virtual healthcare, and the use of artificial intelligence and informatics.
The primary goal of the journal is to support innovation and the advancement of healthcare through the integration of new digital and mobile technologies. When determining if a manuscript is suitable for publication, the journal considers four important criteria: novelty, clinical relevance, scientific rigor, and digital innovation.