PubData Leuphana Repository: Estimation of minimal data sets sizes for machine learning predictions in digital mental health interventions

Please use this identifier to cite or link to this item: https://doi.org/10.48548/pubdata-1651

Full metadata record

Field	Value
Resource type	Journal Article
Title(s)	Estimation of minimal data sets sizes for machine learning predictions in digital mental health interventions
DOI	10.48548/pubdata-1651
Handle	20.500.14123/1732
Creator	Zantvoort, Kirsten 0000-0001-9876-054X Nacke, Barbara 0000-0002-8976-8440 Görlich, Dennis 0000-0002-2574-9419 Hornstein, Silvan 0000-0002-0398-7096 Jacobi, Corinna 0000-0002-0982-0596 Funk, Burkhardt 0000-0001-5855-2666
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.
Language	English
Keywords	Psychiatric Disorder; Therapeutics; Psychische Störung
Year of publication in PubData	2025
Publishing type	Parallel publication
Publication version	Published version
Date issued	2024-12-18
Creation context	Research
Faculty / department	Fakultät Management und Technologie
Notes	This publication was funded by the German Research Foundation (DFG).
Date of Availability	2025-01-21T13:19:17Z
Archiving Facility	Medien- und Informationszentrum (Leuphana Universität Lüneburg 02w2y2t16)
Published by	Medien- und Informationszentrum, Leuphana Universität Lüneburg

Related Resources

Published in	ISSN: 2398-6352 npj Digital Medicine
Supplemented by	Handle: 20.500.14123/1735 Zantvoort, K., Nacke, B., Görlich, D., Hornstein, S., Jacobi, C., Funk, B. (2025). Supplementary Material for the Paper 'Estimation of minimal data sets sizes for machine learning predictions in digital mental health interventions'. Datensatz, Leuphana Universität Lüneburg.
Variant form of	DOI: 10.1038/s41746-024-01360-w Zantvoort, K., Nacke, B., Görlich, D., Hornstein, S., Jacobi, C., Funk, B. (2024). Estimation of minimal data sets sizes for machine learning predictions in digital mental health interventions. npj Digital Medicine, 7(1), Article 361.

Files in This Item:

File	Description	Size	Format
Zantvoort_Estimation_of_minimal_data_sets_sizes_for_machine_learning_predictions_in_digital_mental_health_interventions.pdf MD5: 64e11da8c919933dac81f6ae6908e2ce License: open-access		1.9 MB	Adobe PDF	View/Open

Items in PubData are protected by copyright, with all rights reserved, unless otherwise indicated.

Views

Show simple item record

Citation formats

BibTeX
RIS

Item Export Bar

Access statistics

Page view(s): 2

Download(s): 1