A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders
Expert Review of Pharmacoeconomics & Outcomes Research · 2023
DOI: 10.1080/14737167.2023.2230368 ↗Kurz gefasst
Fachartikel in der Zeitschrift Expert Review of Pharmacoeconomics & Outcomes Research, 2023. Verfasst von Vegard G Svendsen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Center of Economic Evaluation & Machine Learning, Trimbos Institute (Netherlands Institute of Mental Health and Addiction), Utrecht, The Netherlands. Hauptthemen laut MEDLINE: Privacy, Feeding and Eating Disorders. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Research and Development.
Abstract (Originalsprache)
OBJECTIVES: Applying machine-learning methodology to clinical data could present a promising avenue for predicting outcomes in patients receiving treatment for psychiatric disorders. However, preserving privacy when working with patient data remains a critical concern. METHODS: In showcasing how machine-learning can be used to build a clinically relevant prediction model on clinical data, we apply two commonly used machine-learning algorithms (Random Forest and least absolute shrinkage and selection operator) to routine outcome monitoring data collected from 593 patients with eating disorders to predict absence of reliable improvement 12 months after entering outpatient treatment. RESULTS: An RF model trained on data collected at baseline and after three months made 31.3% fewer errors in predicting lack of reliable improvement at 12 months, in comparison with chance. Adding data from a six-month follow-up resulted in only marginal improvements to accuracy. CONCLUSION: We were able to build and validate a model that could aid clinicians and researchers in more accurately predicting treatment response in patients with EDs. We also demonstrated how this could be done without compromising privacy. ML presents a promising approach to developing accurate prediction models for psychiatric disorders such as ED.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center of Economic Evaluation & Machine Learning, Trimbos Institute (Netherlands Institute of Mental Health and Addiction), Utrecht, The Netherlands.
- Department of Health Services Research, Care and Public Health Research, CAPHRI, Maastricht University, Maastricht, The Netherlands.
- Norwegian Centre for Addiction Research, SERAF, University of Oslo, Oslo, Norway.
- Department of Clinical Epidemiology and Medical Technology Assessment, Maastricht University Medical Center, Maastricht, The Netherlands.
- Human Concern, Centre for Eating Disorders, Human Concern, Amsterdam, The Netherlands.
ORCID-Profile: Vegard G Svendsen, Ben F M Wijnen, Jan Alexander De Vos, Silvia M A A Evers, Joran Lokkerbol
Förderung
- Research and Development
Zitieren
APA
Svendsen, V. G., Wijnen, B. F. M., De Vos, J. A., Veenstra, R., Evers, S. M. A. A., & Lokkerbol, J. (2023). A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders. Expert Review of Pharmacoeconomics & Outcomes Research. https://doi.org/10.1080/14737167.2023.2230368
Vancouver
Svendsen VG, Wijnen BFM, De Vos JA, Veenstra R, Evers SMAA, Lokkerbol J. A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders. Expert Review of Pharmacoeconomics & Outcomes Research. 2023. doi:10.1080/14737167.2023.2230368
BibTeX
@article{Svendsen2023,
author = {Svendsen, Vegard G and Wijnen, Ben F M and De Vos, Jan Alexander and Veenstra, Ravian and Evers, Silvia M A A and Lokkerbol, Joran},
title = {A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders},
journal = {Expert Review of Pharmacoeconomics & Outcomes Research},
year = {2023},
doi = {10.1080/14737167.2023.2230368}
}
EUVIMED