Quinty Walschots
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Quinty Walschots has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Astrid Mariska Kamperman
Department of Psychiatry, Erasmus University Medical Center
1 shared publication - Maurits Unkel
Department of Psychiatry, Erasmus MC
1 shared publication - Milan Zarchev
Department of Child and Adolescent Psychiatry/Psychology, Erasmus MC, Rotterdam, the Netherlands; Department of Psychiatry, Erasmus MC, Rotterdam, the Netherlands; The Generation R Study Group, Erasmus MC, Rotterdam, the Netherlands
1 shared publication
Latest Publications
- Open Access
- 12 September 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (9) , 408
Using Wearable Technology to Detect, Monitor, and Predict Major Depressive Disorder—A Scoping Review and Introductory Text for Clinical Professionals
The rising popularity of wearable devices allows for extensive and unobtrusive collection of personal health data for extended periods of time. Recent studies have used machine learning to create predictive algorithms to assess symptoms of major depressive disorder (MDD) based on these data. This review evaluates the clinical relevance of these models. Studies were selected to represent the range of methodologies and applications of wearables for MDD algorithms, with a focus on wrist-worn devices. The reviewed studies demonstrated that wearable-based algorithms were able to predict symptoms of MDD with considerable accuracy. These models may be used in the clinic to complement the monitoring of treatments or to facilitate early intervention in high-risk populations. In a preventative context, they could prompt users to seek help for earlier intervention and better clinical outcomes. However, the lack of standardized methodologies and variation in which performance metrics are reported complicates direct comparisons between studies. Issues with reproducibility, overfitting, small sample sizes, and limited population demographics also limit the generalizability of findings. As such, wearable-based algorithms show considerable promise for predicting and monitoring MDD, but there is significant room for improvement before this promise can be fulfilled.
- 12 September 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (9) , 408
Open AccessUsing Wearable Technology to Detect, Monitor, and Predict Major Depressive Disorder—A Scoping Review and Introductory Text for Clinical Professionals
The rising popularity of wearable devices allows for extensive and unobtrusive collection of personal health data for extended periods of time. Recent studies have used machine learning to create predictive algorithms to assess symptoms of major depressive disorder (MDD) based on these data. This review evaluates the clinical relevance of these models. Studies were selected to represent the range of methodologies and applications of wearables for MDD algorithms, with a focus on wrist-worn devices. The reviewed studies demonstrated that wearable-based algorithms were able to predict symptoms of MDD with considerable accuracy. These models may be used in the clinic to complement the monitoring of treatments or to facilitate early intervention in high-risk populations. In a preventative context, they could prompt users to seek help for earlier intervention and better clinical outcomes. However, the lack of standardized methodologies and variation in which performance metrics are reported complicates direct comparisons between studies. Issues with reproducibility, overfitting, small sample sizes, and limited population demographics also limit the generalizability of findings. As such, wearable-based algorithms show considerable promise for predicting and monitoring MDD, but there is significant room for improvement before this promise can be fulfilled.