Machine learning algorithms for the detection and prediction of depression in diabetes: A systematic review.
1
Population-Based Medicine, University of Tuebingen, Tuebingen, Germany
2
Psychology, University College Dublin, Dublin, Ireland
3
Artificial Intelligence Research Institute CSIC, Barcelona, Spain
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
INTRODUCTION:
Artificial intelligence (AI) holds great potential for being able develop automated systems that can detect and predict depression or depressive symptoms. This review seeks to synthesize the AI machine learning methods that have been implemented in the detection and prediction of depression in people with type 1, type 2, and gestational diabetes.
METHODS:
Databases, including PubMed, Embase, Web of Science, CINAHL, PsychInfo, IEEE Xplore, and ACM Digital Library are searched for relevant articles. No restrictions are placed on the AI approach, depressive symptom measure, or type of dataset used (e.g., wearable sensor data, electronic health records, or cohort data). Article screening, selection, data extraction, and risk of bias is conducted by 2 independent reviewers.
RESULTS:
Results will be synthesized in a narrative review. Key characteristics such as algorithms used, data sources, depression measure used, feature selection methods, validation strategies, and performance metrics will be compared and discussed.
CONCLUSIONS:
This review will provide an overview of the ways in which AI has been used to detect and predict depression in people with all types of diabetes. It will highlight the types of data and models used, identify methodological trends and limitations, and offer recommendations for future research in this emerging interdisciplinary field.
Artificial intelligence (AI) holds great potential for being able develop automated systems that can detect and predict depression or depressive symptoms. This review seeks to synthesize the AI machine learning methods that have been implemented in the detection and prediction of depression in people with type 1, type 2, and gestational diabetes.
METHODS:
Databases, including PubMed, Embase, Web of Science, CINAHL, PsychInfo, IEEE Xplore, and ACM Digital Library are searched for relevant articles. No restrictions are placed on the AI approach, depressive symptom measure, or type of dataset used (e.g., wearable sensor data, electronic health records, or cohort data). Article screening, selection, data extraction, and risk of bias is conducted by 2 independent reviewers.
RESULTS:
Results will be synthesized in a narrative review. Key characteristics such as algorithms used, data sources, depression measure used, feature selection methods, validation strategies, and performance metrics will be compared and discussed.
CONCLUSIONS:
This review will provide an overview of the ways in which AI has been used to detect and predict depression in people with all types of diabetes. It will highlight the types of data and models used, identify methodological trends and limitations, and offer recommendations for future research in this emerging interdisciplinary field.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
