Radar de Estudos Clínicos

Performance of machine learning-based prediction models for diabetic foot ulcer risk

The primary outcome is the predictive performance of machine learning-based models developed to estimate the risk of diabetic foot ulceration in patients with diabetes. Models will be trained using supervised machine learning techniques, with optimal hyperparameters identified through cross-validation. In the initial evaluation phase, model performance will be assessed for the ability to discriminate between patients with and without existing diabetic foot ulcers. In a subsequent phase, the models' ability to prospectively predict the development of diabetic foot ulcers during follow-up will be evaluated. Model robustness will be improved through an iterative process in which redundant variables are excluded and models are retrained. Predictive performance will be quantified using established metrics such as discrimination, calibration, and classification accuracy. To account for uncertainty in individual predictions, the final models will be combined with Conformal Prediction meth

From study start to 2027-12-31

Identification and interpretability of risk factors for diabetic foot ulcer development

The secondary outcome is the identification and validation of clinical, demographic, and socioeconomic variables that are potential risk factors for diabetic foot ulcer development in patients with diabetes. Variables and risk factor categories will be identified using electronic health record data from the primary care information system Assynja Whisp in Region Västra Götaland, linked with national registry data from Statistics Sweden (SCB), together with established scientific and empirical evidence. A case-control study design will be applied, in which patients with diabetes who develop foot ulcers are compared with a control group of patients with diabetes who do not develop foot ulcers. Population-level analyses will be conducted to examine associations and co-variation between the occurrence of diabetic foot ulcers and other relevant factors.

From study start to 2027-12-31