Conectar
To develop and externally validate a two-stage machine learning framework that integrates polygenic risk and clinical variables for early identification of individuals at risk of developing type 2 diabetes.
We conducted a prospective prediction study using data from the All of Us Research Program for model development and the UK Biobank for external validation. Two models were constructed. Stage 1 used gradient boosted decision trees (XGBoost) with cross validation, automated hyperparameter optimisation and class weighting to predict 5-year incident type 2 diabetes using demographic, clinical and polygenic predictors. Stage 2 incorporated glycated haemoglobin or fasting glucose measurements to refine risk estimates. Model interpretation used SHapley Additive exPlanations values and permutation importance, and logistic regression and random forest models served as comparators. Discrimination of all models was compared using the DeLong test.
The Stage 1 model achieved an area under the receiver operating characteristic curve (AUROC) of 0.81 in All of Us and 0.82 in UK Biobank, performing significantly better than the phenotype-only model in UK Biobank (DeLong p=1.05x10–⁷⁶). Higher polygenic risk quartiles were associated with increased incidence of type 2 diabetes in both cohorts (global 2 p
A two-stage machine learning framework that integrates genetic and clinical information can support personalised screening for type 2 diabetes across diverse populations. The approach demonstrated robust performance across cohorts and offers a practical structure for early risk identification.
The number of patients requiring wound care is increasing, placing a burden on healthcare institutions and clinicians. While negative pressure wound therapy (NPWT) use has become increasingly common, Middle East-specific wound care guidelines are limited. An in-person meeting was held in Dubai with 15 wound care experts to develop guidelines for NPWT and NPWT with instillation and dwell (NPWTi-d) use for the Middle East. A literature search was performed using PubMed, Science Direct and Cochrane Reviews. Prior to the meeting, panel members reviewed literature and existing guidelines on NPWT and/or NPWTi-d use. A wound management treatment algorithm was created. Patient and wound assessment at presentation and throughout the treatment plan was recommended. Primary closure was recommended for simple wounds, and NPWT use was suggested for complex wounds requiring wound bed preparation. NPWTi-d use was advised when wound cleansing is required, if the patient is unsuitable for surgical debridement, or if surgical debridement is delayed. When NPWTi-d is unavailable, panel members recommended NPWT. Panel members recommended NPWT for wound bed preparation and NPWTi-d when wound cleansing is needed. These recommendations provide general guidance for NPWT and NPWTi-d use and should be updated as more clinical evidence becomes available.
FreshRSS 