Models

As part of the DiaClusT project, we developed a multinomial logistic regression classifier to assign patients to distinct type 2 diabetes clusters based on their clinical characteristics. The current approach, including age, sex, BMI, HbA1c, and triglyceride levels, achieved an overall accuracy of 92%, with sensitivity, specificity, and F1-score all exceeding 0.87. The model’s robust performance highlights the potential of incorporating cluster assignment into routine admission workflows, ...

The interim results are the results from the local statistical analysis at each centre, which were subsequently pooled in the mixed effects meta-analysis.

Note, that the centres are pseudonymised. Interim results are provided for the subset of centres (out of ten), who provided their consent for sharing the results as they were used for the meta-analysis. The pseudonymised names are those that are mentioned in some of the text files for the meta-analysis.

The folder suffix identifies whether ...

The provided software provides the R modules for both parts of the applied POLAR_MI ETL Pipeline, the distributed analysis approach developed within POLAR_MI:

Part 1: local data retrieval (WP_1_1_local_DataRetrieval.zip) and local statistical analysis (WP_1_1_local_StatisticalAnalysis.zip) for local execution at each centre

Part 2: meta-analysis of local results (WP_1_1_central_Metaanalysis.zip)

Within compressed folder, we provide “read me” files with further information.

The Core Ontology of Phenotyping (COP) defines core entities relevant to the modelling of phenotypic knowledge and the development of model-driven phenotyping software (such as the TOP Framework). The COP is founded on GFO-light.

The provided software provides the R modules for both parts of the applied POLAR_MI ETL Pipeline, the distributed analysis approach developed within POLAR_MI:

• Part 1: local data retrieval (WP_1_5_local_DataRetrieval.zip) and local statistical analysis (WP_1_5_local_StatisticalAnalysis.zip) for local execution at each centre
• Part 2: meta-analysis of local results (interim results; WP_1_5_central_Metaanalysis.zip)

Within compressed folder, we provide “read me” files with further information.

The 'Future 10-year risk calculator' is a tool designed to help determine the optimal timing for follow-up counseling based on the cumulative breast cancer risks provided in the CanRisk-Report created by the CanRisk website as a result of the BOADICEA risk assessment. It is not a replacement for the BOADICEA model, nor is it intended for medical diagnosis, treatment decisions, or the monitoring of health conditions. The risk estimation assumes that the individual's and family's risk profile remains ...