Matches in SemOpenAlex for { <https://semopenalex.org/work/W3127218785> ?p ?o ?g. }
- W3127218785 abstract "Abstract Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data from the single-payer health system in Ontario, Canada. A Gradient Boosting Decision Tree model was trained on data from 1,029,366 patients, validated on 272,864 patients, and tested on 265,406 patients. Discrimination was assessed using the AUC statistic and calibration was assessed visually using calibration plots overall and across population subgroups. Our model predicting three-year risk of adverse outcomes due to diabetes complications (hyper/hypoglycemia, tissue infection, retinopathy, cardiovascular events, amputation) included 700 features from multiple diverse data sources and had strong discrimination (average test AUC = 77.7, range 77.7–77.9). Through the design and validation of a high-performance model to predict diabetes complications adverse outcomes at the population level, we demonstrate the potential of machine learning and administrative health data to inform health planning and healthcare resource allocation for diabetes management." @default.
- W3127218785 created "2021-02-15" @default.
- W3127218785 creator A5018155329 @default.
- W3127218785 creator A5021505164 @default.
- W3127218785 creator A5027341076 @default.
- W3127218785 creator A5028677801 @default.
- W3127218785 creator A5034414826 @default.
- W3127218785 creator A5039366263 @default.
- W3127218785 creator A5041339654 @default.
- W3127218785 creator A5050289436 @default.
- W3127218785 creator A5051816127 @default.
- W3127218785 creator A5052746002 @default.
- W3127218785 creator A5066621096 @default.
- W3127218785 date "2021-02-12" @default.
- W3127218785 modified "2023-10-17" @default.
- W3127218785 title "Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data" @default.
- W3127218785 cites W1517291977 @default.
- W3127218785 cites W1551909886 @default.
- W3127218785 cites W1562955038 @default.
- W3127218785 cites W1678356000 @default.
- W3127218785 cites W1973055540 @default.
- W3127218785 cites W1980504238 @default.
- W3127218785 cites W1990748933 @default.
- W3127218785 cites W2001286026 @default.
- W3127218785 cites W2017313359 @default.
- W3127218785 cites W2035398107 @default.
- W3127218785 cites W2046621583 @default.
- W3127218785 cites W2049706465 @default.
- W3127218785 cites W2052611008 @default.
- W3127218785 cites W2057367182 @default.
- W3127218785 cites W2060142852 @default.
- W3127218785 cites W2074791350 @default.
- W3127218785 cites W2078197568 @default.
- W3127218785 cites W2099661430 @default.
- W3127218785 cites W2102797756 @default.
- W3127218785 cites W2106041274 @default.
- W3127218785 cites W2107295258 @default.
- W3127218785 cites W2108598243 @default.
- W3127218785 cites W2118095379 @default.
- W3127218785 cites W2137540532 @default.
- W3127218785 cites W2139634859 @default.
- W3127218785 cites W2139923324 @default.
- W3127218785 cites W2145548284 @default.
- W3127218785 cites W2147325147 @default.
- W3127218785 cites W2148414695 @default.
- W3127218785 cites W2154029809 @default.
- W3127218785 cites W2155653793 @default.
- W3127218785 cites W2159205453 @default.
- W3127218785 cites W2165560933 @default.
- W3127218785 cites W2168575206 @default.
- W3127218785 cites W2217007515 @default.
- W3127218785 cites W2232857057 @default.
- W3127218785 cites W2239135493 @default.
- W3127218785 cites W2308294708 @default.
- W3127218785 cites W2345478245 @default.
- W3127218785 cites W2351770388 @default.
- W3127218785 cites W2400708766 @default.
- W3127218785 cites W2609207702 @default.
- W3127218785 cites W2612292012 @default.
- W3127218785 cites W2755458934 @default.
- W3127218785 cites W2769264260 @default.
- W3127218785 cites W2773944606 @default.
- W3127218785 cites W2793603994 @default.
- W3127218785 cites W2802561155 @default.
- W3127218785 cites W2807046356 @default.
- W3127218785 cites W2809483962 @default.
- W3127218785 cites W2884128841 @default.
- W3127218785 cites W2889526011 @default.
- W3127218785 cites W2895230293 @default.
- W3127218785 cites W2903277834 @default.
- W3127218785 cites W2908201961 @default.
- W3127218785 cites W2921431948 @default.
- W3127218785 cites W2923014074 @default.
- W3127218785 cites W2925214600 @default.
- W3127218785 cites W2943505205 @default.
- W3127218785 cites W2945447024 @default.
- W3127218785 cites W2945583287 @default.
- W3127218785 cites W2956091366 @default.
- W3127218785 cites W2963847595 @default.
- W3127218785 cites W2964010366 @default.
- W3127218785 cites W2964696298 @default.
- W3127218785 cites W2966350165 @default.
- W3127218785 cites W2968847082 @default.
- W3127218785 cites W2972732442 @default.
- W3127218785 cites W2976252475 @default.
- W3127218785 cites W2981427782 @default.
- W3127218785 cites W2989324284 @default.
- W3127218785 cites W2995507340 @default.
- W3127218785 cites W2999615587 @default.
- W3127218785 cites W3000127051 @default.
- W3127218785 cites W3004527153 @default.
- W3127218785 cites W3004712038 @default.
- W3127218785 cites W3005474298 @default.
- W3127218785 cites W3036804145 @default.
- W3127218785 cites W3098949126 @default.
- W3127218785 cites W3102476541 @default.
- W3127218785 cites W3106503709 @default.
- W3127218785 cites W3198570063 @default.
- W3127218785 cites W4237918386 @default.
- W3127218785 doi "https://doi.org/10.1038/s41746-021-00394-8" @default.