FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4251638793> ?p ?o ?g. }

• W4251638793 abstract "<sec> <title>BACKGROUND</title> With the rapid adoption of electronic medical records (EMRs), there is an ever-increasing opportunity to collect data and extract knowledge from EMRs to support patient-centered stroke management. </sec> <sec> <title>OBJECTIVE</title> This study aims to compare the effectiveness of state-of-the-art automatic text classification methods in classifying data to support the prediction of clinical patient outcomes and the extraction of patient characteristics from EMRs. </sec> <sec> <title>METHODS</title> Our study addressed the computational problems of information extraction and automatic text classification. We identified essential tasks to be considered in an ischemic stroke value-based program. The 30 selected tasks were classified (manually labeled by specialists) according to the following value agenda: tier 1 (achieved health care status), tier 2 (recovery process), care related (clinical management and risk scores), and baseline characteristics. The analyzed data set was retrospectively extracted from the EMRs of patients with stroke from a private Brazilian hospital between 2018 and 2019. A total of 44,206 sentences from free-text medical records in Portuguese were used to train and develop 10 supervised computational machine learning methods, including state-of-the-art neural and nonneural methods, along with ontological rules. As an experimental protocol, we used a 5-fold cross-validation procedure repeated 6 times, along with <i>subject-wise sampling</i>. A heatmap was used to display comparative result analyses according to the best algorithmic effectiveness (F1 score), supported by statistical significance tests. A feature importance analysis was conducted to provide insights into the results. </sec> <sec> <title>RESULTS</title> The top-performing models were support vector machines trained with lexical and semantic textual features, showing the importance of dealing with noise in EMR textual representations. The support vector machine models produced statistically superior results in 71% (17/24) of tasks, with an F1 score &gt;80% regarding care-related tasks (patient treatment location, fall risk, thrombolytic therapy, and pressure ulcer risk), the process of recovery (ability to feed orally or ambulate and communicate), health care status achieved (mortality), and baseline characteristics (diabetes, obesity, dyslipidemia, and smoking status). Neural methods were largely outperformed by more traditional nonneural methods, given the characteristics of the data set. Ontological rules were also effective in tasks such as baseline characteristics (alcoholism, atrial fibrillation, and coronary artery disease) and the Rankin scale. The complementarity in effectiveness among models suggests that a combination of models could enhance the results and cover more tasks in the future. </sec> <sec> <title>CONCLUSIONS</title> Advances in information technology capacity are essential for scalability and agility in measuring health status outcomes. This study allowed us to measure effectiveness and identify opportunities for automating the classification of outcomes of specific tasks related to clinical conditions of stroke victims, and thus ultimately assess the possibility of proactively using these machine learning techniques in real-world situations. </sec>" @default.
• W4251638793 created "2022-05-12" @default.
• W4251638793 creator A5006271187 @default.
• W4251638793 creator A5009156529 @default.
• W4251638793 creator A5012195161 @default.
• W4251638793 creator A5012766481 @default.
• W4251638793 creator A5018690278 @default.
• W4251638793 creator A5034467582 @default.
• W4251638793 creator A5034821010 @default.
• W4251638793 creator A5046370637 @default.
• W4251638793 creator A5046683090 @default.
• W4251638793 creator A5051477267 @default.
• W4251638793 creator A5052823852 @default.
• W4251638793 creator A5057646226 @default.
• W4251638793 creator A5070958167 @default.
• W4251638793 creator A5072961099 @default.
• W4251638793 date "2021-03-29" @default.
• W4251638793 modified "2023-09-29" @default.
• W4251638793 title "Stroke Outcome Measurements From Electronic Medical Records: Cross-sectional Study on the Effectiveness of Neural and Nonneural Classifiers (Preprint)" @default.
• W4251638793 cites W1966716734 @default.
• W4251638793 cites W2012451988 @default.
• W4251638793 cites W2014898084 @default.
• W4251638793 cites W2017820014 @default.
• W4251638793 cites W2023248478 @default.
• W4251638793 cites W2025428542 @default.
• W4251638793 cites W2037842918 @default.
• W4251638793 cites W2046649513 @default.
• W4251638793 cites W2058384458 @default.
• W4251638793 cites W2062093912 @default.
• W4251638793 cites W2073249703 @default.
• W4251638793 cites W2078718894 @default.
• W4251638793 cites W2114584591 @default.
• W4251638793 cites W2127544153 @default.
• W4251638793 cites W2133506114 @default.
• W4251638793 cites W2137532674 @default.
• W4251638793 cites W2140302476 @default.
• W4251638793 cites W2153653693 @default.
• W4251638793 cites W2157874634 @default.
• W4251638793 cites W2232857057 @default.
• W4251638793 cites W2276489640 @default.
• W4251638793 cites W2314799854 @default.
• W4251638793 cites W2343412830 @default.
• W4251638793 cites W2462051711 @default.
• W4251638793 cites W2467857459 @default.
• W4251638793 cites W2550999023 @default.
• W4251638793 cites W2593739814 @default.
• W4251638793 cites W2604265436 @default.
• W4251638793 cites W2735585131 @default.
• W4251638793 cites W2759511880 @default.
• W4251638793 cites W2760314420 @default.
• W4251638793 cites W2768488789 @default.
• W4251638793 cites W2783859835 @default.
• W4251638793 cites W2789894922 @default.
• W4251638793 cites W2795240784 @default.
• W4251638793 cites W2808897169 @default.
• W4251638793 cites W2890177287 @default.
• W4251638793 cites W2898155085 @default.
• W4251638793 cites W2899740939 @default.
• W4251638793 cites W2913946809 @default.
• W4251638793 cites W2921112006 @default.
• W4251638793 cites W2954580219 @default.
• W4251638793 cites W2966351171 @default.
• W4251638793 cites W2999859295 @default.
• W4251638793 cites W3000817905 @default.
• W4251638793 cites W3018021611 @default.
• W4251638793 cites W3022371575 @default.
• W4251638793 cites W3034655770 @default.
• W4251638793 cites W3091602774 @default.
• W4251638793 cites W3096180285 @default.
• W4251638793 cites W3097271252 @default.
• W4251638793 cites W3101448279 @default.
• W4251638793 cites W3102749286 @default.
• W4251638793 cites W3104761038 @default.
• W4251638793 cites W3105625590 @default.
• W4251638793 cites W3109501393 @default.
• W4251638793 cites W3112739210 @default.
• W4251638793 cites W3122092081 @default.
• W4251638793 cites W3126191299 @default.
• W4251638793 cites W3134399782 @default.
• W4251638793 cites W3135207877 @default.
• W4251638793 cites W4229954146 @default.
• W4251638793 cites W4231934124 @default.
• W4251638793 doi "https://doi.org/10.2196/preprints.29120" @default.
• W4251638793 hasPublicationYear "2021" @default.
• W4251638793 type Work @default.
• W4251638793 citedByCount "0" @default.
• W4251638793 crossrefType "posted-content" @default.
• W4251638793 hasAuthorship W4251638793A5006271187 @default.
• W4251638793 hasAuthorship W4251638793A5009156529 @default.
• W4251638793 hasAuthorship W4251638793A5012195161 @default.
• W4251638793 hasAuthorship W4251638793A5012766481 @default.
• W4251638793 hasAuthorship W4251638793A5018690278 @default.
• W4251638793 hasAuthorship W4251638793A5034467582 @default.
• W4251638793 hasAuthorship W4251638793A5034821010 @default.
• W4251638793 hasAuthorship W4251638793A5046370637 @default.
• W4251638793 hasAuthorship W4251638793A5046683090 @default.
• W4251638793 hasAuthorship W4251638793A5051477267 @default.
• W4251638793 hasAuthorship W4251638793A5052823852 @default.
• W4251638793 hasAuthorship W4251638793A5057646226 @default.
• W4251638793 hasAuthorship W4251638793A5070958167 @default.

• next