FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204853677> ?p ?o ?g. }

• W3204853677 endingPage "103930" @default.
• W3204853677 startingPage "103930" @default.
• W3204853677 abstract "Most end-stage renal disease patients rely on hemodialysis (HD) to maintain their life, and they face a serious financial burden and high risk of mortality. Due to the current situation of the health care system in China, a large number of patients on HD are lost to follow-up, making the identification of patients with high mortality risks an intractable problem. This paper aims to propose a maintenance HD mortality prediction approach using longitudinal HD data under the situation of data imbalance caused by follow-up losses. A long short-term memory autoencoder (LSTM AE) based model is proposed to capture the physical condition changes of HD patients and distinguish between surviving and nonsurviving patients. The approach adopts anomaly detection theory, using only the surviving samples in the model training and identifying dead samples based on autoencoder reconstruction errors. The data are from a Chinese hospital electronic health record system between July 30, 2007, and August 25, 2016, and 36/72/108 continuous HD sessions were used to predict mortality within prediction windows of 90/180/365 days. Furthermore, the model performance is compared to that of logistic regression, support vector machine, random forest, LSTM classifier, isolation forest, and stacked autoencoder models. Data for 1200 patients (survival: 1055, death: 145) were used to predict mortality during the next 90 days using 36 continuous HD sessions. The area under the PR curve for the LSTM AE was 0.57, the Recallmacro was 0.86, and the F1-scoremacro was 0.87, outperforming the other models. Upon varying the observation window or prediction window length, LSTM AE continued to outperform the other models. According to the variable importance analysis, the dialysis session length was the feature that contributed the most to the prediction model. The proposed approach was able to detect patients on maintenance HD with high mortality risk from an imbalanced dataset using anomaly detection theory and leveraging longitudinal HD data." @default.
• W3204853677 created "2021-10-11" @default.
• W3204853677 creator A5005314950 @default.
• W3204853677 creator A5012884053 @default.
• W3204853677 creator A5023138112 @default.
• W3204853677 creator A5032454574 @default.
• W3204853677 creator A5055151897 @default.
• W3204853677 creator A5079594267 @default.
• W3204853677 date "2021-11-01" @default.
• W3204853677 modified "2023-10-07" @default.
• W3204853677 title "A maintenance hemodialysis mortality prediction model based on anomaly detection using longitudinal hemodialysis data" @default.
• W3204853677 cites W1498436455 @default.
• W3204853677 cites W1965387207 @default.
• W3204853677 cites W1966716734 @default.
• W3204853677 cites W1968324276 @default.
• W3204853677 cites W1977173556 @default.
• W3204853677 cites W1998249118 @default.
• W3204853677 cites W2015882577 @default.
• W3204853677 cites W2030174339 @default.
• W3204853677 cites W2030959372 @default.
• W3204853677 cites W2043922598 @default.
• W3204853677 cites W2052996051 @default.
• W3204853677 cites W2062624311 @default.
• W3204853677 cites W2064675550 @default.
• W3204853677 cites W2069494863 @default.
• W3204853677 cites W2070765725 @default.
• W3204853677 cites W2076174804 @default.
• W3204853677 cites W2079048757 @default.
• W3204853677 cites W2087347434 @default.
• W3204853677 cites W2093483948 @default.
• W3204853677 cites W2097399944 @default.
• W3204853677 cites W2098577659 @default.
• W3204853677 cites W2102324358 @default.
• W3204853677 cites W2148143831 @default.
• W3204853677 cites W2155983179 @default.
• W3204853677 cites W2158892379 @default.
• W3204853677 cites W2160663184 @default.
• W3204853677 cites W2179775398 @default.
• W3204853677 cites W2260668761 @default.
• W3204853677 cites W2296719434 @default.
• W3204853677 cites W2502635255 @default.
• W3204853677 cites W2528775700 @default.
• W3204853677 cites W2564198924 @default.
• W3204853677 cites W2586384977 @default.
• W3204853677 cites W2612293302 @default.
• W3204853677 cites W2752621721 @default.
• W3204853677 cites W2775697911 @default.
• W3204853677 cites W2796762894 @default.
• W3204853677 cites W2797069187 @default.
• W3204853677 cites W2799895073 @default.
• W3204853677 cites W2803344989 @default.
• W3204853677 cites W2903428876 @default.
• W3204853677 cites W2911964244 @default.
• W3204853677 cites W2913869006 @default.
• W3204853677 cites W2917653738 @default.
• W3204853677 cites W2947805333 @default.
• W3204853677 doi "https://doi.org/10.1016/j.jbi.2021.103930" @default.
• W3204853677 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34624552" @default.
• W3204853677 hasPublicationYear "2021" @default.
• W3204853677 type Work @default.
• W3204853677 sameAs 3204853677 @default.
• W3204853677 citedByCount "3" @default.
• W3204853677 countsByYear W32048536772022 @default.
• W3204853677 countsByYear W32048536772023 @default.
• W3204853677 crossrefType "journal-article" @default.
• W3204853677 hasAuthorship W3204853677A5005314950 @default.
• W3204853677 hasAuthorship W3204853677A5012884053 @default.
• W3204853677 hasAuthorship W3204853677A5023138112 @default.
• W3204853677 hasAuthorship W3204853677A5032454574 @default.
• W3204853677 hasAuthorship W3204853677A5055151897 @default.
• W3204853677 hasAuthorship W3204853677A5079594267 @default.
• W3204853677 hasBestOaLocation W32048536771 @default.
• W3204853677 hasConcept C101738243 @default.
• W3204853677 hasConcept C108583219 @default.
• W3204853677 hasConcept C119857082 @default.
• W3204853677 hasConcept C12267149 @default.
• W3204853677 hasConcept C126322002 @default.
• W3204853677 hasConcept C151956035 @default.
• W3204853677 hasConcept C154945302 @default.
• W3204853677 hasConcept C169258074 @default.
• W3204853677 hasConcept C2778063415 @default.
• W3204853677 hasConcept C41008148 @default.
• W3204853677 hasConcept C71924100 @default.
• W3204853677 hasConcept C739882 @default.
• W3204853677 hasConceptScore W3204853677C101738243 @default.
• W3204853677 hasConceptScore W3204853677C108583219 @default.
• W3204853677 hasConceptScore W3204853677C119857082 @default.
• W3204853677 hasConceptScore W3204853677C12267149 @default.
• W3204853677 hasConceptScore W3204853677C126322002 @default.
• W3204853677 hasConceptScore W3204853677C151956035 @default.
• W3204853677 hasConceptScore W3204853677C154945302 @default.
• W3204853677 hasConceptScore W3204853677C169258074 @default.
• W3204853677 hasConceptScore W3204853677C2778063415 @default.
• W3204853677 hasConceptScore W3204853677C41008148 @default.
• W3204853677 hasConceptScore W3204853677C71924100 @default.
• W3204853677 hasConceptScore W3204853677C739882 @default.
• W3204853677 hasFunder F4320321001 @default.
• W3204853677 hasFunder F4320329742 @default.

• next