Vincent Lequertier, Tao Wang, Julien Fondrevelle, Vincent Augusto, Stéphanie Polazzi, Antoine Duclos
{"title":"利用深度神经网络,通过急诊和急救护理的标准化医院数据预测住院时间。","authors":"Vincent Lequertier, Tao Wang, Julien Fondrevelle, Vincent Augusto, Stéphanie Polazzi, Antoine Duclos","doi":"10.1097/MLR.0000000000001975","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Length of stay (LOS) is an important metric for the organization and scheduling of care activities. This study sought to propose a LOS prediction method based on deep learning using widely available administrative data from acute and emergency care and compare it with other methods.</p><p><strong>Patients and methods: </strong>All admissions between January 1, 2011 and December 31, 2019, at 6 university hospitals of the Hospices Civils de Lyon metropolis were included, leading to a cohort of 1,140,100 stays of 515,199 patients. Data included demographics, primary and associated diagnoses, medical procedures, the medical unit, the admission type, socio-economic factors, and temporal information. A model based on embeddings and a Feed-Forward Neural Network (FFNN) was developed to provide fine-grained LOS predictions per hospitalization step. Performances were compared with random forest and logistic regression, with the accuracy, Cohen kappa, and a Bland-Altman plot, through a 5-fold cross-validation.</p><p><strong>Results: </strong>The FFNN achieved an accuracy of 0.944 (CI: 0.937, 0.950) and a kappa of 0.943 (CI: 0.935, 0.950). For the same metrics, random forest yielded 0.574 (CI: 0.573, 0.575) and 0.602 (CI: 0.601, 0.603), respectively, and 0.352 (CI: 0.346, 0.358) and 0.414 (CI: 0.408, 0.422) for the logistic regression. The FFNN had a limit of agreement ranging from -2.73 to 2.67, which was better than random forest (-6.72 to 6.83) or logistic regression (-7.60 to 9.20).</p><p><strong>Conclusion: </strong>The FFNN was better at predicting LOS than random forest or logistic regression. Implementing the FFNN model for routine acute care could be useful for improving the quality of patients' care.</p>","PeriodicalId":18364,"journal":{"name":"Medical Care","volume":" ","pages":"225-234"},"PeriodicalIF":3.3000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Length of Stay Prediction With Standardized Hospital Data From Acute and Emergency Care Using a Deep Neural Network.\",\"authors\":\"Vincent Lequertier, Tao Wang, Julien Fondrevelle, Vincent Augusto, Stéphanie Polazzi, Antoine Duclos\",\"doi\":\"10.1097/MLR.0000000000001975\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>Length of stay (LOS) is an important metric for the organization and scheduling of care activities. This study sought to propose a LOS prediction method based on deep learning using widely available administrative data from acute and emergency care and compare it with other methods.</p><p><strong>Patients and methods: </strong>All admissions between January 1, 2011 and December 31, 2019, at 6 university hospitals of the Hospices Civils de Lyon metropolis were included, leading to a cohort of 1,140,100 stays of 515,199 patients. Data included demographics, primary and associated diagnoses, medical procedures, the medical unit, the admission type, socio-economic factors, and temporal information. A model based on embeddings and a Feed-Forward Neural Network (FFNN) was developed to provide fine-grained LOS predictions per hospitalization step. Performances were compared with random forest and logistic regression, with the accuracy, Cohen kappa, and a Bland-Altman plot, through a 5-fold cross-validation.</p><p><strong>Results: </strong>The FFNN achieved an accuracy of 0.944 (CI: 0.937, 0.950) and a kappa of 0.943 (CI: 0.935, 0.950). For the same metrics, random forest yielded 0.574 (CI: 0.573, 0.575) and 0.602 (CI: 0.601, 0.603), respectively, and 0.352 (CI: 0.346, 0.358) and 0.414 (CI: 0.408, 0.422) for the logistic regression. The FFNN had a limit of agreement ranging from -2.73 to 2.67, which was better than random forest (-6.72 to 6.83) or logistic regression (-7.60 to 9.20).</p><p><strong>Conclusion: </strong>The FFNN was better at predicting LOS than random forest or logistic regression. Implementing the FFNN model for routine acute care could be useful for improving the quality of patients' care.</p>\",\"PeriodicalId\":18364,\"journal\":{\"name\":\"Medical Care\",\"volume\":\" \",\"pages\":\"225-234\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical Care\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/MLR.0000000000001975\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/2/12 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical Care","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/MLR.0000000000001975","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/12 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
Length of Stay Prediction With Standardized Hospital Data From Acute and Emergency Care Using a Deep Neural Network.
Objective: Length of stay (LOS) is an important metric for the organization and scheduling of care activities. This study sought to propose a LOS prediction method based on deep learning using widely available administrative data from acute and emergency care and compare it with other methods.
Patients and methods: All admissions between January 1, 2011 and December 31, 2019, at 6 university hospitals of the Hospices Civils de Lyon metropolis were included, leading to a cohort of 1,140,100 stays of 515,199 patients. Data included demographics, primary and associated diagnoses, medical procedures, the medical unit, the admission type, socio-economic factors, and temporal information. A model based on embeddings and a Feed-Forward Neural Network (FFNN) was developed to provide fine-grained LOS predictions per hospitalization step. Performances were compared with random forest and logistic regression, with the accuracy, Cohen kappa, and a Bland-Altman plot, through a 5-fold cross-validation.
Results: The FFNN achieved an accuracy of 0.944 (CI: 0.937, 0.950) and a kappa of 0.943 (CI: 0.935, 0.950). For the same metrics, random forest yielded 0.574 (CI: 0.573, 0.575) and 0.602 (CI: 0.601, 0.603), respectively, and 0.352 (CI: 0.346, 0.358) and 0.414 (CI: 0.408, 0.422) for the logistic regression. The FFNN had a limit of agreement ranging from -2.73 to 2.67, which was better than random forest (-6.72 to 6.83) or logistic regression (-7.60 to 9.20).
Conclusion: The FFNN was better at predicting LOS than random forest or logistic regression. Implementing the FFNN model for routine acute care could be useful for improving the quality of patients' care.
期刊介绍:
Rated as one of the top ten journals in healthcare administration, Medical Care is devoted to all aspects of the administration and delivery of healthcare. This scholarly journal publishes original, peer-reviewed papers documenting the most current developments in the rapidly changing field of healthcare. This timely journal reports on the findings of original investigations into issues related to the research, planning, organization, financing, provision, and evaluation of health services.