Jianfang Liu, Sherry Glied, Olga Yakusheva, Cohen Bevin, Amelia E Schlak, Sunmoo Yoon, Kristine M Kulage, Lusine Poghosyan
{"title":"Using machine-learning methods to predict in-hospital mortality through the Elixhauser index: A Medicare data analysis.","authors":"Jianfang Liu, Sherry Glied, Olga Yakusheva, Cohen Bevin, Amelia E Schlak, Sunmoo Yoon, Kristine M Kulage, Lusine Poghosyan","doi":"10.1002/nur.22322","DOIUrl":null,"url":null,"abstract":"<p><p>Accurate in-hospital mortality prediction can reflect the prognosis of patients, help guide allocation of clinical resources, and help clinicians make the right care decisions. There are limitations to using traditional logistic regression models when assessing the model performance of comorbidity measures to predict in-hospital mortality. Meanwhile, the use of novel machine-learning methods is growing rapidly. In 2021, the Agency for Healthcare Research and Quality published new guidelines for using the Present-on-Admission (POA) indicator from the International Classification of Diseases, Tenth Revision, for coding comorbidities to predict in-hospital mortality from the Elixhauser's comorbidity measurement method. We compared the model performance of logistic regression, elastic net model, and artificial neural network (ANN) to predict in-hospital mortality from Elixhauser's measures under the updated POA guidelines. In this retrospective analysis, 1,810,106 adult Medicare inpatient admissions from six US states admitted after September 23, 2017, and discharged before April 11, 2019 were extracted from the Centers for Medicare and Medicaid Services data warehouse. The POA indicator was used to distinguish pre-existing comorbidities from complications that occurred during hospitalization. All models performed well (C-statistics >0.77). Elastic net method generated a parsimonious model, in which there were five fewer comorbidities selected to predict in-hospital mortality with similar predictive power compared to the logistic regression model. ANN had the highest C-statistics compared to the other two models (0.800 vs. 0.791 and 0.791). Elastic net model and AAN can be applied successfully to predict in-hospital mortality.</p>","PeriodicalId":54492,"journal":{"name":"Research in Nursing & Health","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10330510/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Research in Nursing & Health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/nur.22322","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/5/23 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"NURSING","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate in-hospital mortality prediction can reflect the prognosis of patients, help guide allocation of clinical resources, and help clinicians make the right care decisions. There are limitations to using traditional logistic regression models when assessing the model performance of comorbidity measures to predict in-hospital mortality. Meanwhile, the use of novel machine-learning methods is growing rapidly. In 2021, the Agency for Healthcare Research and Quality published new guidelines for using the Present-on-Admission (POA) indicator from the International Classification of Diseases, Tenth Revision, for coding comorbidities to predict in-hospital mortality from the Elixhauser's comorbidity measurement method. We compared the model performance of logistic regression, elastic net model, and artificial neural network (ANN) to predict in-hospital mortality from Elixhauser's measures under the updated POA guidelines. In this retrospective analysis, 1,810,106 adult Medicare inpatient admissions from six US states admitted after September 23, 2017, and discharged before April 11, 2019 were extracted from the Centers for Medicare and Medicaid Services data warehouse. The POA indicator was used to distinguish pre-existing comorbidities from complications that occurred during hospitalization. All models performed well (C-statistics >0.77). Elastic net method generated a parsimonious model, in which there were five fewer comorbidities selected to predict in-hospital mortality with similar predictive power compared to the logistic regression model. ANN had the highest C-statistics compared to the other two models (0.800 vs. 0.791 and 0.791). Elastic net model and AAN can be applied successfully to predict in-hospital mortality.
期刊介绍:
Research in Nursing & Health ( RINAH ) is a peer-reviewed general research journal devoted to publication of a wide range of research that will inform the practice of nursing and other health disciplines. The editors invite reports of research describing problems and testing interventions related to health phenomena, health care and self-care, clinical organization and administration; and the testing of research findings in practice. Research protocols are considered if funded in a peer-reviewed process by an agency external to the authors’ home institution and if the work is in progress. Papers on research methods and techniques are appropriate if they go beyond what is already generally available in the literature and include description of successful use of the method. Theory papers are accepted if each proposition is supported by research evidence. Systematic reviews of the literature are reviewed if PRISMA guidelines are followed. Letters to the editor commenting on published articles are welcome.