Predicting Inpatient Acute Kidney Injury over Different Time Horizons: How Early and Accurate?. Cheng, P., Waitman, L. R., Hu, Y., & Liu, M. AMIA Annual Symposium Proceedings, 2017:565–574, April, 2018. ![Predicting Inpatient Acute Kidney Injury over Different Time Horizons: How Early and Accurate? [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Incidence of Acute Kidney Injury (AKI) has increased dramatically over the past two decades due to rising prevalence of comorbidities and broadening repertoire of nephrotoxic medications. Hospitalized patients with AKI are at higher risk for complications and mortality, thus early recognition of AKI is crucial. Building AKI prediction models based on electronic medical records (EMRs) can enable early recognition of high-risk patients, facilitate prevention of iatrogenically induced AKI events, and improve patient outcomes. This study builds machine learning models to predict hospital-acquired AKI over different time horizons using EMR data. The study objectives are to assess (1) whether early AKI prediction is possible; (2) whether information prior to admission improves prediction; (3) what type of risk factors affect AKI prediction the most. Evaluation results showed a good cross-validated AUC of 0.765 for predicting AKI events 1-day prior and adding data prior to admission did not improve model performance.
@article{cheng_predicting_2018,
title = {Predicting {Inpatient} {Acute} {Kidney} {Injury} over {Different} {Time} {Horizons}: {How} {Early} and {Accurate}?},
volume = {2017},
issn = {1942-597X},
shorttitle = {Predicting {Inpatient} {Acute} {Kidney} {Injury} over {Different} {Time} {Horizons}},
url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977670/},
abstract = {Incidence of Acute Kidney Injury (AKI) has increased dramatically over the past two decades due to rising prevalence of comorbidities and broadening repertoire of nephrotoxic medications. Hospitalized patients with AKI are at higher risk for complications and mortality, thus early recognition of AKI is crucial. Building AKI prediction models based on electronic medical records (EMRs) can enable early recognition of high-risk patients, facilitate prevention of iatrogenically induced AKI events, and improve patient outcomes. This study builds machine learning models to predict hospital-acquired AKI over different time horizons using EMR data. The study objectives are to assess (1) whether early AKI prediction is possible; (2) whether information prior to admission improves prediction; (3) what type of risk factors affect AKI prediction the most. Evaluation results showed a good cross-validated AUC of 0.765 for predicting AKI events 1-day prior and adding data prior to admission did not improve model performance.},
urldate = {2018-06-21TZ},
journal = {AMIA Annual Symposium Proceedings},
author = {Cheng, Peng and Waitman, Lemuel R. and Hu, Yong and Liu, Mei},
month = apr,
year = {2018},
pmid = {29854121},
pmcid = {PMC5977670},
pages = {565--574}
}
Downloads: 0
{"_id":"Kn2EDQuAE5T8q7eRd","bibbaseid":"cheng-waitman-hu-liu-predictinginpatientacutekidneyinjuryoverdifferenttimehorizonshowearlyandaccurate-2018","downloads":0,"creationDate":"2019-03-07T14:08:40.494Z","title":"Predicting Inpatient Acute Kidney Injury over Different Time Horizons: How Early and Accurate?","author_short":["Cheng, P.","Waitman, L. R.","Hu, Y.","Liu, M."],"year":2018,"bibtype":"article","biburl":"https://bibbase.org/zotero/Robert Laurine","bibdata":{"bibtype":"article","type":"article","title":"Predicting Inpatient Acute Kidney Injury over Different Time Horizons: How Early and Accurate?","volume":"2017","issn":"1942-597X","shorttitle":"Predicting Inpatient Acute Kidney Injury over Different Time Horizons","url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977670/","abstract":"Incidence of Acute Kidney Injury (AKI) has increased dramatically over the past two decades due to rising prevalence of comorbidities and broadening repertoire of nephrotoxic medications. Hospitalized patients with AKI are at higher risk for complications and mortality, thus early recognition of AKI is crucial. Building AKI prediction models based on electronic medical records (EMRs) can enable early recognition of high-risk patients, facilitate prevention of iatrogenically induced AKI events, and improve patient outcomes. This study builds machine learning models to predict hospital-acquired AKI over different time horizons using EMR data. The study objectives are to assess (1) whether early AKI prediction is possible; (2) whether information prior to admission improves prediction; (3) what type of risk factors affect AKI prediction the most. Evaluation results showed a good cross-validated AUC of 0.765 for predicting AKI events 1-day prior and adding data prior to admission did not improve model performance.","urldate":"2018-06-21TZ","journal":"AMIA Annual Symposium Proceedings","author":[{"propositions":[],"lastnames":["Cheng"],"firstnames":["Peng"],"suffixes":[]},{"propositions":[],"lastnames":["Waitman"],"firstnames":["Lemuel","R."],"suffixes":[]},{"propositions":[],"lastnames":["Hu"],"firstnames":["Yong"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Mei"],"suffixes":[]}],"month":"April","year":"2018","pmid":"29854121","pmcid":"PMC5977670","pages":"565–574","bibtex":"@article{cheng_predicting_2018,\n\ttitle = {Predicting {Inpatient} {Acute} {Kidney} {Injury} over {Different} {Time} {Horizons}: {How} {Early} and {Accurate}?},\n\tvolume = {2017},\n\tissn = {1942-597X},\n\tshorttitle = {Predicting {Inpatient} {Acute} {Kidney} {Injury} over {Different} {Time} {Horizons}},\n\turl = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977670/},\n\tabstract = {Incidence of Acute Kidney Injury (AKI) has increased dramatically over the past two decades due to rising prevalence of comorbidities and broadening repertoire of nephrotoxic medications. Hospitalized patients with AKI are at higher risk for complications and mortality, thus early recognition of AKI is crucial. Building AKI prediction models based on electronic medical records (EMRs) can enable early recognition of high-risk patients, facilitate prevention of iatrogenically induced AKI events, and improve patient outcomes. This study builds machine learning models to predict hospital-acquired AKI over different time horizons using EMR data. The study objectives are to assess (1) whether early AKI prediction is possible; (2) whether information prior to admission improves prediction; (3) what type of risk factors affect AKI prediction the most. Evaluation results showed a good cross-validated AUC of 0.765 for predicting AKI events 1-day prior and adding data prior to admission did not improve model performance.},\n\turldate = {2018-06-21TZ},\n\tjournal = {AMIA Annual Symposium Proceedings},\n\tauthor = {Cheng, Peng and Waitman, Lemuel R. and Hu, Yong and Liu, Mei},\n\tmonth = apr,\n\tyear = {2018},\n\tpmid = {29854121},\n\tpmcid = {PMC5977670},\n\tpages = {565--574}\n}\n\n","author_short":["Cheng, P.","Waitman, L. R.","Hu, Y.","Liu, M."],"key":"cheng_predicting_2018","id":"cheng_predicting_2018","bibbaseid":"cheng-waitman-hu-liu-predictinginpatientacutekidneyinjuryoverdifferenttimehorizonshowearlyandaccurate-2018","role":"author","urls":{"Paper":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977670/"},"downloads":0},"search_terms":["predicting","inpatient","acute","kidney","injury","over","different","time","horizons","early","accurate","cheng","waitman","hu","liu"],"keywords":[],"authorIDs":[],"dataSources":["yP2f7ZTqzqGzG39kW"]}