Saul Blecker1, David Sontag2, Leora I Horwitz3, Gilad Kuperman4, Hannah Park5, Alex Reyentovich6, Stuart D Katz6. 1. Department of Population Health, New York Univeristy School of Medicine, New York, New York; Department of Medicine, New York Univeristy School of Medicine, New York, New York. Electronic address: saul.blecker@nyumc.org. 2. Department of Computer Science, New York University, New York, New York. 3. Department of Population Health, New York Univeristy School of Medicine, New York, New York; Department of Medicine, New York Univeristy School of Medicine, New York, New York. 4. New York-Presbyterian Hospital, New York, New York. 5. Department of Population Health, New York Univeristy School of Medicine, New York, New York. 6. Department of Medicine, New York Univeristy School of Medicine, New York, New York.
Abstract
BACKGROUND: Interventions to reduce readmissions after acute heart failure hospitalization require early identification of patients. The purpose of this study was to develop and test accuracies of various approaches to identify patients with acute decompensated heart failure (ADHF) with the use of data derived from the electronic health record. METHODS AND RESULTS: We included 37,229 hospitalizations of adult patients at a single hospital during 2013-2015. We developed 4 algorithms to identify hospitalization with a principal discharge diagnosis of ADHF: 1) presence of 1 of 3 clinical characteristics, 2) logistic regression of 31 structured data elements, 3) machine learning with unstructured data, and 4) machine learning with the use of both structured and unstructured data. In data validation, algorithm 1 had a sensitivity of 0.98 and positive predictive value (PPV) of 0.14 for ADHF. Algorithm 2 had an area under the receiver operating characteristic curve (AUC) of 0.96, and both machine learning algorithms had AUCs of 0.99. Based on a brief survey of 3 providers who perform chart review for ADHF, we estimated that providers spent 8.6 minutes per chart review; using this this parameter, we estimated that providers would spend 61.4, 57.3, 28.7, and 25.3 minutes on secondary chart review for each case of ADHF if initial screening were done with algorithms 1, 2, 3, and 4, respectively. CONCLUSIONS: Machine learning algorithms with unstructured notes had the best performance for identification of ADHF and can improve provider efficiency for delivery of quality improvement interventions.
BACKGROUND: Interventions to reduce readmissions after acute heart failure hospitalization require early identification of patients. The purpose of this study was to develop and test accuracies of various approaches to identify patients with acute decompensated heart failure (ADHF) with the use of data derived from the electronic health record. METHODS AND RESULTS: We included 37,229 hospitalizations of adult patients at a single hospital during 2013-2015. We developed 4 algorithms to identify hospitalization with a principal discharge diagnosis of ADHF: 1) presence of 1 of 3 clinical characteristics, 2) logistic regression of 31 structured data elements, 3) machine learning with unstructured data, and 4) machine learning with the use of both structured and unstructured data. In data validation, algorithm 1 had a sensitivity of 0.98 and positive predictive value (PPV) of 0.14 for ADHF. Algorithm 2 had an area under the receiver operating characteristic curve (AUC) of 0.96, and both machine learning algorithms had AUCs of 0.99. Based on a brief survey of 3 providers who perform chart review for ADHF, we estimated that providers spent 8.6 minutes per chart review; using this this parameter, we estimated that providers would spend 61.4, 57.3, 28.7, and 25.3 minutes on secondary chart review for each case of ADHF if initial screening were done with algorithms 1, 2, 3, and 4, respectively. CONCLUSIONS: Machine learning algorithms with unstructured notes had the best performance for identification of ADHF and can improve provider efficiency for delivery of quality improvement interventions.
Authors: Robert O Bonow; Theodore G Ganiats; Craig T Beam; Kathleen Blake; Donald E Casey; Sarah J Goodlin; Kathleen L Grady; Randal F Hundley; Mariell Jessup; Thomas E Lynn; Frederick A Masoudi; David Nilasena; Ileana L Piña; Paul D Rockswold; Lawrence B Sadwin; Joanna D Sikkema; Carrie A Sincak; John Spertus; Patrick J Torcson; Elizabeth Torres; Mark V Williams; John B Wong Journal: Circulation Date: 2012-04-23 Impact factor: 29.690
Authors: Clyde W Yancy; Mariell Jessup; Biykem Bozkurt; Javed Butler; Donald E Casey; Mark H Drazner; Gregg C Fonarow; Stephen A Geraci; Tamara Horwich; James L Januzzi; Maryl R Johnson; Edward K Kasper; Wayne C Levy; Frederick A Masoudi; Patrick E McBride; John J V McMurray; Judith E Mitchell; Pamela N Peterson; Barbara Riegel; Flora Sam; Lynne W Stevenson; W H Wilson Tang; Emily J Tsai; Bruce L Wilkoff Journal: J Am Coll Cardiol Date: 2013-06-05 Impact factor: 24.094
Authors: Patricia S Keenan; Sharon-Lise T Normand; Zhenqiu Lin; Elizabeth E Drye; Kanchana R Bhat; Joseph S Ross; Jeremiah D Schuur; Brett D Stauffer; Susannah M Bernheim; Andrew J Epstein; Yongfei Wang; Jeph Herrin; Jersey Chen; Jessica J Federer; Jennifer A Mattera; Yun Wang; Harlan M Krumholz Journal: Circ Cardiovasc Qual Outcomes Date: 2008-09
Authors: Robb D Kociol; Eric D Peterson; Bradley G Hammill; Kathryn E Flynn; Paul A Heidenreich; Ileana L Piña; Barbara L Lytle; Nancy M Albert; Lesley H Curtis; Gregg C Fonarow; Adrian F Hernandez Journal: Circ Heart Fail Date: 2012-08-28 Impact factor: 8.790
Authors: Eduard E Vasilevskis; Sunil Kripalani; Michael K Ong; J Thomas Rosenthal; David E Longnecker; Brian Harmon; Samuel F Hohmann; Kelly Wright; Jeanne T Black Journal: Acad Med Date: 2016-04 Impact factor: 6.893
Authors: Saul Blecker; Stuart D Katz; Leora I Horwitz; Gilad Kuperman; Hannah Park; Alex Gold; David Sontag Journal: JAMA Cardiol Date: 2016-12-01 Impact factor: 14.676
Authors: Elizabeth H Bradley; Heather Sipsma; Leora I Horwitz; Chima D Ndumele; Amanda L Brewster; Leslie A Curry; Harlan M Krumholz Journal: J Gen Intern Med Date: 2014-12-19 Impact factor: 5.128
Authors: Chaitanya Shivade; Preethi Raghavan; Eric Fosler-Lussier; Peter J Embi; Noemie Elhadad; Stephen B Johnson; Albert M Lai Journal: J Am Med Inform Assoc Date: 2013-11-07 Impact factor: 4.497
Authors: Piero Pollesello; Tuvia Ben Gal; Dominique Bettex; Vladimir Cerny; Josep Comin-Colet; Alexandr A Eremenko; Dimitrios Farmakis; Francesco Fedele; Cândida Fonseca; Veli-Pekka Harjola; Antoine Herpain; Matthias Heringlake; Leo Heunks; Trygve Husebye; Visnja Ivancan; Kristian Karason; Sundeep Kaul; Jacek Kubica; Alexandre Mebazaa; Henning Mølgaard; John Parissis; Alexander Parkhomenko; Pentti Põder; Gerhard Pölzl; Bojan Vrtovec; Mehmet B Yilmaz; Zoltan Papp Journal: J Clin Med Date: 2019-11-01 Impact factor: 4.241
Authors: Amitava Banerjee; Suliang Chen; Ghazaleh Fatemifar; Mohamad Zeina; R Thomas Lumbers; Johanna Mielke; Simrat Gill; Dipak Kotecha; Daniel F Freitag; Spiros Denaxas; Harry Hemingway Journal: BMC Med Date: 2021-04-06 Impact factor: 11.150