Matthew F Toerper1, Eleni Flanagan2, Sauleh Siddiqui3, Jeff Appelbaum4, Edward K Kasper5, Scott Levin6. 1. Johns Hopkins Department of Emergency Medicine, 1830 East Monument Street, Suite 6-100, Baltimore, MD 21287, USA Johns Hopkins Health System Operations Integration, 600 N. Wolfe Street, Administration Bldg. Suite 420, Baltimore, MD 21287, USA mtoerper@jhu.edu. 2. Johns Hopkins Heart and Vascular Institute, 600 N. Wolfe Street, The Johns Hopkins Hospital, Baltimore, MD 21287, USA. 3. Department of Civil Engineering, Johns Hopkins Systems Institute, Johns Hopkins University, 3400 N Charles Street, Baltimore, MD 21218, USA Department of Applied Mathematics and Statistics, Johns Hopkins Systems Institute, Johns Hopkins University, 3400 N Charles Street, Baltimore, MD 21218, USA. 4. Johns Hopkins Health System Operations Integration, 600 N. Wolfe Street, Administration Bldg. Suite 420, Baltimore, MD 21287, USA. 5. Division of Cardiology, Department of Medicine, Johns Hopkins Medical Institutions, Baltimore, Maryland. 6. Johns Hopkins Department of Emergency Medicine, 1830 East Monument Street, Suite 6-100, Baltimore, MD 21287, USA Johns Hopkins Health System Operations Integration, 600 N. Wolfe Street, Administration Bldg. Suite 420, Baltimore, MD 21287, USA.
Abstract
OBJECTIVE: To develop and prospectively evaluate a web-based tool that forecasts the daily bed need for admissions from the cardiac catheterization laboratory using routinely available clinical data within electronic medical records (EMRs). METHODS: The forecast model was derived using a 13-month retrospective cohort of 6384 catheterization patients. Predictor variables such as demographics, scheduled procedures, and clinical indicators mined from free-text notes were input to a multivariable logistic regression model that predicted the probability of inpatient admission. The model was embedded into a web-based application connected to the local EMR system and used to support bed management decisions. After implementation, the tool was prospectively evaluated for accuracy on a 13-month test cohort of 7029 catheterization patients. RESULTS: The forecast model predicted admission with an area under the receiver operating characteristic curve of 0.722. Daily aggregate forecasts were accurate to within one bed for 70.3% of days and within three beds for 97.5% of days during the prospective evaluation period. The web-based application housing the forecast model was used by cardiology providers in practice to estimate daily admissions from the catheterization laboratory. DISCUSSION: The forecast model identified older age, male gender, invasive procedures, coronary artery bypass grafts, and a history of congestive heart failure as qualities indicating a patient was at increased risk for admission. Diagnostic procedures and less acute clinical indicators decreased patients' risk of admission. Despite the site-specific limitations of the model, these findings were supported by the literature. CONCLUSION: Data-driven predictive analytics may be used to accurately forecast daily demand for inpatient beds for cardiac catheterization patients. Connecting these analytics to EMR data sources has the potential to provide advanced operational decision support.
OBJECTIVE: To develop and prospectively evaluate a web-based tool that forecasts the daily bed need for admissions from the cardiac catheterization laboratory using routinely available clinical data within electronic medical records (EMRs). METHODS: The forecast model was derived using a 13-month retrospective cohort of 6384 catheterization patients. Predictor variables such as demographics, scheduled procedures, and clinical indicators mined from free-text notes were input to a multivariable logistic regression model that predicted the probability of inpatient admission. The model was embedded into a web-based application connected to the local EMR system and used to support bed management decisions. After implementation, the tool was prospectively evaluated for accuracy on a 13-month test cohort of 7029 catheterization patients. RESULTS: The forecast model predicted admission with an area under the receiver operating characteristic curve of 0.722. Daily aggregate forecasts were accurate to within one bed for 70.3% of days and within three beds for 97.5% of days during the prospective evaluation period. The web-based application housing the forecast model was used by cardiology providers in practice to estimate daily admissions from the catheterization laboratory. DISCUSSION: The forecast model identified older age, male gender, invasive procedures, coronary artery bypass grafts, and a history of congestive heart failure as qualities indicating a patient was at increased risk for admission. Diagnostic procedures and less acute clinical indicators decreased patients' risk of admission. Despite the site-specific limitations of the model, these findings were supported by the literature. CONCLUSION: Data-driven predictive analytics may be used to accurately forecast daily demand for inpatient beds for cardiac catheterization patients. Connecting these analytics to EMR data sources has the potential to provide advanced operational decision support.
Authors: T M Bashore; E R Bates; P B Berger; D A Clark; J T Cusma; G J Dehmer; M J Kern; W K Laskey; M P O'Laughlin; S Oesterle; J J Popma; R A O'Rourke; J Abrams; E R Bates; B R Brodie; P S Douglas; G Gregoratos; M A Hlatky; J S Hochman; S Kaul; C M Tracy; D D Waters; W L Winters Journal: J Am Coll Cardiol Date: 2001-06-15 Impact factor: 24.094
Authors: Alan S Go; Dariush Mozaffarian; Véronique L Roger; Emelia J Benjamin; Jarett D Berry; Michael J Blaha; Shifan Dai; Earl S Ford; Caroline S Fox; Sheila Franco; Heather J Fullerton; Cathleen Gillespie; Susan M Hailpern; John A Heit; Virginia J Howard; Mark D Huffman; Suzanne E Judd; Brett M Kissela; Steven J Kittner; Daniel T Lackland; Judith H Lichtman; Lynda D Lisabeth; Rachel H Mackey; David J Magid; Gregory M Marcus; Ariane Marelli; David B Matchar; Darren K McGuire; Emile R Mohler; Claudia S Moy; Michael E Mussolino; Robert W Neumar; Graham Nichol; Dilip K Pandey; Nina P Paynter; Matthew J Reeves; Paul D Sorlie; Joel Stein; Amytis Towfighi; Tanya N Turan; Salim S Virani; Nathan D Wong; Daniel Woo; Melanie B Turner Journal: Circulation Date: 2013-12-18 Impact factor: 29.690
Authors: C Daniel Smith; Thomas Spackman; Karen Brommer; Michael W Stewart; Michael Vizzini; James Frye; William C Rupp Journal: J Am Coll Surg Date: 2013-04 Impact factor: 6.113
Authors: Gregory J Dehmer; Douglas Weaver; Matthew T Roe; Sarah Milford-Beland; Susan Fitzgerald; Anthony Hermann; John Messenger; Issam Moussa; Kirk Garratt; John Rumsfeld; Ralph G Brindis Journal: J Am Coll Cardiol Date: 2012-10-17 Impact factor: 24.094
Authors: Diego A Martinez; Erin M Kane; Mehdi Jalalpour; James Scheulen; Hetal Rupani; Rohit Toteja; Charles Barbara; Bree Bush; Scott R Levin Journal: J Med Syst Date: 2018-06-18 Impact factor: 4.460