A decision support tool for allocating hospital bed resources and determining required acuity of care Steven Walczak a, * , Walter E. Pofahl b , Ronald J. Scorpio c a College of Business and Administration, University of Coloradoat Denver, Campus Box 165, PO Box 173364, Denver, CO 80217-3364, USA b Department of Surgery, Brody School of Medicine, East Carolina University, Greenville, NC 27835, USA c Spartanburg Regional Healthcare System, 101 East Wood Street, Spartanburg, SC 29303, USA Accepted 28 February 2002 Abstract Limitations in health care funding require physicians and hospitals to find effective ways to utilize resources. Neural networks provide a method for predicting resource utilization of costly resources used for prolonged periods of time. Injury severity knowledge is used to determine the acuity of care required for each patient and length of stay is used to determine duration of inpatient hospitalization. Neural networks perform well on these medical domain problems, predicting total length of stay within 3 days for pediatric trauma (population mean and S.D. 4.37 F 45.12) and within 4 days for acute pancreatitis patients (7.75 F 79.19). D 2002 Elsevier Science B.V. All rights reserved. Keywords: Neural networks; Hospitalization; Length of stay; Trauma; Pancreatitis; Acuity of care; Fuzzy ARTMAP; Backpropagation 1. Introduction Hospitals are faced with limited resources includ- ing beds to hold admitted patients. This resource constraint is particularly important in specialized areas of the hospital, such as intensive care (ICU) and intermediate care units, since the number of beds available is a fraction of the number of floor beds, where the intensity of care is less. Cost-effective patient management is critically dependent on accu- rate assessment of individual patient outcome and resource utilization [3]. Evaluating length of stay (LOS) information is a challenging task [21], but is essential for the operational success of a hospital. Intensive care resources in particular are often limited and pose scheduling problems for hospital staff and administrators [18]. Predicting LOS is difficult and is often only done retrospectively. There are different components of a patient’s LOS. Lengths of stay may be evaluated for ICUs, step down units, and floor units individually, and may also be evaluated as an aggregation of all areas to provide a total LOS. Existing research in this area looks at predicting or analyzing the LOS for patients in a specific hospital area (e.g., ICU) [3,7,10,11,18]. The research presented in this article will initially be concerned with ICU LOS, but will ultimately address predicting the LOS for a patient at all levels of care in the hospital and providing a total LOS. A patient’s LOS is correlated with that patient’s injury or illness severity [9], that is patients who are 0167-9236/02/$ - see front matter D 2002 Elsevier Science B.V. All rights reserved. PII:S0167-9236(02)00071-4 * Corresponding author. Tel.: +1-303-556-6777; fax: +1-303- 556-6619. E-mail addresses: swalczak@carbon.cudenver.edu (S. Walczak), wpofahl@mail.ecu.edu (W.E. Pofahl). www.elsevier.com/locate/dsw Decision Support Systems 34 (2002) 445 – 456