The key to timely interventions and reducing avoidable incidence is the early identification of patients at risk for developing pressure ulcers. To enable the automatic detection of such patients and inform acute care interdisciplinary providers, a filter feature model using heuristic statistical methods was applied to a relational database of retrospective patient data including demographics, medications, and clinical visit details. These attributes served as input for the C4.5 decision tree induction algorithm, which was used to classify patient risk. The validity of the resulting classification model, Electronic Pressure Ulcer Prediction (ePUP), was assessed using a fourfold cross-validation. The current results show a limited application of such a naïve classification algorithm for automating pressure ulcer risk assessments. Additional refinements will be necessary before the predictions of ePUP are sufficient for general clinical use and the improvement of patient safety in acute care settings, and during the transition from hospital to home.
Adams, R. , & Duchene, P. (1985). Computerization of patient acuity and nursing care planning. New approach to improved patient care and cost-effective staffing . Journal of Nursing Administration, 15(4), 11-17 .
2.
Adriaans, P. , & Zantinge, D. (1996). Data mining. Boston, MA: Addison-Wesley .
3.
Agency for Health Care Policy and Research [AHCPR]. (1992). Pressure ulcers in adults: Prediction and prevention (Publication number 92-0047). Retrieved May 2, 2007, from http://www.ncbi.nlm.nih.gov/books/bv.fcgi?rid=hstat2.section.4508
4.
Allman, R.M. , Goode, P.S. , Burst, N. , Bartolucci, A.A. , & Thomas, D.R. (1999). Pressure ulcers, hospital complications, and disease severity: Impact on hospital costs and length of stay . Advances in Wound Care, 12(1), 22-30 .
5.
American Medical Directors Association [AMDA]. ( 2004). Pressure ulcers: Percentage of patients with documented assessment of skin for breakdown. Retrieved May 2, 2007, from National Quality Measures Clearinghouse (http://www.qualitymeasures.ahrq.gov).
6.
Anthony, D. , Clark, M. , & Dallender, J. (2000). An optimization of the Waterlow score using regression and artificial neural networks . Clinical Rehabilitation, 14(1), 102-109 .
7.
Anthony, D. , Reynolds, T. , & Russell, L. (2000). An investigation into the use of serum albumin in pressure sore prediction . Journal of Advanced Nursing, 32(2), 359-365 .
8.
Anthony, D. , Reynolds, T. , & Russell, L. (2003). A regression analysis of the Waterlow score in pressure ulcer risk assessment . Clinical Rehabilitation, 17(2), 216-223 .
9.
Baumgartner, C. , Bohm, C. , & Baumgartner, D. (2005). Modelling of classification rules on metabolic patterns including machine learning and expert knowledge . Journal of Biomedical Informatics, 38(2), 89-98 .
10.
Beerenwinkel, N. , Schmidt, B. , Walter, H. , Kaiser, R. , Lengauer, T. , Hoffmann, D. , et al. (2002). Diversity and complexity of HIV-1 drug resistance: A bioinformatics approach to predicting phenotype from genotype . Proceedings of the National Academy of Sciences of the United States of America, 99(12), 8271-8276 .
11.
Bergstrom, N. , Braden, B.J. , Laguzza, A. , & Holman, V. (1987). The Braden Scale for Predicting Pressure Sore Risk . Nursing Research, 36(4), 205-210 .
12.
Blockeel, H. , & Struyf, J. (2002). Efficient algorithms for decision tree cross-validation . Journal of Machine Learning Research, 3, 621-650 .
13.
Bridel, J. (1993). Assessing the risk of pressure sores . Nursing Standard, 7(25), 32-35 .
14.
Brown, S.J. (2004). The Braden Scale. A review of the research evidence. OrthopedicNursing, 23(1), 30-38 .
15.
Centers for Medicare and Medicaid Services. ( 2004). Guidance to surveyors for long term care facilities (CMS manual system. Provider certification, Transmittal 4, Pub. 100-07 state operations). Washington, DC: Author, Department of Health and Human Services .
16.
Cimino, J.J. (2000). From data to knowledge through concept-oriented terminologies: Experience with the Medical Entities Dictionary. Journal of theAmerican Medical Informatics Association , 7(3), 288-297.
17.
Cimino, J.J. , Clayton, P.D. , Hripcsak, G. , & Johnson, S.B. (1994). Knowledge-based approaches to the maintenance of a large controlled medical terminology. Journal of theAmerican Medical Informatics Association , 1(1), 35-50.
18.
Cimino, J.J. , Hripcsak, G. , Johnson, S. , & Clayton, P.D. (1989, November). Designing an introspective, controlled medical vocabulary . Proceedings of the Thirteenth Annual Symposium on Computer Applications in Medical Care, Washington, DC. IEEE Computer Society Press.
19.
Cubbin, B. , & Jackson, C. (1991). Trial of a pressure area risk calculator for intensive therapy patients . Intensive Care Nursing, 7(1), 40-44 .
20.
Edwards, M. (1994). The rationale for the use of risk calculators in pressure sore prevention, and the evidence of the reliability and validity of published scales . Journal of Advanced Nursing, 20(2), 288-296 .
21.
El-Solh, A. , Mylotte, J. , Sherif, S. , Serghani, J. , & Grant, B.J. (1997). Validity of a decision tree for predicting active pulmonary tuberculosis . American Journal of Respiratory and Critical Care Medicine, 155(5), 1711-1716 .
22.
Gawron, C.L. (1994). Risk factors for and prevalence of pressure ulcers among hospitalized patients. Journal of Wound, Ostomy, and ContinenceNursing, 21(6), 232-240 .
23.
Han, J. , & Kamber, M. (2001). Data mining: Concepts and techniques. San Francisco: Morgan Kaufmann .
24.
Harbit, M.D. (1996). Computer identification of patients at risk for skin breakdown . Clinical Nurse Specialist, 10(3): 125-127 .
25.
Holmes, J.H. , Durbin, D.R. , & Winston, F.K. (2000). Discovery of predictive models in an injury surveillance database: An application of data mining in clinical research . Proceedings of the American Medical Informatics Association Symposium (Los Angeles, CA), 359-363.
26.
John, G. , Kohavi, R. , & Pfleger, K. (1994, July). Irrelevant Features and the Subset Selection Problem . Proceedings of the Eleventh Annual International Conference on Machine Learning (ICML), San Francisco, CA , pp. 121-129. Morgan Kaufmann.
27.
Kim, T.Y. , & Lang, N.M. (2006). Predictive modeling for the prevention of hospital-acquired pressure ulcers . Proceedings/AMIA . . . Annual Symposium, 434-438.
28.
Kohavi, R. (1995, August). A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection . Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), San Francisco, CA, pp. 1137-1143. Morgan Kaufmann .
29.
Langlotz, C.P. , Shortliffe, E.H. , & Fagan, L.M. (1988). A methodology for generating computer-based explanations of decision-theoretic advice . Medical Decision Making, 8(4), 290-303 .
30.
Larson, E. (1986). Evaluating validity of screening tests . Nursing Research, 35(3), 186-188 .
31.
Masic, N. , Gagro, A. , Rabatic, S. , Sabioncello, A. , Dasic, G. , Jaksic, B. , et al. (1998). Decision-tree approach to the immunophenotype-based prognosis of the B-cell chronic lymphocytic leukemia . American Journal of Hematology, 59(2), 143-148 .
32.
Moret, B. (1982). Decision trees and diagrams . Computing Surveys, 14(4), 593-623 .
33.
Pagano, M. , & Gauvreau, K. (2000). Principles of biostatistics (2nd ed.). Pacific Grove, CA: Duxbury .
34.
Perneger, T.V. , Heliot, C. , Rae, A.C. , Borst, F. , & Gaspoz, J.M. (1998). Hospital-acquired pressure ulcers: Risk factors and use of preventive devices . Archives of Internal Medicine , 158(17), 1940-1945 .
35.
Pieper, B. , Sugrue, M. , Weiland, M. , Sprague, K. , & Heiman, C. (1998). Risk factors, prevention methods, and wound care for patients with pressure ulcers . Clinical Nurse Specialist , 12(1), 7-12 ; quiz 13-14 .
36.
Prichard, V. (1986). Calculating the risk . Nursing Times, 2(19), 59-61 .
37.
Quinlan, J.R. (1993). C4.5: Programs for machine learning. San Mateo, CA: Morgan Kaufmann .
38.
Salzberg, C.A. , Byrne, D.W. , Cayten, C.G. , van Niewerburgh, P. , Murphy, J.G. , & Viehbeck, M. (1996). A new pressure ulcer risk assessment scale for individuals with spinal cord injury . American Journal of Physical Medicine and Rehabilitation, 75(2), 96-104 .
39.
Samantha, M. , & Thomas, K. (1998). Predicting pressure sore risk with the Norton, Braden and Waterlow scales in a Hong Kong rehabilitation hospital . Nursing Research, 47(3), 147-153 .
40.
Schapire, R.E. (2002, March). The boosting approach to machine learning: An overview. In D . D. Denison , M. H. Hansen , C. Holmes , B. Mallick & B. Yu (Eds.), Nonlinear Estimation and Classification: Springer: New York .
41.
Schoonhoven, L. , Grobbee, D.E. , Bousema, M.T. , & Buskens, E. (2005). Predicting pressure ulcers: Cases missed using a new clinical prediction rule . Journal of Advanced Nursing , 49(1), 16-22 .
42.
Seongsook, J. , Ihnsook, J. , & Younghee, L. (2004). Validity of pressure ulcer risk assessment scales: Cubbin and Jackson, Braden, and Douglas scale . International Journal of Nursing Studies, 41, 199-204 .
43.
Towey, A. , & Erland, S. (1998). Validity and reliability of an assessment tool for pressure ulcer risk . Decubitus, 1(2), 40-48 .
44.
Venta, I. (1993). Predictive model for impaction of lower third molars . Oral Surgery, Oral Medicine, and Oral Pathology, 76(6), 699-703 .
45.
Wound, Ostomy, and Continence Nurses Society. ( 2003). Guideline for prevention and management of pressure ulcers (WOCN Clinical Practice Guideline No. 2). Glenview, IL : Author .
