Enhancement of Decision Rules to Increase Generalizability and Performance of the Rule-Based System Assessing Risk for Pressure Ulcer

J. Choi; H. Kim

doi:10.4338/ACI-2012-12-RA-0056

Applied Clinical Informatics, Table of Contents

Appl Clin Inform 2013; 04(02): 251-266
DOI: 10.4338/ACI-2012-12-RA-0056

Research Article

Schattauer GmbH

Enhancement of Decision Rules to Increase Generalizability and Performance of the Rule-Based System Assessing Risk for Pressure Ulcer

Authors

J. Choi

¹University of Wisconsin Milwaukee, College of Nursing, Milwaukee, Wisconsin, United States
H. Kim

²University of California, San Diego, Division of Biomedical Informatics, La Jolla, California, United States

Abstract

Summary

Background: A rule-based system, the Braden Scale based Automated Risk Assessment Tool (BART), was developed to assess risk for pressure ulcer in a previous study. However, the BART illustrated two major areas in need of improvement, which were: 1) the enhancement of decision rules and 2) validation of generalizability to increase performance of BART.

Objectives: To enhance decision rules and validate generalizability of the enhanced BART.

Method: Two layers of decision rule enhancement were performed: 1) finding additional data items with the experts and 2) validating logics of decision rules utilizing a guideline modeling language. To refine the decision rules of the BART further, a survey study was conducted to ascertain the operational level of patient status description of the Braden Scale.

The enhanced BART (BART2) was designed to assess levels of pressure ulcer risk of patients (N = 99) whose data were collected by the nurses. The patients’ level of pressure ulcer risk was assessed by the nurses using a Braden Scale, by an expert using a Braden Scale, and by the automatic BART2 electronic risk assessment. SPSS statistical software version 20 (IBM, 2011) was used to test the agreement between the three different risk assessments performed on each patient.

Results: The level of agreement between the BART2 and the expert pressure ulcer assessments was “very good (0.83)”. The sensitivity and the specificity of the BART2 were 86.8% and 90.3% respectively.

Conclusion: This study illustrated successful enhancement of decision rules and increased general-izability and performance of the BART2. Although the BART2 showed a “very good” level of agreement (kappa = 0.83) with an expert, the data reveal a need to improve the moisture parameter of the Braden Scale. Once the moisture parameter has been improved, BART2 will improve the quality of care, while accurately identifying the patients at risk for pressure ulcers.

Citation: Choi J, Kim H. Enhancement of Decision Rules to Increase Generalizability and Performance of the Rule-Based System Assessing Risk for Pressure Ulcer. Appl Clin Inf 2013; 4: 251–266

http://dx.doi.org/10.4338/ACI-2012-12-RA-0056

Keywords

Generalizability - decision support system - guideline interchange format - pressure ulcer risk

Full Text

References

References
1 Bakken S, Ruland C. Translating Clinical informatics interventions into routine clinical care: How can the RE-AIM framework help?. J Am Med Inform Assoc 2009; 16: 889-898.
2 Glasgo RE, Bull S, Gillette C, Klesges LM, Dzewaltowski DA. Behavior change intervention research in health care settings: a review of recent reports with emphasis on external validity. Am J Prev Med 2002; 23: 62-69.
3 Ammentorp J, Kofoed P. Research in communication skills training translated into practice in a large organization: A proactive use of the RE-AIM framework. Patient Educ Couns 2011; 82: 482-487.
4 Ash JS, Berg M, Coiera E. Some unintended consequences of information technology in health care: The nature of patient care information system-related errors. JAMA 2004; 11: 104-112.
5 Kim H, Harris MR, Savova GK, Speedie SM, Chute CG. Toward near real-time acuity estimation: a feasibility study. Nurs Res 2007; 56 (04) 288-294.
6 Kottner J, Dassen T. An interrater reliability study of the Braden scale in two nursing homes. Int J Nurs Stud 2008; 45: 1501-1511.
7 Beeckman D, Vanderwee K, Demarre L, Paquay L, VanHecke A. DeFloor T Pressure ulcer prevention: Development and psychometric validation of a knowledge assessment instrument. Int J Nurs Stud 2010; 47: 399-410.
8 Kim H, Choi J, Thompson S, Meeker L, Dykes P, Goldsmith D, Ohno-Machado L. Automating pressure ulcer risk assessment using documented patient data. Int J Med Inform 2010; 79 (12) 840-848.
9 Davis FD. Perceived usefulness, perceived ease of use, and user acceptance of information technology. MISQ 1989; 13 (03) 319-340.
10 Palchuk MB, Fang EA, Cygielnik JM, Labreche M, Shubina M, Ramelson HZ. et al. An unintended consequence of electronic prescriptions: prevalence and impact of internal discrepancies. JAMIA 2010; 17: 472-476.
11 Ruland CM. Integrating patient preferences for self-care capability in nursing care: effects on nurses’ care priorities and patient outcomes. [dissertation]. Cleveland (OH): Case Western Reserve University; 1998
12 Moreland PJ, Gallagher S, Bena JF, Morrison S, Albert NM. Nursing satisfaction with implementation of electronic medication administration record. CIN 2012; 30 (02) 97-103.
13 Bergstrom N, Braden BJ, Laguzza A, Holman V. The Braden Scale for predicting pressure sore risk. Nurs Res 1987; 36 (04) 205-210.
14 Boxwala A, Peleg M, Tu S, Pgunyemi O, Zeng WT, Wang D. et al. GLIF3: a representation format for sharable computer-interpretable clinical practice guidelines. J Biomed Inform 2004; 37 (Suppl. 03) 147-161.
15 Peleg M, Tu S, Bury J, Ciccarese P, Fox J, Boxwala AA, Ogunyemi O. et al. GLIF3: the evolution of a guideline representation format AMIA Annual Symposium. Los Angeles, CA; 2000: 645-649.
16 Peleg M, Boxwala A, Tu S, Wang D, Ogunyemi O, Zeng Q. Guideline Interchange Format 3.5 Technical Specification. InterMed Collaboratory 2004; Retrieved from http://mis.hevra.haifa.ac.il/~morpeleg/Intermed/effectsof
17 Wang D, Peleg M, Tu S, Boxwala A, Ogunyemi O, Zeng Q. et al. Design and Implementation of the GLIF3 guideline execution engine. J Biomed Inform 2004; 37 (03) 305318.
18 Gorecki C, Brown JM, Nelson EA, Briggs M, Schoonhoven L, Dealey C. et al. Impact of pressure ulcers on quality of life in older patients: a systematic review. JAGS 2009; 57 (07) 1175-1183.
19 Solis LR, Gyawali S, Seres P, Curtis CA, Chong SL, Thompson RB, Mushahwar VK. Effects of intermittent electrical stimulation on superficial pressure, tissue oxygenation, and discomfort levels for the prevention of deep tissue injury. Ann Biomed Eng 2011; 39 (02) 649-663.
20 Cox J. Predictive power of the Braden scale for pressure sore risk in adult critical care patients: a comprehensive review. J Wound Ostomy Continence Nurs 2012; 39 (06) 613-621.
21 Gadd MM. Preventing hospital-acquired pressure ulcers: improving quality of outcomes by placing emphasis on the Braden subscale scores. J Wound Ostomy Continence Nurs 2012; 39 (03) 292-294.
22 Nixon J, Cranny G, Bond S. Skin alterations of intact skin and risk factors associated with pressure ulcer development in surgical patients: a cohort study. Int J Nurs Stud 2007; 44: 655-663.
23 Serpa LF, Santos VLCG. Assessment of the nutritional risk for pressure ulcer development through Braden scale. 39th Annual Wound, Ostomy and Continence Nurses Annual Conference. J Wound Ostomy Continence Nurs 2007: S4-S6.
24 Hatanaka N, Yamamoto Y, Ichlhara K, Mastuo S, Nakamura Y, Watanabe M. et al. A new predictive indicator for development of pressure ulcers in bedridden patients based on common laboratory tests results. J Clin Path 2008; 61 (04) 514-518.
25 Ayello E, Boltz M, Greenberg S. Predicting pressure ulcer risk. Try this: best practices in nursing care to older adults. AJN 2007; 107 (11) 45-47.
26 Stotts N, Gunningberg L. How to try this. Predicting pressure ulcer risk: using the Braden scale with hospitalized older adults: the evidence supports it. AJN 2007; 107 (Suppl. 11) 40-44 47-49.
27 McElhinny M, Hooper C. Reducing hospital-acquired heel ulcer rates in an acute care facility: an evaluation of a nurse-driven performance improvement project. J Wound Ostomy Continence Nurs 2008; 35 (01) 79-83.
28 Coleman S, Gorecki C, Nelson EA, Closs SJ, Defloor T, Halfens R. et al. Patient risk factors for pressure ulcer development: Systematic review. Int J Nurs Stud. 2013 DOI:10.1016/j.ijnurstu.2012.11.019
29 Choi J, Choi JE. A Framework for Effective Implementation and Local Adaptation of Decision Support Systems. American Medical Informatics Association Annual Symposium. Washington DC; USA: 2008. p. 907.
30 Engstrom M, Scandurra I, Ljunggren B, Lindqvist R, Koch S, Carlsson M. Evaluation of OLD@HOME Virtual Health Record staff opinions of the system and satisfactions with work. Telemed J E Health 2009; 8 (01) 53-61.
31 Johnson CM, Johnson TR, Zhang JA. User-centered framework for redesigning health care interfaces?. J Biomed Inform. 2005; 38: 75-87.
32 Karsh B-T. Beyond usability: designing effective technology implementation systems to promote patient safety. Qual Saf Health Care 2004; 13: 388-394.
33 Kim H, Choi J, Secalag L, Dibsie L, Boxwala A, Ohno-Machado L. Building an ontology for pressure ulcer risk assessment to allow data sharing and comparisons across hospitals. J Am Med Infor Assoc 2010; 13: 382-386.
34 Magnan M, Maklebust J. The effect of web-based Braden Scale training on the reliability of Braden sub-scale ratings. J Wound Ostomy Continence Nurs 2008; 35: 199-208.
35 Stechmiller J, Cowan L, Whitney J, Phillips L, Aslam R, Barbul A. et al. Guidelines for prevention of pressure ulcers. Wound Repair Regen 2008; 16: 151-168.