Browse > Article
http://dx.doi.org/10.17703/IJACT.2019.7.1.8

Tree-based Approach to Predict Hospital Acquired Pressure Injury  

Hyun, Sookyung (College of Nursing, Pusan National University)
Moffatt-Bruce, Susan (Department of Surgery, The Ohio State University)
Newton, Cheryl (Central Quality and Education, The Ohio State University Wexner Medical Center)
Hixon, Brenda (Health System Nursing Education, The Ohio State University Wexner Medical Center)
Kaewprag, Pacharmon (Department of Computer Engineering, Ramkhamhaeng University)
Publication Information
International Journal of Advanced Culture Technology / v.7, no.1, 2019 , pp. 8-13 More about this Journal
Abstract
Despite technical advances in healthcare, the rates of hospital-acquired pressure injury (HAPI) are still high although many are potentially preventable. The purpose of this study was to determine whether tree-based prediction modeling is suitable for assessing the risk of HAPI in ICU patients. Retrospective cohort study has been carried out. A decision tree model was constructed with Age, Weight, eTube, diabetes, Braden score, Isolation, and Number of comorbid conditions as decision nodes. We used RStudio for model training and testing. Correct prediction rate of the final prediction model was 92.4 and the Area Under the ROC curve (AUC) was 0.699, which means there is about 70% chance that the model is able to distinguish between HAPI and non-HAPI. The results of this study has limited generalizability as the data were from a single academic institution. Our research finding shows that the data-driven tree-based prediction modeling may potentially support ICU sensitive risk assessment for HAPI prevention.
Keywords
hospital-acquired pressure injury; intensive care units; decision tree;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Tabaton M, Odetti P, Cammarata S, Borghi R, Monacelli F, Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment. J Alzheimers Dis, 2010. 19(3): p. 1035-40. 10.3233/JAD-2010-1300.   DOI
2 Kuhn M, Johnson K, Applied Predictive Modeling. 2016, New York: Springer.
3 Kaewprag P, Newton C, Vermillion B, Hyun S, Huang K, Machiraju R, Predictive models for pressure ulcers from intensive care unit electronic health records using Bayesian networks. BMC Med Inform Decis Mak, 2017. 17(Suppl 2): p. 65. 10.1186/s12911-017-0471-z.   DOI
4 Hyun S, Vermillion B, Newton C, Fall M, Li X, Kaewprag P, et al., Predictive validity of the Braden scale for patients in intensive care units, American Journal of Critical Care, 2013. 22(6): p. 514-520. 10.4037/ajcc2013991.   DOI
5 Dreiseitl S, Ohno-Machado L, Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform, 2002. 35(5-6): p. 352-9.   DOI
6 Kottner J, Dassen T, Pressure ulcer risk assessment in critical care: interrater reliability and validity studies of the Braden and Waterlow scales and subjective ratings in two intensive care units. International Journal of Nursing Studies, 2010. 47(6): p. 671-677. 10.1016/j.ijnurstu.2009.11.005.   DOI
7 The National Pressure Ulcer Advisory Panel. National Pressure Ulcer Advisory Panel (NPUAP) announces a change in terminology from pressure ulcer to pressure injury and updates the stages of pressure injury. Available from: http://www.npuap.org/national-pressure-ulcer-advisory-panel-npuap-announces-a-change-in-terminology-from-pressure-ulcer-to-pressure-injury-and-updates-the-stages-of-pressure-injury/.
8 Bergstrom N, Braden BJ, Kemp M, Champagne M, Ruby E., Predicting pressure ulcer risk: a multisite study of the predictive validity of the Braden Scale. Nurs Res, 1998. 47(5): p. 261-9.   DOI
9 Schoonhoven L, Haalboom J, Bousema M, Algra A, Grobbee D, Grypdonck M, et al., Prospective cohort study of routine use of risk assessment scales for prediction of pressure ulcers. BMJ, 2002. 325(7368).
10 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(6): p. 613-21; quiz 622-3. 10.1097/WON.0b013e31826a4d83.   DOI
11 Liew P, Lee Y, Lin Y, Lee T, Lee W, Wang W, et al., Comparison of artificial neural networks with logistic regression in prediction of gallbladder disease among obese patients. Dig Liver Dis, 2007. 39(4): p. 356-62.   DOI
12 Kurt I, Ture M, Kurum A, Comparing performances of logistic regression classification and regression tree, and neural networks for predicting coronary artery disease. Expert Systems with Applications, 2008. 34: p. 366-374.   DOI
13 Worachartcheewan A, Nantasenamat C, Isarankura-Na-Ayudhya C, Pidetcha P, Prachayasittikul V, Identification of metabolic syndrome using decision tree analysis. Diabetes Res Clin Pract, 2010. 90(1): p. e15-8. 10.1016/j.diabres.2010.06.009.   DOI
14 Mullins I, Siadaty M, Lyman J, Scully K, Garrett C, Miller W, et al., Data mining and clinical data repositories: Insights from a 667,000 patient data set. Comput Biol Med, 2006. 36(12): p. 1351-77.   DOI
15 Ellenius J, Groth T, Dynamic decision support graph--visualization of ANN-generated diagnostic indications of pathological conditions developing over time. Artif Intell Med, 2008. 42(3): p. 189-98.   DOI
16 Brickley M, Shepherd J, Armstrong R, Neural networks: a new technique for development of decision support systems in dentistry. J Dent, 1998. 26(4): p. 305-9.   DOI
17 Ridinger M, Rice J, Predictive modeling points way to future risk status. Health Manag Technol, 2000. 21(2): p. 10-2.
18 Lin S, Lee C, Lu Y, Hsu L, A comparison of MICU survival prediction using the logistic regression model and artificial neural network model. J Nurs Res, 2006. 14(4): p. 306-14.   DOI