Applying of Decision Tree Analysis to Risk Factors Associated with Pressure Ulcers in Long-Term Care Facilities
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Objectives: The purpose of this study was to use decision tree analysis to explore the factors associated with pressure ulcers (PUs) among elderly people admitted to Korean long-term care facilities. Methods: The data were extracted from the 2014 National Inpatient Sample (NIS)—data of Health Insurance Review and Assessment Service (HIRA). A MapReduce-based program was implemented to join and filter 5 tables of the NIS. The outcome predicted by the decision tree model was the prevalence of PUs as defined by the Korean Standard Classification of Disease-7 (KCD-7; code L89*). Using R 3.3.1, a decision tree was generated with the finalized 15,856 cases and 830 variables. Results: The decision tree displayed 15 subgroups with 8 variables showing 0.804 accuracy, 0.820 sensitivity, and 0.787 specificity. The most significant primary predictor of PUs was length of stay less than 0.5 day. Other predictors were the presence of an infectious wound dressing, followed by having diagnoses numbering less than 3.5 and the presence of a simple dressing. Among diagnoses, “injuries to the hip and thigh” was the top predictor ranking 5th overall. Total hospital cost exceeding 2,200,000 Korean won (US $2,000) rounded out the top 7. Conclusions: These results support previous studies that showed length of stay, comorbidity, and total hospital cost were associated with PUs. Moreover, wound dressings were commonly used to treat PUs. They also show that machine learning, such as a decision tree, could effectively predict PUs using big data.
Abstract
Objectives: The purpose of this study was to use decision tree analysis to explore the factors associated with pressure ulcers (PUs) among elderly people admitted to Korean long-term care facilities. Methods: The data were extracted from the 2014 National Inpatient Sample (NIS)—data of Health Insurance Review and Assessment Service (HIRA). A MapReduce-based program was implemented to join and filter 5 tables of the NIS. The outcome predicted by the decision tree model was the prevalence of PUs as defined by the Korean Standard Classification of Disease-7 (KCD-7; code L89*). Using R 3.3.1, a decision tree was generated with the finalized 15,856 cases and 830 variables. Results: The decision tree displayed 15 subgroups with 8 variables showing 0.804 accuracy, 0.820 sensitivity, and 0.787 specificity. The most significant primary predictor of PUs was length of stay less than 0.5 day. Other predictors were the presence of an infectious wound dressing, followed by having diagnoses numbering less than 3.5 and the presence of a simple dressing. Among diagnoses, “injuries to the hip and thigh” was the top predictor ranking 5th overall. Total hospital cost exceeding 2,200,000 Korean won (US $2,000) rounded out the top 7. Conclusions: These results support previous studies that showed length of stay, comorbidity, and total hospital cost were associated with PUs. Moreover, wound dressings were commonly used to treat PUs. They also show that machine learning, such as a decision tree, could effectively predict PUs using big data.
참고문헌 (30)
- National Pressure Ulcer Advisory Panel, "Prevention and treatment of pressure ulcers:quick reference guide", Cambridge Media, ~ (2014)
- Demarre L, "The cost of pressure ulcer prevention and treatment in hospitals and nursing homes in Flanders : a cost-of-illness study", Int J Nurs Stud, 52(7), pp.1166~1179 (2015)
- Gunningberg L, "Tracking quality over time:what do pressure ulcer data show?", Int J Qual Health Care, 20(4), pp.246~253 (2008)
- Lyder CH, "Patient safety and quality: an evidence-based handbook for nurses" (2008), Agency for Healthcare Research and Quality
- Mueller C, "ANA nurse sensitive quality indicators for long-term care facilities", J Nurs Care Qual, 19(1), pp.39~47 (2004)
- Keelaghan E, "Prevalence of pressure ulcers on hospital admission among nursing home residents transferred to the hospital", Wound Repair Regen, 16(3), pp.331~336 (2008)
- "Long-term care insurance" (2010)[URL]
- "KHISS current state of long term care facilities" (2014)[URL]
- Lahmann NA, "Mobility is the key! Trends and associations of common care problems in German long-term care facilities from 2008 to 2012", Int J Nurs Stud, 52(1), pp.167~174 (2015)
- Shin JH, "Nurse staffing and quality of care of nursing home residents in Korea", J Nurs Scholarsh, 47(6), pp.555~564 (2015)
- Coleman S, "Patient risk factors for pressure ulcer development : systematic review", Int J Nurs Stud, 50(7), pp.974~1003 (2013)
- Murdoch TB, "The inevitable application of big data to health care", JAMA, 309(13), pp.1351~1352 (2013)
- Kim L, "A guide for the utilization of Health Insurance Review and Assessment Service National Patient Samples", Epidemiol Health, 36, pp.e2014008~ (2014)
- "Drowning in big data? Reducing information technology complexities and costs for healthcare organizations" (2011)[URL]
- Raghupathi W, "Big data analytics in healthcare : promise and potential", Health Inf Sci Syst, 2, pp.3~ (2014)
- Bellazzi R, "Predictive data mining in clinical medicine : current issues and guidelines", Int J Med Inform, 77(2), pp.81~97 (2008)
- Pedrassani de Lira C, "Use of data mining to predict the risk factors associated with osteoporosis and osteopenia in women", Comput Inform Nurs, 34(8), pp.369~375 (2016)
- Raju D, "Exploring factors associated with pressure ulcers : a data mining approach", Int J Nurs Stud, 52(1), pp.102~111 (2015)
- Kang Y, "Utilizing home healthcare electronic health records for telehomecare patients with heart failure : a decision tree approach to detect associations with rehospitalizations", Comput Inform Nurs, 34(4), pp.175~182 (2016)
- Michelet D, "Factors affecting recovery of postoperative bowel function after pediatric laparoscopic surgery", J Anaesthesiol Clin Pharmacol, 32(3), pp.369~375 (2016)
- Kim SR, "Smoking cessation failure among Korean adolescents", J Sch Nurs, 32(3), pp.155~163 (2016)
- Ramezankhani A, "Applying decision tree for identification of a low risk population for type 2 diabetes. Tehran Lipid and Glucose Study", Diabetes Res Clin Pract, 105(3), pp.391~398 (2014)
- Lee TT, "Factors related to the prevention and management of pressure ulcers", Comput Inform Nurs, 30(9), pp.489~495 (2012)
- Dean J, "MapReduce : simplified data processing on large clusters", Commun ACM, 51(1), pp.107~113 (2008)
- "Regulation on drug classification numbers" (2013)[URL]
- "The standard of classification of disease and cause of death" (2016)[URL]
- Baratloo A, "Part 1:Simple definition and calculation of accuracy, sensitivity and specificity", Emerg (Tehran), 3(2), pp.48~49 (2015)
- Graves N, "Effect of pressure ulcers on length of hospital stay", Infect Control Hosp Epidemiol, 26(3), pp.293~297 (2005)
- Santamaria N, "Pressure ulcer prevalence and its relationship to comorbidity in nursing home residents : results from phase 1 of the PRIME Trial", Prim Intent Aust J Wound Manag, 13(3), pp.107~116 (2005)
- Dealey C, "The cost of pressure ulcers in the United Kingdom", J Wound Care, 21(6), pp.261~266 (2012)