# Applying of Decision Tree Analysis to Risk Factors Associated with Pressure Ulcers in Long-Term Care Facilities

## Article information

Healthc Inform Res. 2017;23(1):43-52
Publication date (electronic) : 2017 January 31
doi : https://doi.org/10.4258/hir.2017.23.1.43
1College of Nursing, the Research Institute of Nursing Science, Kyungpook National University, Daegu, Korea.
2College of Nursing, Keimyung University, Daegu, Korea.
Corresponding Author: Soo-Kyoung Lee, PhD, RN. College of Nursing, Keimyung University, 1095 Dalgubeol-daero, Dalseo-gu, Daegu 42601, Korea. Tel: +82-53-580-3919, soo1005@kmu.ac.kr
Received 2017 January 02; Revised 2017 January 24; Accepted 2017 January 24.

## 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.

### 2. Predictive Performance

Figure 3 shows a box plot of the 10-fold cross-validation results. Accuracy ranged from 0.771 to 0.804, sensitivity ranged from 0.793 to 0.876, and specificity ranged from 0.707 to 0.787. Of the models considered, the model with the highest accuracy was selected as the best model for this study. The model showed 0.804 accuracy, 0.820 sensitivity, and 0.787 specificity. The results indicated that decision tree analysis was the best predictor with 80.4% accuracy.

### 3. Decision Tree

Figure 4 presents the decision tree derived from the best predictive model in the R output. Decision tree analysis identified 15 subgroups (nodes) and 8 associated factors. A length of stay shorter than 0.5 (a half) days was identified as the top associated factor with the presence of PUs. Next was the presence of an infectious wound dressing followed by a number of diagnoses less than 3.5, and then the presence of a simple dressing. Among diagnoses, “injuries to the hip and thigh” was the top predictor, ranking 5th overall, followed by a number of diagnoses less than 5.5 and episodic and paroxysmal disorders, total hospital cost, and bed grade.

### Decision tree.

The group most likely to have PUs was the 1,391 patients who stayed in the hospital for more than or equal to 0.5 days and had infectious wound dressing. The second pressure group included 1,212 patients. Patients who stayed in the hospital for a period longer than or equal to 0.5 days, who did not have infectious wound dressing, who had 3.5 or more than diagnoses, who did not have simple dressing, who did not have injuries the hip and thigh, who had 5.5 or more diagnoses were more likely to have PUs when they had total hospital cost exceeding US \$2,000 (2,200,000 Korean won).

### 4. Variables Associated with PUs from the Statistical Analyses

Table 2 shows the association between PUs and 8 variables identified by a decision tree. There were statistically significant differences in infection wound dressing (χ2 = 1658.0, p < 0.001), simple dressing (χ2 = 985.1, p < 0.001), injuries to the hip and thigh (χ2 = 426.6, p < 0.001), and episodic and paroxysmal disorders (χ2 = 115.0, p < 0.001). Patients with these diseases and procedures had a higher proportion of PUs than patients without them. There were significant differences in length of stay (t = −33.2, p < 0.001), the number of diagnoses (t = −69.7, p < 0.001), the hospital cost (t = −41.3, p < 0.001), and the bed grade (t = 8.6, p < 0.001) between the PU and non-PU group. The PU group had longer length of stay, more medical diagnoses and hospital cost, and lower bed numbers.

## IV. Discussion

This study explored the factors associated with the development of PUs using a data mining approach. The data were extracted from the HIRS NIS. A decision tree was generated with 15,856 cases and 830 variables. The decision tree displayed 15 subgroups with 8 variables showing good prediction performance. First of all, this study highlighted the usefulness of the data mining approach in managing and analyzing healthcare big data, such as the HIRA NIS data. Data mining accurately identified meaningful associations between an outcome and many variables.

The length of stay was the top variable associated with PUs. Moreover, the group with PU had a significantly longer length of stay. These results were similar to those of previous PU studies. PU could be a significant factor that prolongs the length of stay beyond expectations based on diagnosis at admission [28].

Infectious wound dressings and simple dressings were the second- and fourth-most commonly associated variables with PU. The results are quite reasonable because wound dressing is a main component of PU care. Dressings are used to keep a wound bed moist or to keep the periwound dry and prevent maceration to facilitate healing [1]. This study provides limited information regarding types of dressings because the procedure codes for the reimbursement claims did not reflect dressing types. Various types of dressings could be applied over time as an ulcer heals or deteriorates.

The number of medical diagnoses was an important variable to predict PUs. The numbers of diagnoses less than 3.5 and 5.5 were ranked 3rd and 6th splits. The number of medical diagnoses could be considered as a comorbidity. The results confirmed that comorbidity is a risk factor for PUs [29]. Of the individual medical diagnoses, “injuries to the hip and thigh” was the fifth most commonly related to PUs in. This diagnosis classification includes diseases such as ’fracture of femur‘ and ’injury of nerves at hip and thigh level‘ affecting the mobility of patients. This could be because immobility is common in patients with these diseases, and it increases the risk of developing PUs [9]. This study highlights the need for careful assessment of the elderly with higher comorbidity or these diseases to prevent PUs in long-term care facilities.

We found that total hospital cost was a factor associated with PUs, and this is supported in the literature. Multiple factors, including the prolonged stay, labor of healthcare providers, and treatment material costs can increase hospital costs [230]. Today, the increases in hospital costs caused by PUs could receive more attention due to the limited budgets for healthcare. Therefore, PU prevention is vital to reduce the costs related to PUs.

Overall, the results of this study with big data confirmed other previous study results related to PUs; our results appear to be more valid and generalizable than those of previous studies. PUs are associated with length of stay, number of diagnoses, and total hospital costs. Moreover, elderly patients with PUs are more likely to have simple, infected dressings. Eventually, longer length of stay or additional procedures, such as changing the dressing could lead to increased hospital costs for PU patients. Therefore, the importance of PU prevention to alleviate the financial burden of long-term care facilities is highlighted by this study.

Contrary to our expectation, the results did not show any drug associated with PUs even though previous research has identified specific drugs that seem to increase the incidence of PUs [411]. Further studies with pre-processing in detail could be conducted to identify other association factors.

Big data continue to impact healthcare; such information can be used to improve patient care and clinical decision-making. However, big data are very large and complex, and they are hard to manage with traditional manipulation methods. This study suggested that the use of data mining in healthcare big data can minimize the time spent manually search while minimizing insignificant studies; it can identify association [1617]. Furthermore, the decision tree analysis used in this study was used to create a model of association factors and can deal with non-linear relationships to automatically capture multilevel interactions among variables [22]. Therefore, data mining can help manage a variety of healthcare big data.

In conclusion, this study used a decision tree to find factors associated with PUs using the 2014 NIS, which is data from the HIRA. A decision tree was generated with 15,856 cases and 830 variables. The decision tree displayed 15 subgroups with 8 variables showing 0.804 accuracy, 0.820 sensitivity, and 0.787 specificity. These results support those of previous studies that showed length of stay, comorbidity, and total hospital cost were associated with developing PUs. Moreover, wound dressings were commonly used to treat PUs. Finally, this study showed that data mining methods, such as decision tree analysis, could identify outcome variables in a big data set with many variables.

## Acknowledgments

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (NRF-2015R1C1A2A01054883).

## Notes

Conflict of Interest: No potential conflict of interest relevant to this article was reported.

## References

1. National Pressure Ulcer Advisory Panel. European Pressure Ulcer Advisory Panel. Pan Pacific Pressure Injury Alliance. Prevention and treatment of pressure ulcers: quick reference guide 2nd edth ed. Perth, Australia: Cambridge Media; 2014.
2. Demarre L, Verhaeghe S, Annemans L, Van Hecke A, Grypdonck M, Beeckman D. The cost of pressure ulcer prevention and treatment in hospitals and nursing homes in Flanders: a cost-of-illness study. Int J Nurs Stud 2015;52(7):1166–1179. 25862410.
3. Gunningberg L, Stotts NA. Tracking quality over time: what do pressure ulcer data show? Int J Qual Health Care 2008;20(4):246–253. 18390902.
4. Lyder CH, Ayello EA. Pressure ulcers: a patient safety issue. In : Hughes RG, ed. Patient safety and quality: an evidence-based handbook for nurses Rockville (MD): Agency for Healthcare Research and Quality; 2008.
5. Mueller C, Karon SL. ANA nurse sensitive quality indicators for long-term care facilities. J Nurs Care Qual 2004;19(1):39–47. 14717147.
6. Keelaghan E, Margolis D, Zhan M, Baumgarten M. Prevalence of pressure ulcers on hospital admission among nursing home residents transferred to the hospital. Wound Repair Regen 2008;16(3):331–336. 18471251.
7. National Health Insurance Service. Long-term care insurance [Internet] Wonju, Korea: National Health Insurance Service; 2010. cited at 2017 Jan 23. Available from: http://longtermcare.or.kr/npbs/e/e/100/index.web.
8. Korean Health Industry Development Institute. KHISS current state of long term care facilities [Internet] Cheongju, Korea: Korean Health Industry Development Institute; 2014. cited at 2017 Jan 23. Available from: http://www.khiss.go.kr/treeManager.do?task=treeFrm&vw_cd=MT_ITITLE&list_id=358_E&htxt_code=125369725751510746110771881221239.
9. Lahmann NA, Tannen A, Kuntz S, Raeder K, Schmitz G, Dassen T, et al. 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 2015;52(1):167–174. 25240483.
10. Shin JH, Hyun TK. Nurse staffing and quality of care of nursing home residents in Korea. J Nurs Scholarsh 2015;47(6):555–564. 26467903.
11. 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;50(7):974–1003. 23375662.
12. Murdoch TB, Detsky AS. The inevitable application of big data to health care. JAMA 2013;309(13):1351–1352. 23549579.
13. Kim L, Kim JA, Kim S. A guide for the utilization of Health Insurance Review and Assessment Service National Patient Samples. Epidemiol Health 2014;36:e2014008. 25078381.
14. Frost & Sullivan. Drowning in big data? Reducing information technology complexities and costs for healthcare organizations [Internet] Mountain View (CA): Frost & Sullivan; 2011. cited at 2017 Jan 23. Available from: https://www.emc.com/collateral/analyst-reports/frostsullivan-reducing-information-technology-complexities-ar.pdf.
15. Raghupathi W, Raghupathi V. Big data analytics in healthcare: promise and potential. Health Inf Sci Syst 2014;2:3. 25825667.
16. Bellazzi R, Zupan B. Predictive data mining in clinical medicine: current issues and guidelines. Int J Med Inform 2008;77(2):81–97. 17188928.
17. Pedrassani de Lira C, Toniazzo de Abreu LL, Veiga Silva AC, Mazzuchello LL, Rosa MI, Comunello E, et al. Use of data mining to predict the risk factors associated with osteoporosis and osteopenia in women. Comput Inform Nurs 2016;34(8):369–375. 27270629.
18. Raju D, Su X, Patrician PA, Loan LA, McCarthy MS. Exploring factors associated with pressure ulcers: a data mining approach. Int J Nurs Stud 2015;52(1):102–111. 25192963.
19. Kang Y, McHugh MD, Chittams J, Bowles KH. Utilizing home healthcare electronic health records for telehomecare patients with heart failure: a decision tree approach to detect associations with rehospitalizations. Comput Inform Nurs 2016;34(4):175–182. 26848645.
20. Michelet D, Andreu-Gallien J, Skhiri A, Bonnard A, Nivoche Y, Dahmani S. Factors affecting recovery of postoperative bowel function after pediatric laparoscopic surgery. J Anaesthesiol Clin Pharmacol 2016;32(3):369–375. 27625488.
21. Kim SR, Kim HK, Kim JY, Kim HY, Ko SH, Park M. Smoking cessation failure among Korean adolescents. J Sch Nurs 2016;32(3):155–163. 26459106.
22. Ramezankhani A, Pournik O, Shahrabi J, Khalili D, Azizi F, Hadaegh F. Applying decision tree for identification of a low risk population for type 2 diabetes. Tehran Lipid and Glucose Study. Diabetes Res Clin Pract 2014;105(3):391–398. 25085758.
23. Lee TT, Lin KC, Mills ME, Kuo YH. Factors related to the prevention and management of pressure ulcers. Comput Inform Nurs 2012;30(9):489–495. 22584879.
24. Dean J, Ghemawat S. MapReduce: simplified data processing on large clusters. Commun ACM 2008;51(1):107–113.
25. Korea Ministry of Food and Drug Society. Regulation on drug classification numbers [Internet] Cheongju, Korea: Ministry of Food and Drug Society; 2013. cited at 2017 Jan 4. Available from: http://www.mfds.go.kr/index.do?mid=1015&pageNo=6&seq=6325&sitecode=2013-04-05&cmd=v.
26. Korean Standard Statistical Classification. The standard of classification of disease and cause of death [Internet] Daejeon, Korea: Korean Standard Statistical Classification; 2016. cited at 2017 Jan 2. Available from: https://kssc.kostat.go.kr:8443/ksscNew_web/link.do?gubun=004.
27. Baratloo A, Hosseini M, Negida A, El Ashal G. Part 1: Simple definition and calculation of accuracy, sensitivity and specificity. Emerg (Tehran) 2015;3(2):48–49. 26495380.
28. Graves N, Birrell F, Whitby M. Effect of pressure ulcers on length of hospital stay. Infect Control Hosp Epidemiol 2005;26(3):293–297. 15796283.
29. Santamaria N, Carville K, Prentice J, Ellis I, Ellis T, Lewin G, et al. 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 2005;13(3):107–116.
30. Dealey C, Posnett J, Walker A. The cost of pressure ulcers in the United Kingdom. J Wound Care 2012;21(6):261–266. 22886290.

## Article information Continued

Funded by : National Research Foundation of Koreahttp://dx.doi.org/10.13039/501100003725
Award ID : NRF-2015R1C1A2A01054883

### Characteristics of variables

Values are presented as number (%) or mean (range).

KCD-7: Korean Standard Classification of Diseases-7, OPD: outpatient department.

aThe only top or meaningful value was described. bTop 3 variables among the variables were selected and described.

### Association between 8 variables and pressure ulcers (PU)

Values are presented as number (%) or mean (range).

aBilling codes. bKorean Standard Classification of Disease 7 (KCD-7) codes.