Increasingly available open medical and health datasets encourage data-driven research with a promise of improving patient care through knowledge discovery and algorithm development. Among efficient approaches to such high-dimensional problems are a number of machine learning methods, which are applied in this paper to pressure ulcer prediction in modular critical care data. An inherent property of many health-related datasets is a high number of irregularly sampled time-variant and scarcely populated features, often exceeding the number of observations. Although machine learning methods are known to work well under such circumstances, many choices regarding model and data processing exist. In particular, this paper address both theoretical and practical aspects related to the application of six classification models to pressure ulcers, while utilizing one of the largest available Medical Information Mart for Intensive Care (MIMIC-IV) databases. Random forest, with an accuracy of 96%, is the best-performing approach among the considered machine learning algorithms.

Department of Burns and Plastic Surgery Faculty Hospital Brno and Faculty of Medicine Masaryk University Jihlavská 20 625 00 Brno Czech Republic

Department of Health Sciences Faculty of Medicine Masaryk University Kamenice 5 625 00 Brno Czech Republic

Department of Physiology Faculty of Medicine Masaryk University Kamenice 5 625 00 Brno Czech Republic

Institute of Computer Aided Engineering and Computer Science Faculty of Civil Engineering Brno University of Technology Veveří 331 95 602 00 Brno Czech Republic

Zobrazit více v PubMed

Sen C.K., Gordillo G.M., Roy S., Kirsner R., Lambert L., Hunt T.K., Gottrup F., Gurtner G.C., Longaker M.T. Human Skin Wounds: A Major and Snowballing Threat to Public Health and the Economy. Wound Repair Regen. 2009;17:763–771. doi: 10.1111/j.1524-475X.2009.00543.x. PubMed DOI PMC

Haesler E., European Pressure Ulcer Advisory Panel (EPUAP) National Pressure Injury Advisory Panel (NPIAP) Pan Pacific Pressure Injury Alliance (PPPIA) Prevention and Treatment of Pressure Ulcers/Injuries: Clinical Practice Guideline. [(accessed on 27 March 2022)]. Available online: https://www.internationalguideline.com/

Pokorná A., Leaper D. Assessment and Documentation of Non-Healing, Chronic Wounds in Inpatient Health Care Facilities in the Czech Republic: An Evaluation Study. Int. Wound J. 2015;12:224–231. doi: 10.1111/iwj.12372. PubMed DOI PMC

Hiser B., Rochette J., Philbin S., Lowerhouse N., Terburgh C., Pietsch C. Implementing a Pressure Ulcer Prevention Program and Enhancing the Role of the CWOCN: Impact on Outcomes. Ostomy. Wound Manag. 2006;52:48–59. PubMed

Samaniego I.A. A Sore Spot in Pediatrics: Risk Factors for Pressure Ulcers. Pediatr. Nurs. 2003;29:278. PubMed

Tubaishat A., Papanikolaou P., Anthony D., Habiballah L. Pressure Ulcers Prevalence in the Acute Care Setting: A Systematic Review, 2000–2015. Clin. Nurs. Res. 2018;27:643–659. doi: 10.1177/1054773817705541. PubMed DOI

Al Mutairi K.B., Hendrie D. Global Incidence and Prevalence of Pressure Injuries in Public Hospitals: A Systematic Review. Wound Med. 2018;22:23–31. doi: 10.1016/j.wndm.2018.05.004. DOI

Moore Z., Cowman S. Pressure Ulcer Prevalence and Prevention Practices in Care of the Older Person in the Republic of Ireland. J. Clin. Nurs. 2012;21:362–371. doi: 10.1111/j.1365-2702.2011.03749.x. PubMed DOI

Russo C.A., Steiner C., Spector W. Hospitalizations Related to Pressure Ulcers among Adults 18 Years and Older, 2006: Statistical Brief# 64. Agency for Healthcare Research and Quality; Rockville, MD, USA: 2006. PubMed

Pokorná A., Benešová K., Mužík J., Jarkovskỳ J., Dušek L. Data Sources for Monitoring of Non-Healing Wounds in a National Health Information System–Epidemiology of Non-Healing Wounds–Analysis of the National Register of Hospitalized Patients in 2007–2015. Čes. Slov. Neurol. Neurochir. 2017;80:S8–S17. doi: 10.14735/amcsnn2017S8. DOI

Pokorná A., Benešová K., Jarkovskỳ J., Mužík J., Beeckman D. Pressure Injuries in Inpatient Care Facilities in the Czech Republic. J. Wound. Ostomy Cont. Nurs. 2017;44:331–335. doi: 10.1097/WON.0000000000000344. PubMed DOI

Pokorná A., Štrombachová V., Mužík J., Dolanová D., Búřilová P., Pospíšil M., Kučerová J., Gregor J., Komenda M., Dušek L. SHNU—Úvod. [(accessed on 23 February 2022)]. Available online: https://shnu.uzis.cz/

Búřilová P., Dolanová D., Saibertová S., Benešová K., Jarkovský J., Krupová L., Pokorná A. Základní Epidemiologická Analýza Pacientů s Dekubity v Národním Zdravotnickém Informačním Systému. Léčba Ran. 2021;8:6–7.

Kottner J., Cuddigan J., Carville K., Balzer K., Berlowitz D., Law S., Litchford M., Mitchell P., Moore Z., Pittman J., et al. Pressure Ulcer/Injury Classification Today: An International Perspective. J. Tissue Viability. 2020;29:197–203. doi: 10.1016/j.jtv.2020.04.003. PubMed DOI

Hess C.T. Classification of Pressure Injuries. Adv. Skin Wound Care. 2020;33:558–559. doi: 10.1097/01.ASW.0000697324.90597.6d. PubMed DOI

Chan W.S., Pang S.M.C., Kwong E.W.Y. Assessing Predictive Validity of the Modified Braden Scale for Prediction of Pressure Ulcer Risk of Orthopaedic Patients in an Acute Care Setting. J. Clin. Nurs. 2009;18:1565–1573. doi: 10.1111/j.1365-2702.2008.02757.x. PubMed DOI

Šáteková L., Žiaková K., Zeleníková R. Predikčná Validita Bradenovej Škály, Nortonovej Škály a Waterlowej Škály v Slovenskej Republike. Cent. Eur. J. Nurs. Midwifery. 2015;6:283–290. doi: 10.15452/CEJNM.2015.06.0017. DOI

Becker D., Tozo T.C., Batista S.S., Mattos A.L., Silva M.C.B., Rigon S., Laynes R.L., Salomão E.C., Hubner K.D.G., Sorbara S.G.B., et al. Pressure Ulcers in ICU Patients: Incidence and Clinical and Epidemiological Features: A Multicenter Study in Southern Brazil. Intensive Crit. Care Nurs. 2017;42:55–61. doi: 10.1016/j.iccn.2017.03.009. PubMed DOI

Borghardt A.T., do Prado T.N., Bicudo S.D.S., de Castro D.S., Bringuente M.E.d.O. Pressure Ulcers in Critically Ill Patients: Incidence and Associated Factors. Rev. Bras. Enferm. 2016;69:460–467. doi: 10.1590/0034-7167.2016690307i. PubMed DOI

Bluestein D., Javaheri A. Pressure Ulcers: Prevention, Evaluation, and Management. Am. Fam. Physician. 2008;78:1186–1194. PubMed

Garcia A.D., Thomas D.R. Assessment and Management of Chronic Pressure Ulcers in the Elderly. Med. Clin. 2006;90:925–944. doi: 10.1016/j.mcna.2006.05.018. PubMed DOI

Jaul E. Assessment and Management of Pressure Ulcers in the Elderly. Drugs Aging. 2010;27:311–325. doi: 10.2165/11318340-000000000-00000. PubMed DOI

Lichterfeld-Kottner A., Lahmann N., Kottner J. Sex-Specific Differences in Prevention and Treatment of Institutional-Acquired Pressure Ulcers in Hospitals and Nursing Homes. J. Tissue Viability. 2020;29:204–210. doi: 10.1016/j.jtv.2020.05.001. PubMed DOI

Kröger K., Niebel W., Maier I., Stausberg J., Gerber V., Schwarzkopf A. Prevalence of Pressure Ulcers in Hospitalized Patients in Germany in 2005: Data from the Federal Statistical Office. Gerontology. 2009;55:281–287. PubMed

Stotts N.A., Wu H.-S. Hospital Recovery Is Facilitated by Prevention of Pressure Ulcers in Older Adults. Crit. Care Nurs. Clin. N. Am. 2007;19:269–275. doi: 10.1016/j.ccell.2007.05.005. PubMed DOI

Redelings M.D., Lee N.E., Sorvillo F. Pressure Ulcers: More Lethal than We Thought? Adv. Skin Wound Care. 2005;18:367–372. doi: 10.1097/00129334-200509000-00010. PubMed DOI

Hokynková A., Babula P., Pokorná A., Nováková M., Nártová L., Šín P. Oxidative Stress in Wound Healing—Current Knowledge. Ceska Slov. Neurol. Neurochir. 2019;82:37–39. doi: 10.14735/amcsnn2019S37. DOI

Syed M., Syed S., Sexton K., Syeda H.B., Garza M., Zozus M., Syed F., Begum S., Syed A.U., Sanford J., et al. Application of Machine Learning in Intensive Care Unit (ICU) Settings Using MIMIC Dataset: Systematic Review. Informatics. 2021;8:16. doi: 10.3390/informatics8010016. PubMed DOI PMC

Caicedo-Torres W., Gutierrez J. ISeeU: Visually Interpretable Deep Learning for Mortality Prediction inside the ICU. J. Biomed. Inform. 2019;98:103269. doi: 10.1016/j.jbi.2019.103269. PubMed DOI

Home—IEEE Big Data. [(accessed on 1 February 2022)]. Available online: https://bigdata.ieee.org/

Rehman A., Naz S., Razzak I. Leveraging Big Data Analytics in Healthcare Enhancement: Trends, Challenges and Opportunities. Multimed. Syst. 2021:1–33. doi: 10.1007/s00530-020-00736-8. DOI

Johnson A., Bulgarelli L., Pollard T., Horng S., Celi L.A., Mark IV R. Mimic-Iv (Version 0.4) PhysioNet. 2022 doi: 10.13026/a3wn-hq05. DOI

Kozier B. Fundamentals of Nursing: Concepts, Process and Practice. Pearson Education; London, UK: 2008.

Scikit-Learn: Machine Learning in Python—Scikit-Learn 1.0.2 Documentation. [(accessed on 3 February 2022)]. Available online: https://scikit-learn.org/stable/

Sklearn.Decomposition.SparseCoder. [(accessed on 3 February 2022)]. Available online: https://scikit-learn/stable/modules/generated/sklearn.decomposition.SparseCoder.html.

Hastie T., Tibshirani R., Friedman J.H., Friedman J.H. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Volume 2 Springer; Berlin/Heidelberg, Germany: 2009.

Nijs N., Toppets A., Defloor T., Bernaerts K., Milisen K., Van Den Berghe G. Incidence and Risk Factors for Pressure Ulcers in the Intensive Care Unit. J. Clin. Nurs. 2009;18:1258–1266. doi: 10.1111/j.1365-2702.2008.02554.x. PubMed DOI

Tavazzi E., Daberdaku S., Vasta R., Calvo A., Chiò A., Di Camillo B. Exploiting Mutual Information for the Imputation of Static and Dynamic Mixed-Type Clinical Data with an Adaptive k-Nearest Neighbours Approach. BMC Med. Inform. Decis. Mak. 2020;20:174. doi: 10.1186/s12911-020-01166-2. PubMed DOI PMC

Ubaidillah S.H.S.A., Sallehuddin R., Ali N.A. Cancer Detection Using Aritifical Neural Network and Support Vector Machine: A Comparative Study. J. Teknol. 2013;65 doi: 10.11113/jt.v65.1788. DOI

Pan S.-M., Lin C.-H. Fractal Features Classification for Liver Biopsy Images Using Neural Network-Based Classifier; Proceedings of the 2010 International Symposium on Computer, Communication, Control and Automation (3CA); Tainan, Taiwan. 5–7 May 2010; pp. 227–230.

Azmi M.S.B.M., Cob Z.C. Breast Cancer Prediction Based on Backpropagation Algorithm; Proceedings of the 2010 IEEE Student Conference on Research and Development (SCOReD); Kuala Lumpur, Malaysia. 13–14 December 2010; pp. 164–168.

Nasser I.M., Abu-Naser S.S. Lung Cancer Detection Using Artificial Neural Network. Social Science Research Network; Rochester, NY, USA: 2019.

Kingma D.P., Ba J. Adam: A Method for Stochastic Optimization. arXiv. 201714126980

Miranda E., Irwansyah E., Amelga A.Y., Maribondang M.M., Salim M. Detection of Cardiovascular Disease Risk’s Level for Adults Using Naive Bayes Classifier. Healthc. Inform. Res. 2016;22:196–205. doi: 10.4258/hir.2016.22.3.196. PubMed DOI PMC

Fernando Z.T., Trivedi P., Patni A. DOCAID: Predictive Healthcare Analytics Using Naive Bayes Classification; Proceedings of the Second Student Research Symposium (SRS), International Conference on Advances in Computing, Communications and Informatics (ICACCI’13); Mysore, India. 22–25 August 2013; pp. 1–5.

Kaur P., Kumar R., Kumar M. A Healthcare Monitoring System Using Random Forest and Internet of Things (IoT) Multimed. Tools Appl. 2019;78:19905–19916. doi: 10.1007/s11042-019-7327-8. DOI

Jyothi P.N., Rajya D., Rama N. Identifying Fraudulent Behaviors in Healthcare Claims Using Random Forest Classifier With SMOTEchnique. Int. J. E-Collab. 2020;16:30–47. doi: 10.4018/IJeC.2020100103. DOI

Simsekler M.C.E., Qazi A., Alalami M.A., Ellahham S., Ozonoff A. Evaluation of Patient Safety Culture Using a Random Forest Algorithm. Reliab. Eng. Syst. Saf. 2020;204:107186. doi: 10.1016/j.ress.2020.107186. DOI

Song J., Gao Y., Yin P., Li Y., Li Y., Zhang J., Su Q., Fu X., Pi H. The Random Forest Model Has the Best Accuracy Among the Four Pressure Ulcer Prediction Models Using Machine Learning Algorithms. Risk Manag. Healthc. Policy. 2021;14:1175–1187. doi: 10.2147/RMHP.S297838. PubMed DOI PMC

Bradley A.P. The Use of the Area under the ROC Curve in the Evaluation of Machine Learning Algorithms. Pattern Recognit. 1997;30:1145–1159. doi: 10.1016/S0031-3203(96)00142-2. DOI

Therrien C.W. In: Decision, Estimation and Classification: An Introduction to Pattern Recognition and Related Topics. International, editor. John Wiley and Sons Ltd.; New York, NY, USA: 1989.

Yacouby R., Axman D. Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models; Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems; Online. November 2020; [(accessed on 27 March 2022)]. pp. 79–91. Available online: https://aclanthology.org/2020.eval4nlp-1.9.

Alderden J., Pepper G.A., Wilson A., Whitney J.D., Richardson S., Butcher R., Jo Y., Cummins M.R. Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model. Am. J. Crit. Care. 2018;27:461–468. doi: 10.4037/ajcc2018525. PubMed DOI PMC

Ribeiro F., Fidalgo F., Silva A., Metrôlho J., Santos O., Dionisio R. Literature Review of Machine-Learning Algorithms for Pressure Ulcer Prevention: Challenges and Opportunities. Informatics. 2021;8:76. doi: 10.3390/informatics8040076. DOI