Modeling the conditions of regular сompliance with recommendations for cardiological patients at the outpatient stage using decision trees

The paper is concerned with the use of decision trees with a view to designing the model of regular сompliance with recommendations for cardiological patients. Machine learning of feature significance in a tree-like structure was conducted based on the statistical sampling gathered after examining 69 patients that had received treatment in a cardiological department and who had been being observed for 6 months after discharge. To build a decision tree, input data was employed: age, gender, social status, reasons for hospitalization, description of previous illnesses, treatment strategy, reasons for missed doses, adherence to recommendations. As output data, regular / irregular compliance with the recommendations during 6 months after discharge was used. The decision tree that reflects the conditions influencing the compliance with medication intake after discharge has been built. Analysis of factor scaling influence at branching points will provide the means for defining the regularity of compliance with the prescribed medical treatment in the form of their conjunctions at each branch of the decision tree. Significance of the features associated with the factors of influence was evaluated according to Gini index value. This intelligent technology identified the factors that determine the outcome: providing patients with clear recommendations, missed doses due to forgetfulness, patient’s general state, social status, changes in therapy, patients’ age, duration of arterial hypertension.

1. 1. Gasanova I.A., Pariiskii V.A., Gribkov A.A. Iskusstvennyi intellekt v klinicheskoi meditsine i stomatologii. Tendentsii razvitiya nauki i obrazovaniya. 2018;38(4):17–21. (In Russ.).

2. 2. Simpson S.H., Eurich D.T., Majumdar S.R. A meta-analysis of the association between adherence to drug therapy and mortality. The BMJ. 2006;333(7557):15.

3. 3. Osterberg L., Blaschke T. Adherence to medication. The New England Journal of Medicine. 2005;353(5):487–497.

4. 4. World Health Organisation: Adherence to long-term therapies, evidence for action. Geneva, WHO: 2003. 209 p.

5. 5. Jeffery RA, Navarro T., Wilczynski NL, Iserman EC, Keepanasseril A, Sivaramalingam B., Agoritsas T, Haynes R.B. Adherence measurement and patient recruitment methods are poor in intervention trials to improve patient adherence. Journal of Clinical Epidemiology. 2014;67(10):1076–1082.

6. 6. Karanasiou G.S., Tripoliti E.E., Papadopoulos T.G., Kalatzis F.G., Goletsis Y., Naka K.K., Bechlioulis A., Errachid A., Fotiadis D.I. Predicting adherence of patients with HF through machine learning techniques. Healthcare technology letters. 2016;3(3):165–170. DOI: 10.1049/htl.2016.0041.

7. 7. LI H, Wu TT, Yang DL. Decision tree model for predicting in-hospital cardiac arrest among patients admitted with acute coronary syndrome. Clin Cardiol. 2019;42(11):1087–1093. DOI: 10.1002/clc.23255.

8. 8. Karaolis M.A., Moutiris J.A., Hadjipanayi D., Pattichis C.S. Assessment of the risk factors of coronary heart events based on data mining with decision trees. IEEE Transactions on Information Technology in Biomedicine. 2010;14(3):559–566.

9. 9. Mašetić Z, Subasi A. Detection of congestive heart failures using C4.5 decision tree. Southeast Europe Journal of Soft Computing. 2013;2(2):74–77.

10. 10. Naumova E.A., Tarasenko E.V., Shvarts Y.G. Vliyanie standartizirovannykh naglyadnykh motivirovannykh rekomendatsii dlya patsientov na priverzhennost' k dolgosrochnoi terapii. Mezhdunarodnyi meditsinskii zhurnal = International Medical Journal. 2007;1:123–129. (In Russ.).

11. 11. Zharkova O.S., Sharopin K.A., Seidova A.S., Berestneva E.V., Osadchaya I.A. Construction of decision support systems in medicine based decision tree. Sovremennye naukoemkie tekhnologii = Modern High Technologies. 2016;6(1):33–37. (In Russ.).

12. 12. Gast A., Mathes T. Medication adherence influencing factors—an (updated) overview of systematic reviews. Systematic Reviews. 2019;8(1):112. DOI: 10.1186/s13643-019-1014-8.

13. 13. Chen H.Y., Saczynski J.S., Lapane K.L., Kiefe C.I., Goldberg R.J. Adherence to evidence-based secondary prevention pharmacotherapy in patients after an acute coronary syndrome: a systematic review. Heart & Lung. 2015;44(4):299–308.

14. 14. Oosterom-Calo R., van Ballegooijen A.J, Terwee C.B., te Velde S.J., Brouwer I.A., Jaarsma T., Brug J. Determinants of adherence to heart failure medication: a systematic literature review. Heart Failure Reviews. 2013;18(4):409–427.

15. 15. Aziz H., Hatah E., Makmor Bakry M., Islahudin F. How payment scheme affects patients’ adherence to medications? A systematic review. Patient Prefer Adherence. 2016;10:837–850.

16. 16. Lewey J., Shrank W.H., Bowry ADK, Kilabuk E, Brennan T.A, Choudhry N.K. Gender and racial disparities in adherence to statin therapy: a meta-analysis. American Heart Journal. 2013;165(5):665–678.

17. 17. Nachega J.B., Uthman O.A., Peltzer K., Richardson L.A., Mills E.J., Amekudzi K, Ouédraogo A. Association between antiretroviral therapy adherence and employment status: systematic review and meta-analysis. Bulletin of the World Health Organization. 2015;93(1):29–41.

18. 18. Gourzoulidis G., Kourlaba G., Stafylas P., Giamouzis G., Parissis J., Maniadakis N. Association between copayment, medication adherence and outcomes in the management of patients with diabetes and heart failure. Health Policy. 2017;121(4):363–377.

19. 19. Alsabbagh MHDW, Lemstra M., Eurich D., Lix L.M, Wilson T.W., Watson E, Blackburn D.F. Socioeconomic status and nonadherence to antihypertensive drugs: a systematic review and meta-analysis. Value Health. 2014;17(2):288–296.

20. 20. Crawshaw J., Auyeung V., Norton S., Weinman J. Identifying psychosocial predictors of medication non-adherence following acute coronary syndrome: a systematic review and meta-analysis. Journal of Psychosomatic Research. 2016;90:10–32.

21. 21. Shalnova S.A., Deev A.D., Vikhireva O.V. Arterial hypertension: ambulatory patients’ point of view. First results of GARANT Study. Kardiovaskulyarnaya Terapiya i Profilaktika = Cardiovascular Therapy and Prevention. 2007;6(5):30–3. (In Russ.).

22. 22. Carney R.M., Freedland K.E, Eisen S.A, Rich M.W., Skala J.A., Jaffe A.S. Adherence to a prophylactic medication regimen in patients with symptomatic versus asymptomatic ischemic heart disease. Behavioral Medicine. 1998;24(1):35–39.

23. 23. Saini S., Schoenfeld., Kaulback K., Dubinsky M. Effect of medication dosing frequency on adherence in chronic diseases. The American Journal of Managed Care. 2009;15(6):22–33.

24. 24. Norberg S., Gustafsson M. Older Peoples' Adherence and Awareness of Changes in Drug Therapy after Discharge from Hospital. Pharmacy (Basel). 2018;6(2):38. DOI: 10.3390/pharmacy6020038.

25. 25. Björklund E., Nielsen S.J., Hansson E.C., Karlsson M., Wallinder A., Martinsson A., Tygesen H., Romlin B.S., Malm C.J., Pivodic A., Jepsson A. Secondary prevention medications after coronary artery bypass grafting and long-term survival: a population – based longitudinal study from the SWEDEHEART registry. European Heart Journal. 2020;41(17):1653-1661. DOI:10.1093/eurheartj/ehz714.