Prediction Model of Immunosuppressive Medication Non-adherence for Renal Transplant Patients Based on Machine Learning Technology

Xiao Zhu, Bo Peng, QiFeng Yi, Jia Liu, Jin Yan, Xiao Zhu, Bo Peng, QiFeng Yi, Jia Liu, Jin Yan

Abstract

Objectives: Predicting adherence to immunosuppressive medication (IM) is important to improve and design future prospective, personalized interventions in Chinese renal transplant patients (RTPs).

Methods: A retrospective, multicenter, cross-sectional study was performed in 1,191 RTPs from October 2020 to February 2021 in China. The BAASIS was used as the standard to determine the adherence of the patients. Variables of the combined theory, including the general data, the HBM, the TPB, the BMQ, the PSSS and the GSES, were used to build the models. The machine learning (ML) models included LR, RF, MLP, SVM, and XG Boost. The SHAP method was used to evaluate the contribution of predictors to predicting the risk of IM non-adherence in RTPs.

Results: The IM non-adherence rate in the derivation cohort was 38.5%. Ten predictors were screened to build the model based on the database. The SVM model performed better among the five models, with sensitivity of 0.59, specificity of 0.73, and average AUC of 0.75. The SHAP analysis showed that age, marital status, HBM-perceived barriers, use pill box after transplantation, and PSSS-family support were the most important predictors in the prediction model. All of the models had good performance validated by external data.

Conclusions: The IM non-adherence rate of RTPs was high, and it is important to improve IM adherence. The model developed by ML technology could identify high-risk patients and provide a basis for the development of relevant improvement measures.

Keywords: immunosuppressive medication; machine learning technology; non-adherence; prediction model; renal transplant patients.

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2022 Zhu, Peng, Yi, Liu and Yan.

Figures

Figure 1
Figure 1
The enrollment of patients in the derivation cohort and validation cohort.
Figure 2
Figure 2
The ROC curves and average AUC of the ML models. (A) The logistic regression (LR) model. (B) The multilayer perceptron (MLP) model. (C) The random forest (RF) model. (D) The support vector machine (SVM) model. (E) eXtreme Gradient Boosting (XGBoost). ROC curve, receiver operating characteristic curve. AUC area under the curve.
Figure 3
Figure 3
The SHAP values of predictors.
Figure 4
Figure 4
The rank of the SHAP values of predictors.

References

    1. Weng L, Yang Y, Huang H, Chiang Y, Tsai Y. Factors that determine self-reported immunosuppressant adherence in kidney transplant recipients: a correlational study. J Adv Nurs. (2017) 73:228–39. 10.1111/jan.13106
    1. Ganjali R, Sabbagh MG, Nazemiyan F. Factors associated with adherence to immunosuppressive therapy and barriers in Asian Kidney Transplant Recipients (vol 8, pg 53, 2019). Immunotargets Therapy. (2020) 9:141. 10.2147/ITT.S258315
    1. Griva K, Neo HLM, Vathsala A. Unintentional and intentional non-adherence to immunosuppressive medications in renal transplant recipients. Int J Clin Pharm-Net. (2018) 40:1234–41. 10.1007/s11096-018-0652-6
    1. Liu J, Zhu X, Yan J, Gong L, Wu X, Liu M, et al. . Association between regulatory emotional self-efficacy and immunosuppressive medication adherence in renal transplant recipients: does medication belief act as a mediator? Front Pharmacol. (2021) 12:559368. 10.3389/fphar.2021.559368
    1. Zhang P, Zhu X, Yan J, Liu J. Identification of immunosuppressive medication nonadherence factors through a combined theory model in renal transplant recipients 6-12. Front Pharmacol. (2021) 12:655836. 10.3389/fphar.2021.655836
    1. Xia M, Yan J, Liu S, Liu J. Beliefs of immunosuppressive medication among chinese renal transplant recipients, as assessed in a cross-sectional study with the basel assessment of adherence to immunosuppressive medications scale. Transpl Proc. (2019) 51:742–8. 10.1016/j.transproceed.2018.10.029
    1. Rebafka A. Medication adherence after renal transplantation-a review of the literature. J Renal Care. (2016) 42:239–56. 10.1111/jorc.12181
    1. Teng S. Using the Theory of Planned Theory (TPB) to Investigate the Factors of Immunosuppressive Medication Adherence Among Liver Transplant Recipients. Beijing: Beijing University of Chinese Medicine; (2016). p. 71.
    1. Landolfi A, Ricciardi C, Donisi L, Cesarelli G, Troisi J, Vitale C, et al. . Machine learning approaches in Parkinson's disease. Curr Med Chem. (2021) 28:6548–68. 10.2174/0929867328999210111211420
    1. Wang D, Li J, Sun Y, Ding X, Zhang X, Liu S, et al. . A machine learning model for accurate prediction of sepsis in ICU patients. Front Public Health. (2021) 9:754348. 10.3389/fpubh.2021.754348
    1. Beam AL, Kohane IS. Big data and machine learning in health care. J Am Med Assoc. (2018) 319:1317–8. 10.1001/jama.2017.18391
    1. Tang J, Liu R, Zhang Y, Liu M, Hu Y, Shao M, et al. . Application of machine-learning models to predict tacrolimus stable dose in renal transplant recipients. Sci Rep. (2017) 7:42192. 10.1038/srep42192
    1. Feng Y. Prediction Model of Postoperative Recurrence of Early Non-small Cell Lung Cancer Based on Machine Learning. Shanghai: Shanghai University of Finance and Economics; (2020). p. 73.
    1. Chen T, Li X, Li Y, Xia E, Qin Y, Liang S, et al. . Prediction and risk stratification of kidney outcomes in IgA nephropathy. Am J Kidney Dis. (2019) 74:300–9. 10.1053/j.ajkd.2019.02.016
    1. Segal Z, Kalifa D, Radinsky K, Ehrenberg B, Elad G, Maor G, et al. . Machine learning algorithm for early detection of end-stage renal disease. BMC Nephrol. (2020) 21:1–10. 10.1186/s12882-020-02093-0
    1. Yoo KD, Noh J, Lee H, Kim DK, Lim CS, Kim YH, et al. . A machine learning approach using survival statistics to predict graft survival in kidney transplant recipients: a multicenter cohort study. Sci Rep. (2017) 7:1–12. 10.1038/s41598-017-08008-8
    1. Liu J, Liu S, Yan J, Yi Q, Huang H. Adherence to immunosuppressive medication in renal transplant recipients from follow-up outpatient in China: association of 2 different measurement methods. Clin Ther. (2015) 37:2572–80. 10.1016/j.clinthera.2015.09.014
    1. Shang YB, Teng S, Liu HX, Wang L, Zhang J, Lin XH, et al. . Reliability and validity of Chinese version of Basel assessment of adherence to immunosuppressive medication scale in accessing liver transplant recipients. J Nurs Admin. (2017) 17:17–9.
    1. Zhao Y, Chen L, Qi W, Wang B. Application of the health belief model to improve the understanding of antihypertensive medication adherence among Chinese patients. Patient Educ Couns. (2015) 98:669–73. 10.1016/j.pec.2015.02.007
    1. Chisholm MA, Williamson GM, Lance CE, Mulloy LL. Predicting adherence to immunosuppressant therapy: a prospective analysis of the theory of planned behaviour. Nephrol Dial Transpl. (2007) 22:2339–48. 10.1093/ndt/gfm149
    1. Du C, Wu S, Liu H, Hu Y, Li J. Influencing factors of the intention of taking medicine among renal transplant recipients. Nurs Sci. (2018) 33:33–5.
    1. Andrew BJ, Mullan BA, de Wit JBF, Monds LA, Todd J, Kothe EJ. Does the theory of planned behaviour explain condom use behaviour among men who have sex with men? A meta-analytic review of the literature. Aids Behav. (2016) 20:2834–44. 10.1007/s10461-016-1314-0
    1. Caru M, Curnier D, Levesque A, Sultan S, Marcil V, Laverdiere C, et al. . Children's physical activity behavior following a supervised physical activity program in pediatric oncology. J Cancer Res Clin. (2020) 146:3037–48. 10.1007/s00432-020-03294-8
    1. Horne R, Weinman J. Patients' beliefs about prescribed medicines and their role in adherence to treatment in chronic physical illness. J Psychosom Res. (1999) 47:555–67. 10.1016/S0022-3999(99)00057-4
    1. Lv Y, Li Z, Han MY, Xianhui M, Cheng G, An FR. The reliability and validity of the Chinese version of Beliefs about Medical Questionnaire among elderly patients with depressive disorder. Chin J Nursing. (2014) 49:389–93. 10.3761/j.jssn.0254.1769.2014.04.001
    1. Huang L, Jiang Qj, Ren WH. Coping, perceived social support and psychosomatic symptom among cancer patients. Chin Mental Health J. (1996) 10:160–1.
    1. Zimet GD, Powell SS, Farley GK, Werkman S, Berkoff KA. Psychometric characteristics of the multidimensional scale of perceived social support. J Person Assess. (1990) 55:610–7. 10.1207/s15327752jpa5503&4_17
    1. Huo X. Study on the Relationship Between the Health Literacy, Perceived Social Support and Quality of Life of Patients With Coronary Heart Disease. Nanchang: Nanchang University; (2018), p. 73.
    1. Schwarzer R, Aristi B. Optimistic self-beliefs :Assessment of general perceived self efficacy in thirteen cultures. Word Psychol. (1997) 3:177–90.
    1. Wang CK, Hu ZF, Liu Y. Reliability and validity of general self-efficacy scale. Chin J Appl Paychol. (2001) 37–40. doi:
    1. Prihodova L, Nagyova I, Rosenberger J, Majernikova M, Roland R, Groothoff JW, et al. . Adherence in patients in the first year after kidney transplantation and its impact on graft loss and mortality: a cross-sectional and prospective study. J Adv Nurs. (2014) 70:2871–83. 10.1111/jan.12447
    1. Tang J, Kerklaan J, Wong G, Howell M, Scholes-Robertson N, Guha C, et al. . Perspectives of solid organ transplant recipients on medicine-taking: systematic review of qualitative studies. Am J Transplant. (2021) 21:3369–87. 10.1111/ajt.16613
    1. Mellon L, Doyle F, Hickey A, Ward KD, De Freitas DG, Mccormick PA, et al. . Interventions for Improving Medication Adherence in Solid Organ Transplant Recipients. (2017). Available online at: (accessed August 14, 2021).
    1. Weng FL, Chandwani S, Kurtyka KM, Zacker C, Chisholm-Burns MA, Demissie K. Prevalence and correlates of medication non-adherence among kidney transplant recipients more than 6 months post-transplant: a cross-sectional study. BMC Nephrol. (2013) 14:261. 10.1186/1471-2369-14-261
    1. Reese PP, Bloom RD, Trofe-Clark J, Mussell A, Leidy D, Levsky S, et al. . Automated reminders and physician notification to promote immunosuppression adherence among kidney transplant recipients: a randomized trial. Am J Kidney Dis. (2017) 69:400–9. 10.1053/j.ajkd.2016.10.017
    1. Paterson TSE, O'Rourke N, Shapiro RJ, Thornton WL. Medication adherence in renal transplant recipients: a latent variable model of psychosocial and neurocognitive predictors. PLoS ONE. (2018) 13:e02042199. 10.1371/journal.pone.0204219
    1. Belaiche S, Decaudin B, Dharancy S, Noel C, Odou P, Hazzan M. Factors relevant to medication non-adherence in kidney transplant: a systematic review. Int J Clin Pharm Net. (2017) 39:582–93. 10.1007/s11096-017-0436-4
    1. Patel SJ, Hofmeyer BA, Moore CA, Descourouez JL, Nguyen DT, Graviss EA, et al. . Medication nonadherence monitoring management in adult kidney transplantation: a survey of practices perceptions at US-based transplant programs. J Am Coll Clin Pharm. (2021) 4:1100–108. 10.1002/jac5.1477
    1. Kung PC, Yeh MC, Lai MK, Liu HE. Renal transplant recipients: the factors related to immunosuppressive medication adherence based on the health belief model. J Nurs Res. (2017) 25:392–7. 10.1097/JNR.0000000000000181
    1. Gokoel SR, Gombert-Handoko KB, Zwart TC, van der Boog PJ, Moes DJ, de Fijter JW. Medication non-adherence after kidney transplantation: a critical appraisal and systematic review. Transplant Rev Orlan. (2020) 34:1–18. 10.1016/j.trre.2019.100511
    1. Spivey CA, Chisholm-Burns MA, Damadzadeh B, Billheimer D. Determining the effect of immunosuppressant adherence on graft failure risk among renal transplant recipients. Clin Transplant. (2014) 28:96–104. 10.1111/ctr.12283
    1. Ladin K, Daniels A, Osani M, Bannuru RR. Is social support associated with post-transplant medication adherence and outcomes? A systematic review and meta-analysis. Transplant Rev Orlan. (2018) 32:16–28. 10.1016/j.trre.2017.04.001
    1. Peng A. Effect of family medication box on medication compliance and prognosis of stroke patients. Nurs Pract Res. (2016) 13:39–40. 10.3969/j.issn.1672-9676.2016.08.017
    1. Chisholm-Burns MA, Spivey CA, Wilks SE. Social support and immunosuppressant therapy adherence among adult renal transplant recipients. Clin Transplant. (2010) 24:312–20. 10.1111/j.1399-0012.2009.01060.x

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi