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

Study protocol for the development and validation of a questionnaire evaluating predisposition to immunosuppressant medication non-adherence of kidney pre-transplant patients. The KATITA project

Non-adherence to immunosuppressive medication after kidney transplant is an important cause of graft rejection and loss. Approaches to minimization of non-adherence have focused on the identification of episodes of medication non-adherence, but by then irreparable harm to the graft may already have occurred, and a more effective approach would be to adopt preventive measures in patients who may have difficulty in adhering to medication. The aim of this study protocol is to develop and validate a clinical questionnaire for assessing, in kidney transplant candidate patients in the pre-transplant setting, the predisposition to non-adherence to immunosuppressive medication. In this multicenter, prospective study, a pilot questionnaire in Brazilian Portuguese language, composed of Likert-scaled statements expressing patients' beliefs, behaviors and barriers regarding medication taking will be assembled from a literature review, from focus groups, and an expert panel. The pilot questionnaire will be administered to a minimum of 300 patients in kidney transplant waiting lists and exploratory factor analysis will be used for development of the definitive questionnaire. A random subsample of a minimum of 60 patients will have the scale re-administered after one month for evaluation of test-retest reliability. A multicenter, external validation study will include 364 kidney transplant candidates who will be evaluated immediately before surgery and at months 3, 6 and 12 post-transplant for assessment of concurrent validity, by comparison with two scales that assess medication non-adherence, and for determination of predictive validity using a triangulation method for assessment of medication non-adherence. Structural validity will be assessed with confirmatory factor analysis using structural equation modeling. Cross-cultural generalizability and validity will be assessed by a multicenter study, in which a translation of the scale to another language will be administered to kidney transplant candidate patients from a different culture, with a subsample being selected for test-retest. This study will be conducted in Spain with a Spanish translation of the scale.

Development and Internal Validation of a Questionnaire Assessing Predisposition to Nonadherence to Immunosuppressive Medication in Kidney Pretransplant Patients

BACKGROUND

After kidney transplant, nonadherence to immunosuppressive therapy is the main cause of impaired kidney function and graft loss. The objective of this study was the development and internal validation of a clinical questionnaire for assessing the predisposition to adherence to immunosuppressive therapy in kidney pretransplant patients.

METHODS

Multicenter prospective study conducted in 7 kidney hemodialysis and 6 kidney transplant centers of 3 Brazilian state capitals. Kidney transplant candidate patients of both sexes and >18-y-old were included. Retransplanted patients were excluded. A 72-item pilot version of the questionnaire, created through literature review complemented with a focus group of 8 kidney pretransplant patients, was administered to 541 kidney transplant candidate patients. Factor analysis with varimax rotation was used for questionnaire development. Internal validity evaluation used Cronbach's alpha and test-retest reliability. Construct validity was assessed by differentiation by known groups.

RESULTS

The final questionnaire, named Kidney AlloTransplant Immunosuppressive Therapy Adherence (KATITA) Questionnaire, consisting of 25 items in 3 dimensions, presented good internal consistency reliability (Cronbach's alpha 0.81). The 3 dimensions and respective Cronbach's alpha were "Carelessness" (14 items, 0.81), "Skepticism" (6 items, 0.57), and "Concern" (5 items, 0.62). The interdimension correlation matrix showed low correlation coefficients (<0.35). Test-retest reliability, evaluated with 154 patients, showed an intraclass correlation coefficient of 0.62 (moderate agreement). The scale showed construct validity.

CONCLUSIONS

The KATITA-25 questionnaire is the first psychometric instrument for evaluation of predisposition to nonadherence to immunosuppressive medication in candidate patients for kidney transplant in the pretransplant setting.

A Machine Learning Model to Predict Patients' Adherence Behavior and a Decision Support System for Patients With Metastatic Breast Cancer: Protocol for a Randomized Controlled Trial

BACKGROUND

Adherence to oral anticancer treatments is critical in the disease trajectory of patients with breast cancer. Given the impact of nonadherence on clinical outcomes and the associated economic burden for the health care system, finding ways to increase treatment adherence is particularly relevant.

OBJECTIVE

The primary end point is to evaluate the effectiveness of a decision support system (DSS) and a machine learning web application in promoting adherence to oral anticancer treatments among patients with metastatic breast cancer. The secondary end point is to collect a set of new physical, psychological, social, behavioral, and quality of life predictive variables that could be used to refine the preliminary version of the machine learning model to predict patients' adherence behavior.

METHODS

This prospective, randomized controlled study is nested in a large-scale international project named "Enhancing therapy adherence among metastatic breast cancer patients" (Pfizer 65080791), aimed to develop a predictive model of nonadherence and associated DSS and guidelines to foster patients' engagement and therapy adherence. A web-based DSS named TREAT (treatment adherence support) was developed using a patient-driven approach, with 4 sections, that is, Section A: Metastatic Breast Cancer; Section B: Adherence to Cancer Therapies; Section C: Promoting Adherence; and Section D: My Adherence Diary. Moreover, a machine learning-based web application was developed to predict patients' risk factors of adherence to anticancer treatment, specifically pertaining to physical status and comorbid conditions, as well as short and long-term side effects. Overall, 100 patients consecutively admitted at the European Institute of Oncology (IEO) at the Division of Medical Senology will be enrolled; 50 patients with metastatic breast cancer will be exposed to the DSS and machine learning web application for 3 months (experimental group), and 50 patients will not be exposed to the intervention (control group). Each participant will fill a weekly medication diary and a set of standardized self-reports evaluating psychological and quality of life variables (Adherence Attitude Inventory, Beck Depression Inventory-II, Brief Pain Inventory, 13-item Sense of Coherence scale, Brief Italian version of Cancer Behavior Inventory, European Organization for Research and Treatment of Cancer Quality of Life 23-item Breast Cancer-specific Questionnaire, European Organization for Research and Treatment of Cancer Quality of Life Questionnaire, 8-item Morisky Medication Adherence Scale, State-Trait Anxiety Inventory forms I and II, Big Five Inventory, and visual analogue scales evaluating risk perception). The 3 assessment time points are T0 (baseline), T1 (1 month), T2 (2 months), and T3 (3 months). This study was approved by the IEO ethics committee (R1786/22-IEO 1907).

RESULTS

The recruitment process started in May 2023 and is expected to conclude on December 2023.

CONCLUSIONS

The contribution of machine learning techniques through risk-predictive models integrated into DSS will enable medication adherence by patients with cancer.

TRIAL REGISTRATION

ClinicalTrials.gov NCT06161181; https://clinicaltrials.gov/study/NCT06161181.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/48852.

Development and validation of a LASSO-based prediction model for immunosuppressive medication nonadherence in kidney transplant recipients

INTRODUCTION

To establish a prediction model to predict immunosuppressive medication (IM) nonadherence in kidney transplant recipients (KTRs) based on a combined theory framework.

METHODS

This polycentric, cross-sectional study included 1191 KTRs from October 2020 to February 2021 in China, with 1011 KTRs enrolled in the derivation set and 180 in the external validation set. Variables selected based on the combined theory of planned behavior (TPB)/health belief model (HBM) theory were analyzed by the least absolute shrinkage and selection operator (LASSO). Internal 10 cross-validation was conducted to determine the optimal lambda value. The receiver operating characteristic (ROC) curve, specificity, and sensitivity were used to evaluate the prediction model, and further assessment was run by external validation.

RESULTS

IM nonadherence rate was 38.48% in the derivation set and 37.22% in the validation set. The LASSO model was developed with eight predictors for IM nonadherence: age, preoperative drinking history, education, marital status, perceived barriers, social support, perceived behavioral control, and perceived susceptibility. The model demonstrated acceptable discrimination with the area under the ROC curve of 0.797 (95% CI: 0.745-0.850) in the internal validation set and 0.757 (95% CI: 0.684-0.829) in the external validation set. The specificity and sensitivity in the internal validation and external validation set were 0.741, 0.748, 0.673, and 0.716, respectively.

CONCLUSIONS

The LASSO model was developed to guide identifying high-risk nonadherent patients and timely and effective interventions to improve their prognosis and survival.