Machine learning algorithms' accuracy in predicting kidney disease progression: a systematic review and meta-analysis.

BACKGROUND: Kidney disease progression rates vary among patients. Rapid and accurate prediction of kidney disease outcomes is crucial for disease management. In recent years, various prediction models using Machine Learning (ML) algorithms have been established in nephrology. However, their accuracy have been inconsistent. Therefore, we conducted a systematic review and meta-analysis to investigate the diagnostic accuracy of ML algorithms for kidney disease progression. METHODS: We searched PubMed, EMBASE, Cochrane Central Register of Controlled Trials, the Chinese Biomedicine Literature Database, Chinese National Knowledge Infrastructure, Wanfang Database, and the VIP Database for diagnostic studies on ML algorithms' accuracy in predicting kidney disease prognosis, from the establishment of these databases until October 2020. Two investigators independently evaluate study quality by QUADAS-2 tool and extracted data from single ML algorithm for data synthesis using the bivariate model and the hierarchical summary receiver operating characteristic (HSROC) model. RESULTS: Fifteen studies were left after screening, only 6 studies were eligible for data synthesis. The sample size of these 6 studies was 12,534, and the kidney disease types could be divided into chronic kidney disease (CKD) and Immunoglobulin A Nephropathy, with 5 articles using end-stage renal diseases occurrence as the primary outcome. The main results indicated that the area under curve (AUC) of the HSROC was 0.87 (0.84-0.90) and ML algorithm exhibited a strong specificity, 95% confidence interval and heterogeneity (I2) of (0.87, 0.84-0.90, [I2 99.0%]) and a weak sensitivity of (0.68, 0.58-0.77, [I2 99.7%]) in predicting kidney disease deterioration. And the the results of subgroup analysis indicated that ML algorithm's AUC for predicting CKD prognosis was 0.82 (0.79-0.85), with the pool sensitivity of (0.64, 0.49-0.77, [I2 99.20%]) and pool specificity of (0.84, 0.74-0.91, [I2 99.84%]). The ML algorithm's AUC for predicting IgA nephropathy prognosis was 0.78 (0.74-0.81), with the pool sensitivity of (0.74, 0.71-0.77, [I2 7.10%]) and pool specificity of (0.93, 0.91-0.95, [I2 83.92%]). CONCLUSION: Taking advantage of big data, ML algorithm-based prediction models have high accuracy in predicting kidney disease progression, we recommend ML algorithms as an auxiliary tool for clinicians to determine proper treatment and disease management strategies.

Validity, reliability, and application of the electronic version of a chronic kidney disease patient awareness questionnaire: a pilot study.

OBJECTIVES: A questionnaire which provides desirable reliability and validity has been previously developed to assess the disease awareness of diagnosed chronic kidney disease (CKD) patients. However, conventional paper questionnaires often have disadvantages, including recall bias. To substantially improve this, we therefore aimed to explore the feasibility of developing a smartphone-based electronic version (e-version) based upon its original paper version and subsequently tested its validity, reliability, and applicability. METHODS: A pilot study was conducted at Guangdong Provincial Hospital of Chinese Medicine in Guangzhou, China, during August 2019. The e-version had identical content to the paper version and was adapted in terms of layout and assisted functions via the Wechat-incorporated Wen-Juan-Xing platform. Eligible patients with diagnosed CKD were invited to participate and were assigned the e-version. Randomly selected respondents received a test-retest of the same e-version 2 weeks after their first completion. In some instances, psychometric properties, including validity and reliability of the e-version, were examined. In others, its clinical application was also tested, which included comparisons among the clinical profiles of patients who had/had not responded to the questionnaire as well as patients with above or below average questionnaire scores. RESULTS: Of the 225 patients screened, 217 were enrolled to participate, with a response rate of 52.5%. Desirable reliability (Cronbachα = 0.962, ICC for total scores = 0.948), while good convergent validity (Cronbachα = 0.962) and low discriminant validity (one extracted component), of the e-version were detected. Performing inter-group comparisons highlighted statistical differences in terms of higher education level (z = -2.436, P = 0.015) and earlier CKD stages (z = -1.978, P = 0.048), with these patients often preferring to respond. No significant differences were detected in the clinical profiles between respondents who obtained an above or below average questionnaire score. CONCLUSION: The e-version is reliable but was not shown to be a valid approach. Audiences with higher education levels and less advanced disease condition may prefer to respond to the e-version. Adaptation of this e-questionnaire, from its original paper version, may not be a direct transition and meticulous modifications may be required during the transition process. TRIAL REGISTRATION: Chinese Clinical Trial Registry (ChiCTR1900024633).

Refinement and Evaluation of a Chinese and Western Medication Adherence Scale for Patients with Chronic Kidney Disease: Item Response Theory Analyses.

PURPOSE: This study aimed to simplify the version-1 Chinese and Western medication adherence scale for patients with chronic kidney disease (CKD) to a version-2 scale using item response theory (IRT) analyses, and to further evaluate the performance of the version-2 scale. MATERIALS AND METHODS: Firstly, we refined the version-1 scale using IRT analyses to examine the discrimination parameter (a), difficulty parameter (b) and maximum information function peak (Imax). The final scale refinement from version-1 to version-2 scale was also decided upon clinical considerations. Secondly, we analyzed the reliability and validity of version-2 scale using classical test theory (CTT), as well as difficulty, discrimination and Imax of version-1 and version-2 scale using IRT in order to conduct scale evaluation. RESULTS: For scale refinement, the 26-item version-1 scale was reduced to a 15-item version-2 scale after IRT analyses. For scale evaluation using CTT, internal consistency reliability (total Cronbach α = 0.842) and test-rest reliability (r = 0.909) of version-2 scale were desirable. Content validity indicated 3 components of knowledge, belief and behaviors. We found meritorious construct validity with 3 detected components as the same construct of medication knowledge (items 1-9), medication behavior (items 13-15), and medication belief (items 10-12) based upon exploratory factor analysis. The correlation between the version-2 scale and Morisky, Green and Levine scale (MGL scale) was weak (Pearson coefficient = 0.349). For scale evaluation with IRT, the findings showed enhanced discrimination and decreased difficulty of most retained items (items 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15), decreased Imax of items 1, 2, 3, 4, 6, 11, 14, as well as increased Imax of items 5, 7, 8, 9, 10, 12, 13, 14, 15 in the version-2 scale than in the version-1 scale. CONCLUSION: The original Chinese and Western medication adherence scale was refined to a 15-item version-2 scale after IRT analyses. The scale evaluation using CTT and IRT showed the version-2 scale had the desirable reliability, validity, discrimination, difficulty, and information providedoverall. Therefore, the version-2 scale is clinically feasible to assess the medication adherence of CKD patients.

A Chinese and Western medication adherence scale in patients with Chronic Kidney Disease.

OBJECTIVE: The self-reported scale is a widely used method to assess patients' medication adherence in clinical practice, but there is still a lack of medicine adherence measurement scale for patients with Chronic Kidney Disease (CKD). Therefore, this study aimed to develop a medication adherence measurement scale of traditional Chinese medicine and Western medicine, providing a tool for evaluating medicine adherence of CKD patients. METHODS: In the preliminary stage, we formed the prediction scale after three rounds Delphi method and it was filled by 20 patients, who were selected randomly. After pre-investigation and language adaption, we adjusted the prediction measurement scale which included 31 items based on Knowledge-Attitude-Belief Theory. Then, 222 CKD patients in Guangdong Hospital of traditional Chinese Medicine were investigated by this 31-item scale. We screened 31 items by Items analysis theory, including critical ratio, item correlation analysis, internal consistency analysis, principal component analysis and other methods. The left 26 items made up a formal scale. We collected and analyzed data of the 26-item scale and Chinese version of MGL scale, and took their scores correlation analysis as the criterion validity of the 26-item scale. At the same time, we evaluated content validity, Cronbach alpha coefficient and retest reliability of the 26-item scale. RESULTS: We developed a scale with 26 items and 5 dimensions finally. In the validation analysis, the scale had good construct validity and content validity. The Pearson relation index between respective scores of the scale and Chinese version of MGL scale was 0.426, P<0.01. The scale also had good reliability as its 0.915 in Cronbach alpha, 0.753 in retest reliability and P<0.01. CONCLUSION: The scale revealed great reliability and validity, which could be used as a measurement tool to evaluate the medication adherence of patients with CKD.