Association of Symptoms and Collaborative Care Intervention (TACcare) with Systemic Inflammation Biomarkers in End-Stage Kidney Disease.

BACKGROUND: Patient-reported symptoms are associated with inflammation biomarkers in many chronic diseases. We examined associations of inflammation biomarkers with pain, fatigue, and depression in patients with end-stage kidney disease (ESKD) and the effects of a Technology Assisted stepped Collaborative Care (TACcare) intervention on these biomarkers. METHODS: In the TACcare multi-site randomized control trial, data on patient-reported symptoms were collected at baseline, 3, and 6 months. Anti-inflammatory [interleukin 1 receptor agonist (IL-1RA), IL-10], pro-inflammatory [tumor necrosis factor alpha (TNF-α), high sensitivity C-reactive protein (hs-CRP), IL-6] and regulatory [IL-2] biomarkers were assayed. Linear mixed-effects modeling was used to examine within- and between-group differences after adjusting for age, sex, race, and comorbidities. RESULTS: Among the 160 patients (mean age 58±14 years, 55% men, 52% white), there were no significant associations between inflammation biomarkers and pain, fatigue or depression at baseline. Both intervention and control group demonstrated reductions in IL-10 and IL-1RA over 6 months (ß range=-1.22 to -0.40, p range=<0.001 to 0.02) At 3 months, the treatment group exhibited decreases in TNF-α (ß=-0.22, p<0.001) and IL-2 (ß=-0.71, p<0.001), whereas the control group showed increases in IL-6/IL-10 ratio (ß=0.33, p=0.03). At 6 months, both groups exhibited decreases in IL-2 (ß range=-0.66 to -0.57,p<0.001); the control group showed significant increases in the ratio of IL-6/IL-10 (ß=0.75,p<0.001) and decrease in TNF-α (ß=-0.16, p=0.02). Compared to controls, the treatment group demonstrated significantly decreased IL-2 at 3 months (ß=-0.53, p<0.001). Significant interaction effects of treatment were observed on the association between changes in pro-inflammatory biomarkers (TNF-α and hs-CRP) levels and changes in symptom scores from baseline to 6 months. CONCLUSIONS: The TACcare intervention had a short-term impact on reducing inflammatory burden in patients with ESKD. More studies are needed to confirm our findings and to determine if these biomarkers mediate the link between symptoms and disease progression.

Electronic Health Record Population Health Management for Chronic Kidney Disease Care: A Cluster Randomized Clinical Trial.

Importance: Large gaps in clinical care in patients with chronic kidney disease (CKD) lead to poor outcomes. Objective: To compare the effectiveness of an electronic health record-based population health management intervention vs usual care for reducing CKD progression and improving evidence-based care in high-risk CKD. Design, Setting, and Participants: The Kidney Coordinated Health Management Partnership (Kidney CHAMP) was a pragmatic cluster randomized clinical trial conducted between May 2019 and July 2022 in 101 primary care practices in Western Pennsylvania. It included patients aged 18 to 85 years with an estimated glomerular filtration rate (eGFR) of less than 60 mL/min/1.73m2 with high risk of CKD progression and no outpatient nephrology encounter within the previous 12 months. Interventions: Multifaceted intervention for CKD comanagement with primary care clinicians included a nephrology electronic consultation, pharmacist-led medication management, and CKD education for patients. The usual care group received CKD care from primary care clinicians as usual. Main Outcomes and Measures: The primary outcome was time to 40% or greater reduction in eGFR or end-stage kidney disease. Results: Among 1596 patients (754 intervention [47.2%]; 842 control [52.8%]) with a mean (SD) age of 74 (9) years, 928 (58%) were female, 127 (8%) were Black, 9 (0.6%) were Hispanic, and the mean (SD) estimated glomerular filtration rate was 36.8 (7.9) mL/min/1.73m2. Over a median follow-up of 17.0 months, there was no significant difference in rate of primary outcome between the 2 arms (adjusted hazard ratio, 0.96; 95% CI, 0.67-1.38; P = .82). Angiotensin-converting enzyme inhibitor/angiotensin receptor blocker exposure was more frequent in intervention arm compared with the control group (rate ratio, 1.21; 95% CI, 1.02-1.43). There was no difference in the secondary outcomes of hypertension control and exposure to unsafe medications or adverse events between the arms. Several COVID-19-related issues contributed to null findings in the study. Conclusion and Relevance: In this study, among patients with moderate-risk to high-risk CKD, a multifaceted electronic health record-based population health management intervention resulted in more exposure days to angiotensin-converting enzyme inhibitors/angiotensin receptor blockers but did not reduce risk of CKD progression or hypertension control vs usual care. Trial Registration: ClinicalTrials.gov Identifier: NCT03832595.

A clinician's guide to understanding and critically appraising machine learning studies: a checklist for Ruling Out Bias Using Standard Tools in Machine Learning (ROBUST-ML).

Developing functional machine learning (ML)-based models to address unmet clinical needs requires unique considerations for optimal clinical utility. Recent debates about the rigours, transparency, explainability, and reproducibility of ML models, terms which are defined in this article, have raised concerns about their clinical utility and suitability for integration in current evidence-based practice paradigms. This featured article focuses on increasing the literacy of ML among clinicians by providing them with the knowledge and tools needed to understand and critically appraise clinical studies focused on ML. A checklist is provided for evaluating the rigour and reproducibility of the four ML building blocks: data curation, feature engineering, model development, and clinical deployment. Checklists like this are important for quality assurance and to ensure that ML studies are rigourously and confidently reviewed by clinicians and are guided by domain knowledge of the setting in which the findings will be applied. Bridging the gap between clinicians, healthcare scientists, and ML engineers can address many shortcomings and pitfalls of ML-based solutions and their potential deployment at the bedside.

Predictors of sleep quality among university students: the use of advanced machine learning techniques.

PURPOSE: To assess the prevalence of sleep disturbances among university students and investigate potential correlated factors and their relative importance in quantifying sleep quality using advanced machine learning techniques. METHODS: A total of 1600 university students participated in this cross-sectional study. Sociodemographic information was collected, and the Pittsburgh Sleep Quality Index (PSQI) was administered to assess sleep quality among university students. Study variables were evaluated using logistic regression and advanced machine learning techniques. Study variables that were significant in the logistic regression and had high mean decrease in model accuracy in the machine learning technique were considered important predictors of sleep quality. RESULTS: The mean (SD) age of the sample was 26.65 (6.38) and 57% of them were females. The prevalence of poor sleep quality in our sample was 70%. The most accurate and balanced predictive model was the random forest model with a 74% accuracy and a 95% specificity. Age and number of cups of tea per day were identified as protective factors for a better sleep quality, while electronics usage hours, headache, other systematic diseases, and neck pain were found risk factors for poor sleep quality. CONCLUSIONS: Six predictors of poor sleep quality were identified in university students in which 2 of them were protective and 3 were risk factors. The results of this study can be used to promote health and well-being in university students, improve their academic performance, and assist in developing appropriate interventions.