Using structured problem solving to promote fluid consumption in the prevention of urinary stones with hydration (PUSH) trial.

BACKGROUND: Structured Problem Solving (SPS) is a patient-centered approach to promoting behavior change that relies on productive collaboration between coaches and participants and reinforces participant autonomy. We aimed to describe the design, implementation, and assessment of SPS in the multicenter Prevention of Urinary Stones with Hydration (PUSH) randomized trial. METHODS: In the PUSH trial, individuals with a history of urinary stone disease and low urine output were randomized to control versus a multicomponent intervention including SPS that was designed to promote fluid consumption and thereby prevent recurrent stones. We provide details specifically about training and fidelity assessment of the SPS coaches. We report on implementation experiences related to SPS during the initial conduct of the trial. RESULTS: With training and fidelity assessment, coaches in the PUSH trial applied SPS to help participants overcome barriers to fluid consumption. In some cases, coaches faced implementation barriers such as variable participant engagement that required tailoring their work with specific participants. The coaches also faced challenges including balancing rapport with problem solving, and role clarity for the coaches. CONCLUSIONS: We adapted SPS to the setting of kidney stone prevention and overcame challenges in implementation, such as variable patient engagement. Tools from the PUSH trial may be useful to apply to other health behavior change settings in nephrology and other areas of clinical care. TRIAL REGISTRATION: ClinicalTrials.gov Identifier NCT03244189.

Deep learning imaging features derived from kidney ultrasounds predict chronic kidney disease progression in children with posterior urethral valves.

BACKGROUND: We sought to use deep learning to extract anatomic features from postnatal kidney ultrasounds and evaluate their performance in predicting the risk and timing of chronic kidney disease (CKD) progression for boys with posterior urethral valves (PUV). We hypothesized that these features would predict CKD progression better than clinical characteristics such as nadir creatinine alone. METHODS: We performed a retrospective cohort study of boys with PUV treated at two pediatric health systems from 1990 to 2021. Features of kidneys were extracted from initial postnatal kidney ultrasound images using a deep learning model. Three time-to-event prediction models were built using random survival forests. The Imaging Model included deep learning imaging features, the Clinical Model included clinical data, and the Ensemble Model combined imaging features and clinical data. Separate models were built to include time-dependent clinical data that were available at 6 months, 1 year, 3 years, and 5 years. RESULTS: Two-hundred and twenty-five patients were included in the analysis. All models performed well with C-indices of 0.7 or greater. The Clinical Model outperformed the Imaging Model at all time points with nadir creatinine driving the performance of the Clinical Model. Combining the 6-month Imaging Model (C-index 0.7; 95% confidence interval [CI] 0.6, 0.79) with the 6-month Clinical Model (C-index 0.79; 95% CI 0.71, 0.86) resulted in a 6-month Ensemble Model that performed better (C-index 0.82; 95% CI 0.77, 0.88) than either model alone. CONCLUSIONS: Deep learning imaging features extracted from initial postnatal kidney ultrasounds may improve early prediction of CKD progression among children with PUV. A higher resolution version of the Graphical abstract is available as Supplementary information.

Improving Care Management in Attention-Deficit/Hyperactivity Disorder: An RCT.

OBJECTIVES: To compare the effectiveness of care management combined with a patient portal versus a portal alone for communication among children with attention-deficit/hyperactivity disorder (ADHD). METHODS: Randomized controlled trial conducted at 11 primary care practices. Children aged 5 to 12 years old with ADHD were randomly assigned to care management + portal or portal alone. The portal included parent-reported treatment preferences and goals, medication side effects, and parent- and teacher-reported ADHD symptom scales. Care managers provided education to families; communicated quarterly with parents, teachers, and clinicians; and coordinated care. The main outcome, changes in the Vanderbilt Parent Rating Scale (VPRS) score as a measure of ADHD symptoms, was assessed using intention-to-treat analysis. RESULTS: A total of 303 eligible children (69% male; 46% Black) were randomly assigned, and 273 (90%) completed the study. During the 9-month study, parents in the care management + portal arm communicated inconsistently with care managers (mean 2.2; range 0-6) but similarly used the portal (mean 2.3 vs 2.2) as parents in the portal alone arm. In multivariate models, VPRS scores decreased over time (Adjusted ß = -.015; 95% confidence interval -0.023 to -0.07) in both groups, but there were no intervention-by-time effects (Adjusted ß = .000; 95% confidence interval -0.011 to 0.012) between groups. Children who received ≥2 care management sessions had greater reductions in VPRS scores than those with fewer sessions. CONCLUSIONS: Results did not provide evidence that care management combined with a patient portal was different from portal use alone among children with ADHD. Both groups demonstrated similar reductions in ADHD symptoms. Those families with greater care management engagement demonstrated greater reductions than those with less engagement.