Machine learning for prediction of chronic kidney disease progression: Validation of the Klinrisk model in the CANVAS Program and CREDENCE trial.

AIM: To validate the Klinrisk machine learning model for prediction of chronic kidney disease (CKD) progression in patients with type 2 diabetes in the pooled CANVAS/CREDENCE trials. MATERIALS AND METHODS: We externally validated the Klinrisk model for prediction of CKD progression, defined as 40% or higher decline in estimated glomerular filtration rate (eGFR) or kidney failure. Model performance was assessed for prediction up to 3 years with the area under the receiver operating characteristic curve (AUC), Brier scores and calibration plots of observed and predicted risks. We compared performance of the model with standard of care using eGFR (G1-G4) and urine albumin-creatinine ratio (A1-A3) Kidney Disease Improving Global Outcomes (KDIGO) heatmap categories. RESULTS: The Klinrisk model achieved an AUC of 0.81 (95% confidence interval [CI] 0.78-0.83) at 1 year, and 0.88 (95% CI 0.86-0.89) at 3 years. The Brier scores were 0.020 (0.018-0.022) and 0.056 (0.052-0.059) at 1 and 3 years, respectively. Compared with the KDIGO heatmap, the Klinrisk model had improved performance at every interval (P < .01). CONCLUSIONS: The Klinrisk machine learning model, using routinely collected laboratory data, was highly accurate in its prediction of CKD progression in the CANVAS/CREDENCE trials. Integration of the model in electronic medical records or laboratory information systems can facilitate risk-based care.

Expanding Access to High KDPI Kidney Transplant for Recipients Aged 60 y and Older: Cost Utility and Survival.

Background: Modern organ allocation systems are tasked with equitably maximizing the utility of transplanted organs. Increasing the use of deceased donor organs at risk of discard may be a cost-effective strategy to improve overall transplant benefit. We determined the survival implications and cost utility of increasing the use of marginal kidneys in an older adult Canadian population of patients with end-stage kidney disease. Methods: We constructed a cost-utility model with microsimulation from the perspective of the Canadian single-payer health system for incident transplant waitlisted patients aged 60 y and older. A kidney donor profile index score of ≥86 was considered a marginal kidney. Donor- and recipient-level characteristics encompassed in the kidney donor profile index and estimated posttransplant survival scores were used to derive survival posttransplant. Patients were followed up for 10 y from the date of waitlist initiation. Our analysis compared the routine use of marginal kidneys (marginal kidney scenario) with the current practice of limited use (status quo scenario). Results: The 10-y mean cost and quality-adjusted life-years per patient in the marginal kidney scenario were estimated at $379 485.33 (SD: $156 872.49) and 4.77 (SD: 1.87). In the status quo scenario, the mean cost and quality-adjusted life-years per patient were $402 937.68 (SD: $168 508.85) and 4.37 (SD: 1.87); thus, the intervention was considered dominant. At 10 y, 62.8% and 57.0% of the respective cohorts in the marginal kidney and status quo scenarios remained alive. Conclusions: Increasing the use of marginal kidneys in patients with end-stage kidney disease aged 60 y and older may offer cost savings, improved quality of life, and greater patient survival in comparison with usual care.

Costs of Assisted Home Dialysis: A Single-Payer Canadian Model From Manitoba.

RATIONALE & OBJECTIVE: The prevalence of kidney failure is increasing globally. Most of these patients will require life-sustaining dialysis at a substantial cost to the health care system. Assisted peritoneal dialysis (PD) and assisted home hemodialysis (HD) are potential alternatives to in-center HD and have demonstrated equivalent outcomes with respect to mortality and morbidity. We aim to describe the costs associated with assisted continuous cycling PD (CCPD) and assisted home HD. STUDY DESIGN: Cost minimization model. SETTING & POPULATION: Adult incident maintenance dialysis patients in Manitoba, Canada. INTERVENTION: Full- and partial-assist home HD and CCPD. Full-assist modalities were defined as nurse-assisted dialysis setup and takedown performed by a health care aide, whereas partial-assist modalities only included nurse-assisted setup. Additionally, full-assist home HD was evaluated under a complete care scenario with the inclusion of a health care aide remaining with the patient throughout the duration of treatment. OUTCOMES: Annual per-patient maintenance and training costs related to assisted and self-care home HD and CCPD, presented in 2019 Canadian dollars. MODEL PERSPECTIVE & TIME FRAME: This model took the perspective of the Canadian public health payer using a 1-year time frame. RESULTS: Annual total per-patient maintenance (and training) costs by modality were the following: full-assist CCPD, $75.717 (initial training costs, $301); partial-assist CCPD, $67,765 ($4,385); full-assist home HD, $47,862 ($301); partial-assist home HD, $44,650 ($14,813); and full-assist home HD (complete care), $64,659 ($301). LIMITATIONS: This model did not account for costs taken from the societal perspective or costs related to PD failure and modality switching. Additionally, this analysis reflects only costs experienced by a single center. CONCLUSIONS: Assisted home-based dialysis modalities are viable treatment options for patients from a cost perspective. Future studies to consider graduation rates to full self-care from assisted dialysis and the cost implications of respite care are needed.

Percutaneous Versus Surgical Insertion of Peritoneal Dialysis Catheters: A Systematic Review and Meta-Analysis.

BACKGROUND: Home-based peritoneal dialysis (PD) is an alternative to facility-based hemodialysis and has lower costs and greater freedom for patients with kidney failure. For a patient to undergo PD, a safe and reliable method of accessing the peritoneum is needed. However, different catheter insertion techniques may affect patient health outcomes. OBJECTIVE: To compare the risk of infectious and mechanical complications between surgical (open and laparoscopic) PD catheter insertion and percutaneous catheter insertion. DESIGN: Systematic review and meta-analysis. SETTING: We searched for observational studies and randomized controlled trials (RCTs) in CENTRAL, EMBASE, MEDLINE, PubMed, and SCOPUS from inception until June 2018. Data were extracted by 2 independent reviewers based on a preformed template. PATIENTS: Adult (aged 18+) patients with kidney failure who underwent a PD catheter insertion procedure. MEASUREMENTS: We analyzed leak, malfunction, and bleed as early complications (occurring within 1 month of catheter insertion). Infectious complications (exit-site infections, tunnel infections, and peritonitis) were presented as both early complications and with the longest duration of follow-up. METHODS: Random effects meta-analyses with the generic inverse variance method to estimate pooled rate ratios and 95% confidence intervals. We quantified heterogeneity by using the I2 statistic for inconsistency and assessed heterogeneity using the χ2 test. Sensitivity analysis was performed by removing studies at high risk of bias as measured with the Newcastle-Ottawa Scale and the Cochrane Risk of Bias tool. RESULTS: Twenty-four studies (22 observational, 2 RCTs) with 3108 patients and 3777 catheter insertions were selected. Data from 2 studies were unable to be extracted and were qualitatively assessed. In the remaining 22 studies, percutaneous insertion was associated with a lower risk of both exit-site infections (risk ratio [RR] = 0.36, 95% confidence interval [CI] = 0.24-0.53, I2 = 0%) and peritonitis (RR = 0.52, 95% CI = 0.36-0.77, I2 = 3%) within 1 month of the procedure. There was no difference in mechanical complication rates between the 2 techniques. LIMITATIONS: Lack of consistency in the time periods for the various outcomes reported, risk of bias concerns with respect to population comparability, and the inability to analyze individual component causes of primary nonfunction (catheter obstruction, catheter migration, and leak). CONCLUSIONS: Our meta-analysis suggests differences in early infectious complications in favor of percutaneous insertion and no significant differences in mechanical complications compared with surgical insertion. These findings have implications on the direction of PD programs in terms of maximizing operating room resources.

CONTEXTE: La dialyse péritonéale à domicile (DPD) est une alternative plus économique à l'hémodialyse en centre et offre une plus grande liberté aux patients atteints d'insuffisance rénale. Or, pour qu'un patient soit traité par DPD, il est essentiel de recourir à une méthode d'accès au péritoine qui soit fiable et sûre. Les techniques existantes pour l'insertion du cathéter sont toutefois susceptibles d'affecter les résultats de santé du patient. OBJECTIFS: Comparer le risque de complications mécaniques et infectieuses entre l'insertion chirurgicale (incision et laparoscopie) et percutanée d'un cathéter de DP. TYPE D'ÉTUDE: Revue systématique et méta-analyse. CADRE: Nous avons consulté les bases de données CENTRAL, EMBASE, MEDLINE, PubMed et SCOPUS à la recherche d'études observationnelles et d'essais contrôlés à répartition aléatoire (ECRA) de la création à juin 2018. Deux réviseurs indépendants ont procédé à l'extraction des données en suivant un modèle préformé. SUJETS: Des adultes atteints d'insuffisance rénale ayant subi une procédure d'insertion d'un cathéter de DP. MESURES: Nous avons analysé les fuites, le dysfonctionnement et les saignements comme des complications précoces (survenant dans le mois suivant l'insertion du cathéter). Les complications infectieuses (infections au point de sortie, infections des tunnels, péritonite) ont été présentées comme complications précoces et avec la plus longue durée de suivi. MÉTHODOLOGIE: Nous avons procédé à des méta-analyses selon la méthode générique de l'inverse de la variance avec effets aléatoires pour estimer les rapports des taux combinés et les intervalles de confiance à 95 %. L'hétérogénéité a été quantifiée en utilisant la statistique I2 pour l'incohérence et a été évaluée par le test du Chi-Deux. L'analyse de sensibilité a été réalisée en retirant les études présentant un risque élevé de biais, lesquelles ont été définies à l'aide de l'échelle Newcastle-Ottawa et de l'outil Cochrane sur le risque de biais. RÉSULTATS: En tout, 24 études (22 études observationnelles, 2 ECRA) ont été sélectionnées, ce qui représente 3 108 patients et 3 777 insertions de cathéters. Les données de deux études n'ont pu être extraites et ont été évaluées qualitativement. Dans les 22 autres études, l'insertion percutanée a été associée, dans le mois suivant la procédure, à un risque plus faible d'infections au site de sortie (RR = 0,36; IC à 95 %: 0,24-0,53; I2 = 0 %) et de péritonite (RR = 0,52; IC à 95 %: 0,36-0,77; I2 = 3 %). Aucune différence dans les taux de complications mécaniques n'a été observée entre les deux techniques. LIMITES: Les résultats sont limités par le manque de cohérence dans les périodes associées aux divers résultats signalés, le risque de biais quant à la comparabilité des populations et l'incapacité d'analyser les causes individuelles du non-fonctionnement primaire (obstruction du cathéter, migration du cathéter, fuite). CONCLUSION: Notre méta-analyse suggère des différences en faveur de l'insertion percutanée par rapport à l'insertion chirurgicale pour les complications infectieuses précoces, mais aucune différence significative en ce qui concerne les complications mécaniques. Ces résultats ont des implications sur l'orientation des programmes de DP relativement à l'optimisation des ressources du bloc opératoire.

Strategies to prevent hospital readmission and death in patients with chronic heart failure, chronic obstructive pulmonary disease, and chronic kidney disease: A systematic review and meta-analysis.

BACKGROUND: Readmission following hospital discharge is common and is a major financial burden on healthcare systems. OBJECTIVES: Our objectives were to 1) identify studies describing post-discharge interventions and their efficacy with respect to reducing risk of mortality and rate of hospital readmission; and 2) identify intervention characteristics associated with efficacy. METHODS: A systematic review of the literature was performed. We searched MEDLINE, PubMed, Cochrane, EMBASE and CINAHL. Our selection criteria included randomized controlled trials comparing post-discharge interventions with usual care on rates of hospital readmission and mortality in high-risk chronic disease patient populations. We used random effects meta-analyses to estimate pooled risk ratios for all-cause and cause-specific mortality as well as all-cause and cause-specific hospitalization. RESULTS: We included 31 randomized controlled trials encompassing 9654 patients (24 studies in CHF, 4 in COPD, 1 in both CHF and COPD, 1 in CKD and 1 in an undifferentiated population). Meta-analysis showed post-discharge interventions reduced cause-specific (RR = 0.71, 95% CI = 0.63-0.80) and all cause (RR = 0.90, 95% CI = 0.81-0.99) hospitalization, all-cause (RR = 0.73, 95% CI = 0.65-0.83) and cause-specific mortality (RR = 0.68, 95% CI = 0.54-0.84) in CHF studies, and all-cause hospitalization (RR = 0.52, 95% CI = 0.32-0.83) in COPD studies. The inclusion of a cardiac nurse in the multidisciplinary team was associated with greater efficacy in reducing all-cause mortality among patients discharged after heart failure admission (HR = 0.64, 95% CI = 0.54-0.75 vs. HR = 0.87, 95% CI = 0.73-1.03). CONCLUSIONS: Post-discharge interventions reduced all-cause mortality, cause-specific mortality, and cause-specific hospitalization in CHF patients and all-cause hospitalization in COPD patients. The presence of a cardiac nurse was associated with greater efficacy in included studies. Additional research is needed on the impact of post-discharge intervention strategies in COPD and CKD patients.

Cost-Utility of Dialysis in Canada: Hemodialysis, Peritoneal Dialysis, and Nondialysis Treatment of Kidney Failure.

RATIONALE & OBJECTIVE: The kidney failure population is growing, necessitating the expansion of dialysis programs. These programs are costly and require a substantial amount of health care resources. Tools that accurately forecast resource use can aid efficient allocation. The objective of this study is to describe the development of an economic simulation model that incorporates treatment history and detailed modality transitions for patients with kidney disease using real-world data to estimate associated costs, utility, and survival by initiating modality. STUDY DESIGN: Cost-utility model with microsimulation. SETTING & POPULATION: Adult incident maintenance dialysis patients in Canada who initiated facility-based hemodialysis (HD) or home peritoneal dialysis (PD) between 2004 and 2013. INTERVENTION: HD and PD. OUTCOMES: Costs (related to dialysis, transplantation, infections, and hospitalizations), survival, utility, and dialysis modality mix over time. MODEL PERSPECTIVE & TIMEFRAME: The model took the perspective of the health care payer. Patients were followed up for 10 years from initiation of dialysis. Our cost-utility analysis compared the intervention with receiving no treatment. RESULTS: During a 10-year time horizon, the cost-utility ratio for all patients initiating dialysis was $103,779 per quality-adjusted life-year (QALY) in comparison to no treatment. Patients who initiated with facility-based HD were treated at a cost-utility ratio of $104,880/QALY and patients who initiated with home PD were treated at a cost-utility ratio of $83,762/QALY. During this time horizon, the total mean cost and QALYs per patient were estimated at $350,774 ± $204,704 and 3.38 ± 2.05) QALYs respectively. LIMITATIONS: The results do not include costs from the societal perspective. Rare patient trajectories were unable to be assessed. CONCLUSIONS: This model demonstrates that patients who initiated dialysis with PD were treated more cost-effectively than those who initiated with HD during a 10-year time horizon.