BackgroundOn the basis of previous analyses of the incidence of urinary incontinence (UI) after radical prostatectomy (RP), the hospital RP volume threshold in the Netherlands was gradually... Show moreBackgroundOn the basis of previous analyses of the incidence of urinary incontinence (UI) after radical prostatectomy (RP), the hospital RP volume threshold in the Netherlands was gradually increased from 20 per year in 2017, to 50 in 2018 and 100 from 2019 onwards.ObjectiveTo evaluate the impact of hospital RP volumes on the incidence and risk of UI after RP (RP-UI).Design, setting, and participantsPatients who underwent RP during 2016–2020 were identified in the claims database of the largest health insurance company in the Netherlands. Incontinence was defined as an insurance claim for ≥1 pads/d.Outcome measurements and statistical analysisThe relationship between hospital RP volume (HV) and RP-UI was assessed via multivariable analysis adjusted for age, comorbidity, postoperative radiotherapy, and lymph node dissection.Results and limitationsRP-UI incidence nationwide and by RP volume category did not decrease significantly during the study period, and 5-yr RP-UI rates varied greatly among hospitals (19–85%). However, low-volume hospitals (≤120 RPs/yr) had a higher percentage of patients with RP-UI and higher variation in comparison to high-volume hospitals (>120 RPs/yr). In comparison to hospitals with low RP volumes throughout the study period, the risk of RP-UI was 29% lower in hospitals shifting from the low-volume to the high-volume category (>120 RPs/yr) and 52% lower in hospitals with a high RP volume throughout the study period (>120 RPs/yr for 5 yr).ConclusionsA focus on increasing hospital RP volumes alone does not seem to be sufficient to reduce the incidence of RP-UI, at least in the short term. Measurement of outcomes, preferably per surgeon, and the introduction of quality assurance programs are recommended.Patient summaryIn the Netherlands, centralization of surgery to remove the prostate (RP) because of cancer has not yet improved the occurrence of urinary incontinence (UI) after surgery. Hospitals performing more than 120 RP operations per year had better UI outcomes. However, there was a big difference in UI outcomes between hospitals. Show less
Egmond, M.B. van; Spini, G.; Galien, O. van der; IJpma, A.; Veugen, T.; Kraaij, W.; ... ; Kooij-Janic, M. 2021
Background Recent developments in machine learning have shown its potential impact for clinical use such as risk prediction, prognosis, and treatment selection. However, relevant data are often... Show moreBackground Recent developments in machine learning have shown its potential impact for clinical use such as risk prediction, prognosis, and treatment selection. However, relevant data are often scattered across different stakeholders and their use is regulated, e.g. by GDPR or HIPAA. As a concrete use-case, hospital Erasmus MC and health insurance company Achmea have data on individuals in the city of Rotterdam, which would in theory enable them to train a regression model in order to identify high-impact lifestyle factors for heart failure. However, privacy and confidentiality concerns make it unfeasible to exchange these data. Methods This article describes a solution where vertically-partitioned synthetic data of Achmea and of Erasmus MC are combined using Secure Multi-Party Computation. First, a secure inner join protocol takes place to securely determine the identifiers of the patients that are represented in both datasets. Then, a secure Lasso Regression model is trained on the securely combined data. The involved parties thus obtain the prediction model but no further information on the input data of the other parties. Results We implement our secure solution and describe its performance and scalability: we can train a prediction model on two datasets with 5000 records each and a total of 30 features in less than one hour, with a minimal difference from the results of standard (non-secure) methods. Conclusions This article shows that it is possible to combine datasets and train a Lasso regression model on this combination in a secure way. Such a solution thus further expands the potential of privacy-preserving data analysis in the medical domain. Show less