Comparing Decentralized Learning Methods for Health Data Models to Nondecentralized Alternatives: Protocol for a Systematic Review.

BACKGROUND: Considering the soaring health-related costs directed toward a growing, aging, and comorbid population, the health sector needs effective data-driven interventions while managing rising care costs. While health interventions using data mining have become more robust and adopted, they often demand high-quality big data. However, growing privacy concerns have hindered large-scale data sharing. In parallel, recently introduced legal instruments require complex implementations, especially when it comes to biomedical data. New privacy-preserving technologies, such as decentralized learning, make it possible to create health models without mobilizing data sets by using distributed computation principles. Several multinational partnerships, including a recent agreement between the United States and the European Union, are adopting these techniques for next-generation data science. While these approaches are promising, there is no clear and robust evidence synthesis of health care applications. OBJECTIVE: The main aim is to compare the performance among health data models (eg, automated diagnosis and mortality prediction) developed using decentralized learning approaches (eg, federated and blockchain) to those using centralized or local methods. Secondary aims are comparing the privacy compromise and resource use among model architectures. METHODS: We will conduct a systematic review using the first-ever registered research protocol for this topic following a robust search methodology, including several biomedical and computational databases. This work will compare health data models differing in development architecture, grouping them according to their clinical applications. For reporting purposes, a PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 flow diagram will be presented. CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies)-based forms will be used for data extraction and to assess the risk of bias, alongside PROBAST (Prediction Model Risk of Bias Assessment Tool). All effect measures in the original studies will be reported. RESULTS: The queries and data extractions are expected to start on February 28, 2023, and end by July 31, 2023. The research protocol was registered with PROSPERO, under the number 393126, on February 3, 2023. With this protocol, we detail how we will conduct the systematic review. With that study, we aim to summarize the progress and findings from state-of-the-art decentralized learning models in health care in comparison to their local and centralized counterparts. Results are expected to clarify the consensuses and heterogeneities reported and help guide the research and development of new robust and sustainable applications to address the health data privacy problem, with applicability in real-world settings. CONCLUSIONS: We expect to clearly present the status quo of these privacy-preserving technologies in health care. With this robust synthesis of the currently available scientific evidence, the review will inform health technology assessment and evidence-based decisions, from health professionals, data scientists, and policy makers alike. Importantly, it should also guide the development and application of new tools in service of patients' privacy and future research. TRIAL REGISTRATION: PROSPERO 393126; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=393126. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/45823.

Secur-e-Health Project: Towards Federated Learning for Smart Pediatric Care.

The application of machine learning (ML) algorithms to electronic health records (EHR) data allows the achievement of data-driven insights on various clinical problems and the development of clinical decision support (CDS) systems to improve patient care. However, data governance and privacy barriers hinder the use of data from multiple sources, especially in the medical field due to the sensitivity of data. Federated learning (FL) is an attractive data privacy-preserving solution in this context by enabling the training of ML models with data from multiple sources without any data sharing, using distributed remotely hosted datasets. The Secur-e-Health project aims at developing a solution in terms of CDS tools encompassing FL predictive models and recommendation systems. This tool may be especially useful in Pediatrics due to the increasing demands on Pediatric services, and the current scarcity of ML applications in this field compared to adult care. Herein we provide a description of the technical solution proposed in this project for three specific pediatric clinical problems: childhood obesity management, pilonidal cyst post-surgical care and retinography imaging analysis.

Untangling Absorption Mechanisms and Variability in Bioequivalence Studies Using Population Analysis.

PURPOSE: Both inter-individual (IIV) and inter-occasion (IOV) variabilities are observed in bioequivalence studies. High IOV may be a cause of problems on the demonstration of bioequivalence, despite strict measures are taken to control it. The objective of this study is to investigate further means of controlling IIV by optimizing study design of crossover studies. METHODS: Data from 18 bioequivalence studies were used to develop population pharmacokinetics (popPK) models to characterize the absorption and disposition processes of 14 drugs, to estimate IOV for each drug substance and to evaluate possible correlations with biopharmaceutical properties of drug substances, classified in accordance to the Biopharmaceutics Drug Disposition Classification System (BDDCS). RESULTS: Plasma-pharmacokinetics profiles for the 14 drugs analyzed were successfully described using popPK. The pharmacokinetic parameters that showed greater variability were first-order rate constant of absorption, duration of the zero-order absorption process, relative bioavailability and time of latency. ISCV% estimated for Cmax seems to correlate with the log-Dose-Number for Class 1, 2 and 3, despite no direct correlation was observed between popPK model residual variability (RUV) and ISCV%. Nevertheless, higher RUV estimates were observed for Class 2 drugs in comparison to Class 1 and 3. CONCLUSION: Pharmacokinetic parameters related to drug absorption showed greater variability. Ingestion of the IMP along with 240 mL of water showed to standardize gastric emptying. Given the dependency between Cmax variability and dose-solubility ratio, for classes 2 and 4, ad libitum water intake may increase Cmax and AUC ISCV%. A water ingestion standardization until the expected Tmax of the drug is suggested.