SEARCH · PubMed Health

Results for “Federated Learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

15 recordsLinked to original sources

PubMed2026

Fedflow: cloud orchestration for federated learning with the FeatureCloud platform.

MOTIVATION: Federated learning (FL) enables collaborative model training on geographically distributed genomic and clinical datasets while complying with data privacy laws and regulatory constraints. FeatureCloud is an existing platform for FL that provides an accessible web-based interface and a large repository of implemented methods. However, due to its graphical interface, FeatureCloud requires manual interaction of all participants, limiting automation, iteration, and reproducibility. RESULTS: We introduce fedflow, a Python-based command-line tool for headless orchestration of FL tasks with FeatureCloud. This tool uses distributed computing resources such as virtual machines or cloud instances to automate such workflows. This allows for scalable federated computing either in local simulations or deployed in a trusted environment. Further, we demonstrate how fedflow can be used to integrate FeatureCloud in reproducible Snakemake workflows. For this, we reanalyse a metagenomic dataset with two federated algorithms and compare the results to the centralized approach with pooled data. Overall, fedflow enables automation of multi-client FL tasks, facilitates embedding of FeatureCloud in standard bioinformatics pipelines and thereby helps increase reproducibility. AVAILABILITY: Fedflow is open-source and available at https://github.com/W-L/fedflow.

Journal Article↗

PubMed2025

Federated learning for the pathogenicity annotation of genetic variants in multi-site clinical settings.

MOTIVATION: Rare diseases collectively affect 5% of the population. However, fewer than 50% of rare disease patients receive a molecular diagnosis after whole genome sequencing. Supervised machine learning is a valuable approach for the pathogenicity scoring of human genetic variants. However, existing methods are often trained on curated but limited central repositories, resulting in poor accuracy when tested on external cohorts. Yet, large collections of variants generated at hospitals and research institutions remain inaccessible to machine-learning purposes because of privacy and legal constraints. Federated learning (FL) algorithms have been recently developed enabling institutions to collaboratively train models without sharing their local datasets. RESULTS: Here, we present a proof-of-concept study evaluating the effectiveness of FL for the clinical classification of genetic variants. A comprehensive array of diverse FL strategies was assessed for coding and non-coding Single Nucleotide Variants as well as Copy Number Variants. Our results showed that federated models generally achieved comparable or superior performance to traditional centralized learning. In addition, federated models reached a robust generalization to independent sets with smaller data fractions as compared to their centralized model counterparts. Our findings support the adoption of FL to establish secure multi-institutional collaborations in human variant interpretation. AVAILABILITY AND IMPLEMENTATION: All source code required to reproduce the results presented in this article, implemented in Python, is available under the GNU General Public License v3 at https://github.com/RausellLab/FedLearnVar.

Humans↗

PubMed2026

PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning.

Non-identically distributed data is a major challenge in Federated Learning (FL). Personalized FL tackles this by balancing local model adaptation with global model consistency. One variant, partial FL, leverages the observation that early layers learn more transferable features by federating only early layers. However, current partial FL approaches use predetermined, architecture-specific rules to select layers, limiting their applicability. We introduce Principled Layer-wise-FL (PLayer-FL), which uses a novel federation sensitivity metric to identify layers that benefit from federation. This metric, inspired by model pruning, quantifies each layer's contribution to cross-client generalization after the first training epoch, identifying a transition point in the network where the benefits of federation diminish. We first demonstrate that our federation sensitivity metric shows strong correlation with established generalization measures across diverse architectures. Next, we show that PLayer-FL outperforms existing FL algorithms on a range of tasks, also achieving more uniform performance improvements across clients.

Journal Article↗

PubMed2026

Safeguarding biomedical AI: a critical scoping review of privacy-enhancing technologies, hybrid approaches, and deployment models.

BACKGROUND: Biomedical artificial intelligence (AI) requires the integration of privacy-enhancing technologies (PETs) to safeguard sensitive clinical, imaging, and genomic data while preserving analytical utility. OBJECTIVES: This review critically and systematically maps applications of PETs across the biomedical AI lifecycle in accordance with PRISMA-ScR guidelines and evaluates their technical trade-offs, deployment feasibility, and residual risks. METHODS: We systematically searched PubMed, IEEE Xplore, ACM Digital Library, and Scopus for studies published between 2015 and 2025. Eligible studies addressed differential privacy, federated learning, secure multiparty computation, homomorphic encryption, or hybrid approaches in biomedical AI. Data were charted on PET type, modality, lifecycle stage, utility metrics, privacy parameters, and deployment considerations. A critical appraisal rubric assessed threat-model adequacy, methodological clarity, reproducibility, privacy-utility transparency, and deployment realism. Additionally, we hand-searched major venues (USENIX Security, NeurIPS, AAAI) and screened Google Scholar for grey literature, applying de-duplication across sources. RESULTS: We identified 87 studies spanning clinical decision support, genomics, and medical imaging. From 25,761 initial records, 3,754 underwent title/abstract screening and 1,968 underwent full-text assessment. PETs demonstrated distinct strengths and limitations: differential privacy provided provable guarantees but reduced performance on imbalanced data; federated learning improved data access but remained vulnerable to gradient leakage; and cryptographic methods ensured confidentiality at high computational cost. Synthetic data generation supported privacy-conscious data sharing and benchmarking but remained sensitive to disclosure risk, fidelity loss, and subgroup representation. Hybrid and emerging approaches, including trusted execution environments, zero-knowledge proofs, and privacy-preserving transformer architectures, mitigated composability gaps yet lacked full end-to-end assurance. Case studies at hospital and biobank scale illustrated practical feasibility and infrastructure demands. CONCLUSIONS: Situating PETs within technical and operational contexts clarifies their capabilities, limitations, and deployment challenges. Residual risks persist, including fairness concerns, inference-time leakage, and overreliance on PETs as compliance proxies. Sustained technical innovation and institutional governance remain essential for the trustworthy integration of PETs in biomedical AI.

biomedical AI↗

PubMed2026

The Continuity Trap in Data Science Health Research.

Secondary use is now the ordinary condition of data science health research rather than an exception to it. Electronic health records collected for clinical care become prediction tools and inputs for generative AI; imaging archives become foundation-model corpora; genomic datasets become resources for polygenic risk scores; and legacy biospecimens become renewable, indefinitely distributable cell lines. Governance has responded by emphasizing verifiable instruments such as provenance logs, repository approvals, broad-consent forms, data-use agreements, model cards, records of processing, and locality-preserving architectures. These instruments are necessary, and they answer real questions about lineage, privacy, institutional responsibility, and accountability, but they are not sufficient to establish that a present use remains ethically justified. We define ethical continuity as the persistence of normatively relevant relationships between the original conditions of data generation or material collection and subsequent downstream uses, such that current uses remain justifiable in light of the expectations, permissions, meanings, and relational obligations present at entrustment. We then define the Continuity Trap as a review-stage governance error in which a salient signal of continuity in one domain is treated as sufficient evidence of ethical continuity overall, causing inquiry into the remaining domains to close prematurely. The trap is not ordinary noncompliance, ethics creep, or a demand for universal rereview; it is a cross-domain inference error that can arise even in careful, good-faith review. We distinguish it from proxy closure, of which it is a continuity-specific subtype, and from Goodhart's and Campbell's laws, which describe how measures degrade once they become targets. We operationalize ethical continuity across 4 domains: provenance, semantics, authorization, and relational standing, developed in our Representational Veracity framework, and we show that these domains can diverge as data are linked, transformed, modeled, and redeployed. We identify the institutional mechanisms-provenance privilege, descriptor sedimentation, authorization fossilization, and community effacement-that cause auditable signals to be overread, and we examine how the US Health Insurance Portability and Accountability Act (HIPAA) of 1996, the General Data Protection Regulation, the European Health Data Space, US Food and Drug Administration guidance, the US National Institute of Standards and Technology (NIST) AI Risk Management Framework, and federated-learning governance can reduce risk while still inducing continuity traps. We apply the framework to consent and nonconsent settings, including public health, immunization, syndromic, and wastewater surveillance, polygenic risk scores, induced pluripotent stem cells, federated learning, and health-related large language models. The policy implication is trigger-based continuity review: rather than rereviewing every reuse, investigators and reviewers should identify the weakest continuity domain at the present data stage and impose a domain-matched safeguard, recorded in a short continuity statement. This reframing is intended for the committees, repositories, funders, and governance bodies that decide whether reuse may proceed, and it matters most in cross-border and low-resource settings. Provenance should begin ethical review; it should not end it.

Data Science↗

PubMed2026

Artificial Intelligence and Machine Learning Applications in Fibromuscular Dysplasia: Transforming Diagnosis, Risk Stratification, and Clinical Decision-Making.

Fibromuscular dysplasia (FMD) is a non-atherosclerotic vascular disorder with heterogeneous presentations, making diagnosis and management highly dependent on imaging and clinical expertise. This narrative review examines how artificial intelligence (AI) and machine learning (ML) are transforming FMD care. AI-enhanced imaging, particularly convolutional neural network-based analysis, improves detection of the characteristic "string-of-beads" pattern on CT angiography, magnetic resonance angiography, and ultrasound, although FMD-specific validation remains limited. ML models facilitate risk stratification, prediction of disease progression, and early identification of complications such as aneurysms and stroke by integrating clinical, imaging, and genomic data. AI-driven clinical decision support systems further enable personalized treatment selection through pharmacogenomic insights and robot-assisted interventions. Despite promising real-world applications, challenges persist, including limited large-scale datasets, workflow integration, regulatory barriers, and algorithmic bias affecting underrepresented populations. Future advances in explainable AI, federated learning, and digital health integration may enable a shift toward predictive, patient-centered FMD management.

Humans↗

PubMed2026

dGAMLSS: an exact, distributed algorithm to fit Generalized Additive Models for Location, Scale, and Shape for privacy-preserving population reference charts.

MOTIVATION: There is growing interest in estimating population reference ranges across age and sex to better identify atypical clinically-relevant measurements throughout the lifespan. For this task, the World Health Organization recommends using Generalized Additive Models for Location, Scale, and Shape (GAMLSS), which can model non-linear growth trajectories under complex distributions that address the heterogeneity in human populations.Fitting GAMLSS models requires large, generalizable sample sizes, especially for accurate estimation of extreme quantiles, but obtaining such multi-site data can be challenging due to privacy concerns and practical considerations. In settings where patient data cannot be shared, privacy-preserving distributed algorithms for federated learning can be used, but no such algorithm exists for GAMLSS. RESULTS: We propose distributed GAMLSS (dGAMLSS), a distributed algorithm that can fit GAMLSS models across multiple sites without sharing patient-level data. This includes specific considerations for the fitting of smooth functions at varying levels of communication efficiency. We demonstrate the effectiveness of dGAMLSS in constructing population reference charts across clinical, genomics, and neuroimaging settings and show that dGAMLSS is able to reproduce pooled reference charts and inference down to numerical differences. AVAILABILITY AND IMPLEMENTATION: An R package providing examples of the dGAMLSS algorithm, as well as functions for sharing and aggregating site-specific parameters, is available at https://github.com/hufengling/dGAMLSS.

Algorithms↗

PubMed2026

Multimodal artificial intelligence and machine learning in oncology: from data integration to precision cancer care.

Cancer remains a major global health burden, with approximately 20 million new cases and 9.7 million cancer-related deaths reported globally in 2022. While advances in radiological imaging, molecular profiling, and clinical data have enhanced the interpretation of disease progression, the availability of multiple such modalities still does not meet the needs of a large patient population. This narrative review focuses on the role of multimodal artificial intelligence and machine learning in bridging the gap in interpreting heterogeneous modalities to improve risk prediction, prognostic assessment, and treatment decision-making in precision oncology. Multimodal frameworks such as Pathomic Fusion illustrate how complementary histopathological and genomic information can be integrated for cancer diagnosis and prognostic modeling. Multimodal models have demonstrated potential in virtual biopsy, cancer screening, prognostic prediction, radiotherapy planning, intraoperative guidance, and clinical-trial design using digital twins and synthetic control arms. The major limitations of incorporating multimodal artificial intelligence and machine learning in oncology include data heterogeneity, demographic or institutional biases, and reproducibility challenges that hinder translation. Accordingly, appropriate data-governance strategies, fairness audits, and privacy-preserving approaches such as federated learning should be considered where appropriate. Future progress will depend on the development of standardized benchmarking datasets, robust external validation, seamless integration with electronic health records and picture archiving and communication systems, and the implementation of explainable, secure, and clinically validated multimodal artificial intelligence frameworks that support precision oncology in routine clinical practice.

deep learning↗

PubMed2026

Biological Foundation Models for Complex Disease Research and Clinical Translation.

Complex diseases, including cancer, rare genetic disorders, neurodevelopmental and psychiatric conditions, and neurodegenerative diseases, arise from interactions among genetic variation, gene regulation, and cellular states that are difficult to capture using a single data type or biological scale. Biological foundation models address this challenge by treating nucleotides and genes as tokens and learning representations that can be transferred to downstream biomedical and clinical tasks. In this review, we examine two major model classes, genomic sequence foundation models and cell foundation models, and compare their tokenization strategies, model architectures, pretraining objectives, and adaptation methods. We summarize their emerging applications in regulatory variant interpretation, disease-associated cell-state analysis, drug-response prediction, and therapeutic target discovery across complex diseases. We distinguish applications supported by experimental or retrospective validation from those that remain primarily computational or conceptual. We further discuss key challenges to clinical translation, including multimodal data integration, model interpretability, benchmarking, patient-specific prediction, and privacy protection. We highlight future opportunities to integrate biological foundation models with emerging frameworks of medical digital twins, agentic AI, and federated learning. By linking model design to translational goals, this review provides a practical framework for evaluating biological foundation models and their readiness for complex disease research and clinical use.

biological foundation model↗

PubMed2026

AI-Driven Precision Medicine in Alzheimer's Disease: Drug Repurposing, Digital Therapeutics and Clinical Decision Support.

Alzheimer's Disease (AD) is a neurodegenerative disease that causes significant clinical, social, and economic burden worldwide. Despite improvements in understanding its multifaceted pathogenesis, current treatments are mostly symptomatic and ineffective across varied patient populations. To overcome these constraints, AI-driven precision medicine allows tailored risk assessment, treatment selection, and disease monitoring. This review covers AI's role in AD precision medicine, focusing on drug repurposing, digital therapies and clinical decision support systems. Machine and deep learning models are used to predict medication response, integrate heterogeneous data sources such as genomics, transcriptomics, neuroimaging and electronic health records, and uncover pharmacogenomic treatment success factors. The paper covers AIenabled precision pharmacology, including tailored dosing algorithms, adaptive therapeutic monitoring, and adverse drug reaction prediction. Bioinformatics-based target identification, network pharmacology, graphbased AI models, virtual screening, and real-world and clinical data validation are emphasized in AI-driven medication repurposing. AI-powered digital treatments like personalized cognitive training platforms, wearable- derived digital biomarkers, virtual and mixed reality interventions, adherence monitoring, and digital twins for therapy optimization have been discussed. AI-based clinical decision support systems are also thoroughly assessed for clinical value, accuracy, and explainability in disease subtyping, trajectory prediction, and risk stratification in preclinical and prodromal AD. Despite these promises, data heterogeneity, algorithmic bias, legal barriers, and privacy concerns exist. Federated learning enables safe multi-center collaboration and hybrid AI-human approaches, and it represents the future. AI's ability to alter AD care opens the door to precision medicine paradigms that use repurposed medications, digital tools and intelligent decision-making to improve patient outcomes.

Alzheimer’s disease↗

PubMed2026

Decoding the spatiotemporal patterns of food spoilage microbial communities: Integrating multi-omics and artificial intelligence to enable precision preservation.

In the global food supply chain, food wastage caused by spoilage has resulted in significant economic losses, food shortages, and environmental pressure. This process is fundamentally driven by the spatiotemporal dynamics of microbial communities. However, traditional research methods struggle to elucidate the complex mechanisms of spatial heterogeneity, interspecies interactions, and functional succession. This limits the development of effective preservation strategies. This review systematically reviews the cutting-edge progress of integrating multi-omics technologies and artificial intelligence (AI) to study food spoilage microbial communities, breaking through this bottleneck. We propose an intelligent theoretical framework that could potentially analyze microbial metabolic activities and predict dynamic shelf life if implemented. The conceptual framework integrates multidimensional data, including spatial metabolomics, temporal metatranscriptomics, single-cell transcriptomics, and longitudinal metagenomics. It can also be combined with AI models, such as graph neural networks. The article elaborates on the principles and applications of spatio-temporal monitoring technologies, such as nano secondary ion mass spectrometry, hyperspectral imaging, and the Internet of Things sensing. Through illustrative cases of typical perishable foods, it also explores how such a multi-omics - AI system might be applied to spoilage warning and precise intervention. Additionally, the article addresses the current challenges in data coverage, model generalization, and federated learning implementation. Then the research further explores emerging areas such as engineered probiotics, edge AI, and microfluidic sensing. These areas are targeted at transforming food preservation from an empirical control approach to a data-driven, precise regulatory framework. This transformation provides theoretical support and technical approaches for developing a smart, sustainable food preservation system.

Multiomics↗

PubMed2026

Decoding cancer with artificial intelligence: Transforming research, diagnosis, and therapy with future insights.

Cancer remains one of the leading global health burdens, with increasing complexity in genomic, imaging, and clinical datasets presenting significant challenges for effective management. Artificial intelligence (AI) has emerged as a powerful tool to address these challenges by enabling pattern recognition, knowledge integration, and data-driven decision-making. This review highlights recent advances in the application of AI across cancer research, diagnosis, and therapy. In research, AI accelerates drug discovery and repurposing, enhances genomic data interpretation, and facilitates biomarker identification through multi-omics integration. In diagnosis, AI has demonstrated high technical performance in radiology for lesion detection and image segmentation, in pathology for tumour grading and molecular prediction, and in liquid biopsy for non-invasive biomarker analysis. In therapy, AI supports precision medicine by predicting treatment responses, monitoring disease progression, and optimizing clinical trial design. Despite these advances, barriers such as data heterogeneity, algorithmic bias, interpretability, and regulatory challenges remain. Future directions, including explainable AI, federated learning, multimodal modelling, and digital twins, hold promise for translating AI-driven innovations into routine oncology practice. Significance Statement This review provides a timely synthesis of recent (2020-2025) advances in artificial intelligence across cancer research, diagnosis, and therapy, highlighting applications in drug discovery, genomics, multi-omics biomarker identification, and clinical decision-making. By integrating technological progress with translational and clinical relevance, this work serves as a valuable resource for bridging AI innovation with precision oncology practice. As a narrative review, the literature was identified through targeted PubMed, Scopus, and Google Scholar searches, combining terms for artificial intelligence, machine learning, and deep learning with cancer-related keywords, with priority given to peer-reviewed studies published between 2020 and 2025, seminal earlier works, and official regulatory or guideline documents. Within each domain, representative studies were selected to illustrate methodological diversity, clinical context, and current translational readiness rather than to provide exhaustive coverage of an extremely rapidly evolving field.

Artificial intelligence↗

PubMed2026

Secure bioinformatics: privacy-preserving federated analytics using homomorphic encryption.

MOTIVATION: Large-scale bioinformatics analyses increasingly require collaboration across multiple cohorts and institutions, yet existing workflows often rely on data co-localization, which is slow, difficult to scale, and raises privacy concerns. We present a privacy-preserving federated analytics framework that enables secure statistical analysis across distributed datasets without transferring raw data, by performing all computations on encrypted data via cryptographic methods. RESULTS: We evaluate the framework by validating polygenic risk scores and conducting meta-analyses on two real-world cohorts. The proposed solution achieves over 99.9% accuracy relative to plaintext analyses, while maintaining scalable runtime performance with increasing data size and number of participating sites. These results demonstrate the feasibility of secure federated analytics for practical bioinformatics applications involving sensitive data.

Computational Biology↗

PubMed2026

From the establishment of a national bioinformatics society to the development of a national bioinformatics infrastructure.

We describe the evolution of a bioinformatics national capacity from scattered professionals into a collaborative organisation, and advancements in the adoption of the bioinformatics infrastructure philosophy by the national community. The Romanian Society of Bioinformatics (RSBI), a national professional society, was founded in 2019 to accelerate the development of Romanian bioinformatics. Incrementally, RSBI expanded its role to include: i) developing a community and engaging the public and stakeholders, ii) a national training approach, including through increased interactions with European training resources, and iii) advocating national participation in European bioinformatics infrastructures. In a next step RSBI led the development of the national bioinformatics infrastructure, the Romanian Bioinformatics Cluster (CRB) with the mission to act as an ELIXIR National Node. In this paper we report both the successful projects in training, public engagement, and policy projects, as well as initiatives related to data federation that, while not successful, can serve as valuable learning experiences for future implementations. We explain CRB's structure and the role such an entity can play in the national bioinformatics infrastructure for data, tools, and training. Finally, we offer insights into the evolving role of the bioinformatics professional society and the synergies and interactions with the forthcoming National ELIXIR Node.

Computational Biology↗

PubMed2026

Ethical Governance of Open Data Across Biomedical Research, Healthcare, and Public Health: Privacy, Equity, Trust, and Controlled Access.

Open data has become central to biomedical research and public health, but health information is uniquely sensitive and difficult to share responsibly. In this narrative review, open data is considered as a spectrum of health-data sharing arrangements, ranging from public aggregate datasets to controlled-access repositories, federated analysis, and synthetic data. This narrative review synthesizes the scientific and societal rationale for greater openness with the ethical, legal, and governance constraints that shape what "open" can realistically mean in healthcare. We examine how data sharing supports reproducibility, machine learning, and more efficient research, while also enabling public health surveillance and learning health systems. Against these benefits, we analyze privacy and re-identification risks, consent challenges in large-scale secondary use, inequities including data colonialism, and tensions introduced by commercialization. We integrate lessons from prominent case examples spanning pandemic data sharing, genomic initiatives, population registries, patient-led rare disease infrastructures, and regional data spaces. Across these domains, experience suggests that durable progress depends less on unrestricted openness than on calibrated access, privacy-preserving architectures, clear accountability, and sustained public engagement. We conclude by proposing a pragmatic ethical orientation for healthcare open data: treat openness as a spectrum of controlled sharing arrangements, embed equity and reciprocity into governance, and institutionalize trust-building measures that can persist beyond emergencies and political cycles.

Data colonialism↗