Federated machine learning in healthcare: A systematic review on clinical applications and technical architecture

Teo, Zhen Ling; Jin, Liyuan; Liu, Nan; Li, Siqi; Miao, Di; Zhang, Xiaoman; Ng, Wei Yan; Tan, Ting Fang; Lee, Deborah Meixuan; Chua, Kai Jie; Heng, John; Liu, Yong; Goh, Rick Siow Mong; Ting, Daniel Shu Wei

doi:10.1016/j.xcrm.2024.101419

Cited by 4 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random forests are an ensemble learning approach that successfully tackles the overfitting issue of single decision trees by building many decision trees during training time (Zhang et al, 2024). This technique makes it more robust and precise for predictive modeling in healthcare, giving an effective way to forecast patient outcomes in many situations, including illness progression and response to therapy based on genetic markers (Teo et al, 2024). Random forests have been effectively implemented in healthcare, making them a viable tool for healthcare practitioners and academics.…”

Section: Random Forestsmentioning

confidence: 99%

“…Balancing the potential benefits of machine learning in healthcare with ethical considerations requires a careful and considerate approach. This involves constant dialogue and engagement between healthcare professionals, patients, ethicists, technologists, and regulators to ensure that the deployment of these technologies serves the best interests of all stakeholders, especially the patients (Teo et al, 2024).…”

Section: Addressing Ethical Considerationsmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning's role in personalized medicine & treatment optimization

Deepak Kumar,

Priyanka Pramod Pawar,

Hari Gonaygunta

et al. 2024

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

The advent of machine learning in personalized medicine has revolutionized the healthcare industry by providing an enhanced diagnosis and treatment regimen to patients based on their unique characteristics such as genetic predispositions, lifestyle variables, and medical history. Machine learning algorithms can analyze vast amounts of patient data to generate accurate diagnoses, establish tailored treatment plans, and improve patient outcomes. By combining multiple data sources, machine learning algorithms can identify patterns, predict the likelihood of specific illnesses, and recommend personalized treatment options. The technology has enabled healthcare professionals to access diverse datasets, including genetic information, medical history, and lifestyle variables, and derive insights from them that were previously inaccessible. However, the isolation of user data in silos across multiple hospitals and medical institutions presents challenges for researchers working in this sector. The article examines the possible obstacles and ethical implications associated with the widespread implementation of machine learning in personalized medicine and assesses the consequences of these breakthroughs for patient care, healthcare systems, and the future of medical research.

show abstract

Section: Random Forestsmentioning

confidence: 99%

Section: Addressing Ethical Considerationsmentioning

confidence: 99%

Machine learning's role in personalized medicine & treatment optimization

Deepak Kumar,

Priyanka Pramod Pawar,

Hari Gonaygunta

et al. 2024

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

show abstract

Embryonic Machine-Deep Learning, Smart Healthcare and Privacy Deliberations in Hospital Industry: Lensing Confidentiality of Patient’s Information and Personal Data in Legal-Ethical Landscapes Projecting Futuristic Dimensions

Singh,

Kaunert

2024

Engineering Cyber-Physical Systems and Critical Infrastructures

View full text Add to dashboard Cite

Data interoperability in context: the importance of open source implementations when choosing open standards (Preprint)

Kapitan,

Heddema,

Dekker

et al. 2024

Preprint

View full text Add to dashboard Cite

UNSTRUCTURED In response to the proposal of Tsafnat et al. to converge towards three open health data standards, this viewpoint provides a critical reflection on the proposed alignment of using openEHR, FHIR and OMOP as the default standards for clinical care and administration, data exchange and longitudinal analysis, respectively. We argue that open standards are a necessary but not sufficient condition to achieve health data interoperability. The ecosystem of open source implementations needs to be considered when choosing an appropriate standard for a given context. We discuss two specific contexts, namely standardization of i) health data for federated learning, and ii) health data sharing in low- and middle income countries (LMICs). Specific design principles, practical considerations and implementation choices for these two contexts are described, based on ongoing work in both areas. In the case of federated learning, we observe convergence towards OMOP and FHIR, where the two standards can effectively be used side-by-side given the availibility of mediators between the two. In the case of health information exchanges in LMICs, we see a strong convergence towards FHIR as the primary standard, with as yet limited adoption of OMOP and openEHR. We propose practical guidelines for context-specific adaptation of open standards.

show abstract

Federated machine learning in healthcare: A systematic review on clinical applications and technical architecture

Cited by 4 publications

References 30 publications

Machine learning's role in personalized medicine & treatment optimization

Machine learning's role in personalized medicine & treatment optimization

Embryonic Machine-Deep Learning, Smart Healthcare and Privacy Deliberations in Hospital Industry: Lensing Confidentiality of Patient’s Information and Personal Data in Legal-Ethical Landscapes Projecting Futuristic Dimensions

Data interoperability in context: the importance of open source implementations when choosing open standards (Preprint)

Contact Info

Product

Resources

About