Context-Aware Support for Cardiac Health Monitoring Using Federated Machine Learning

Ogbuabor, Godwin; Augusto, Juan Carlos; Moseley, Ralph; Wyk, Aléchia van

doi:10.1007/978-3-030-91100-3_22

Cited by 8 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of the 26 studies, 17 studies addressed the challenge of expensive communication. Among them, 9 studies [ 4 , 9 , 12 , 13 , 20 , 26 , 27 , 30 , 36 ] used the FedAvg algorithm [ 8 ] to reduce communication overhead, as FedAvg [ 8 ] is frequently adopted as a method to reduce the number of required communication rounds. In addition, Xiao et al [ 37 ] proposed a system that only calculates and circulates the average weights after receiving the model weights from a certain number of connected users in order to improve communication efficiency.…”

Section: Resultsmentioning

confidence: 99%

“…Two types of data commonly used in these studies are electrocardiograms (ECGs) and electrodermal activity. Additionally, 3 other studies [19][20][21] proposed FL-based systems for cardiac health monitoring. For instance, Raza et al [21] designed an FL framework for ECG monitoring, which has the ability to effectively classify various arrhythmias.…”

Section: Applications and Type Of Data Usedmentioning

confidence: 99%

“…Other medical conditions, such as epilepsy, can also be detected through activity monitoring, with electrocorticography being used to classify patients with epilepsy [15]. Other data types, such as ECG, electrodermal activity, blood volume pulse, and body temperature, can be used to monitor stress [16][17][18], cardiac health [19][20][21], and related conditions. Skin disease or breast cancer detection often relies on the analysis of disease-related images [26][27][28].…”

Section: Applications and Type Of Data Usedmentioning

confidence: 99%

“…Remote monitoring a [4,12,13,[30][31][32][33][34][35][36][37][38] Activities of daily living [12,13] Parkinson disease [15] Epilepsy [22] Diabetes [19][20][21] Cardiac health [23] Obesity [16][17][18] Stress Diagnostic and treatment support b [9] Depression [26,27] Dermatological disease [28] Cancer [29] Perioperative complications a Remote monitoring allows individuals to self-monitor their health status and manage the progression of chronic diseases from a remote location, such as their own home. b Diagnostic and treatment support refers to the provision of assistance for the diagnosis and treatment of patients from a remote location.…”

Section: Studies Areas and Applicationsmentioning

confidence: 99%

“…Statistical heterogeneity [4,9,12,13,15,20,21,[26][27][28]30,32,[34][35][36][37][38] An increase in the number of devices participating in an FL system would result in an increase in the number of global communication rounds, as well as the size of the transmitted messages in each round (ie, communication is typically slower than local computation in FL).…”

Section: Referencesmentioning

confidence: 99%

See 4 more Smart Citations

Applications of Federated Learning in Mobile Health: Scoping Review

Wang¹,

Du²,

Gong³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background The proliferation of mobile health (mHealth) applications is partly driven by the advancements in sensing and communication technologies, as well as the integration of artificial intelligence techniques. Data collected from mHealth applications, for example, on sensor devices carried by patients, can be mined and analyzed using artificial intelligence–based solutions to facilitate remote and (near) real-time decision-making in health care settings. However, such data often sit in data silos, and patients are often concerned about the privacy implications of sharing their raw data. Federated learning (FL) is a potential solution, as it allows multiple data owners to collaboratively train a machine learning model without requiring access to each other’s raw data. Objective The goal of this scoping review is to gain an understanding of FL and its potential in dealing with sensitive and heterogeneous data in mHealth applications. Through this review, various stakeholders, such as health care providers, practitioners, and policy makers, can gain insight into the limitations and challenges associated with using FL in mHealth and make informed decisions when considering implementing FL-based solutions. Methods We conducted a scoping review following the guidelines of PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews). We searched 7 commonly used databases. The included studies were analyzed and summarized to identify the possible real-world applications and associated challenges of using FL in mHealth settings. Results A total of 1095 articles were retrieved during the database search, and 26 articles that met the inclusion criteria were included in the review. The analysis of these articles revealed 2 main application areas for FL in mHealth, that is, remote monitoring and diagnostic and treatment support. More specifically, FL was found to be commonly used for monitoring self-care ability, health status, and disease progression, as well as in diagnosis and treatment support of diseases. The review also identified several challenges (eg, expensive communication, statistical heterogeneity, and system heterogeneity) and potential solutions (eg, compression schemes, model personalization, and active sampling). Conclusions This scoping review has highlighted the potential of FL as a privacy-preserving approach in mHealth applications and identified the technical limitations associated with its use. The challenges and opportunities outlined in this review can inform the research agenda for future studies in this field, to overcome these limitations and further advance the use of FL in mHealth.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Applications and Type Of Data Usedmentioning

confidence: 99%

Section: Applications and Type Of Data Usedmentioning

confidence: 99%

Section: Studies Areas and Applicationsmentioning

confidence: 99%

Section: Referencesmentioning

confidence: 99%

See 3 more Smart Citations

Applications of Federated Learning in Mobile Health: Scoping Review

Wang¹,

Du²,

Gong³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

Federated Learning for Human Activity Recognition on the MHealth Dataset

Sanchez,

Machacuay,

Quinde

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Towards engineering higher quality intelligent environments: a multi case study approach

Santokhee,

Augusto,

Brodie

2024

Software Qual J

View full text Add to dashboard Cite

This study addresses the need to enhance the quality of Intelligent Environments, recognizing their unique characteristics and the absence of adequate guidance on quality management during development. It pursues three primary objectives: proposing a novel quality-in-use model, presenting an enhanced version of the User-Centered Intelligent Environment Development Process, and reporting on the application of these approaches through a multiple case study. To embed quality into systems, we advocate for the integration of quality characteristics from ISO/IEC 25000 standards with functional requirements. Stakeholders collaboratively define targets using measures from quality standards, and metrics enable early problem detection and resolution during development. The proposed quality-in-use model provides an insightful and objective perspective on system capabilities, guiding development and ensuring stakeholder involvement. However, challenges such as shortening development cycles for early and regular stakeholder feedback and managing an increased number of system tests were noted. Our study makes a significant contribution to the field of Intelligent Environments by providing a structured approach to embedding and managing quality throughout the development lifecycle. The multiple case study offers empirical evidence of the effectiveness of the proposed approaches, with ongoing considerations for challenges in the development process.

show abstract

Context-Aware Support for Cardiac Health Monitoring Using Federated Machine Learning

Abstract: 2021) Context-aware support for cardiac health monitoring using federated machine learning.

Cited by 8 publications

References 22 publications

Applications of Federated Learning in Mobile Health: Scoping Review

Applications of Federated Learning in Mobile Health: Scoping Review

Federated Learning for Human Activity Recognition on the MHealth Dataset

Towards engineering higher quality intelligent environments: a multi case study approach

Contact Info

Product

Resources

About