Federated Learning for the Healthcare Metaverse: Concepts, Applications, Challenges, and Future Directions

Victor, Nancy; Bhattacharya, Sweta; Huynh‐The, Thien; Chengoden, Rajeswari; Yenduri, Gokul; Maddikunta, Praveen Kumar Reddy; Pham, Quoc-Viet; Gadekallu, Thippa Reddy; Liyanage, Madhusanka

doi:10.1109/jiot.2023.3304790

Cited by 27 publications

(6 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fifth largest cluster, #4, comprises 8 members with a silhouette value of 0.714 and is labeled as "federated learning" by LLR. The major citing article within this cluster is on federated learning for the healthcare metaverse by Bashir, Ak (2023.0-JAN) [9]. The most cited members within this cluster are from the Russian Federation (25), India (25), and Ireland (7).…”

Section: Country Collaboration Analysis Of Digital Twin For Educationmentioning

confidence: 99%

See 1 more Smart Citation

Scientometric Insights of Digital Twins in Industry 4.0

Kaur,

Bhatia

2024

Preprint

View full text Add to dashboard Cite

Industry 4.0 is a new era of digitization that integrates digital technologies to create smart, interconnected production systems, marking a paradigm shift in different domains. One of the key technologies in this era is 'Digital Twin', which offers virtual representations of physical assets and processes. It is crucial to analyze the role of digital twin technology in the context of Industry 4.0 using scientometric analysis with citeSpace, a powerful tool for visualizing and analyzing citation networks. This research focuses on the growth trajectory of digital twin literature, identifies influential authors, institutions, and journals, and analyzes the geographical distribution of research contributions from the Scopus database for 2018-2024. The findings reveal insights into the current state of digital twin research, its impact on Industry 4.0, and opportunities for future exploration and collaboration in this rapidly evolving field.

show abstract

Section: Country Collaboration Analysis Of Digital Twin For Educationmentioning

confidence: 99%

“…The most cited members within this cluster are from the United States(65), Australia (14), and Norway (9). The fifth largest cluster, #4, comprises 8 members with a silhouette value of 0.714 and is labeled as "federated learning" by LLR.…”

Section: Country Collaboration Analysis Of Digital Twin For Educationmentioning

confidence: 99%

Scientometric Insights of Digital Twins in Industry 4.0

Kaur,

Bhatia

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The combination of data mining [11], Internet of Things (IoT) [12], and Machine Learning (ML) [13] represents a potential solution for addressing various problems. Medical data is difficult to analyze due to its sheer size and enormous feature set [14].…”

Section: Related Workmentioning

confidence: 99%

Improving Healthcare Prediction of Diabetic Patients Using KNN Imputed Features and Tri-Ensemble Model

Alnowaiser

2024

IEEE Access

View full text Add to dashboard Cite

Objective: Diabetes ranks as the most prevalent ailment in developing nations. Vital steps to mitigate the consequences of diabetes include early detection and expert medical intervention. A highly effective approach for identifying diabetes involves assessing the specific indicators associated with this condition. When it comes to automated diabetes detection, frequently encountered datasets frequently exhibit gaps in data, which can markedly impact the effectiveness of machine learning models. Methods: The aim of this study is to propose an automated method for predicting diabetes, with a focus on appropriately dealing with missing data and improving accuracy. The proposed framework makes use of K-Nearest Neighbour (KNN) imputed features along with a Tri-ensemble voting classifier model. Results:By incorporating the KNN imputer, the presented model demonstrates impressive performance metrics, including an accuracy of 97.49%, precision of 98.16%, recall of 99.35%, and an F1 score of 98.84%. The study conducted a thorough comparison of this proposed model against seven alternative machine learning algorithms, assessing them under two conditions: one with omitted missing values and another with the KNN imputer applied. These findings support the proposed model's efficacy, highlighting its superiority over currently established state-of-the-art techniques. Conclusion: This research explores the problem of missing data in diabetes diagnosis and highlights the efficacy of the KNN-imputed technique. The results are promising for healthcare practitioners as they could facilitate early detection and improve the quality of diabetic patient care.

show abstract

“…Because the operation is performed in a virtual space, the doctor has the opportunity of trial and error. Namely, the doctor can evaluate the operation time, occurrence rate of complication and radiation exposure of different plans, and modify the plan based on the evaluation [37] .…”

Section: Civilitymentioning

confidence: 99%

Metaverse for Healthcare: Technologies, Challenges, and Vision

Yang,

Zhou,

et al. 2023

Int. J. Crowd Sci.

View full text Add to dashboard Cite

The continuous enhancement of living conditions imposes higher requirements for medical and healthcare services. Although improved to a certain extent, there still exist critical challenges in current medical pattern, such as the shortage of medical resources, inefficient medical treatment, and limited medical technology level. The metaverse can offer a novel mechanism to address these problems in traditional healthcare domain, and thus, to enhance the quality of medical services. Generally, the metaverse is a dynamic feedback system that facilitates the collaboration and coexistence between the virtual and physical worlds. By fostering collaboration and evolution between intelligent agents in the virtual world, knowledge of this interdependence can be reconstructed in the digital realm. This allows problems existed in the real world to be abstracted and represented in the digital space, where models can be established and computational experiments can be conducted. The outcomes obtained can dynamically guide or control the execution of strategies in the real world, with real-world execution results serving as dynamic data inputs to continually update the virtual world's model. In addition, this paper summarizes the current research status of different healthcare application scenarios for metaverse, highlights the challenges and vision, and aims to inspire further research in this field. KEYWORDSmetaverse; healthcare; application scenario; key technologies; challenges; vision T he continuous enhancement of living conditions has expedited novel and urgent requirements for medical and healthcare service industry. The realistic demands for the healthcare service industry have become higher and more diverse [1] . Although improved to a certain extent, there still exist critical challenges in current medical patterns. From a social perspective, firstly, there is a shortage of medical resources. In fact, overall medical resources are in short supply. For instance, the medical treatment is inefficient, and thus, the coverage of chronic disease diagnosis and treatment management is relatively low at this stage [2] . Secondly, the level of medical technology is limited. Specifically, the distribution of medical resources is uneven in different regions, and there are variations in medical technology and capabilities, which needs more perfect technology platforms and patterns to enhance the overall level [3] . Thirdly, the pressure on cost control is huge, especially the cost control of medical insurance funds is hard, which requires technical means to improve medical efficiency and reduce the waste of medical resources [4] . From an individual perspective, firstly, the communication between doctors and patients is relatively inefficient. In fact, it is not easy and straightforward for patients and their family members to understand the principles of the disease and the surgical process, which makes them fear the operation and have low compliance with the treatment [5] . Secondly, the surgical accuracy and safety need to be...

show abstract

Federated Learning for the Healthcare Metaverse: Concepts, Applications, Challenges, and Future Directions

Cited by 27 publications

References 102 publications

Scientometric Insights of Digital Twins in Industry 4.0

Scientometric Insights of Digital Twins in Industry 4.0

Improving Healthcare Prediction of Diabetic Patients Using KNN Imputed Features and Tri-Ensemble Model

Metaverse for Healthcare: Technologies, Challenges, and Vision

Contact Info

Product

Resources

About