A federated learning method for real-time emotion state classification from multi-modal streaming

Nandi, Arijit; Xhafa, Fatos

doi:10.1016/j.ymeth.2022.03.005

Cited by 38 publications

(23 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because characteristics of populations, PCa incidence, and diagnostic approaches frequently change, making accurate real-time predictions adapted to the continuous evolution is challenging [ 39 ]. Continuous updating of risk calculators from the feedback of new cases, integrating the generation of big data, appropriate machine-learning algorithm design [ 40 , 41 ], and federated networks will provide the opportunity to develop future predictive models and risk calculators guaranteeing accurate and enduring overall and specific predictions [ 42 ].…”

Section: Discussionmentioning

confidence: 99%

A Clinically Significant Prostate Cancer Predictive Model Using Digital Rectal Examination Prostate Volume Category to Stratify Initial Prostate Cancer Suspicion and Reduce Magnetic Resonance Imaging Demand

Moróte

Borque‐Fernando

Triquell

et al. 2022

Cancers

View full text Add to dashboard Cite

A predictive model including age, PCa family history, biopsy status (initial vs repeat), DRE (normal vs abnormal), serum prostate-specific antigen (PSA), and DRE prostate volume ca-tegory was developed to stratify initial PCa suspicion in 1486 men with PSA > 3 ng/mL and/or abnormal DRE, in whom mpMRI followed; 2- to 4-core TRUS-guided biopsies where Prostate Imaging Report and Data System (PI-RADS) > 3 lesions and/or 12-core TRUS systematic biopsies were performed in one academic institution between 1 January 2016–31 December 2019. The csPCa detection rate, defined as International Society of Uro-Pathology grade group 2 or higher, was 36.9%. An external validation of designed BCN-RC 1 was carried out on 946 men from two other institutions in the same metropolitan area, using the same criteria of PCa suspicion and diagnostic approach, yielded a csPCa detection rate of 40.8%. The areas under the receiver operating characteristic curves of BCN-RC 1 were 0.823 (95% CI: 0.800–0.846) in the development cohort and 0.837 (95% CI: 0.811–0.863) in the validation cohort (p = 0.447). In both cohorts, BCN-RC 1 exhibited net benefit over performing mpMRI in all men from 8 and 12% risk thresholds, respectively. At 0.95 sensitivity of csPCa, the specificities of BCN-RC 1 were 0.24 (95% CI: 0.22–0.26) in the development cohort and 0.34 (95% CI: 0.31–0.37) in the validation cohort (p < 0.001). The percentages of avoided mpMRI scans were 17.2% in the development cohort and 22.3% in the validation cohort, missing between 1.8% and 2% of csPCa among men at risk of PCa. In summary, BCN-RC 1 can stratify initial PCa suspicion, reducing the demand of mpMRI, with an acceptable loss of csPCa.

show abstract

Section: Discussionmentioning

confidence: 99%

A Clinically Significant Prostate Cancer Predictive Model Using Digital Rectal Examination Prostate Volume Category to Stratify Initial Prostate Cancer Suspicion and Reduce Magnetic Resonance Imaging Demand

Moróte

Borque‐Fernando

Triquell

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“… 63 Fed-ReMECS fuses various signals for real-time emotional state classification. 64 Liang et al. developed a privacy-focused multimodal model for mood assessment, surpassing unimodal models in performance.…”

Section: Opportunities For Solutions In C 4 Settingsmentioning

confidence: 99%

Learning across diverse biomedical data modalities and cohorts: Challenges and opportunities for innovation

Rajendran,

Pan,

Sabuncu

et al. 2024

Patterns

View full text Add to dashboard Cite

“…In addition to applying FL to medical image data, some studies adopt patient biosignal datasets to analyze their diseases. Representative research examples include classifying arrhythmia by applying federated learning into the CNN analysis of electrocardiogram data, the Fed-REMCS (Real-time Emotion State Classification from Multi-modal Streaming) study [37] that classified human emotions by analyzing physiological signals, and the PFCM (Personalized Federated Cluster Model) study [38] that analyzed depression severity through HRV analysis.…”

Section: Federated Learning For Dtxmentioning

confidence: 99%

Cutting-Edge Technologies for Digital Therapeutics: A Review and Architecture Proposals for Future Directions

2023

View full text Add to dashboard Cite

Digital therapeutics, evidence-based treatments delivered through software programs, are revolutionizing healthcare by utilizing cutting-edge computing technologies. Unlike conventional medical treatment methods, digital therapeutics are based on multiple information technologies, from data collection to analysis algorithms, and treatment support approaches. In this research, we provide a comprehensive overview of the latest technologies involved in the development of digital therapeutics and highlight specific technologies necessary for the future growth of the rapidly evolving digital therapeutics market. Furthermore, we present a system design of digital therapeutics for depression, currently being developed by our research team, to provide a detailed explanation of the technical process. Digital therapeutics require various technical supports, such as collecting user data in a security-enhanced medical environment, processing and analyzing the collected data, and providing personalized treatment methods to the user. The findings from this research will enable digital therapeutic companies to enhance their product performance, consequently bolstering their market competitiveness. Additionally, the research can be further extended to explore applicable methodologies at different stages of digital therapeutic environments.

show abstract

A federated learning method for real-time emotion state classification from multi-modal streaming

Cited by 38 publications

References 9 publications

A Clinically Significant Prostate Cancer Predictive Model Using Digital Rectal Examination Prostate Volume Category to Stratify Initial Prostate Cancer Suspicion and Reduce Magnetic Resonance Imaging Demand

A Clinically Significant Prostate Cancer Predictive Model Using Digital Rectal Examination Prostate Volume Category to Stratify Initial Prostate Cancer Suspicion and Reduce Magnetic Resonance Imaging Demand

Learning across diverse biomedical data modalities and cohorts: Challenges and opportunities for innovation

Cutting-Edge Technologies for Digital Therapeutics: A Review and Architecture Proposals for Future Directions

Contact Info

Product

Resources

About