A comprehensive review on Federated Learning for Data-Sensitive Application: Open issues &amp; challenges

Narula, Manu; Meena, Jasraj; Vishwakarma, Dinesh Kumar

doi:10.1016/j.engappai.2024.108128

Cited by 4 publications

(1 citation statement)

References 112 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternative emerging approaches to circumvent these issues include federated learning and generation of simulated/ synthetic datasets. 34 Synthetic datasets show a small decrease in model accuracy in supervised machine learning problems than models trained on real data however studies evaluating their generalisability within unsupervised machine learning paradigms are limited. 35 However, there is promising evidence that synthetic datasets can be created that balance risk of private information leakage and maintaining the statistical properties of the original datasets.…”

Section: Discussionmentioning

confidence: 99%

Assessing Clustering Replicability in Sensorineural Hearing Loss: Insights from the UK's Largest Audiogram Cohort

Dimitrov,

lilaonitkul,

Mehta

2024

Preprint

View full text Add to dashboard Cite

Despite nearly 20% of the global population experiencing hearing loss, there remains limited insight into the underlying subtypes of its most prevalent cause, sensorineural hearing loss (SNHL). This understanding is crucial for effective therapeutic and preventative strategies. A recent study using a Gaussian Mixture Model (GMM) identified 10 distinct SNHL phenotypes in a large US cohort, highlighting the potential of unsupervised machine learning to provide a data-driven solution to this task. Rigorous validation of these models is essential; however, it is limited due to several factors, including the absence of ground truth labels for model evaluation, restricted data access, and the lack of a standardized reporting framework for comparing results across clustering studies. Here, we apply GMM to a UK database of 109,854 audiograms, revealing 9 phenotypes, partly overlapping prior findings. Notably, our study cohort is characterized by advanced age, a higher proportion of female participants, and more severe hearing impairments. We observed instability in the GMM model when subjected to variations in the original dataset. To enhance practices, we propose a Clustering Replicability Framework, ensuring robustness in unsupervised machine learning-driven health research for safe clinical translation. Words: 187

show abstract

Section: Discussionmentioning

confidence: 99%