首页|University of Eastern Finland Reports Findings in Obstructive Sleep Apnea (A com parative analysis of unsupervised machine-learning methods in PSG-related phenot yping)
University of Eastern Finland Reports Findings in Obstructive Sleep Apnea (A com parative analysis of unsupervised machine-learning methods in PSG-related phenot yping)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews-New research on Respiratory Tract Diseases and Co nditions - Obstructive Sleep Apnea is thesubject of a report. According to news reporting from Kuopio, Finland, by NewsRx journalists, researchstated, "Obstru ctive sleep apnea is a heterogeneous sleep disorder with varying phenotypes. Sev eralstudies have already performed cluster analyses to discover various obstruc tive sleep apnea phenotypicclusters."Funders for this research include Tampereen Tuberkuloosisaatio, Orionin Tutkimus saatio, HengityssairauksienTutkimussaatio, Agence Nationale de la Recherche.The news correspondents obtained a quote from the research from the University o f Eastern Finland,"However, the selection of the clustering method might affect the outputs. Consequently, it is unclearwhether similar obstructive sleep apne a clusters can be reproduced using different clustering methods.In this study, we applied four well-known clustering methods: Agglomerative Hierarchical Cluste ring; Kmeans;Fuzzy C-means; and Gaussian Mixture Model to a population of 865 suspected obstructive sleepapnea patients. By creating five clusters with each method, we examined the effect of clustering methodson forming obstructive slee p apnea clusters and the differences in their physiological characteristics. Weutilized a visualization technique to indicate the cluster formations, Cohen's k appa statistics to find thesimilarity and agreement between clustering methods, and performance evaluation to compare the clusteringperformance. As a result, two out of five clusters were distinctly different with all four methods, whilethree other clusters exhibited overlapping features across all methods. In terms of agreement, Fuzzy Cmeansand K-means had the strongest (k = 0.87), and Agglo merative hierarchical clustering and GaussianMixture Model had the weakest agre ement (k = 0.51) between each other. The K-means showed thebest clustering perf ormance, followed by the Fuzzy C-means in most evaluation criteria. Moreover, Fu zzyC-means showed the greatest potential in handling overlapping clusters compa red with other methods."
KuopioFinlandEuropeApneaCraniofa cialCyborgsEmerg-ing TechnologiesFuzzy LogicHealth and MedicineMachine LearningObstructive Sleep ApneaOtolaryngologyPulmonologyRespiration Diso rdersRespiratory Tract Diseases and ConditionsSleep ApneaSleep Diseases an d ConditionsSleep Disorders
NETL
NSTL
