首页|Data on Machine Learning Reported by Vidhya Chellamuthu and Colleagues (Fine tun ed personalized machine learning models to detect insomnia risk based on data fr om a smart bed platform)
Data on Machine Learning Reported by Vidhya Chellamuthu and Colleagues (Fine tun ed personalized machine learning models to detect insomnia risk based on data fr om a smart bed platform)
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 Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting from San Jose, California, by NewsRx journalists, research stated, "Insomnia causes serious adverse health ef fects and is estimated to affect 10-30% of the worldwide populatio n. This study leverages personalized fine-tuned machine learning algorithms to d etect insomnia risk based on questionnaire and longitudinal objective sleep data collected by a smart bed platform." The news correspondents obtained a quote from the research, "Users of the Sleep Number smart bed were invited to participate in an IRB approved study which requ ired them to respond to four questionnaires (which included the Insomnia Severit y Index; ISI) administered 6 weeks apart from each other in the period from Nove mber 2021 to March 2022. For 1,489 participants who completed at least 3 questio nnaires, objective data (which includes sleep/wake and cardio-respiratory metric s) collected by the platform were queried for analysis. An incremental, passive- aggressive machine learning model was used to detect insomnia risk which was def ined by the ISI exceeding a given threshold. Three ISI thresholds (8, 10, and 15 ) were considered. The incremental model is advantageous because it allows perso nalized finetuning by adding individual training data to a generic model. The g eneric model, without personalizing, resulted in an area under the receiving-ope rating curve (AUC) of about 0.5 for each ISI threshold. The personalized fine-tu ning with the data of just five sleep sessions from the individual for whom the model is being personalized resulted in AUCs exceeding 0.8 for all ISI threshold s. Interestingly, no further AUC enhancements resulted by adding personalized da ta exceeding ten sessions."
San JoseCaliforniaUnited StatesNor th and Central Amer-caBusinessCyborgsEmerging TechnologiesMachine Learni ngRisk and PreventionSleep Number Corporation
NETL
NSTL
