首页|Copenhagen University Hospital Reports Findings in Biomarkers (Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET- derived features)
Copenhagen University Hospital Reports Findings in Biomarkers (Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET- derived features)
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 Daily News - New research on Diagnostics and Screen ing - Biomarkers is the subject of a report.According to news originating from Copenhagen, Denmark, by NewsRx correspondents, research stated,“To better asses s the pathology of neurodegenerative disorders and the efficacy of neuroprotecti ve interventions,it is necessary to develop biomarkers that can accurately capt ure age-related biological changesin the human brain. Brain serotonin 2A recept ors (5-HT2AR) show a particularly profound age-relateddecline and are also redu ced in neurodegenerative disorders, such as Alzheimer’s disease.”Our news journalists obtained a quote from the research from Copenhagen Universi ty Hospital, “Thisstudy investigates whether the decline in 5-HT2AR binding, me asured in vivo using positron emissiontomography (PET), can be used as a biomar ker for brain aging. Specifically, we aim to (1) predict brainage using 5-HT2AR binding outcomes, (2) compare 5-HT2AR-based predictions of brain age to predict ionsbased on gray matter (GM) volume, as determined with structural magnetic re sonance imaging (MRI),and (3) investigate whether combining 5-HT2AR and GM volu me data improves prediction. We used PETand MR images from 209 healthy individu als aged between 18 and 85 years (mean = 38, std = 18) andestimated 5-HT2AR bin ding and GM volume for 14 cortical and subcortical regions. Different machine learning algorithms were applied to predict chronological age based on 5-HT2AR bin ding, GM volume, andthe combined measures. The mean absolute error (MAE) and a cross-validation approach were used forevaluation and model comparison. We find that both the cerebral 5-HT2AR binding (mean MAE = 6.63years, std = 0.74 years ) and GM volume (mean MAE = 6.95 years, std = 0.83 years) predict chronologicalage accurately. Combining the two measures improves the prediction further (mean MAE = 5.54 years,std = 0.68).”
CopenhagenDenmarkEuropeBiomarkersCyborgsDiagnostics and ScreeningEmerging TechnologiesHealth and MedicineMachine LearningRisk and Prevention
NETL
NSTL
