首页|Amsterdam University Medical Center Reports Findings in Artificial Intelligence (Validation of an Artificial Intelligence-Based Prediction Model Using 5 Externa l PET/CT Datasets of Diffuse Large B-Cell Lymphoma)
Amsterdam University Medical Center Reports Findings in Artificial Intelligence (Validation of an Artificial Intelligence-Based Prediction Model Using 5 Externa l PET/CT Datasets of Diffuse Large B-Cell Lymphoma)
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 Artificial Intelligenc e is the subject of a report. According to news originating from Amsterdam, Neth erlands, by NewsRx correspondents, research stated, “The aim of this study was t o validate a previously developed deep learning model in 5 independent clinical trials. The predictive performance of this model was compared with the internati onal prognostic index (IPI) and 2 models incorporating radiomic PET/CT features (clinical PET and PET models).” Our news journalists obtained a quote from the research from Amsterdam Universit y Medical Center, “In total, 1,132 diffuse large B-cell lymphoma patients were i ncluded: 296 for training and 836 for external validation. The primary outcome w as 2-y time to progression. The deep learning model was trained on maximum-inten sity projections from PET/CT scans. The clinical PET model included metabolic tu mor volume, maximum distance from the bulkiest lesion to another lesion, SUV, ag e, and performance status. The PET model included metabolic tumor volume, maximu m distance from the bulkiest lesion to another lesion, and SUV Model performance was assessed using the area under the curve (AUC) and Kaplan-Meier curves. The IPI yielded an AUC of 0.60 on all external data. The deep learning model yielded a significantly higher AUC of 0.66 (<0.01). For each indi vidual clinical trial, the model was consistently better than IPI. Radiomic mode l AUCs remained higher for all clinical trials. The deep learning and clinical P ET models showed equivalent performance (AUC, 0.69; > 0. 05). The PET model yielded the highest AUC of all models (AUC, 0.71; <0.05). The deep learning model predicted outcome in all trials with a higher pe rformance than IPI and better survival curve separation.”
AmsterdamNetherlandsEuropeArtifici al IntelligenceB-Cell LymphomaCancerClinical ResearchClinical Trials and StudiesEmerging TechnologiesHealth and MedicineHematologyImmunoprolifer ative DisordersLarge B-Cell LymphomaLymphatic Diseases and ConditionsLymph omaLymphoproliferative DisordersMachine LearningOncology
NETL
NSTL
