首页|NIHR Moorfields Biomedical Research Centre Reports Findings in Artificial Intell igence (Artificial Intelligence-Based Disease Activity Monitoring to Personalize d Neovascular Age-Related Macular Degeneration Treatment: A Feasibility Study)
NIHR Moorfields Biomedical Research Centre Reports Findings in Artificial Intell igence (Artificial Intelligence-Based Disease Activity Monitoring to Personalize d Neovascular Age-Related Macular Degeneration Treatment: A Feasibility Study)
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 reporting from London, United Ki ngdom, by NewsRx journalists, research stated, “To evaluate the performance of a disease activity (DA) model developed to detect DA in participants with neovasc ular age-related macular degeneration (nAMD). Post hoc analysis. Patient dataset from the phase III HAWK and HARRIER (H&H) studies.” The news correspondents obtained a quote from the research from NIHR Moorfields Biomedical Research Centre, “An artificial intelligence (AI)-based DA model was developed to generate a DA score based on measurements of OCT images and other p arameters collected from H&H study participants. Disease activity a ssessments were classified into 3 categories based on the extent of agreement be tween the DA model’s scores and the H&H investigators’ decisions: a greement (‘easy’), disagreement (‘noisy’), and close to the decision boundary (‘ difficult’). Then, a panel of 10 international retina specialists (‘panelists’) reviewed a sample of DA assessments of these 3 categories that contributed to th e training of the final DA model. A panelists’ majority vote on the reviewed cas es was used to evaluate the accuracy, sensitivity, and specificity of the DA mod el. The DA model’s performance in detecting DA compared with the DA assessments made by the investigators and panelists’ majority vote. A total of 4472 OCT DA a ssessments were used to develop the model; of these, panelists reviewed 425, cat egorized as ‘easy’ (17.2%), ‘noisy’ (20.5%), and ‘diff icult’ (62.4%). False-positive and false negative rates of the DA m odel’s assessments decreased after changing the assessment in some cases reviewe d by the panelists and retraining the DA model. Overall, the DA model achieved 8 0% accuracy. For ‘easy’ cases, the DA model reached 96% accuracy and performed as well as the investigators (96% accuracy) and panelists (90% accuracy). For ‘noisy’ cases, the DA model per formed similarly to panelists and outperformed the investigators (84% , 86%, and 16% accuracies, respectively). The DA mode l also outperformed the investigators for ‘difficult’ cases (74% a nd 53% accuracies, respectively) but underperformed the panelists (86% accuracy) owing to lower specificity. Subretinal and intraret inal fluids were the main clinical parameters driving the DA assessments made by the panelists. These results demonstrate the potential of using an AI-based DA model to optimize treatment decisions in the clinical setting and in detecting a nd monitoring DA in patients with nAMD.”
LondonUnited KingdomEuropeAge-Rela ted Macular DegenerationArtificial IntelligenceEmerging TechnologiesEye Di seases and ConditionsHealth and MedicineMachine LearningMacular Degenerati onRetinal DegenerationRetinal Diseases and Conditions
NETL
NSTL
