首页|Fondazione Policlinico Universitario A. Gemelli IRCCS Reports Findings in Artifi cial Intelligence (Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: The SIBILLA project)
Fondazione Policlinico Universitario A. Gemelli IRCCS Reports Findings in Artifi cial Intelligence (Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: The SIBILLA project)
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 Rome, Italy, by NewsRx correspondents, research stated, “Formulating reliable prognosis for isc hemic stroke patients remains a challenging task. We aimed to develop an artific ial intelligence model able to formulate in the first 24 h after stroke an indiv idualized prognosis in terms of NIHSS.” Our news journalists obtained a quote from the research from Fondazione Policlin ico Universitario A. Gemelli IRCCS, “Seven hundred ninety four acute ischemic st roke patients were divided into a training (597) and testing (197) cohort. Clini cal and instrumental data were collected in the first 24 h. We evaluated the per formance of four machine-learning models (Random Forest, -Nearest Neighbors, Sup port Vector Machine, XGBoost) in predicting NIHSS at discharge both in terms of variation between discharge and admission (regressor approach) and in terms of s everity class namely NIHSS 0-5, 6-10, 11-20, >20 (classi fier approach). We used Shapley Additive exPlanations values to weight features impact on predictions. XGBoost emerged as the best performing model. The classif ier and regressor approaches perform similarly in terms of accuracy (80% vs 75%) and f1-score (79% vs 77%) respec tively. However, the regressor has higher precision (85% vs 68% ) in predicting prognosis of very severe stroke patients (NIHSS > 20). NIHSS at admission and 24 hours, GCS at 24 hours, heart rate, acute ischem ic lesion on CT-scan and TICI score were the most impacting features on the pred iction. Our approach, which employs an artificial intelligence based-tool, inher ently able to continuously learn and improve its performance, could improve care pathway and support stroke physicians in the communication with patients and ca regivers.”
RomeItalyEuropeArtificial Intellig enceCerebrovascular Diseases and ConditionsEmerging TechnologiesHealth and MedicineMachine LearningStroke
NETL
NSTL
