首页|Icahn School of Medicine at Mount Sinai Reports Findings in Gastrointestinal Ble eding (Prediction of gastrointestinal active arterial extravasation on computed tomographic angiography using multivariate clinical modeling)
Icahn School of Medicine at Mount Sinai Reports Findings in Gastrointestinal Ble eding (Prediction of gastrointestinal active arterial extravasation on computed tomographic angiography using multivariate clinical modeling)
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 Digestive System Disea ses and Conditions - Gastrointestinal Bleeding is the subject of a report. Accor ding to news reporting out of New York City, United States, by NewsRx editors, r esearch stated, “To evaluate the ability of logistic regression and machine lear ning methods to predict active arterial extravasation on computed tomographic an giography (CTA) in patients with acute gastrointestinal hemorrhage using clinica l variables obtained prior to image acquisition. CT angiograms performed for the indication of gastrointestinal bleeding at a single institution were labeled re trospectively for the presence of arterial extravasation.” Our news journalists obtained a quote from the research from the Icahn School of Medicine at Mount Sinai, “Positive and negative cases were matched for age, gen der, time period, and site using Propensity Score Matching. Clinical variables w ere collected including recent history of gastrointestinal bleeding, comorbiditi es, laboratory values, and vitals. Data were partitioned into training and testi ng datasets based on the hospital site. Logistic regression, XGBoost, Random For est, and Support Vector Machine classifiers were trained and five-fold internal cross-validation was performed. The models were validated and evaluated with the area under the receiver operating characteristic curve. Two-hundred and thirtyone CTA studies with arterial gastrointestinal extravasation were 1:1 matched wi th 231 negative studies (N=462). After data preprocessing, 389 patients and 36 f eatures were included in model development and analysis. Two hundred and fifty-f ive patients (65.6%) were selected for the training dataset. Valida tion was performed on the remaining 134 patients (34.4%); the area under the receiver operating characteristic curve for the logistic regression, X GBoost, Random Forest, and Support Vector Machine classifiers was 0.82, 0.68, 0. 54, and 0.78, respectively.”
New York CityUnited StatesNorth and Central AmericaAngiographyCardiologyCardiovascular Diagnostic TechniquesComputed Tomographic AngiographyCyborgsDigestive System Diseases and Conditi onsEmerging TechnologiesGastroenterologyGastrointestinal BleedingHealth and MedicineImaging TechnologyMachine LearningSupport Vector MachinesTec hnologyTomographic AngiographyVector Machines
NETL
NSTL
