首页|University Hospital Vall d’Hebron Reports Findings in Artificial Intelligence (U tility of artificial intelligence for detection of pneumothorax on chest radiopgraphs done after transthoracic percutaneous transthoracic biopsy guided by computed …)
University Hospital Vall d’Hebron Reports Findings in Artificial Intelligence (U tility of artificial intelligence for detection of pneumothorax on chest radiopgraphs done after transthoracic percutaneous transthoracic biopsy guided by computed …)
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 Artificial Intelligenc e is the subject of a report. According tonews reporting originating from Barce lona, Spain, by NewsRx correspondents, research stated, “To assessthe ability o f an artificial intelligence software to detect pneumothorax in chest radiograph s done afterpercutaneous transthoracic biopsy. We included retrospectively in o ur study adult patients who underwentCT-guided percutaneous transthoracic biops ies from lung, pleural or mediastinal lesions from June 2019to June 2020, and w ho had a follow-up chest radiograph after the procedure.”Our news editors obtained a quote from the research from University Hospital Val l d’Hebron, “Thesechest radiographs were read to search the presence of pneumot horax independently by an expert thoracicradiologist and a radiodiagnosis resid ent, whose unified lecture was defined as the gold standard, and theresult of e ach radiograph after interpretation by the artificial intelligence software was documented forposterior comparison with the gold standard. A total of 284 chest radiographs were included in the studyand the incidence of pneumothorax was 14 .4%. There were no discrepancies between the two readers’interpret ation of any of the postbiopsy chest radiographs. The artificial intelligence so ftware was ableto detect 41/41 of the present pneumothorax, implying a sensitiv ity of 100% and a negative predictivevalue of 100%, with a specificity of 79.4% and a positive predictive value of 45% . The accuracy was82.4%, indicating that there is a high probabili ty that an individual will be adequately classified by thesoftware. It has also been documented that the presence of Port-a-cath is the cause of 8 of the 50 of falsepositives by the software. The software has detected 100% o f cases of pneumothorax in the postbiopsychest radiographs.”
BarcelonaSpainEuropeArtificial Int elligenceComputed TomographyEmerging TechnologiesHealth and MedicineImag ing TechnologyMachine LearningPleural Diseases and ConditionsPneumothoraxRespiratory Tract Diseases and ConditionsSoftwareTechnology
NETL
NSTL
