PT -期刊文章盟Nilakash Das AU -苏菲Happaerts AU - Iwein Gyselinck AU -迈克尔sta盟Eric Derom AU -家伙Brusselle盟Felip布尔戈斯AU -马可Contoli盟安老爷Dinh-Xuan主机Franssen盟盟-熔化- Sherif Gonem AU -尼尔绿化盟Christel Haenebalcke AU -威廉直流。人非盟-豪尔赫莫伊塞斯盟-鲁迪也是盟Vitalii Poberezhets盟迈克尔·c·施泰纳-珍妮弗·k·昆特盟盟Eef Vanderhelst AU -穆斯塔法Abdo盟Marko Topalovic AU - TI -维姆·詹森合作可辩解的人工智能和位肺脏改善肺功能的准确性测试解释援助- 10.1183/13993003.01720 -2022 DP - 2023可能01 TA -欧洲呼吸杂志》第六PG - 2201720 - 61 IP - 5 4099 - //www.qdcxjkg.com/content/61/5/2201720.short 4100 - //www.qdcxjkg.com/content/61/5/2201720.full所以欧元和J2023可能01;61 AB -背景很少有研究调查和人工智能(AI)之间的合作潜力位肺脏诊断肺部疾病。我们提出,合作是胸腔和AI的解释(可辩解的AI(新品))优越的诊断解释肺功能测试(击球)比不支持治疗。方法研究是在两个阶段进行,monocentre研究(第一阶段)和多中心的干预研究每个阶段(阶段2)。利用两组不同的24击球的报道患者临床诊断金标准进行验证。每个击球解释没有(控制)和新品的建议(干预)。位肺脏组成的鉴别诊断提供诊断和优惠可选三个额外的诊断。主要终点相比精度控制和干预之间的优惠和额外的诊断。二次端点的诊断鉴别诊断,诊断信心和两分的协议。我们也分析了新品如何影响位肺脏的决定。Results In phase 1 (n=16 pulmonologists), mean preferential and differential diagnostic accuracy significantly increased by 10.4% and 9.4%, respectively, between control and intervention (p<0.001). Improvements were somewhat lower but highly significant (p<0.0001) in phase 2 (5.4% and 8.7%, respectively; n=62 pulmonologists). In both phases, the number of diagnoses in the differential diagnosis did not reduce, but diagnostic confidence and inter-rater agreement significantly increased during intervention. Pulmonologists updated their decisions with XAI's feedback and consistently improved their baseline performance if AI provided correct predictions.Conclusion A collaboration between a pulmonologist and XAI is better at interpreting PFTs than individual pulmonologists reading without XAI support or XAI alone.This study demonstrates that pulmonologists improve their individual diagnostic interpretation of pulmonary function tests when supported by AI-based computer protocols with automated explanations. Such teamwork may become commonplace in the future. https://bit.ly/3ZKK4Eu