AI-based chest X-ray prioritization in the lung cancer diagnostic pathway: the LungIMPACT randomized controlled trial.

This prospective, multicentre, randomized controlled trialtested whether immediate AI prioritization of primary care-requested chest X-rays (CXR) influenced time to computed tomography (CT) and lung cancer diagnosis, the primary outcomes.

这项前瞻性、多中心、随机对照试验测试了立即对初级保健请求的胸部X光片（CXR）进行AI优先排序是否会影响计算机断层扫描（CT）和肺癌诊断的时间，这是主要的结果。

Secondary outcomes included the number of urgent suspected lung cancer referrals, incidenceand stage of lung cancer, times to urgent referral and treatment, concordance between AI and radiology reports, and algorithm accuracy.

次要结果包括紧急疑似肺癌转诊的数量、肺癌的发病率和分期、紧急转诊和治疗的时间以及人工智能与放射学报告之间的一致性，以及算法的准确性。

AI was available in both study arms, with AI prioritization randomized by day.

人工智能在两个研究组中均可使用，人工智能优先级按天随机化。

Of 97,731 participant CXRs, 4,405 were excluded due to data compliance issues or failure of randomization, resulting in 93,326 CXRs analyzed (45,987 and 47,339 in the prioritization 'on' or 'off' arms, respectively).

在97,731名参与者的胸部X光片中，由于数据一致性问题或随机化失败，排除了4,405张，最终分析了93,326张胸部X光片（'优先级开启'组45,987张，'优先级关闭'组47,339张）。

A total of 13,347 CTs were identified, with 2,766 performed within 14 days of CXR.

共识别出13,347次CT检查，其中2,766次在胸部X光片后14天内进行。

Median (interquartile range) times to CT were 53 days (17-145) and 53 days (19-141), with and without AI prioritization, corresponding to a ratio of geometric means of 0.97 (95% confidence interval(CI) = 0.93-1.02; P = 0.31).

计算机断层扫描（CT）的中位时间（四分位数范围）分别为53天（17-145天）和53天（19-141天），无论是否采用人工智能（AI）优先排序，对应的几何平均数比率为0.97（95%置信区间（CI）= 0.93-1.02；P = 0.31）。

When restricted to CTs performed within 14 days of CXR, the median time to CT was 8 days (5-11) in both groups.

当仅限于在胸部X线摄影（CXR）后14天内进行的CT时，两组的CT中位时间均为8天（5-11天）。

Lung cancer was diagnosed in 558 people (0.6% of CXRs).

在558人中诊断出肺癌（占胸部X光片的0.6%）。

Median times to diagnosis were 44 days (26-90) and 46 days (24-105) respectively, with a ratio of geometric means of 0.98 (95% CI = 0.83-1.16; P = 0.84).

诊断的中位时间分别为44天（26-90天）和46天（24-105天），几何平均数之比为0.98（95%置信区间=0.83-1.16；P=0.84）。

No significant differences were observed in time to lung cancer referral (14 versus 15 days; P = 0.13), time to treatment (76 versus 72.5 days; P = 0.99) or stage at diagnosis (P = 0.34).

在肺癌转诊时间（14天对比15天；P=0.13）、治疗时间（76天对比72.5天；P=0.99）或诊断时的疾病分期（P=0.34）上未观察到显著差异。

Discordance between AI and radiology reports occurred in 28,261 CXRs (30.3%) and expert radiology review identified actionable findings in 6,750 cases (23.9%).

在28,261张胸部X光片中，人工智能与放射科报告之间存在不一致（30.3%），专家放射科复查在6,750例病例中识别出可采取行动的发现（23.9%）。

AI prioritization of CXR requested by UK primary care has no significant impact on the lung cancer pathway.

AI优先处理英国初级保健请求的胸部X光片对肺癌诊疗路径没有显著影响。

Therefore, CXR AI deployments should not include worklist prioritization in this context.

因此，在这个背景下，CXR AI部署不应包括工作列表优先级排序。

Future research should differentiate between primary pathway changes and the direct impact of AI.

未来的研究应该区分主要途径的变化和人工智能的直接影响。

ISRCTN registration: 78987039 .

ISRCTN 注册号：78987039。