SOREU, Agenzia Regionale Emergenza Urgenza (AREU), Milano, Italy.
Department of Anesthesia, Critical Care and Pain Medicine, ASST Grande Ospedale Metropolitano Niguarda, Milano, Italy.
Emerg Med J. 2023 Nov 28;40(12):810-820. doi: 10.1136/emermed-2022-212853.
The regional emergency medical service (EMS) in Lombardy (Italy) developed clinical algorithms based on operator-based interviews to detect patients with COVID-19 and refer them to the most appropriate hospitals. Machine learning (ML)-based models using additional clinical and geospatial epidemiological data may improve the identification of infected patients and guide EMS in detecting COVID-19 cases before confirmation with SARS-CoV-2 reverse transcriptase PCR (rtPCR).
This was an observational, retrospective cohort study using data from October 2020 to July 2021 (training set) and October 2021 to December 2021 (validation set) from patients who underwent a SARS-CoV-2 rtPCR test within 7 days of an EMS call. The performance of an operator-based interview using close contact history and signs/symptoms of COVID-19 was assessed in the training set for its ability to determine which patients had an rtPCR in the 7 days before or after the call. The interview accuracy was compared with four supervised ML models to predict positivity for SARS-CoV-2 within 7 days using readily available prehospital data retrieved from both training and validation sets.
The training set includes 264 976 patients, median age 74 (IQR 55-84). Test characteristics for the detection of COVID-19-positive patients of the operator-based interview were: sensitivity 85.5%, specificity 58.7%, positive predictive value (PPV) 37.5% and negative predictive value (NPV) 93.3%. Contact history, fever and cough showed the highest association with SARS-CoV-2 infection. In the validation set (103 336 patients, median age 73 (IQR 50-84)), the best-performing ML model had an AUC of 0.85 (95% CI 0.84 to 0.86), sensitivity 91.4% (95 CI% 0.91 to 0.92), specificity 44.2% (95% CI 0.44 to 0.45) and accuracy 85% (95% CI 0.84 to 0.85). PPV and NPV were 13.3% (95% CI 0.13 to 0.14) and 98.2% (95% CI 0.98 to 0.98), respectively. Contact history, fever, call geographical distribution and cough were the most important variables in determining the outcome.
ML-based models might help EMS identify patients with SARS-CoV-2 infection, and in guiding EMS allocation of hospital resources based on prespecified criteria.
意大利伦巴第大区的区域紧急医疗服务（EMS）开发了基于操作员访谈的临床算法，以检测 COVID-19 患者并将其转介到最合适的医院。使用额外的临床和地理流行病学数据的基于机器学习（ML）的模型可以提高对感染患者的识别，并在使用 SARS-CoV-2 逆转录酶聚合酶链反应（rtPCR）确认之前指导 EMS 检测 COVID-19 病例。
这是一项观察性、回顾性队列研究，使用了 2020 年 10 月至 2021 年 7 月（训练集）和 2021 年 10 月至 2021 年 12 月（验证集）期间接受 SARS-CoV-2 rtPCR 检测的患者数据，这些患者在 EMS 呼叫后 7 天内接受了 SARS-CoV-2 rtPCR 检测。在训练集中评估了基于操作员访谈的接触史和 COVID-19 体征/症状来确定哪些患者在呼叫前或后 7 天内进行了 rtPCR 的能力，以评估其检测 COVID-19 阳性患者的性能。将访谈的准确性与四个监督 ML 模型进行比较，以使用从训练集和验证集检索的现成的院前数据来预测 SARS-CoV-2 在 7 天内的阳性率。
训练集包括 264976 名患者，中位年龄 74（IQR 55-84）。基于操作员访谈的 COVID-19 阳性患者检测的测试特征为：敏感性 85.5%，特异性 58.7%，阳性预测值（PPV）37.5%和阴性预测值（NPV）93.3%。接触史、发热和咳嗽与 SARS-CoV-2 感染的相关性最高。在验证集（103336 名患者，中位年龄 73（IQR 50-84））中，性能最佳的 ML 模型 AUC 为 0.85（95%CI 0.84 至 0.86），敏感性为 91.4%（95%CI%为 0.91 至 0.92），特异性为 44.2%（95%CI 为 0.44 至 0.45），准确率为 85%（95%CI 为 0.84 至 0.85）。PPV 和 NPV 分别为 13.3%（95%CI 为 0.13 至 0.14）和 98.2%（95%CI 为 0.98 至 0.98）。接触史、发热、呼叫地理位置分布和咳嗽是决定结果的最重要变量。
基于 ML 的模型可能有助于 EMS 识别 SARS-CoV-2 感染患者，并根据预设标准指导 EMS 分配医院资源。
