Population Data Science, Health Data Research UK, Swansea University Medical School, Swansea, SA2 8PP.
Health Analysis and Life Events Division, Office for National Statistics, NP10 8XG.
Int J Popul Data Sci. 2022 Feb 15;5(4):1697. doi: 10.23889/ijpds.v5i4.1697. eCollection 2020.
COVID-19 risk prediction algorithms can be used to identify at-risk individuals from short-term serious adverse COVID-19 outcomes such as hospitalisation and death. It is important to validate these algorithms in different and diverse populations to help guide risk management decisions and target vaccination and treatment programs to the most vulnerable individuals in society.
To validate externally the QCOVID risk prediction algorithm that predicts mortality outcomes from COVID-19 in the adult population of Wales, UK.
We conducted a retrospective cohort study using routinely collected individual-level data held in the Secure Anonymised Information Linkage (SAIL) Databank. The cohort included individuals aged between 19 and 100 years, living in Wales on 24 January 2020, registered with a SAIL-providing general practice, and followed-up to death or study end (28 July 2020). Demographic, primary and secondary healthcare, and dispensing data were used to derive all the predictor variables used to develop the published QCOVID algorithm. Mortality data were used to define time to confirmed or suspected COVID-19 death. Performance metrics, including R values (explained variation), Brier scores, and measures of discrimination and calibration were calculated for two periods (24 January-30 April 2020 and 1 May-28 July 2020) to assess algorithm performance.
1,956,760 individuals were included. 1,192 (0.06%) and 610 (0.03%) COVID-19 deaths occurred in the first and second time periods, respectively. The algorithms fitted the Welsh data and population well, explaining 68.8% (95% CI: 66.9-70.4) of the variation in time to death, Harrell's C statistic: 0.929 (95% CI: 0.921-0.937) and D statistic: 3.036 (95% CI: 2.913-3.159) for males in the first period. Similar results were found for females and in the second time period for both sexes.
The QCOVID algorithm developed in England can be used for public health risk management for the adult Welsh population.
COVID-19 风险预测算法可用于识别短期严重 COVID-19 结局（如住院和死亡）的高危个体。在不同和多样化的人群中验证这些算法非常重要，有助于指导风险管理决策，并将疫苗接种和治疗计划针对社会中最脆弱的个体。
在英国威尔士的成年人群中，对预测 COVID-19 死亡率的 QCOVID 风险预测算法进行外部验证。
我们进行了一项回顾性队列研究，使用 Secure Anonymised Information Linkage（SAIL）数据库中收集的个体水平常规数据。该队列包括年龄在 19 至 100 岁之间、2020 年 1 月 24 日居住在威尔士、注册了提供 SAIL 的全科医生、并随访至死亡或研究结束（2020 年 7 月 28 日）的个体。人口统计学、初级和二级医疗保健以及配药数据用于推导用于开发已发表的 QCOVID 算法的所有预测变量。死亡率数据用于确定确诊或疑似 COVID-19 死亡的时间。为两个时期（2020 年 1 月 24 日至 4 月 30 日和 5 月 1 日至 7 月 28 日）计算了性能指标，包括 R 值（解释的变化）、Brier 评分以及区分度和校准度的度量，以评估算法性能。
纳入了 1956760 人。第一和第二个时期分别发生了 1192（0.06%）和 610（0.03%）例 COVID-19 死亡。该算法非常适合威尔士数据和人群，解释了死亡时间的 68.8%（95%CI：66.9-70.4），男性第一时期 Harrell's C 统计量为 0.929（95%CI：0.921-0.937），D 统计量为 3.036（95%CI：2.913-3.159）。在女性和两性的第二个时期也得到了类似的结果。
在英格兰开发的 QCOVID 算法可用于威尔士成年人群的公共卫生风险管理。
