Evaluating equity in performance of an electronic health record-based 6-month mortality risk model to trigger palliative care consultation: a retrospective model validation analysis.
Evaluating equity in performance of an electronic health record-based 6-month mortality risk model to trigger palliative care consultation: a retrospective model validation analysis.
复制标题
评估基于电子健康记录的 6 个月死亡风险模型的绩效公平性以触发姑息治疗咨询：回顾性模型验证分析。
DOI：
10.1136/bmjqs-2022-015173
复制
发表时间：
2023
影响因子：
5.4
通讯作者：
Courtright,Katherine
中科院分区：
文献类型：
--
作者：
Teeple,Stephanie;Chivers,Corey;Linn,KristinA;Halpern,ScottD;Eneanya,Nwamaka;Draugelis,Michael;Courtright,Katherine
目的评估基于电子健康记录 (EHR) 的住院患者 6 个月死亡风险模型的预测性能，该模型旨在触发按年龄、种族、民族、保险和社会经济地位 (SES) 分层的患者群体中的姑息治疗咨询，这些群体可能会因影响健康、医疗保健和健康数据的社会力量（例如种族主义）而有所不同。设计预测模型的回顾性评估。在单一卫生系统内设置三个城市医院。参与者所有患者≥18 岁2017 年 1 月 1 日至 12 月 31 日期间入院，不包括观察、产科、康复和临终关怀（n=58 464 例就诊，41 327 名患者）。主要结果指标一般表现指标（c 统计、综合校准指数 (ICI)、Brier 评分）和与健康公平相关的其他指标（准确性、假阳性率 (FPR)、假阴性率 (FNR)）。结果黑人与黑人相比对于非西班牙裔白人患者，模型的准确性较高（0.051，95%CI 0.044 至 0.059），FPR 较低（-0.060，95%CI -0.067 至 -0.052），FNR 较高（0.049，95%CI 0.023 至 0.078）。在西班牙裔、年轻、有医疗补助/缺少保险或生活在低社会经济地位邮政编码的患者中也观察到了类似的模式。 c 统计、ICI 或 Brier 评分没有出现一致的差异。较年轻的年龄在死亡率预测模型中具有第二大的影响大小，并且年龄存在较大的标准化组差异（例如，非西班牙裔白人与黑人患者的标准化组差异为0.32），这表明年龄可能会导致组间预测概率的系统性差异。结论基于EHR的死亡风险模型不太可能识别出一些边缘化患者可能受益于姑息治疗，而较年轻的年龄被确定为一种可能的机制。评估预测性能是解决医疗保健领域算法不平等问题的关键初步步骤，其中还必须包括评估临床影响以及监督、监测和问责的治理和监管结构。
ObjectiveEvaluate predictive performance of an electronic health record (EHR)-based, inpatient 6-month mortality risk model developed to trigger palliative care consultation among patient groups stratified by age, race, ethnicity, insurance and socioeconomic status (SES), which may vary due to social forces (eg, racism) that shape health, healthcare and health data.DesignRetrospective evaluation of prediction model.SettingThree urban hospitals within a single health system.ParticipantsAll patients ≥18 years admitted between 1 January and 31 December 2017, excluding observation, obstetric, rehabilitation and hospice (n=58 464 encounters, 41 327 patients).Main outcome measuresGeneral performance metrics (c-statistic, integrated calibration index (ICI), Brier Score) and additional measures relevant to health equity (accuracy, false positive rate (FPR), false negative rate (FNR)).ResultsFor black versus non-Hispanic white patients, the model’s accuracy was higher (0.051, 95% CI 0.044 to 0.059), FPR lower (−0.060, 95% CI −0.067 to −0.052) and FNR higher (0.049, 95% CI 0.023 to 0.078). A similar pattern was observed among patients who were Hispanic, younger, with Medicaid/missing insurance, or living in low SES zip codes. No consistent differences emerged in c-statistic, ICI or Brier Score. Younger age had the second-largest effect size in the mortality prediction model, and there were large standardised group differences in age (eg, 0.32 for non-Hispanic white versus black patients), suggesting age may contribute to systematic differences in the predicted probabilities between groups.ConclusionsAn EHR-based mortality risk model was less likely to identify some marginalised patients as potentially benefiting from palliative care, with younger age pinpointed as a possible mechanism. Evaluating predictive performance is a critical preliminary step in addressing algorithmic inequities in healthcare, which must also include evaluating clinical impact, and governance and regulatory structures for oversight, monitoring and accountability.