当前位置: X-MOL 学术J. Am. Soc. Nephrol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
External Validation of an Electronic Health Record-Based Diagnostic Model for Histological Acute Tubulointerstitial Nephritis.
Journal of the American Society of Nephrology ( IF 10.3 ) Pub Date : 2024-11-05 , DOI: 10.1681/asn.0000000556
Dennis G Moledina,Kyra Shelton,Steven Menez,Abinet M Aklilu,Yu Yamamoto,Bashar A Kadhim,Melissa Shaw,Candice Kent,Amrita Makhijani,David Hu,Michael Simonov,Kyle O'Connor,Jack Bitzel,Heather Thiessen-Philbrook,F Perry Wilson,Chirag R Parikh

BACKGROUND Accurate diagnosis of acute tubulointerstitial nephritis (AIN) often requires a kidney biopsy. We previously developed a diagnostic statistical model for predicting biopsy-confirmed AIN by combining four laboratory tests after evaluating over 150 potential predictors from the electronic health record. Here, we validate this diagnostic model in two biopsy-based cohorts at Johns Hopkins Hospital (JHH) and Yale, which were geographically and temporally distinct from the development cohort, respectively. METHODS We analyzed patients who underwent kidney biopsy at JHH and Yale University (2019-2023). We assessed discrimination (AUC) and calibration using previously derived model coefficients and recalibrated the model using an intercept correction factor that accounted for differences in baseline prevalence of AIN between development and validation cohorts. RESULTS We included 1982 participants: 1454 at JHH and 528 at Yale. JHH (5%) and Yale (17%) had lower proportions of biopsies with AIN than the development set (23%). The AUC was 0.73 (0.66-0.79) at JHH and 0.73 (0.67-0.78) at Yale, similar to the development set (0.73 (0.64-0.81)). Calibration was imperfect in validation cohorts, particularly at JHH, but improved with application of an intercept correction factor. The model increased AUC of clinicians' prebiopsy suspicion for AIN by 0.10 to 0.77 (0.71-0.82). CONCLUSIONS An AIN diagnostic model retained discrimination in two validation cohorts but needed recalibration to account for local AIN prevalence. The model improved clinicians' ability to predict AIN.

中文翻译:


基于电子健康记录的组织学急性肾小管间质性肾炎诊断模型的外部验证。



背景 急性肾小管间质性肾炎 (AIN) 的准确诊断通常需要肾活检。我们之前在评估了电子健康记录中的 150 多个潜在预测因子后,通过结合四项实验室测试开发了一个诊断统计模型,用于预测活检确认的 AIN。在这里,我们在约翰霍普金斯医院 (JHH) 和耶鲁大学的两个基于活检的队列中验证了这种诊断模型,它们分别在地理和时间上与开发队列不同。方法 我们分析了在 JHH 和耶鲁大学 (2019-2023) 接受肾活检的患者。我们使用先前得出的模型系数评估了鉴别 (AUC) 和校准,并使用截距校正因子重新校准了模型,该因子解释了开发和验证队列之间 AIN 基线患病率的差异。结果我们纳入了 1982 名参与者: JHH 有 1454 名参与者,耶鲁大学有 528 名参与者。JHH (5%) 和 Yale (17%) 的 AIN 活检比例低于开发组 (23%)。JHH 的 AUC 为 0.73 (0.66-0.79),耶鲁大学的 AUC 为 0.73 (0.67-0.78),与开发集 (0.73 (0.64-0.81)) 相似。在验证队列中,尤其是 JHH 的校准并不完美,但随着截距校正因子的应用而得到改善。该模型将临床医生活检前怀疑 AIN 的 AUC 提高了 0.10 至 0.77 (0.71-0.82)。结论 AIN 诊断模型在两个验证队列中保留了区分度,但需要重新校准以解释当地的 AIN 患病率。该模型提高了临床医生预测 AIN 的能力。
更新日期:2024-11-05
down
wechat
bug