Background

Certain widely used pathological outcome prediction models that were developed in tertiary centers tend to overpredict outcomes in the community setting; thus, the Michigan Urological-Surgery Improvement Collaborative (MUSIC) model was developed in general urology practice to address this issue. Additionally, the development of these models involved a relatively small proportion of Black men, potentially compromising the accuracy of predictions in this patient group. We tested the validity of the MUSIC and three widely used nomograms to compare their overall and race-stratified predictive performance.

Methods

We extracted data from 4139 (1138 Black) men from the Shared Equal Access Regional Cancer Hospital (SEARCH) database of the Veterans Affairs health system. The predictive performance of the MUSIC model was compared to the Memorial-Sloan Kettering (MSK), Briganti-2012, and Partin-2017 models for predicting lymph-node invasion (LNI), extra-prostatic extension (EPE), and seminal vesicle invasion (SVI).

Results

The median PSA of Black men was higher than White men (7.8 vs. 6.8 ng/ml), although they were younger by a median of three years and presented at a lower-stage disease. MUSIC model showed comparable discriminatory capacity (AUC:77.0%) compared to MSK (79.2%), Partin-2017 (74.6%), and Briganti-2012 (76.3%), with better calibration for LNI. AUCs for EPE and SVI were 72.7% and 76.9%, respectively, all comparable to the MSK and Partin models. LNI AUCs for Black and White men were 69.6% and 79.6%, respectively, while EPE and SVI AUCs were comparable between races. EPE and LNI had worse calibration in Black men. Decision curve analysis showed MUSIC superiority over the MSK model in predicting LNI, especially among Black men.

Conclusion

Although the discriminatory performance of all models was comparable for each outcome, the MUSIC model exhibited superior net benefit to the MSK model in predicting LNI outcomes among Black men in the SEARCH population.

中文翻译：

---

解决前列腺癌病理预测模型中的种族差异：多种族 SEARCH 队列中根治性前列腺切除术前四种病理结果预测模型的外部验证和比较

背景

在三级中心开发的某些广泛使用的病理结果预测模型往往会高估社区环境中的结果；因此，在一般泌尿外科实践中开发了密歇根泌尿外科改进协作（MUSIC）模型来解决这个问题。此外，这些模型的开发涉及相对较小比例的黑人男性，可能会影响该患者群体的预测准确性。我们测试了 MUSIC 和三个广泛使用的列线图的有效性，以比较它们的整体和种族分层预测性能。

方法

我们从退伍军人事务部卫生系统的共享平等访问地区癌症医院 (SEARCH) 数据库中提取了 4139 名（1138 名黑人）男性的数据。将 MUSIC 模型与 Memorial-Sloan Kettering (MSK)、Briganti-2012 和 Partin-2017 模型在预测淋巴结侵袭 (LNI)、前列腺外扩展 (EPE) 和精囊侵袭方面的预测性能进行比较（SVI）。

结果

黑人男性的 PSA 中位值高于白人男性（7.8 纳克/毫升与 6.8 纳克/毫升），尽管黑人男性的平均年龄要年轻三岁，并且处于较低阶段的疾病。与 MSK (79.2%)、Partin-2017 (74.6%) 和 Briganti-2012 (76.3%) 相比，MUSIC 模型显示出可比的判别能力 (AUC:77.0%)，并且对 LNI 具有更好的校准。 EPE 和 SVI 的 AUC 分别为 72.7% 和 76.9%，均与 MSK 和 Partin 模型相当。黑人和白人男性的 LNI AUC 分别为 69.6% 和 79.6%，而 EPE 和 SVI AUC 在种族之间具有可比性。 EPE 和 LNI 在黑人中的校准较差。决策曲线分析表明，MUSIC 在预测 LNI 方面优于 MSK 模型，尤其是在黑人男性中。

结论

尽管所有模型的每种结果的区分性能相当，但在预测 SEARCH 人群中黑人男性的 LNI 结果方面，MUSIC 模型表现出优于 MSK 模型的净效益。