Beinecke Jacqueline Michelle, Anders Patrick, Schurrat Tino, Heider Dominik, Luster Markus, Librizzi Damiano, Hauschild Anne-Christin
Department of Mathematics and Computer Science at the Philipps University Marburg, Germany; Institute for Medical Informatics at the University Medical Center Göttingen, Göttingen, Germany.
Department of Nuclear Medicine, University Hospital Marburg, Germany.
Comput Biol Med. 2022 Apr;143:105263. doi: 10.1016/j.compbiomed.2022.105263. Epub 2022 Feb 2.
The main screening parameter to monitor prostate cancer recurrence (PCR) after primary treatment is the serum concentration of prostate-specific antigen (PSA). In recent years, Ga-68-PSMA PET/CT has become an important method for additional diagnostics in patients with biochemical recurrence.
While Ga-68-PSMA PET/CT performs better, it is an expensive, invasive, and time-consuming examination. Therefore, in this study, we aim to employ modern multivariate Machine Learning (ML) methods on electronic health records (EHR) of prostate cancer patients to improve the prediction of imaging confirmed PCR (IPCR).
We retrospectively analyzed the clinical information of 272 patients, who were examined using Ga-68-PSMA PET/CT. The PSA values ranged from 0 ng/mL to 2270.38 ng/mL with a median PSA level at 1.79 ng/mL. We performed a descriptive analysis using Logistic Regression. Additionally, we evaluated the predictive performance of Logistic Regression, Support Vector Machine, Gradient Boosting, and Random Forest. Finally, we assessed the importance of all features using Ensemble Feature Selection (EFS).
The descriptive analysis found significant associations between IPCR and logarithmic PSA values as well as between IPCR and performed hormonal therapy. Our models were able to predict IPCR with an AUC score of 0.78 ± 0.13 (mean ± standard deviation) and a sensitivity of 0.997 ± 0.01. Features such as PSA, PSA doubling time, PSA velocity, hormonal therapy, radiation treatment, and injected activity show high importance for IPCR prediction using EFS.
This study demonstrates the potential of employing a multitude of parameters into multivariate ML models to improve identification of non-recurring patients compared to the current focus on the main screening parameter (PSA). We showed that ML models are able to predict IPCR, detectable by Ga-68-PSMA PET/CT, and thereby pave the way for optimized early imaging and treatment.
监测前列腺癌初次治疗后复发（PCR）的主要筛查参数是前列腺特异性抗原（PSA）的血清浓度。近年来，Ga-68-PSMA PET/CT已成为生化复发患者进行额外诊断的重要方法。
虽然Ga-68-PSMA PET/CT表现更佳，但它是一项昂贵、有创且耗时的检查。因此，在本研究中，我们旨在对前列腺癌患者的电子健康记录（EHR）应用现代多变量机器学习（ML）方法，以改善对影像证实的PCR（IPCR）的预测。
我们回顾性分析了272例接受Ga-68-PSMA PET/CT检查患者的临床信息。PSA值范围为0 ng/mL至2270.38 ng/mL，PSA水平中位数为1.79 ng/mL。我们使用逻辑回归进行描述性分析。此外，我们评估了逻辑回归、支持向量机、梯度提升和随机森林的预测性能。最后，我们使用集成特征选择（EFS）评估所有特征的重要性。
描述性分析发现IPCR与对数PSA值之间以及IPCR与所进行的激素治疗之间存在显著关联。我们的模型能够以0.78±0.13（均值±标准差）的AUC评分和0.997±0.01的灵敏度预测IPCR。使用EFS分析发现，诸如PSA、PSA倍增时间、PSA速度、激素治疗、放射治疗和注射活性等特征对IPCR预测具有高度重要性。
本研究表明，与目前专注于主要筛查参数（PSA）相比，在多变量ML模型中纳入多种参数具有改善识别无复发患者的潜力。我们表明ML模型能够预测通过Ga-68-PSMA PET/CT可检测到的IPCR，从而为优化早期影像检查和治疗铺平道路。
