askMUSIC:利用临床注册数据构建机器学习模型,告知患者相似人群的前列腺癌治疗选择
本研究利用MUSIC前瞻性注册系统中45家泌尿外科实践2015至2017年的数据,开发并验证随机森林机器学习模型,以预测新诊断前列腺癌患者的治疗选择。共纳入7543例患者,验证队列预测准确度高(多分类AUC 0.81),并构建了基于网络的决策辅助平台。
要点
- 基于注册数据和随机森林模型可准确预测前列腺癌治疗选择(AUC 0.81)。
- 模型预测依据相似特征患者的实际治疗决策,可供新诊断患者在线使用。
- 45家实践2015-2017年7543例患者中,45%接受根治性前列腺切除术。
核心结论
- 利用临床注册数据和机器学习方法构建的网络平台,能对大多数前列腺癌治疗选择生成准确预测。
研究设计与样本
- 基于MUSIC前瞻性注册系统45家泌尿外科实践2015至2017年的数据,开发并验证随机森林机器学习模型。
- 按实践地点分层后随机抽取三分之二患者作为推导队列拟合模型,剩余三分之一作为验证队列评估性能。
- 共识别7543例诊断为前列腺癌的男性患者。
主要发现
- 7543例患者中,45%接受根治性前列腺切除术,30%接受监测,17%接受放射治疗,5.6%接受雄激素剥夺治疗,1.8%接受观察等待。
- 验证队列中个性化预测高度准确,多分类AUC为0.81。
临床怎么用
- 新诊断前列腺癌患者可通过在线平台查看基于相似特征患者实际治疗选择的预测决策,辅助医患共同决策。
局限性
- 模型基于MUSIC注册数据开发,外部泛化性需进一步验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Clinical registries provide physicians with a means for making data-driven decisions but few opportunities exist for patients to interact with registry data to help make decisions. OBJECTIVE: We sought to develop a web-based system that uses a prostate cancer (CaP) registry to provide newly diagnosed men with a platform to view predicted treatment decisions based on patients with similar characteristics. DESIGN, SETTING, AND PARTICIPANTS: The Michigan Urological Surgery Improvement Collaborative (MUSIC) is a quality improvement consortium of urology practices that maintains a prospective registry of men with CaP. We used registry data from 45 MUSIC urology practices from 2015 to 2017 to develop and validate a random forest machine learning model. After fitting the random forest model to a derivation cohort consisting of a random two-thirds sample of patients after stratifying by practice location, we evaluated the model performance in a validation cohort consisting of the remaining one-third of patients using a multiclass area under the curve (AUC) measure and calibration plots. RESULTS AND LIMITATIONS: We identified 7543 men diagnosed with CaP, of whom 45% underwent radical prostatectomy, 30% surveillance, 17% radiation therapy, 5.6% androgen deprivation, and 1.8% watchful waiting. The personalized prediction for patients in the validation cohort was highly accurate (AUC 0.81). CONCLUSIONS: Using clinical registry data and machine learning methods, we created a web-based platform for patients that generates accurate predictions for most CaP treatments. PATIENT SUMMARY: We have developed and tested a tool to help men newly diagnosed with prostate cancer to view predicted treatment decisions based on similar patients from our registry. We have made this tool available online for patients to use.
引用
- Auffenberg GB, Ghani KR, Ramani S, et al. askMUSIC: Leveraging a Clinical Registry to Develop a New Machine Learning Model to Inform Patients of Prostate Cancer Treatments Chosen by Similar Men. Eur Urol. 2018. PMID: 30318331. doi:10.1016/j.eururo.2018.09.050
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。