机器学习辅助决策支持模型以更好地识别需要扩大盆腔淋巴结清扫的前列腺癌患者
本研究纳入248例接受根治性前列腺切除术及盆腔淋巴结清扫的患者,利用临床、活检及精确MRI特征构建机器学习模型(LR、SVM、随机森林)并与MSKCC列线图比较。机器学习模型AUC(0.868–0.906)高于MSKCC列线图(0.816,P<0.001),在控制漏诊ePLND<3%时,随机森林模型正预测值更高(51.4%/49.6% vs 40.3%),可多豁免ePLND(56.9%/54.4% vs 43.9%)。
要点
- 机器学习模型AUC 0.868–0.906,高于MSKCC列线图0.816(P<0.001)。
- 控制漏诊ePLND<3%时,随机森林正预测值51.4%/49.6% vs MSKCC 40.3%。
- 5–15%阈值下机器学习模型可豁免≥50%的ePLND,漏诊淋巴结侵犯<3%。
核心结论
- 机器学习模型在5–15%阈值下优于MSKCC列线图,可豁免≥50%的ePLND且漏诊淋巴结侵犯风险<3%。
研究设计与样本
- 纳入248例接受根治性前列腺切除术及ePLND或PLND的患者,利用18个整合特征构建逻辑回归、支持向量机和随机森林模型,并与MSKCC列线图比较。
主要发现
- 手术发现59/248(23.8%)例淋巴结侵犯。
- 机器学习模型AUC:随机森林+/-为0.906/0.885,SVM+/-为0.891/0.868,逻辑回归+/-为0.886/0.882,均高于MSKCC列线图0.816(P<0.001)。
- MSKCC列线图校准在整个预测概率范围内倾向于低估淋巴结侵犯风险。
- 决策曲线分析显示机器学习模型在风险阈值≤80%时显著改善风险预测。
- 控制漏诊ePLND<3%时,随机森林+/-正预测值51.4%/49.6% vs MSKCC 40.3%,负预测值97.2%/97.8% vs 97.2%,豁免ePLND数量56.9%/54.4% vs 43.9%。
关键数值与推荐
- 机器学习模型采用5–15%阈值。
- 控制漏诊ePLND<3%时,随机森林+/-正预测值51.4%/49.6% vs MSKCC 40.3%,负预测值97.2%/97.8% vs 97.2%,豁免ePLND数量56.9%/54.4% vs 43.9%。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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
OBJECTIVES: To develop a machine learning (ML)-assisted model to identify candidates for extended pelvic lymph node dissection (ePLND) in prostate cancer by integrating clinical, biopsy, and precisely defined magnetic resonance imaging (MRI) findings. PATIENTS AND METHODS: In all, 248 patients treated with radical prostatectomy and ePLND or PLND were included. ML-assisted models were developed from 18 integrated features using logistic regression (LR), support vector machine (SVM), and random forests (RFs). The models were compared to the Memorial SloanKettering Cancer Center (MSKCC) nomogram using receiver operating characteristic-derived area under the curve (AUC) calibration plots and decision curve analysis (DCA). RESULTS: A total of 59/248 (23.8%) lymph node invasions (LNIs) were identified at surgery. The predictive accuracy of the ML-based models, with (+) or without (-) MRI-reported LNI, yielded similar AUCs (RFs+ /RFs- : 0.906/0.885; SVM+ /SVM- : 0.891/0.868; LR+ /LR- : 0.886/0.882) and were higher than the MSKCC nomogram (0.816; P < 0.001). The calibration of the MSKCC nomogram tended to underestimate LNI risk across the entire range of predicted probabilities compared to the ML-assisted models. The DCA showed that the ML-assisted models significantly improved risk prediction at a risk threshold of ≤80% compared to the MSKCC nomogram. If ePLNDs missed was controlled at <3%, both RFs+ and RFs- resulted in a higher positive predictive value (51.4%/49.6% vs 40.3%), similar negative predictive value (97.2%/97.8% vs 97.2%), and higher number of ePLNDs spared (56.9%/54.4% vs 43.9%) compared to the MSKCC nomogram. CONCLUSIONS: Our ML-based model, with a 5-15% cutoff, is superior to the MSKCC nomogram, sparing ≥50% of ePLNDs with a risk of missing <3% of LNIs.
引用
- Hou Y, Bao ML, Wu CJ, et al. A machine learning-assisted decision-support model to better identify patients with prostate cancer requiring an extended pelvic lymph node dissection. BJU Int. 2019. PMID: 31392808. doi:10.1111/bju.14892
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。