Department of Urology, Tampere University Hospital, Tampere, Finland.
Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland.
Clin Interv Aging. 2024 Feb 12;19:237-245. doi: 10.2147/CIA.S432368. eCollection 2024.
To evaluate a random forest (RF) algorithm of lower urinary tract symptoms (LUTS) as a predictor of all-cause mortality in a population-based cohort.
A population-based cohort of 3143 men born in 1924, 1934, and 1944 was evaluated using a mailed questionnaire including the Danish Prostatic Symptom Score (DAN-PSS-1) to assess LUTS as well as questions on medical conditions and behavioral and sociodemographic factors. Surveys were repeated in 1994, 1999, 2004, 2009 and 2015. The cohort was followed-up for vital status until the end of 2018. RF uses an ensemble of classification trees for prediction with a good flexibility and without overfitting. RF algorithms were developed to predict the five-year mortality using LUTS, demographic, medical, and behavioral factors alone and in combinations.
A total of 2663 men were included in the study, of whom 917 (34%) died during follow-up (median follow-up time 15.0 years). The LUTS-based RF algorithm showed an area under the curve (AUC) 0.60 (95% CI 0.52-0.69) for five-year mortality. An expanded RF algorithm, including LUTS, medical history, and behavioral and sociodemographic factors, yielded an AUC 0.73 (0.65-0.81), while an algorithm excluding LUTS yielded an AUC 0.71 (0.62-0.78).
An exploratory RF algorithm using LUTS can predict all-cause mortality with acceptable discrimination at the group level. In clinical practice, it is unlikely that LUTS will improve the accuracy to predict death if the patient's background is well known.
评估基于随机森林（RF）算法的下尿路症状（LUTS）作为人群全因死亡率的预测因子。
本研究基于一个人群队列，共纳入了 1924 年、1934 年和 1944 年出生的 3143 名男性，采用邮寄问卷的方式进行评估，问卷包括丹麦前列腺症状评分（DAN-PSS-1）以评估 LUTS 以及有关医疗状况、行为和社会人口学因素的问题。调查于 1994 年、1999 年、2004 年、2009 年和 2015 年重复进行。队列随访至 2018 年底，以确定存活状态。RF 算法使用分类树的集合进行预测，具有很好的灵活性，不会发生过拟合。RF 算法用于开发单独和组合使用 LUTS、人口统计学、医学和行为因素来预测五年死亡率。
共有 2663 名男性纳入本研究，其中 917 名（34%）在随访期间死亡（中位随访时间 15.0 年）。基于 LUTS 的 RF 算法预测五年死亡率的曲线下面积（AUC）为 0.60（95%CI 0.52-0.69）。包含 LUTS、病史以及行为和社会人口学因素的扩展 RF 算法的 AUC 为 0.73（0.65-0.81），而不包含 LUTS 的算法的 AUC 为 0.71（0.62-0.78）。
使用 LUTS 的探索性 RF 算法可以在群组水平上以可接受的区分度预测全因死亡率。在临床实践中，如果患者的背景情况已知，LUTS 不太可能提高预测死亡的准确性。
