Objective

Machine learning (ML) algorithm can improve risk prediction because ML can select features and segment continuous variables effectively unbiased. We generated a risk score model for mortality with ML algorithms in East-Asian patients with heart failure (HF).

Methods

From the Korean Acute Heart Failure (KorAHF) registry, we used the data of 3683 patients with 27 continuous and 44 categorical variables. Grouped Lasso algorithm was used for the feature selection, and a novel continuous variable segmentation algorithm which is based on change-point analysis was developed for effectively segmenting the ranges of the continuous variables. Then, a risk score was assigned to each feature reflecting nonlinear relationship between features and survival times, and an integer score of maximum 100 was calculated for each patient.

Results

During 3-year follow-up time, 32.8% patients died. Using grouped Lasso, we identified 15 highly significant independent clinical features. The calculated risk score of each patient ranged between 1 and 71 points with a median of 36 (interquartile range: 27–45). The 3-year survival differed according to the quintiles of the risk score, being 80% and 17% in the 1st and 5th quintile, respectively. In addition, ML risk score had higher AUCs than MAGGIC-HF score to predict 1-year mortality (0.751 vs. 0.711, P < 0.001).

Conclusions

In East-Asian patients with HF, a novel risk score model based on ML and the new continuous variable segmentation algorithm performs better for mortality prediction than conventional prediction models.

Clinical Trial Registration

Unique identifier: INCT01389843 https://clinicaltrials.gov/ct2/show/NCT01389843.

中文翻译：

---

预测心力衰竭的存活率：基于机器学习和变化点算法的风险评分

客观的

机器学习 (ML) 算法可以改进风险预测，因为 ML 可以有效地无偏地选择特征和分割连续变量。我们使用 ML 算法在东亚心力衰竭 (HF) 患者中生成了死亡率风险评分模型。

方法

从韩国急性心力衰竭 (KorAHF) 登记处，我们使用了 3683 名患者的数据，其中包含 27 个连续变量和 44 个分类变量。采用分组Lasso算法进行特征选择，提出了一种基于变点分析的连续变量分割算法，有效分割连续变量的范围。然后，为每个特征分配一个风险评分，反映特征与生存时间之间的非线性关系，并为每个患者计算最大 100 的整数评分。

结果

在 3 年的随访期间，32.8% 的患者死亡。使用分组套索，我们确定了 15 个非常重要的独立临床特征。每个患者的计算风险评分范围在 1 到 71 分之间，中位数为 36（四分位距：27-45）。3 年生存率因风险评分的五分位数而异，第 1 和第 5 分位数分别为 80% 和 17%。此外，ML 风险评分在预测 1 年死亡率方面的 AUC 高于 MAGGIC-HF 评分（0.751 对 0.711，P  < 0.001）。

结论

在东亚 HF 患者中，基于 ML 的新型风险评分模型和新的连续变量分割算法比传统预测模型在死亡率预测方面表现更好。

临床试验注册

唯一标识符：INCT01389843 https://clinicaltrials.gov/ct2/show/NCT01389843。