基于机器学习的美国普通人群甲状旁腺激素升高预测
该研究基于美国国家健康与营养调查(NHANES)2003至2006年数据,纳入8208名20岁及以上成人,利用人口学、生活方式和生化指标构建6种机器学习模型预测甲状旁腺激素(PTH)升高(>74 pg/mL)。随机森林、梯度提升机和SuperLearner的AUC最高(均为0.79),eGFR是最重要预测因子。作者认为该模型有助于在临床实践中早期识别PTH升高,但需进一步研究评估其能否改善健康结局。
要点
- 在8208名美国成人中,753人(9.2%)PTH>74 pg/mL。
- 随机森林、梯度提升机和SuperLearner的AUC最高,均为0.79。
- eGFR是随机森林和梯度提升机模型中最重要的预测因子。
核心结论
- 在美国全国代表性数据中开发了预测模型,可能有助于在普通临床实践中准确早期发现PTH升高。
- 作者指出需进一步研究评估该预测工具能否改善不良健康结局。
研究设计与样本
- 基于人群的研究,纳入NHANES 2003至2006年20岁及以上、有血清完整PTH测量的成人。
- 使用NHANES 2003至2004队列(n=4096)训练6种机器学习预测模型:逻辑回归(含和不含样条)、lasso回归、随机森林、梯度提升机(GBM)和SuperLearner。
- 使用NHANES 2005至2006队列(n=4112)评估模型性能,包括受试者工作特征曲线下面积(AUC)。
主要发现
- 8208名美国成人中,753人(9.2%)PTH大于74 pg/mL。
- 6种算法中,随机森林AUC(95%CI)=0.79(0.76-0.81)、GBM AUC(95%CI)=0.78(0.75-0.81)、SuperLearner AUC(95%CI)=0.79(0.76-0.81)最高。
- 在逻辑回归模型中为估算肾小球滤过率(eGFR)添加三次样条后,AUC从0.69提高到0.77。
- 含样条的逻辑回归模型校准性能最佳(校准斜率[95%CI]=0.96[0.86-1.06]),其他算法校准较差。
- 在所有纳入的协变量中,eGFR是随机森林模型和GBM最重要的预测因子。
临床怎么用
- 作者认为该预测模型可能有助于在普通临床实践中准确早期发现PTH升高。
- 作者指出需进一步研究评估该预测工具能否改善不良健康结局。
局限性
- 作者指出需进一步研究评估该预测工具能否改善不良健康结局。
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
CONTEXT: Although elevated parathyroid hormone (PTH) levels are associated with higher mortality risks, the evidence is limited as to when PTH is expected to be elevated and thus should be measured among the general population. OBJECTIVE: This work aimed to build a machine learning-based prediction model of elevated PTH levels based on demographic, lifestyle, and biochemical data among US adults. METHODS: This population-based study included adults aged 20 years or older with a measurement of serum intact PTH from the National Health and Nutrition Examination Survey (NHANES) 2003 to 2006. We used the NHANES 2003 to 2004 cohort (n = 4096) to train 6 machine-learning prediction models (logistic regression with and without splines, lasso regression, random forest, gradient-boosting machines [GBMs], and SuperLearner). Then, we used the NHANES 2005 to 2006 cohort (n = 4112) to evaluate the model performance including area under the receiver operating characteristic curve (AUC). RESULTS: Of 8208 US adults, 753 (9.2%) showed PTH greater than 74 pg/mL. Across 6 algorithms, the highest AUC was observed among random forest (AUC [95% CI] = 0.79 [0.76-0.81]), GBM (AUC [95% CI] = 0.78 [0.75-0.81]), and SuperLearner (AUC [95% CI] = 0.79 [0.76-0.81]). The AUC improved from 0.69 to 0.77 when we added cubic splines for the estimated glomerular filtration rate (eGFR) in the logistic regression models. Logistic regression models with splines showed the best calibration performance (calibration slope [95% CI] = 0.96 [0.86-1.06]), while other algorithms were less calibrated. Among all covariates included, eGFR was the most important predictor of the random forest model and GBM. CONCLUSION: In this nationally representative data in the United States, we developed a prediction model that potentially helps us to make accurate and early detection of elevated PTH in general clinical practice. Future studies are warranted to assess whether this prediction tool for elevated PTH would improve adverse health outcomes.
引用
- Kato H, Hoshino Y, Hidaka N, et al. Machine Learning-Based Prediction of Elevated PTH Levels Among the US General Population. J Clin Endocrinol Metab. 2022. PMID: 36125184. doi:10.1210/clinem/dgac544
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。