Simplified Machine Learning Models Can Accurately Identify High-Need High-Cost Patients With Inflammatory Bowel Disease.
Simplified Machine Learning Models Can Accurately Identify High-Need High-Cost Patients With Inflammatory Bowel Disease.
复制标题
简化的机器学习模型可以准确地识别高需求、高成本的炎症性肠病患者。
DOI：
10.14309/ctg.0000000000000507
复制
发表时间：
2022-07-01
影响因子：
3.6
通讯作者：
中科院分区：
文献类型：
--
作者：
住院是炎症性肠病（IBD）相关医疗费用和发病率的主要驱动因素。传统的预测模型在识别计划外医疗利用风险最高的患者方面表现不佳。识别高需求和高成本（HNHC）的患者可以减少计划外的医疗保健利用和医疗保健成本。我们使用全国再入院数据库（2013年全国再入院数据库中的模型推导和2017年全国再入院数据库中的验证）在IBD住院成人患者中进行了一项回顾性队列研究。我们构建了2种基于树的算法（决策树分类器和使用梯度提升框架的决策树[XGBoost]），并比较了传统的逻辑回归，以识别有成为HNHC风险的患者（日历年住院总天数最高十分位的患者）。在47，402例成人IBD住院患者中，我们确定了4，717例HNHC患者。决策树分类器模型（住院时间、Charlson合并症指数、手术、虚弱风险评分和年龄）的受试者工作特征曲线下面积（AUC）平均值在推导数据集中为0.78 ± 0.01，在验证数据集中为0.78 ± 0.02。XGBoost（住院时间、手术、慢性疼痛、药物滥用和糖尿病并发症）在推导和验证数据集中的平均AUC分别为0.79 ± 0.01和0.75 ± 0.02，而传统logistic回归的AUC分别为0.55 ± 0.01和0.56 ± 0.01（消化性溃疡、感觉异常、骨髓炎、肾衰竭和淋巴瘤）。在IBD住院患者中，使用管理索赔数据的简化树型机器学习算法可以准确预测有进展为HNHC风险的患者。
Hospitalization is the primary driver of inflammatory bowel disease (IBD)-related healthcare costs and morbidity. Traditional prediction models have poor performance at identifying patients at highest risk of unplanned healthcare utilization. Identification of patients who are high-need and high-cost (HNHC) could reduce unplanned healthcare utilization and healthcare costs. We conducted a retrospective cohort study in adult patients hospitalized with IBD using the Nationwide Readmissions Database (model derivation in the 2013 Nationwide Readmission Database and validation in the 2017 Nationwide Readmission Database). We built 2 tree-based algorithms (decision tree classifier and decision tree using gradient boosting framework [XGBoost]) and compared traditional logistic regression to identify patients at risk for becoming HNHC (patients in the highest decile of total days spent in hospital in a calendar year). Of 47,402 adult patients hospitalized with IBD, we identified 4,717 HNHC patients. The decision tree classifier model (length of stay, Charlson Comorbidity Index, procedure, Frailty Risk Score, and age) had a mean area under the receiver operating characteristic curve (AUC) of 0.78 ± 0.01 in the derivation data set and 0.78 ± 0.02 in the validation data set. XGBoost (length of stay, procedure, chronic pain, drug abuse, and diabetic complication) had a mean AUC of 0.79 ± 0.01 and 0.75 ± 0.02 in the derivation and validation data sets, respectively, compared with AUC 0.55 ± 0.01 and 0.56 ± 0.01 with traditional logistic regression (peptic ulcer disease, paresthesia, admission for osteomyelitis, renal failure, and lymphoma) in derivation and validation data sets, respectively. In hospitalized patients with IBD, simplified tree-based machine learning algorithms using administrative claims data can accurately predict patients at risk of progressing to HNHC.
登录
查看更多内容
DOI：
10.1016/j.cgh.2018.02.015
发表时间：
2018-08
期刊：
Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
影响因子：
--
作者：
Nguyen NH;Khera R;Ohno-Machado L;Sandborn WJ;Singh S
通讯作者：
Singh S
影响因子：
12.6
作者：
Regueiro, Miguel;Click, Benjamin;Szigethy, Eva
通讯作者：
Szigethy, Eva
影响因子：
4.9
作者：
Waljee AK;Lipson R;Wiitala WL;Zhang Y;Liu B;Zhu J;Wallace B;Govani SM;Stidham RW;Hayward R;Higgins PDR
通讯作者：
Higgins PDR
DOI：
10.1016/j.cgh.2020.08.010
发表时间：
2021-10
期刊：
Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
影响因子：
--
作者：
Qian AS;Nguyen NH;Elia J;Ohno-Machado L;Sandborn WJ;Singh S
通讯作者：
Singh S
影响因子：
120.7
作者：
Dieleman, Joseph L.;Squires, Ellen;Murray, Christopher J. L.
通讯作者：
Murray, Christopher J. L.