Frost David W, Vembu Shankar, Wang Jiayi, Tu Karen, Morris Quaid, Abrams Howard B
Division of General Internal Medicine, University of Toronto, Ontario, Canada; University Health Network, Toronto, Ontario; OpenLab at University Health Network, Toronto, Ontario; University of Toronto, Ontario, Canada.
Donnelly Center for Cellular and Biomolecular Research, Toronto, Ontario; University of Toronto, Ontario, Canada.
Am J Med. 2017 May;130(5):601.e17-601.e22. doi: 10.1016/j.amjmed.2016.12.008. Epub 2017 Jan 5.
A small proportion of patients account for a high proportion of healthcare use. Accurate preemptive identification may facilitate tailored intervention. We sought to determine whether machine learning techniques using text from a family practice electronic medical record can be used to predict future high emergency department use and total costs by patients who are not yet high emergency department users or high cost to the healthcare system.
Text from fields of the cumulative patient profile within an electronic medical record of 43,111 patients was indexed. Separate training and validation cohorts were created. After processing, 11,905 words were used to fit a logistic regression model. The primary outcomes of interest in the 12 months after prediction were 3 or more emergency department visits and being in the top 5% in healthcare expenditures. Outcomes were assessed through linkage to administrative databases housed at the Institute for Clinical Evaluative Sciences.
In the model to predict frequent emergency department visits, after excluding patients who were high emergency department users in the previous year, the area under the receiver operating characteristic curve was 0.71. By using the same methodology, the model to predict the top 5% in total system costs had an area under the receiver operating characteristic curve of 0.76.
Machine learning techniques can be applied to analyze free text contained in electronic medical records. This dataset is more predictive of patients who will generate future high costs than future emergency department visits. It remains to be seen whether these predictions can be used to reduce costs by early interventions in this cohort of patients.
一小部分患者占用了很大比例的医疗资源。准确的预先识别可能有助于进行针对性干预。我们试图确定，使用家庭医疗电子病历中的文本的机器学习技术，是否可用于预测尚未频繁使用急诊科或对医疗系统成本较高的患者未来的高急诊科使用率和总成本。
对43111名患者电子病历中累积患者资料字段的文本进行索引。创建了单独的训练和验证队列。经过处理后，使用11905个单词来拟合逻辑回归模型。预测后12个月内感兴趣的主要结局是3次或更多次急诊科就诊以及医疗支出处于前5%。通过与临床评估科学研究所的行政数据库进行关联来评估结局。
在预测频繁急诊科就诊的模型中，排除上一年频繁使用急诊科的患者后，受试者工作特征曲线下面积为0.71。使用相同方法，预测系统总成本前5%的模型的受试者工作特征曲线下面积为0.76。
机器学习技术可应用于分析电子病历中包含的自由文本。该数据集对未来产生高成本患者的预测能力比对未来急诊科就诊的预测能力更强。这些预测能否通过对这组患者进行早期干预来降低成本还有待观察。
