Yin Ying, Shao Yijun, Ma Phillip, Zeng-Treitler Qing, Nelson Stuart J
Biomedical Informatics Center, George Washington University, Washington, DC 20052, USA.
Veterans Administration Hospital, Washington, DC 20422, USA.
Mach Learn Knowl Extr. 2025 Jun;7(2):36. doi: 10.3390/make7020036. Epub 2025 Apr 17.
We used machine learning (ML) to characterize 894,154 medical records of outpatient visits from the Veterans Administration Central Data Warehouse (VA CDW) by the likelihood of assignment of 200 International Classification of Diseases (ICD) code blocks. Using four different predictive models, we found the ML-derived predictions for the code blocks were consistently more effective in predicting death or 90-day rehospitalization than the assigned code block in the record. We reviewed records of ICD chapter assignments. The review revealed that the ML-predicted chapter assignments were consistently better than those humanly assigned. Impact factor analysis, a method of explanation of AI findings that was developed in our group, demonstrated little effect on any one assigned ICD code block but a marked impact on the ML-derived code blocks of kidney disease as well as several other morbidities. In this study, machine learning was much better than human code assignment at predicting the relatively rare outcomes of death or rehospitalization. Future work will address generalizability using other datasets, as well as addressing coding that is more nuanced than that of the categorization provided by code blocks.
我们使用机器学习（ML），通过200个国际疾病分类（ICD）代码块的分配可能性，对退伍军人事务部中央数据仓库（VA CDW）的894,154份门诊医疗记录进行特征描述。使用四种不同的预测模型，我们发现，对于代码块，由机器学习得出的预测在预测死亡或90天内再次住院方面，始终比记录中分配的代码块更有效。我们审查了ICD章节分配的记录。审查显示，机器学习预测的章节分配始终优于人工分配的章节分配。影响因素分析是我们团队开发的一种解释人工智能结果的方法，它对任何一个分配的ICD代码块几乎没有影响，但对机器学习得出的肾病代码块以及其他几种疾病有显著影响。在本研究中，在预测相对罕见的死亡或再次住院结果方面，机器学习比人工代码分配要好得多。未来的工作将使用其他数据集解决可推广性问题，以及处理比代码块提供的分类更细微的编码问题。
