Department of Biomedical Informatics, The University of Utah, 421 Wakara Way, Suite 140, Salt Lake City, UT, 84108, USA.
Department of Biomedical Informatics, The University of Utah, 421 Wakara Way, Suite 140, Salt Lake City, UT, 84108, USA; Department of Clinical Research and Leadership, The George Washington University, 2600 Virginia Ave., NW, First Floor, Washington DC, 20037, USA.
Int J Med Inform. 2020 Jul;139:104122. doi: 10.1016/j.ijmedinf.2020.104122. Epub 2020 Mar 21.
In ambulatory care settings, physicians largely rely on clinical guidelines and guideline-based clinical decision support (CDS) systems to make decisions on hypertension treatment. However, current clinical evidence, which is the knowledge base of clinical guidelines, is insufficient to support definitive optimal treatment.
The goal of this study is to test the feasibility of using deep learning predictive models to identify optimal hypertension treatment pathways for individual patients, based on empirical data available from an electronic health record database.
This study used data on 245,499 unique patients who were initially diagnosed with essential hypertension and received anti-hypertensive treatment from January 1, 2001 to December 31, 2010 in ambulatory care settings. We used recurrent neural networks (RNN), including long short-term memory (LSTM) and bi-directional LSTM, to create risk-adapted models to predict the probability of reaching the BP control targets associated with different BP treatment regimens. The ratios for the training set, the validation set, and the test set were 6:2:2. The samples for each set were independently randomly drawn from individual years with corresponding proportions.
The LSTM models achieved high accuracy when predicting individual probability of reaching BP goals on different treatments: for systolic BP (<140 mmHg), diastolic BP (<90 mmHg), and both systolic BP and diastolic BP (<140/90 mmHg), F1-scores were 0.928, 0.960, and 0.913, respectively.
The results demonstrated the potential of using predictive models to select optimal hypertension treatment pathways. Along with clinical guidelines and guideline-based CDS systems, the LSTM models could be used as a powerful decision-support tool to form risk-adapted, personalized strategies for hypertension treatment plans, especially for difficult-to-treat patients.
在门诊环境中，医生主要依靠临床指南和基于指南的临床决策支持（CDS）系统来决定高血压的治疗方案。然而，目前的临床证据（即临床指南的知识库）不足以支持明确的最佳治疗方案。
本研究旨在测试使用深度学习预测模型根据电子健康记录数据库中可用的经验数据，为个体患者确定最佳高血压治疗途径的可行性。
本研究使用了 245499 名独特患者的数据，这些患者于 2001 年 1 月 1 日至 2010 年 12 月 31 日在门诊环境中被最初诊断为原发性高血压并接受抗高血压治疗。我们使用了包括长短期记忆（LSTM）和双向 LSTM 在内的递归神经网络（RNN）来创建风险适应模型，以预测不同降压治疗方案相关的血压控制目标的达成概率。训练集、验证集和测试集的比例为 6:2:2。每个集的样本都是从各年独立随机抽取的，比例相同。
LSTM 模型在预测不同治疗方案下个体达到血压目标的概率时具有很高的准确性：对于收缩压（<140mmHg）、舒张压（<90mmHg）和收缩压与舒张压（<140/90mmHg），F1 评分分别为 0.928、0.960 和 0.913。
结果表明，使用预测模型选择最佳高血压治疗途径具有潜力。LSTM 模型与临床指南和基于指南的 CDS 系统一起，可以作为一种强大的决策支持工具，为高血压治疗计划制定风险适应的个性化策略，特别是对于难治性患者。
