Related Experiment Videos
Predicting Optimal Hypertension Treatment Pathways Using Recurrent Neural Networks
Xiangyang Ye1, Qing T Zeng2, Julio C Facelli1
1Department of Biomedical Informatics, The University of Utah, 421 Wakara Way, Suite 140, Salt Lake City, UT, 84108, USA.
Insights
Deep learning models accurately predict optimal hypertension treatment pathways for individual patients. These models can enhance clinical decision support systems for personalized hypertension management.
Area of Science:
- Cardiology
- Medical Informatics
- Artificial Intelligence
Background:
- Physicians in ambulatory care settings rely on clinical guidelines and decision support systems for hypertension treatment.
- Current clinical evidence is insufficient for definitive optimal hypertension treatment strategies.
Purpose of the Study:
- To test the feasibility of deep learning predictive models for identifying optimal hypertension treatment pathways.
- To personalize hypertension treatment based on individual patient data from electronic health records.
Main Methods:
- Utilized a dataset of 245,499 patients with essential hypertension treated between 2001-2010.
- Employed recurrent neural networks (RNN), including long short-term memory (LSTM) and bi-directional LSTM, for risk-adapted predictive modeling.
- Models predicted the probability of achieving blood pressure (BP) control targets with different anti-hypertensive regimens.
Main Results:
- LSTM models demonstrated high accuracy in predicting individual BP control probabilities.
- Achieved F1-scores of 0.928 for systolic BP, 0.960 for diastolic BP, and 0.913 for both (<140/90 mmHg).
Conclusions:
- Predictive models show potential for optimizing hypertension treatment selection.
- LSTM models can serve as decision-support tools, complementing guidelines and CDS systems for personalized, risk-adapted hypertension management, particularly for challenging cases.
Background:
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.
Objective:
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.
Materials And Methods:
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.
Results:
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.
Conclusions:
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.