Learning dynamic treatment strategies for coronary heart diseases by artificial intelligence: real-world data-driven
Haihong Guo1,2,3, Jiao Li2, Hongyan Liu4
1School of Information, Renmin University of China, 59 Zhongguancun Street, Haidian District, Beijing, 100872, China.
Insights
An AI model was developed to provide dynamic treatment recommendations for coronary heart disease (CHD) patients, aiming to reduce mortality and learn from clinician best practices. The model showed promise in improving patient outcomes and clinical decision support.
Area of Science:
- Artificial Intelligence in Medicine
- Clinical Decision Support Systems
- Cardiovascular Disease Research
Background:
- Coronary heart disease (CHD) is a leading global cause of death, necessitating advanced, dynamic treatment strategies.
- Current treatment approaches require continuous adaptation due to the urgent and severe nature of CHD.
- There is a critical need for improved clinical decision support tools for managing CHD patients effectively.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI) model for dynamic treatment recommendations in coronary heart disease (CHD) patients.
- To improve patient outcomes by learning optimal treatment pathways from real-world clinical data.
- To enhance clinical decision support by mimicking best practices identified from experienced clinicians.
Main Methods:
- A supervised reinforcement learning-long short-term memory (SRL-LSTM) framework was employed, integrating supervised learning (SL) and reinforcement learning (RL).
- The AI model processed patient diagnoses and evolving health status to recommend specific drug treatments.
- Experiments utilized a large ICU database of 13,762 CHD patients, comparing SRL-LSTM against other AI models for mortality reduction and clinician decision similarity.
Main Results:
- The AI model demonstrated a reduction in estimated in-hospital mortality through its RL component.
- The model successfully learned clinical best practices via its SL component, showing high similarity to clinician decisions for surviving patients.
- The AI-driven dynamic treatment strategies were found to be clinically interpretable, based on relevant CHD risk factors and monitoring indexes.
Conclusions:
- A novel AI pipeline was proposed for learning dynamic treatment strategies to improve CHD patient outcomes and emulate clinician expertise.
- The developed AI model offers a potential pathway for enhanced clinical decision support in managing coronary heart disease.
- Further research and development are necessary to translate this AI model into widespread clinical practice.
Background:
Coronary heart disease (CHD) has become the leading cause of death and one of the most serious epidemic diseases worldwide. CHD is characterized by urgency, danger and severity, and dynamic treatment strategies for CHD patients are needed. We aimed to build and validate an AI model for dynamic treatment recommendations for CHD patients with the goal of improving patient outcomes and learning best practices from clinicians to help clinical decision support for treating CHD patients.
Methods:
We formed the treatment strategy as a sequential decision problem, and applied an AI supervised reinforcement learning-long short-term memory (SRL-LSTM) framework that combined supervised learning (SL) and reinforcement learning (RL) with an LSTM network to track patients' states to learn a recommendation model that took a patient's diagnosis and evolving health status as input and provided a treatment recommendation in the form of whether to take specific drugs. The experiments were conducted by leveraging a real-world intensive care unit (ICU) database with 13,762 admitted patients diagnosed with CHD. We compared the performance of the applied SRL-LSTM model and several state-of-the-art SL and RL models in reducing the estimated in-hospital mortality and the Jaccard similarity with clinicians' decisions. We used a random forest algorithm to calculate the feature importance of both the clinician policy and the AI policy to illustrate the interpretability of the AI model.
Results:
Our experimental study demonstrated that the AI model could help reduce the estimated in-hospital mortality through its RL function and learn the best practice from clinicians through its SL function. The similarity between the clinician policy and the AI policy regarding the surviving patients was high, while for the expired patients, it was much lower. The dynamic treatment strategies made by the AI model were clinically interpretable and relied on sensible clinical features extracted according to monitoring indexes and risk factors for CHD patients.
Conclusions:
We proposed a pipeline for constructing an AI model to learn dynamic treatment strategies for CHD patients that could improve patient outcomes and mimic the best practices of clinicians. And a lot of further studies and efforts are needed to make it practical.
Related Concept Videos
01:27Coronary Artery Disease V: Interprofessional Care
01:26Coronary Artery Disease IV: Preventive Measures
01:30Coronary Artery Disease I: Introduction
01:26Atherosclerosis III: Management
01:26Angina IV: Management
01:26Coronary Artery Disease II: Pathophysiology