AI Cardiac Event Forecasting for Asymptomatic Risk Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to accurately predict sudden cardiovascular events in asymptomatic individuals within a near-term timeframe, relying instead on long-term risk estimators that are not individual-specific.
Innovation Solution
A large language model is trained using a unique dataset of medical data from asymptomatic individuals who experienced sudden cardiac death, incorporating coronary artery calcium scans, coronary CT angiographies, chest CTs, and blood samples, to predict near-term cardiovascular events through an AI-enabled system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a 10-year risk estimator based on CVD risk factors is used, then population-based epidemiological prediction is provided, but individual-level prediction accuracy is insufficient
Solution Approach 1:
The system changes the prediction timeframe parameter from long-term (10 years) to near-term (months to a year), and transforms the prediction approach from population-based epidemiological estimation to individual-level AI/ML prediction using multiple data types including imaging, blood markers, and clinical data
Solution Approach 2:
The system adds multiple dimensions of data collection and analysis including coronary artery calcium scans, coronary CT angiography, chest CT, blood markers, and electrocardiograms, transitioning from single-parameter risk factor assessment to multi-dimensional comprehensive evaluation
2Reliability
If current risk assessment tools are used, then general cardiovascular risk estimation is provided, but sudden cardiac death prediction in asymptomatic individuals is not possible
Solution Approach 1:
The system applies local quality by customizing the prediction model for specific high-risk populations (asymptomatic individuals with abnormal findings on imaging or blood tests) rather than providing generic population risk assessment, enabling tailored prediction for those most susceptible to sudden cardiac death
Solution Approach 2:
The system performs preliminary identification of high-risk individuals through screening for abnormal coronary artery calcium scores, coronary CT angiography findings, blood markers, or electrocardiogram abnormalities before the actual cardiac event occurs, allowing for early intervention
Data Source
AI summary
According to an aspect of the present invention, there is provided computer-implemented method for forecasting near-term sudden cardiovascular events, comprising: pretraining a large language model transformer architecture using a processor with an associated computer memory device to recognize text associated with sudden cardiovascular events cases reporting sudden cardiovascular events following a medical exam appointment; obtaining relevant data regarding an asymptomatic individual comprising one or more of a coronary artery calcium (CAC) scan, a coronary CT angiography (CCTA), chest CT, blood markers, and electrocardiogram; providing the relevant data of the asymptomatic individual to the trained computer-implemented artificial neural network; receiving a forecast of the chance of near-term sudden cardiovascular events in the asymptomatic individual; and recommending the next diagnostic or therapeutic step for the asymptomatic individual.