AI In Medicine: AI-Enhanced Thermal Imaging Revolutionizes Coronary Artery Disease Diagnosis
Nikhil Prasad Fact checked by:Thailand Medical News Team Jun 05, 2024 1 month, 3 weeks, 1 day, 42 minutes ago
AI In Medicine: A groundbreaking combination of facial thermal imaging and artificial intelligence (AI) can accurately predict the presence of coronary artery disease (CAD), according to research published in BMJ Health & Care Informatics. This non-invasive, real-time approach surpasses traditional diagnostic methods in accuracy and efficiency, paving the way for enhanced clinical practice. The study covered in this
AI In Medicine news report, conducted on 460 patients with suspected heart disease, showcases the potential of this innovative technique, though further testing on larger and more diverse populations is needed.
AI-Enhanced Thermal Imaging Revolutionizes Coronary Artery Disease Diagnosis
The Limitations of Current Diagnostic Methods
Current guidelines for diagnosing CAD heavily rely on risk factor assessments, which are not always accurate or widely applicable. Typically, diagnosis involves a combination of electrocardiograms (ECGs), angiograms, and blood tests. These methods, while effective, are often time-consuming, invasive, and require significant clinical resources.
Thermal imaging, which detects temperature variations on the skin’s surface by capturing emitted infrared radiation, offers a non-invasive alternative. This technique can identify areas of abnormal blood circulation and inflammation, which are indicative of CAD. When combined with AI, which excels at processing and integrating complex data, the accuracy of thermal imaging diagnostics can be significantly enhanced.
The Study: Thermal Imaging and AI in Action
The researchers aimed to evaluate the feasibility of using thermal imaging alongside AI to predict CAD in a cohort of 460 individuals with suspected heart disease. The participants, with an average age of 58, included 126 women (27.5%). Before undergoing confirmatory examinations, thermal images of their faces were captured to develop and validate an AI-assisted imaging model for CAD detection.
Out of the 460 participants, 322 (70%) were confirmed to have CAD. These individuals were generally older, more likely to be male, and exhibited more lifestyle, clinical, and biochemical risk factors. They also had a higher prevalence of preventive medication use.
The thermal imaging plus AI approach demonstrated approximately 13% greater accuracy in predicting CAD compared to traditional risk assessments. Among the key thermal indicators, the most influential was the overall left-right temperature difference of the face, followed by the maximum and average facial temperatures. Notably, the average temperature of the left jaw region emerged as the strongest predictive feature, followed by the temperature range of the right eye region and the left-right temperature difference of the temple regions.
Identifying Traditional Risk Factors with Thermal Imaging
In addition to predicting CAD, the thermal imaging plus AI method effectively identified traditional CAD risk factors such as high cholesterol,
male gender, smoking, excess weight (BMI), fasting blood glucose levels, and indicators of inflammation.
The researchers acknowledge the study’s limitations, including the relatively small sample size and the fact that it was conducted at a single center with participants already referred for confirmatory tests. Despite these constraints, the team remains optimistic about the potential applications and research opportunities presented by thermal imaging and AI.
Potential for Clinical Application
The study’s findings suggest that thermal imaging, combined with AI, could revolutionize CAD diagnosis. As a biophysiological health assessment tool, this method offers disease-relevant information beyond traditional clinical measures, potentially enhancing the assessment of atherosclerotic cardiovascular disease (ASCVD) and related chronic conditions.
The non-contact, real-time nature of thermal imaging allows for instant disease assessment at the point of care, which could streamline clinical workflows and save valuable time for physician-patient decision-making. Furthermore, this approach has the potential to enable mass prescreening, making it a cost-effective option for widespread clinical adoption.
The Future of CAD Diagnosis
The researchers emphasize the need for further investigations involving larger and more diverse patient populations to validate the findings and establish the generalizability of the current results. They commented, “Our developed thermal imaging prediction models, based on advanced machine learning technology, have exhibited promising potential compared with the current conventional clinical tools. Further investigations incorporating larger sample sizes and diverse patient populations are needed to validate the external validity and generalizability of the current findings.”
Conclusion
This study highlights the transformative potential of combining facial thermal imaging with AI to predict CAD. By offering a non-invasive, real-time diagnostic tool, this approach could significantly improve the accuracy and efficiency of CAD diagnosis, ultimately enhancing patient care and clinical outcomes. As research progresses, thermal imaging and AI may become integral components of standard clinical practice, providing a powerful tool for early detection and management of coronary artery disease.
The study findings by the research team from Tsinghua University, Beijing-China, Fuwai Hospital, National Center for Cardiovascular Diseases, Beijing-China and the Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing-China were published in the peer reviewed journal: BMJ Health & Care Informatics.
https://informatics.bmj.com/content/31/1/e100942
For the latest on
AI In Medicine, keep on logging to Thailand Medical News.
Read Also:
https://www.thailandmedical.news/news/revolutionary-ai-tool-enhances-brain-tumor-classification
https://www.thailandmedical.news/news/ai-in-medicine-scientists-utilize-artificial-intelligence-in-coronary-ct-angiography-for-accurate-diagnosis-and-development-of-precision-medicine-prot
https://www.thailandmedical.news/news/ai-in-medicine-yale-scientist-develop-ai-model-that-can-detect-left-ventricular-systolic-dysfunction-lvsd-from-ecgs-obtained-by-wearable-devices
Share
Tweet
Share
