AI in healthcare still faces many challenges

“Artificial intelligence (AI) is being widely applied in clinical cardiology, especially in diagnosis, prognosis and treatment decision support. However, the application of AI in internal medicine practice is limited by transparency, reliability and ethical issues.”

That is the information shared by MSc.-MD Doan Thi Thanh Nguyet, Hoan My Saigon Hospital at the hospital scientific conference with the theme "Comprehensive approach and new technology in modern medicine" held on October 25.

According to MSc. Doan Thi Thanh Nguyet, AI has demonstrated remarkable potential in many areas of cardiology. In heart failure, the PanEcho deep learning system allows for automatic measurement of ejection fraction and detection of valvular heart disease with expert-level accuracy. The Mayo Clinic's AI electrocardiogram (AI ECG) algorithm detects asymptomatic left ventricular dysfunction from a single-lead ECG, opening up the possibility of remote heart failure screening.

Doctor prepares to perform MRI scan on patient

In coronary artery disease, the US Food and Drug Administration (FDA)-approved method for diagnosing coronary heart disease using artificial intelligence (Cleerly ISCHEMIA) can quantify atherosclerotic plaques and predict myocardial ischemia. In the emergency department, the RAPIDx AI system supports the management of chest pain, helping to increase compliance with treatment guidelines. AI also improves the detection of latent atrial fibrillation via routine ECG or wearable devices (Apple Watch, AliveCor). In addition, in hypertension, machine learning models allow the detection of masked hypertension, secondary hypertension, predict cardiovascular events and identify groups of patients who benefit from intensive treatment...

However, the challenges in applying AI are major barriers such as: data bias, lack of evidence, limited interpretability and unclear legal framework. In addition, over-reliance on AI can undermine doctors' clinical skills, while data security and patient privacy remain significant challenges.

“AI is moving towards multimodal learning models that combine ECG, imaging, and genetic data to predict cardiovascular risk more accurately. FDA-approved devices, telehealth tools, and digital twins that simulate patients promise to expand applications in internal medicine practice,” said MSc. Doan Thi Thanh Nguyet, MD.

Also at the conference, Dr. Cao Hung Phong, Head of the Digestive Endoscopy Unit, said that AI can help detect small lesions, polyps, or early-stage cancers that the human eye may miss. Not only does it stop at detection, AI also supports the classification of the nature of the lesions, helping doctors make accurate treatment decisions. In addition, AI also contributes to standardizing the endoscopic process, improving image quality, shortening procedure time, and supporting the training of young human resources.

According to Mr. Nguyen Huu Thinh, Department of Diagnostic Imaging, the automatic AI technology will analyze CT images, search and quantify lung nodules with high accuracy, and support classification according to Lung-RADS standards (lung cancer screening system) to help provide clear and consistent stage assessment. With the ability to directly compare images from before and after scans, the software not only allows monitoring of changes in size or morphology but also automatically updates growth rate and growth index, helping doctors save time, improve reliability and focus more on clinical decisions.

The 2025 annual hospital scientific conference with the theme "Comprehensive approach and new technology in modern medicine" has reports of 31 in-depth research topics, covering many important fields such as cardiovascular, digestive, endoscopy, orthopedic trauma - spine, neurology - stroke, diagnostic imaging, oncology, intensive care, urology, nutrition, nursing...

According to Dr. Nguyen Ngoc Bao Long, Director of Hoan My Saigon Hospital, the conference provides a multi-dimensional scientific perspective, the result of the process of applying medical knowledge and modern technology in medical examination and treatment activities at the hospital.

THANH SON

Source: https://www.sggp.org.vn/ai-trong-y-te-van-con-nhieu-thach-thuc-post819919.html