URUMQI -- A research team in Xinjiang Uygur Autonomous Region in northwest China has developed a novel diagnostic technique that combines spectral analysis with artificial intelligence to rapidly and accurately distinguish between two lethal and easily confused cardiac emergencies, namely aortic dissection and myocardial infarction.

Their method requires only five to 10 minutes of blood sample analysis and achieves a diagnostic accuracy of 94.06 percent in differentiating acute myocardial infarction from aortic dissection, according to a study published in the journal Engineering Applications of Artificial Intelligence.

The research was conducted by a team from the People's Hospital of Xinjiang Uygur Autonomous Region led by Professor Yang Yining, in collaboration with a team from Xinjiang University led by Professor Lyu Xiaoyi.

Both myocardial infarction and aortic dissection present with sudden, severe chest pain, and yet their treatments are fundamentally opposed. A myocardial infarction results from a blocked coronary artery and requires immediate clot-busting therapy to restore blood flow. In contrast, an aortic dissection involves a tear in the aorta, and such drugs are strictly contraindicated as they can trigger catastrophic bleeding. Misdiagnosis can, therefore, be fatal.

Traditional diagnosis depends heavily on imaging techniques such as contrast-enhanced CT scans. These methods require expensive equipment and significant time, and are difficult to deploy in ambulances or primary care facilities, said Yan Lei, a member of the research team. With mortality rates for both conditions escalating the longer it takes to receive effective treatment, a fast and portable diagnostic tool is clearly an urgent priority.

The team's breakthrough lies in capturing the distinct molecular fingerprints these diseases leave in the blood. The researchers employed two complementary techniques, Raman spectroscopy and infrared spectroscopy, to detect biochemical information from patient serum samples.

For further improvements in diagnostic efficiency, the team developed a deep learning model that integrates data from both spectroscopy methods to enable rapid classification of the two diseases.

A diagnostic prototype based on this technology is currently undergoing multi-center clinical validation. According to the research team, the portable device applying this technology could one day become standard equipment in ambulances and community clinics, enabling earlier intervention and buying precious time for patients facing these life-threatening conditions.