Artificial Intelligence demonstrates superiority in foreseeing life-threatening postoperative issues when compared to human doctors.
Johns Hopkins University researchers have developed a groundbreaking AI model that combines Electrocardiogram (ECG) data with patient medical records to predict potentially fatal post-surgery complications with an impressive 85% accuracy.
The research, conducted by a team from the Johns Hopkins School of Medicine and the Whiting School of Engineering, was supported by the National Science Foundation Graduate Research Fellowship DGE2139757. The study's findings are published in the British Journal of Anaesthesia.
The team, led by PhD student Carl Harris, used the ECG, a standard pre-surgical heart test, to create a more accurate way to predict these health risks. They analyzed preoperative ECG data from 37,000 patients who had surgery at Beth Israel Deaconess Medical Center in Boston.
The new AI model has found previously undetected signals in routine heart tests that strongly predict potential deadly complications after surgery. This model significantly outperforms the risk scores currently relied upon by doctors, which are only accurate in about 60% of cases.
The ECG contains a wealth of information about the cardiovascular system, including inflammation, the endocrine system, metabolism, fluids, and electrolytes. By analyzing a large dataset of ECG results with deep learning, the team believes they can extract valuable information not currently available to clinicians.
The team is also interested in determining what other information might be extracted from ECG results through AI. They have developed a method to explain which ECG features might be associated with a heart attack or a stroke after an operation.
The researchers plan to further test the model on datasets from more patients and test it prospectively with patients about to undergo surgery. They hope that this new AI model will improve the assessment of surgical risk and potentially save lives.
Read also:
- Connection Between ADHD and Trauma?
- West Nile Virus detected in Kentucky for the first time; authorities advise locals to adopt safety measures
- "Living at such a rapid pace and taking on so many responsibilities may be beyond our natural limits"
- Enhancing Key Practices: Emphasizing Women's Physical Well-being and Intelligence
