Singapore General Hospital has deployed a predictive AI tool that helps check a patient’s fitness for surgery.
Dubbed CARES-ML (Combined Assessment of Risk Encountered in Surgery-Machine Learning), the predictive tool generates a surgery risk report and Creates a score. It achieved over 90% accuracy in predicting the risk of surgery during an in-hospital trial.
This tool is based on the CARES calculator which was developed by SGH in 2018. It has since been refined and validated on a local dataset of approximately 100,000 surgical patients from 2015 to 2022.
why it matters
According to SGH, the CARES-ML can be used to improve pre-surgery assessment. “CARES-ML augments the anesthesiologist and surgeon in the assessment of each patient and enhances the clinical team’s decision making and recommendations on perioperative planning of patient care. This ultimately improves patient outcomes and enhances patient safety,” said Hairil Rizal, principal investigator and associate professor and senior consultant in anesthesiology at SGH.
The SGH research team is now working on expanding the AI model to predict the length of a patient’s hospital stay and the risk of pneumonia and stroke. They are also looking at leveraging generative AI like ChatGPT to assign patient status classification levels, which CARES-ML also currently does.
big trend
To ensure patients are fit for surgery, the Central Adelaide Local Health Network in Australia has developed a surgical pre-rehabilitation program called My Prehab, which includes a comprehensive health screening questionnaire and a personalized checklist of items. It is being delivered through digital channels designed by Personify Care.
AI is also being leveraged to monitor the condition of patients after surgery. recently, Manipal Hospitals in India collaborated with Singaporean startup ConnectedLife to develop a Fitbit-paired virtual platform for continuous remote monitoring of patients after surgery.











