A university of Florida research recently found that AI can be leveraged for identifying postoperative complications. The predictions can be directly applied to patient care. The system named MySurgeryRisk extracts clinical data in real-time, creating an “analytic pipeline”. Medical data can be automatically acquired and delivered to doctors’ mobile devices.
A study published in the JAMA investigated the association of the undertriage to hospital wards after surgical procedures with mortality and resource use. The study was conducted over 74,417 inpatient surgical procedures involving 58,236 adult patients.
According to the researchers, the automated real-time predictions of postoperative complications with mobile device outputs performed well in clinical settings with prospective validation matching surgeons’ predictive accuracy. The platform is powered by ML and has been developed using nearly seven years of data from more than 74000 procedures.
The system consistently matched the surgeon’s accuracy in predicting surgical outcomes. This will aid patients and doctors by augmenting medical decision-making and reducing complications.
The machine also collected data such as vital signs during the procedures and produced fast and accurate predictions of prolonged intensive care unit stays and mortality risk after procedures. The researchers also claimed that the AI calculated the risk of eight major postoperative complications, including sepsis, acute kidney injury and cardiovascular and neurologic issues.
Source: indiaai.gov.in
