Netcare is seeking regulatory approval for a scientific algorithm that predicts early warning signs of life-threatening deterioration in patients after a successful clinical study in Netcare ICU and high care units.
The artificial neural network applies a machine learning algorithm to analyse real-time patient data, including heart rate, blood pressure, oxygen saturation, and respiratory rate, which are continuously monitored via Netcare’s digital health platform, to predict clinical risk before it becomes otherwise detectable.
Now, the hospital group and Telehealth Competence Centre (TCC) Clinical Solutions GmbH, a German-based clinical AI manufacturer, said they are taking the next step in their partnership as Netcare applies to SAHPRA to become the South African distributor of the technology for wider use in its hospitals, supported by evidence generated during the clinical trial.
After development by TCC scientists, the complex algorithm had been meticulously tested over several years by researchers from Netcare, TCC, the University of KwaZulu-Natal, and DigitalOn Tech (Pty) Ltd in South Africa.
“Already, the quick Sequential Organ Failure Assessment (qSOFA) score has proven valuable in the critical care setting as an indicator of a patient’s potential risk of developing serious conditions like heart failure, respiratory failure requiring mechanical ventilation, infection, sepsis, or acute cardiac arrhythmia,” said Professor Reitze Rodseth, head of clinical data innovation and research at Netcare.
“Building on the capabilities of the algorithm, we are now looking at models that automatically predict the risk of developing renal failure or serious respiratory difficulties while they are in hospital –and even after they have been discharged home, if necessary.”
Dr Anchen Laubscher, group medical director of Netcare, said that judicious use of AI had become an essential part of healthcare.
“The clinical indicators derived from this technology provide valuable data points to support doctors’ treatment decisions, often creating opportunities to prevent clinical deterioration,” she added.
See more from MedicalBrief archives:
Algorithms accurately gauge unconsciousness under general anaesthesia
AI tech gives doctors preview of blood clots forming – Tokyo study
AI cannot replicate the ‘gut feelings’ of human doctors – MIT study
AI analysis IDs warning signs for stillbirth, newborn issues