nViso SA, a leading provider of emotion recognition software, today announced it has received a grant from the Swiss Commission for Technology and Innovation (CTI) to extend its pioneering facial analysis technology to provide new levels of predictive analytics in health care.
The project, valued at 700,000 CHF (US$750,000), will run for 18 months and initially focus on leveraging nViso's artificial intelligence-based face imaging capabilities to more accurately categorize patients who require tracheal intubation for surgeries involving general anesthesia.
Initial results and a demonstration of the pilot project, which involves the anesthesiology department at Lausanne University Hospital (CHUV) under the responsibility of PD Dr. Patrick Schoettker, and the Signal Processing Laboratory of the Ecole Polytechnique Fédérale de Lausanne (EPFL) led by Prof. Jean-Philippe Thiran, will be displayed at the World Medtech Forum in Lucerne.
The results of the pilot project, which collected data from 800 patients, include a 97% classification accuracy in predicting the Mallampati score for patients requiring tracheal intubation, a score used by anesthesiologists to predict difficult airway management.
"The leading cause of morbidity and death in general anesthesia are a result of difficulties in intubation. This stems directly from inaccurate assessment of patients that leads to inappropriate choice of material and plans for anesthesia. These results demonstrate that automated predictive analytics can offer better and more efficient ways to characterize patients, compared to traditional manual and subjective approaches. Better accuracy in pre-operative detection, particularly in airway management, allows optimal preparation and reduces patients' risks and health care costs," said PD Dr. Schoettker of CHUV.
nViso's advanced image processing and computer vision algorithms, which to date have been primarily used to analyze emotional responses to marketing stimuli, will be extended to evaluate dynamic features of the face, mouth, and neck, which are critical to predicting potential intubation problems. The recorded biometric data is analysed with mathematical algorithms to generate a prediction score that is more accurate and efficient than existing methods.
"We are extremely pleased to have passed a rigorous screening process of the CTI Medtech board and apply our face analysis and artificial intelligence technology to new areas. This project will allow us to extend the capabilities of our software and it demonstrates its applicability to a variety of use models that can benefit from automated predictive analytics," said Tim Llewellynn, CEO of nViso.
About nViso
nViso is a leading provider of emotion recognition software that interprets human facial micro-expressions and eye movements captured through video. Its solutions use proprietary 3D facial imaging technology with artificial intelligence to track hundreds of different facial points to recognize human emotions. The company combines the latest advancements in computer science, engineering and behavioral sciences to make automatic emotion recognition a viable reality using any image based device. nViso is based at the Swiss Federal Institute of Technology in Lausanne, Switzerland (EPFL).
Please login or sign up to comment.
Commenting guidelines