[ad_1]
Nvidia and the Scripps Research Translational Institute announced Tuesday a partnership to promote the use of artificial intelligence for early warning and prevention of diseases. More specifically, they will create a center of excellence to accelerate the creation of artificial intelligence applications using data from genomic and digital health sensors.
Until now, AI applications in medicine have largely focused on medical imaging, told reporters Kimberly Powell, vice president of healthcare at Nvidia, last week. Although medical imaging is a powerful diagnostic tool, she said that AI should be applied to medical data collected from a growing number of sources. Data from DNA profiles or portable technologies, for example, can go beyond diagnostics to help doctors and researchers "think about preventing disease or predicting disease risk in the first place".
Researchers from Nvidia and Scripps will work together to develop deep learning approaches to improve mutational detection using genomic data. From mutation detections, deep learning can provide phenotypic information, which can be combined with digital sensor data to create new opportunities for disease prevention and intervention. Patients and clinicians are collecting more and more sensor data from devices such as smartwatches, blood pressure cuffs, and blood glucose meters.
In addition to creating datasets, researchers will need to develop tools such as AI training frameworks that are compatible with genomics and sensor data, Powell said. Existing frameworks were built for text, speech or images, she explained, while "genomics and sensor data will look very different".
To prepare genomic data for a typical setting, it can be transformed into an image, said Powell. "This translation of sensor data into an image that an in-depth learning framework can accept … is something we can provide in a software tool," she said.
When researchers from Nvidia and Scripps build this type of tool, they make it public for the general public.
Source link
