Intel’s work with Philips on bone modeling and lung segmentation demonstrate innovative work at the intersection of healthcare and technology, based on Artificial Intelligence solutions.
Globally as well as in India, the healthcare sector is undergoing a steady transformation. Like many other industries, healthcare has been disrupted by the influx of new technologies—Cloud, Big Data, Machine Learning, Artificial Intelligence (AI) technology, to name a few. Since a crucial step in healthcare is compiling and analysing information (like medical records and other past history), finding the ability to transform the data into insights is both a competitive advantage and a strategic imperative across healthcare. In this context, India provides a huge opportunity, and we can see the beginnings of some relevant work, based on AI solutions.One such example is Intel’s work with Philips at the latter’s Bengaluru campus, wherein insights are driven on the analytics applications that run on the edge devices, in the clinics.
“Intel’s AI solutions are helping to solve some of the most pressing healthcare challenges. Data holds the promise to help reduce costs, improve quality, increase access and pave the way to precision health,” said Prakash Mallya, managing director – Sales & Marketing Group, Intel India. “We are developing models and systems that can assist clinicians in their diagnosis so they can work more efficiently—this would enable earlier diagnosis and ability for families to manage their finances better. And we are helping develop algorithms that could enable faster drug discovery—after faster diagnosis, easier access to relevant medicines could save lives that are often lost owing to chronic diseases,” he informed.
The Philips Innovation Campus in Bangalore has been working on several healthcare analytics projects and applications. The applications are mainly used for screening for diseases using medical images such as X-ray, MRI, and ultrasound. Using Intel Xeon Scalable processors and the OpenVINO toolkit, Intel and Philips tested two healthcare use cases for Deep Learning inference models: One on X-rays of bones for bone-age-prediction modeling, the other on CT scans of lungs for lung segmentation. Intel and Philips achieved a speed improvement of 188 times for the bone-age-prediction model, and a 38 times speed improvement for the lung-segmentation model over the baseline measurements.
Said Ravi Ramaswamy, senior director & head – Health Systems, Philips Innovation Campus, “AI can be a game changer for healthcare, and we call it adaptive intelligence. It combines AI and other methods with knowledge of the clinical, operational, or personal context in which they are used. AI can address paucity of healthcare infrastructure, enabling doctors and hospitals to be more productive and help better patient outcomes. This in turn would bring down cost of care, lead to more patients getting treated, and improved quality of care.”
Another area, that finds application of AI is in the critical care space. “The opportunities are endless and AI if applied with a local context, can enable intelligent healthcare anytime, anywhere,” said Ramaswamy.
At a macro-level, global AI is forecast to reach $200 billion by 2022, and if the current trend holds, healthcare will make up a significant portion of that market. It has the potential to reduce administrative costs, cut patient wait times, and diagnose diseases. Already, AI is enabling healthcare clinicians, researchers and academics to achieve advances and breakthroughs today. “Intel has turned the availability of large datasets into an advantage by leveraging the power of deep learning algorithms—this would address the issue of having limited doctors, wherein machines are able to manage common symptom and diagnosis, and also manage OPD related queries,” Mallya added.