AI is expected to help improve healthcare services in many different ways. One area that needs focus is that of primary care, the first port of call for most patients. However, for various reasons, doctors at the primary level are often unable to diagnose and treat a range of relatively common conditions. This results in many such conditions being missed or patients getting referred to tertiary centers. This, coupled with the overall shortage of professionals, especially in rural settings, leads to poor quality of care at primary care levels, huge load at tertiary and specialist hospitals, and economic and emotional burden on patients and their families.

A first priority would be an e-health infrastructure that enables the collection and management of longitudinal health data of patients across hospitals. This can be complemented by AI-enabled tools that help primary care doctors, especially at PHC's, to diagnose and manage a wider variety of conditions: as examples, diagnostic point-of-care equipment for better treatment, and clinical decision support systems for management of chronic conditions at local levels. At the other end of care, improved screening and diagnostic tools can help reduce the load on specialists. We also discuss research at the E-Health Research Center at IIIT-B both in the areas of health data management as well as applications of AI in patient interactions and medical image analysis.

Dr. T K Srikanth is a Professor in Computer Science at IIIT Bangalore. His research interests are in systems for the management and analysis of healthcare data, data privacy, geometric modeling, and computer graphics. He is a co-convenor of the E-Health Research Center at IIITB and is actively involved in multiple collaborative research projects in healthcare, with a focus on public health. Prior to joining IIITB, he had extensive experience in the software industry, in India and in the US, in mobile and multimedia technologies and geometric modeling. He has a Ph.D. in Computer Science from Cornell University and a B.Tech. in Mechanical Engineering from IIT Madras.

Medical care today is fragmented and inefficient. On one hand, you have disorganized paper-based, error-prone, clunky systems that do not have the patient's or the caregiver's best interest in mind. On the other hand, you have technology-based "perceived" solutions that seem to be the panacea for what ails health care. Unfortunately, these solutions are themselves poorly designed, cumbersome to use, and often make a bad problem worse. They do not help and they do not work.

In a typical health care setting, there are two actors - the patient (the recipient of care) and the care provider (doctors, nurses, and allied professionals). The event that unfolds is care.

Today's actors in the healthcare scene are disenfranchised. What is acutely needed is a framework for empowering them. The framework needs to have an enabler that is tuned to the needs of the two actors and is coupled to the actions that the actors perform.

Augmentation of care through effective technology is the only solution for these problems that can be scaled to a global level.

Dileep Raman is the co-founder and Chief of Healthcare at Cloudphysician, a healthcare technology company that remotely provides ICU expertise to hospitals that do not have access to ICU specialist doctors. In his capacity as the Chief of Healthcare, Dileep is responsible for overseeing the clinical operations and product development of the company. Dileep and his co-founder have grown Cloudphysician to a 100 people organization. He has led large teams in remote healthcare delivery and has led the development of Cloudphysician's state-of-the-art ICU management platform, RADAR. Dileep trained in Pulmonary, Critical Care, and Sleep at the Cleveland Clinic Foundation, USA. He graduated medical school from the Government Medical College Thrissur, India, with a distinguished gold medal in internal medicine for academic excellence. Following which he completed his residency in Internal Medicine at Texas Tech University, USA, where he served as Chief Medical Resident. Dileep has numerous teaching awards for resident and fellow education, including the Cleveland Clinic Foundation teaching excellence award.

Light-weight Convolutional Neural Networks (CNNs) are mobile-friendly models that can provide inference without the need for any specialized hardware. These models can be very effective in point-of-care settings, where the detection of disease has to be performed in real-time. The talk will highlight a few developments of the Medical Imaging Group (MIG) at the Indian Institute of Science, especially towards COVID19 management and diagnosis. Deployment of these lightweight networks on embedded platforms to show highly versatility as well as prove optimal performance in terms of being accurate will also be highlighted. The developed models having latency in the same order as other lightweight networks without compromising the accuracy will also be shown. A first priority would be an e-health infrastructure that enables the collection and management of longitudinal health data of patients across hospitals. This can be complemented by AI-enabled tools that help primary care doctors, especially at PHC's, to diagnose and manage a wider variety of conditions: as examples, diagnostic point-of-care equipment for better treatment, and clinical decision support systems for management of chronic conditions at local levels. At the other end of care, improved screening and diagnostic tools can help reduce the load on specialists. We also discuss research at the E-Health Research Center at IIIT-B both in the areas of health data management as well as applications of AI in patient interactions and medical image analysis.

Phaneendra Yalavarthy received B.Sc. and M.Sc. degrees in physics from Sri Sathya Sai University, Puttaparthy, India, in 1999 and 2001 respectively. He also obtained an M.Sc. degree in Engineering from the Indian Institute of Science, Bangalore, India in 2004. He received a Ph.D., working as a US Department of Defense Breast Cancer Pre-doctoral Fellow, in biomedical computation from Dartmouth College, Hanover, USA, in 2007. He worked as a postdoctoral research associate in the Department of Radiation Oncology, School of Medicine, Washington University in St. Louis, USA, from 2007-2008. Currently, he is working as a Professor in the Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, India.

His research interests include Computational methods in medical imaging, deep learning in medical imaging, medical image processing (reconstruction/analysis), physiological signal processing, diffuse optical imaging, and photoacoustic imaging. He is a senior member of IEEE, OSA, & SPIE and serves as an associate editor of IEEE Transactions on Medical Imaging. More details can be found @ http://cds.iisc.ac.in/faculty/yalavarthy/

A prime challenge in building data-driven inference models is the unavailability of a statistically significant amount of labeled data. Datasets are typically designed for a specific purpose and accordingly are weakly labeled for only a single class of tasks instead of being exhaustively annotated. Despite there being multiple datasets that cumulatively represent a large corpus, their weak labeling poses a challenge for direct use in knowledge integration. In the case of retinal images, specific datasets exist for the development of data-driven machine learning-based algorithms for segmenting anatomical landmarks like vessels and optic disc as well as pathologies like microaneurysms, hemorrhages, hard exudates, and soft exudates. The aspiration is to learn to semantically segment all such classes using only a single fully convolutional neural network (FCN), while the challenge being that there is no single training dataset with all classes annotated. We solve this problem by training a single network using separate weakly labeled datasets.

Essentially we use multi-task and adversarial learning approaches in addition to the classically employed objective of distortion loss minimization for semantic segmentation using FCN. This talk would focus on a general introduction to learning theory, the objectives of performance optimization in deep neural networks through learning, and the art of crafting new learning rules in view of solving such classes of critical problems. This talk would also introduce the "Turing Test Loss" which has been the driver in solving such optimization problems which require perception loss minimization rather than the classical distortion loss minimization. This approach has also helped in developing a just-in-time intervention for COVID-19 CT-based diagnosis while integrating knowledge from multiple partially labeled datasets. Advancing beyond this, a specific use to neuro-imaging would be discussed, whereby employing these basic concepts, we have been able to generate missing MRI sequences in neuro-imaging. This allows us to engage in obtaining missing data sequences when it is not possible to obtain all sequences in MRI imaging.

Dr. Debdoot Sheet is an Assistant Professor of Electrical Engineering with a joint appointment at the Centre of Excellence in Artificial Intelligence at the Indian Institute of Technology Kharagpur and founder of SkinCurate Research. He also serves as the Joint Project Director of the IIT Kharagpur AI4ICPS I Hub Foundation and is the Local Organizing Chair for the IEEE International Symposium on Biomedical Imaging (ISBI) 2022 Kolkata, India. He received the BTech degree in electronics and communication engineering in 2008 from the West Bengal University of Technology, Kolkata, MS, and Ph.D. degrees from the Indian Institute of Technology Kharagpur in 2010 and 2014, respectively. His current research interests include deep learning, high-density multi-linear algebra tensor computation, computational medical imaging, image and multidimensional signal processing, and the social implications of technology. He has been a Chartered Engineer since 2021, DAAD alumni and was a visiting scholar at the Technical University of Munich during 2011-12, recipient of the IEEE Computer Society Richard E. Merwin Student Scholarship in 2012, the Fraunhofer Applications Award at the Indo-German Grand Science Slam in 2012, winner of the GE Edison Challenge 2013, Distinguished Alumni of IEM Kolkata 2016, Senior Member of IEEE class of 2019, member of MICCAI, Life member of IE (India), BMESI, IUPRAI, and serves as Regional Editor of IEEE Pulse.

To combat the rising burden of non-communicable diseases (NCDs) in India, the Ministry of Health and Family Welfare launched the Population-Based Screening and Management of NCDs program under Ayushman Bharat Health and Wellness Centers in 2018. Dell Technologies and Tata Trusts have been partnering with the Ministry since 2017 to develop the technology system for the PBS NCD initiative. It consists of a suite of mobile and web apps on a cloud platform for health workers, doctors, and health administrators and has been deployed in states across the country.

One of the innovations piloted under the program has been an integration with a Clinical Decision Support System developed by AIIMS for medical officers at the public health facilities for hypertension and diabetes. It ran as an implementation science study in Punjab in collaboration with AIIMS & CCDC and has successfully demonstrated the concept of task shifting and the adoption of technology in a busy public health setting.

Sunita Nadhamuni is Head of Digital LifeCare at Dell Technologies, leading an innovation group for the digital transformation of public healthcare services working with the Govt of India for the Ayushman Bharat health program. This is a social impact, CSR initiative of Dell. Sunita has a unique combination of more than a decade of IT experience from the Silicon Valley in the US and a decade in India leading social impact initiatives. She was the CEO and is now Chairperson of Arghyam, a leading charitable foundation working towards water security in India. Sunita has an MS from Rensselaer Polytechnic Institute in NY, and a BE from Andhra University, was a TED India Fellow and on several non-profit boards.