AI-powered retinal diagnostics and non-invasive monitoring signal a shift toward accessible healthcare, and Dr. Abhishek Appaji, an Indian researcher and academic based in Bengaluru, is at the forefront of it.
Dr. Appaji was recently honored with the prestigious 2026 IEEE Theodore W. Hissey Outstanding Young Professional Award, making him the first recipient from India. This global recognition celebrates his dual contributions to cutting-edge healthcare technology and leadership within the engineering community.
Dr. Appaji’s work focuses on democratizing healthcare through AI-driven, non-invasive diagnostic solutions. His innovations include AI-based retinal imaging technology that uses the eye as a “window to the brain” to screen for psychiatric disorders such as schizophrenia and bipolar disorder, offering a low-cost, scalable alternative to traditional diagnostics.
He has also made non-intrusive smart patient monitoring systems, developed in collaboration with industry, that track vital signs using under-mattress sensors, now deployed across 200+ hospitals and thousands of homes in India.
And then there is the portable digital X-ray technology designed for emergency and rural healthcare settings, addressing critical gaps in rapid diagnostics.
Dr. Appaji told The Tech Panda that receiving the 2026 IEEE Theodore W. Hissey Outstanding Young Professional Award is the most rewarding and memorable gift of his life, “Personally, this honor validates a decade and a half of dedication to the academic and research as well as the global engineering community. Being the first recipient from India and the first academician to be so honored is a milestone that I share with my family, my mentors, and the colleagues who have supported the vision of ‘Advancing Technology for Humanity’.”
“I see this as a responsibility to mentor the next generation of innovators, proving that professional leadership and academic rigor can go hand-in-hand to solve global health challenges”
“Firstly, the award provides a global stage to advocate for the transition of Lab Research into Life-saving Solutions, specifically focusing on AI-assisted clinical interpretation. Second, as an academician, I see this as a responsibility to mentor the next generation of innovators, proving that professional leadership and academic rigor can go hand-in-hand to solve global health challenges,” says the researcher, who is also a social entrepreneur and mentor, actively supporting startup incubation and translating academic innovations into real-world healthcare solutions.
Transition Toward AI-Driven Diagnostics
Dr. Appaji’s work focuses on non-invasive, AI-driven diagnostics. The Tech Panda asked him if the India is close to replacing traditional diagnostic methods, and where he sees the biggest resistance coming from.
The transition toward AI-driven diagnostics is not about the replacement of traditional methods, says Dr. Appaji, but rather a shift toward ease with precision.
While we are very close to AI becoming the primary screening tool, it functions as a co-pilot rather than the final diagnostic authority
“In many areas, we are currently in a hybrid era where AI-driven tools are moving from the lab to the bedside. While we are very close to AI becoming the primary screening tool, it functions as a co-pilot rather than the final diagnostic authority,” he explains.
Dr. Appaji’s systems allow for rapid, non-invasive screening that identifies markers traditional methods might miss. These tools act as an early warning system, using signal and image processing to identify subtle clinical markers—such as retinal changes—long before traditional, more invasive benchmarks are met.
However, he points out that despite these technical advancements, significant barriers remain that prevent AI from fully replacing traditional workflows.
“The biggest resistance comes from the Trust Gap and the clinical community’s need for Explainable AI which I happen to teach in class for my students. Practitioners are understandably hesitant to rely on black box systems; they require a clear understanding of the logic behind an AI’s conclusion to align it with their own medical expertise,” he says.
“Furthermore, moving a prototype from a research environment like B.M.S. College of Engineering into a clinical setting involves navigating complex regulatory pathways and the Valley of Death in MedTech innovation,” he adds.
Eye as a “Window to the Brain
Dr. Appaji’s retinal imaging research positions the eye as a “window to the brain” for psychiatric screening. This does involve ethical and clinical challenges of diagnosing mental health conditions through AI.
The eye is a unique pathway, but utilizing it as a “window to the brain” for psychiatric screening requires navigating complex clinical and ethical landscapes, says the academician.
“From a clinical perspective, the primary challenge lies in establishing a definitive causal link between retinal biomarkers and specific mental health conditions. While AI excels at identifying subtle patterns in retinal imaging, we must ensure these findings are reliable diagnostic indicators rather than incidental correlations. Validating these tools across diverse populations is essential to ensure they are robust enough for real-world medical use,” he explains.
While AI excels at identifying subtle patterns in retinal imaging, we must ensure these findings are reliable diagnostic indicators rather than incidental correlations. Validating these tools across diverse populations is essential to ensure they are robust enough for real-world medical use
The ethical challenges are equally significant, particularly regarding data privacy and the risk of diagnostic labeling, he adds, “Since retinal data can potentially reveal early markers of psychiatric conditions long before symptoms appear, we must address who owns this sensitive information and how it is protected.”
He points out that there is a real concern that such data could be misused, leading to social stigma or even insurance-based discrimination.
“My research, spanning my time at Maastricht University, Ohio State University and B.M.S. College of Engineering, has focused on embedding ethical safeguards directly into the algorithmic development process. We must ensure that AI serves as a supportive tool for early intervention and patient care, rather than a tool for exclusion or privacy breaches,” he reiterates.
From Lab Research to Real-World Healthcare Adoption in India
Dr. Appaji’s monitoring systems are already deployed across hundreds of hospitals and homes in India. However, it hasn’t been easy. Moving a prototype from a research lab at B.M.S. College of Engineering into a life-saving tool at hospitals and homes involved overcoming significant structural and systemic hurdles.
The primary barrier in India, he says, is navigating what is called the Valley of Death. This is the difficult transition between a successful academic proof-of-concept and a clinically validated, scalable medical product.
Translating deep-tech research into a robust healthcare solution requires specialized expertise in regulatory compliance, clinical trials, and manufacturing—areas that fall outside the typical academic scope.
“As an academic researcher, I have found that the path to commercialization is particularly challenging because our traditional institutional frameworks are designed for publication and research. Translating deep-tech research into a robust healthcare solution requires specialized expertise in regulatory compliance, clinical trials, and manufacturing—areas that fall outside the typical academic scope. I have been fortunate to work alongside pioneers like Dozee, InnAccel, Autoyos, who are at the forefront of these medical technologies,” he says.
Affordability & Scale
Many AI healthcare innovations struggle with affordability and scale. What has been key to making his technologies viable in low-resource and rural settings, Dr. Appaji says, is a commitment to frugal innovation, the philosophy of designing for the bottom of the pyramid.
Many high-end AI innovations fail to scale because they are built on the assumption of high-speed internet, stable power grids, and expensive specialized hardware and few of them don’t even need AI, hence we need responsible AI
“Many high-end AI innovations fail to scale because they are built on the assumption of high-speed internet, stable power grids, and expensive specialized hardware and few of them don’t even need AI, hence we need responsible AI,” he points out.
He cites the example of the Smart Eye Kiosk, which is designed to be operated by local health workers with minimal training, “We prioritize non-intrusive and robust hardware like the Smart Eye Kiosk. This decentralizes healthcare, moving the diagnostic power from tertiary hospitals directly into the community.”
Transforming Research into Deployable Healthcare Solutions
As someone straddling academia, entrepreneurship, and global engineering leadership, Dr. Appaji believes structural changes are needed to better translate research breakthroughs into deployable healthcare solutions.
“To bridge the gap between academic research and real-world medical impact, we need to shift from a Publication-Centric to a Product-Centric academic culture not only in healthcare but otherwise,” he says.
To bridge the gap between academic research and real-world medical impact, we need to shift from a Publication-Centric to a Product-Centric academic culture not only in healthcare but otherwise
In our current system, he points out, the primary incentive for a researcher is to publish in high-impact journals.
“While fundamental research is the need in science, we need institutional frameworks that prioritize and more reward patenting, technology transfer, and commercialization as equally prestigious academic outputs,” he adds.
He thanks accreditation agencies that have started giving scores for these aspects and also statutory bodies and government (ministry of education) for bringing policies for startups and innovation within academia ex: National Innovation and Startup Policy (NISP).
“I work with many doctors who are now innovators who start working with us from defining problems to helping us to validate the device we develop in spite of them being busy with their clinical time and saving lives,” he says.
As AI continues to integrate into healthcare, its role is increasingly that of an assistive partner, enhancing precision, enabling early detection, and expanding reach rather than replacing traditional systems outright. Yet, as Dr. Appaji’s work shows, the real challenge extends beyond innovation into trust, ethics, and the long journey from lab research to real-world adoption. His call for a shift toward product-driven academic ecosystems and frugal innovation calls out the fact that success of AI in healthcare will depend not just on what it can do, but on how responsibly and widely it can be deployed.
