AI and Healthcare

How does AI Prediction Translate to Patient Care? [David Fajgenbaum] - with Dr. Sanjay Juneja

AI prediction is transforming patient care by accelerating how life-saving treatments are identified, repurposed, and delivered to those in need. Discover how cutting-edge data analysis can uncover overlooked therapies and drive faster clinical decisions that impact real-world outcomes. Dr. Sanjay Juneja interviews Dr. David Fajgenbaum, co-founder of Every Cure, to reveal actionable strategies for leveraging artificial intelligence in healthcare systems. Learn how AI-powered frameworks are optimizing treatment selection, guiding clinical workflows, and informing executive decisions across provider networks, telehealth, laboratories, and diagnostics.

Can AI Find the Cures We've Overlooked for Decades? - with Dr. Sanjay Juneja [FULL PODCAST]

The idea that artificial intelligence can uncover life-saving treatments hidden in plain sight is no longer science fiction. In a healthcare system that often favors costly innovation over accessible solutions, using AI to repurpose existing drugs offers a path to faster, affordable breakthroughs. Join Dr. Sanjay Juneja and Dr. David Fajgenbaum, co-founder of Every Cure, as they reveal how AI is accelerating the identification of overlooked therapies for rare and complex diseases. Learn about the critical frameworks behind drug repurposing, how predictive models like Matrix are reshaping disease treatment, and why open-source collaboration could transform healthcare delivery. If you are a physician, healthcare executive, engineer, or healthcare IT leader, this discussion offers essential insights into the future of clinical decision-making.

How Does Data Normalization Impact AI? - with Mika Newton

Accurate clinical insights depend on more than just throwing a large language model at a problem. Data normalization and structured medical concepts shape how AI delivers precision in healthcare coding, clinical decision support, and patient care. Mika Newton, CEO of xCures, and Rajiv Haravu unpack how proprietary medical content, editorial policies, and knowledge graphs provide essential context that LLMs alone cannot offer. Learn why healthcare organizations still rely on medical code sets for reimbursement, accurate ICD-10 coding, and decision-making workflows - and how AI-driven agents may soon accelerate ontology creation, dictionary migration, and terminology mapping. Discover actionable frameworks and expert perspectives on leveraging AI in clinical environments to minimize hallucinations, enhance accuracy, and maintain relevance in a rapidly evolving healthcare landscape.

What is the biggest challenge in data normalization? - with Mika Newton

Data normalization in healthcare isn't just complex – it's mission critical. When a simple lab result like hemoglobin A1C can be recorded under half a dozen different names, clinicians face real obstacles in tracking trends, managing care, and making timely decisions. Mika Newton, CEO of xCures, and Rajiv Haravu, SVP of Product Management at IMO Health, break down why non-standardized data jeopardizes care quality, public health insights, and patient safety. From mismatched lab terms to inconsistent clinical narratives, they explore how definition decay and evolving medical language complicate interoperability and downstream data uses. Learn the frameworks and methodologies IMO Health uses to combat variability – leveraging clinical terminologists, curated content releases, and continuous surveillance of healthcare terminology. Discover how structured and narrative data normalization impacts providers, IT leaders, and healthcare operations.

The Fight to Clean Up Healthcare Data - with Mika Newton [FULL PODCAST]

Healthcare data is messy, inconsistent, and buried in narrative. AI sounds like the solution. Until it isn’t. In this episode of AI and Healthcare, xCures CEO Mika Newton speaks with Rajiv Haravu, SVP of Product Management at IMO Health, to dissect the real-world challenges of data normalization. From inconsistent documentation of basic lab tests to extracting insights from billions of unstructured notes, Rajiv explains why AI alone falls short - and how precision tools, editorial standards, and clinically-informed design can bridge the gap.

What real pain points in healthcare can AI help with? - with Dr. Sanjay Juneja

Emergency rooms are overwhelmed, not just by medical crises, but by the fallout of systemic failures. A growing number of patients are showing up with issues rooted in poverty, housing instability, and food insecurity. AI is helping change that. By connecting underserved patients to billions in unclaimed public benefits, new tools are offering a path to preventative care that begins outside the hospital walls. Dr. Alister Martin explains how AI is being used to bridge the gap between policy and care, reduce avoidable ER visits, and ease pressure on a healthcare system that spends billions treating conditions that could be prevented. When patients get access to the support they already qualify for, outcomes improve - and so does the bottom line.

Should proficiency in AI be considered in medical school applications?—with Dr. Sanjay Juneja

As AI becomes a core part of modern medicine, the way we train future doctors may be due for a serious rethink. Empathy and adaptability, not just chemistry and memorization, could define what makes a good physician in the age of augmented intelligence. With language models becoming standard tools for both patients and providers, skills like prompting, critical thinking, and emotional intelligence may soon matter more than traditional academic benchmarks.

How can wearables warn you before a stroke?—with Dr. Sanjay Juneja

What started with a rabbit heart in a physiology lab led to a career focused on preventing strokes through early detection of atrial fibrillation. A Stanford cardiologist shares how that moment sparked a lifelong interest in cardiac rhythms and how today’s wearables can now detect AFib through simple, continuous monitoring, long before symptoms appear. This shift from reactive care to early detection marks a major step forward in heart health, powered by straightforward algorithms and a growing role for AI in predicting cardiovascular risk.