Health and Explainable AI Podcast

Dr. Bradley Erickson, Director of the Mayo AI Lab, speaks with HexAI podcast host, Jordan Gass-Pooré in advance of the University of Pittsburgh’s annual AI Summer School program in Medical Imaging Informatics organized by Pitt's Health and Explainable AI Research Lab (HexAI) and the Computational Pathology and AI center of Excellence (CPACE). The episode simulates two different professional vantage point scenarios to help students visualize the vast, multi-dimensional landscape of artificial intelligence in healthcare and radiology.

The first half of the episode drops students directly into the vantage point of an AI expert attending a technical conference, where medical imaging informatics are being contrasted with everyday computer vision. Dr. Erickson explains how medical data often extends into multiple dimensions by incorporating complex spatial matrices and tissue properties like T1 and T2 tracking on MRIs, far surpassing standard 2D photographic pixels. He highlights why generic consumer AI tools like simple heat maps or saliency maps fall short of establishing clinical trust; while they can successfully point to where a brain tumor is, they completely fail to explain what that tumor is or why it is changing texture. Furthermore, Dr. Erickson discusses the profound challenge of "ground truth" uncertainty in medicine, explaining that training predictive algorithms is incredibly difficult because definitive biological labels are frequently masked by biological reactions or a lack of definitive longitudinal data.

The second half of the podcast episode places students into the role and vantage point of a hospital administrator, exposing students to the active economic and structural deliberations currently playing out in modern hospital boardrooms. Dr. Erickson underscores the considerations and financial constraints that hospitals contend with and explains that while new narrowly focused diagnostic AI tools are attractive, the most immediate return on investment for hospitals often comes from practical, language-based text summarization and ambient patient recording systems. Crucially, this administrative perspective teaches students that the health industry desperately needs supportive roles beyond traditional doctors and researchers, such as AI project managers, integration specialists, and governance officers who can oversee model confidence and decide exactly when to adapt AI solutions or pull failing applications or algorithms back.

Dr. Erickson emphasizes that entering this revolutionary field requires a willingness to learn through iteration, push back on assumptions, and manage the critical intersections of technology, safety, and human care. Through an open exploration of technical hurdles and administrative realities, the episode provides a rich conceptual primer for AI Summer School participants designed to cultivate critical thinking informing views on AI in medical imaging, hands-on project development and coding.

Dr. Freddy Nguyen, a physician-scientist-entrepreneur and Director of MIT’s Catalyst Scholars Program, discusses his work at the frontier of translational research, diagnostics, precision medicine and healthcare innovation with Pit HexAI host Jordan Gass-Poore' and his involvement in co-founding Nine Diagnostics, a startup spun out of Memorial Sloan Kettering Cancer Center.

Focusing on innovation in precision medicine, Dr. Nguyen traces his path through initiatives like MIT Hacking Medicine and the MIT Catalyst Scholars Program and his work helping teams identify and turn real clinical problems into projects designed to reach patients. Emphasizing patient‑first and science‑first approaches to innovation, Dr. Nguyen encourages students and collaborators to ask why things work the way they do and to build solutions that can move quickly from lab to clinic. That same mindset underpins Nine Diagnostics, which uses a high‑throughput nanosensor platform to generate molecular “fingerprints” of disease. Instead of tracking a few isolated biomarkers, these fingerprints capture complex patterns across thousands of molecules, reflecting both tumor biology and the broader physiological context of each patient. This shift from genomics alone to “functional precision medicine” enables clinicians and researchers to see what is happening in real time inside the body, monitor treatment response faster and tailor therapies more precisely to each patient.

Touching on how AI and machine learning are making these technologies clinically useful, Dr. Nguyen discusses how advanced algorithms integrate multimodal data streams to discover patterns that would be impossible to detect by eye. These models not only improve sensitivity and specificity when predicting treatment response, but also support emerging “digital twin” computational representations of patient health that can be used to simulate and optimize care. At the same time, he emphasizes that more data is not automatically better, and that explainable AI in healthcare must focus on which signals truly matter for a specific clinical decision and how to close the loop between model outputs and underlying biology.

For students and early‑career researchers, Dr. Nguyen shares practical guidance on getting involved in leveraging AI to advance precision medicine and designing research with translation in mind from day one so that innovations reach patients faster, rather than staying trapped in academic silos.

George Demiris, Associate Dean for Research and Innovation at the University of Pennsylvania School of Nursing and a “Penn Integrates Knowledge University Professor” discusses the transformative integration of responsible and explainable artificial intelligence into nursing, elder care, and hospice settings with Pit HexAI host Jordan Gass-Pooré.
The University of Pennsylvania School of Nursing is actively integrating emerging technologies into its curriculum, research, and clinical practice to enhance person-centered care, ensuring that technological advancements support rather than replace human connection, with the Penn Artificial Intelligence and Technology (PennAITech) Collaboratory for Healthy Aging playing a central role in bringing together interdisciplinary experts to address the technical and ethical challenges of integrating AI into the aging process.
Discussing his work focusing on information technology's role in the healthcare of older adults, specifically through smart home solutions and passive sensing systems that support aging in place, George advocates for a shift from reactive to proactive care, using sensors for example to detect subtle behavioral changes before adverse events like falls occur. However he argues that technology must remain a "decision aid" rather than a final decision-maker, advocating for "self-reflective AI" that explains its reasoning to clinicians. This approach preserves the "moral agency" of nurses, who act as vital patient advocates ensuring AI tools are introduced ethically and reflect the diverse preferences of those they serve.
Looking ahead, the conversation stresses the need for fluid collaboration between academia and industry to keep pace with rapid innovation. George envisions a holistic future for AI that prioritizes human dignity and autonomy, utilizing generative tools to adapt complex medical information to the specific literacy and language needs of patients and their caregivers.

Martin Raison, Co-founder and CTO of Nabla speaks with Pitt HexAI host Jordan Gass-Pooré about Nabla’s central role in architecting the agentic AI era in healthcare. Martin details Nabla’s evolution from a specialized ambient scribing tool into a comprehensive "Adaptive Agentic Platform". They discuss the significant challenges involved in making it possible for AI agents to perform complex clinical tasks and how Nabla has been thrust into tackling a labyrinth of structural and data hurdles. These range from the integration of fragmented, unstructured patient charts and hospital guidelines to the complex technicalities of agent discoverability, interoperability, and the establishment of standardized accountability frameworks.

The interview highlights a significant shift in Nabla's technical strategy: moving from probabilistic Large Language Models (LLMs) toward world models. Raison explains that while LLMs are effective at generating text, they lack a fundamental understanding of cause-and-effect and the ability to simulate evolving environments. To address this, Nabla has entered an exclusive partnership with Advanced Machine Intelligence (AMI), a research lab co-founded by Yann LeCun. This collaboration provides Nabla with early access to world model technologies that can "imagine" different scenarios and simulate the consequences of actions, providing a more deterministic and auditable path for AI in high-stakes clinical settings.

In discussing the technical foundations of computational health, Martin addresses the critical need for inference optimization to manage the millions of model executions required daily at scale. Furthermore, Martin envisions a fundamental shift in the paradigm of AI inference through the adoption of world models. He suggests that these architectures will blur the traditional boundary between training and inference by enabling continuous learning, where the model adjusts and evolves in real-time based on new data and clinician feedback, rather than being limited by the static context windows of current LLMs.

Beyond the core technology, Martin and Jordan discuss the critical importance of explainability and interoperability in the "agentic web" of healthcare. They specifically highlight architectural initiatives like MIT’s Project NANDA, which focuses on the foundational layers of the agentic web, including critical elements like discoverability and authentication that go beyond the AI layer alone. Martin emphasizes that the sector must move toward standardized "Agent Fact Files" to ensure accountability and ease of governance as organizations begin to manage thousands of agents. He concludes by looking toward a future of "emergent intelligence," where the collaboration between multiple models creates sophisticated patterns that can eventually help clinicians improve their own professional practice over time.

Ekaterina Kldiashvili, Vice Rector for Research at Petre Shotadze Tbilisi Medical Academy, and Pitt’s HexAI podcast host, Jordan Gass-Pooré, discuss public health, the incorporation of AI into healthcare, responsible uses of AI, medical education and inter-university collaboration.
Ekaterina and Jordan explore opportunities and concerns surrounding commercial AI applications, noting that while AI can improve healthcare efficiency, it must support clinical reasoning rather than replace it. They cover the Tbilisi Medical Academy’s work on responsible AI usage, particularly in educating providers and patients, demonstrating how AI-enhanced text and visuals can significantly improve patient understanding and follow-up rates. They also touch on challenges associated with the use of AI in non-English languages like Georgian and delve into advances in computational genomics and rapid molecular diagnostics. Looking ahead, they discuss the strengthening ties between the University of Pittsburgh and the Tbilisi Medical Academy through knowledge sharing and faculty training and broadly discuss inter-university collaboration and the idea of seeing students investigate how different cultures and communities trust and accept AI in healthcare settings.