Applied AI Summit Healthcare

Free online conference | April 14-15, 2026

G.A.M.E.R.S: Graph Agents with Multimodal Entities and Reasoning Schemas in Clinical World

Clinical AI faces a fundamental problem: patient data spans multiple modalities-PDFs, radiology images, lab results, pathology slides, clinical notes-yet most AI systems process each in isolation. Context is lost between encounters. Hallucinations emerge when reasoning across complex medical ontologies. The patient’s complete clinical picture remains fragmented across disconnected vector stores and stateless LLM calls.

G.A.M.E.R.S (Graph Agents with Multimodal Entities and Reasoning Schemas) solves this through graph-based context memory.

In this session, you will witness graph agents that maintain persistent context across conversations, patient encounters, and multimodal inputs. The speakers will demonstrate how open-source LLMs, VLMs, hybrid RAG pipelines, and multimodal embeddings-extracted from text, images, and video are fed into a graph-based memory layer where relationships between clinical entities are preserved, queried, and reasoned over, while preserving privacy. This is built upon FHIR in the WHOLE framework ( presented at NODES 2025 )

About the speaker

Krishnendu Dasgupta

Founder @ AXONVERTEX AI, CTO & Co-Founder @ TrialBridge AI at AXONVERTEX AI [ Founder ], Trialbridge [CTO, Co-Founder ]

Krishnendu Dasgupta is a computer science engineer with experience in applied machine learning in healthcare, generative AI, distributed computing for scalability, and AI applications in supply chain, consumer business, and cybersecurity. His current focus includes graph machine learning, natural language and speech processing with visual interfaces, reinforcement learning, and decentralized AI. His work spans privacy-preserving AI solutions, scalable language models, and computer vision, contributing to clinical trial recommendations, disease ontologies, and patient discovery platforms. Combining technical expertise with capital efficiency, market research, and go-to-market strategy, he ensures the development of scalable and effective AI solutions. With over a decade of experience, Krishnendu has held key roles at Mondosano GmbH, PwC, NTT Data, and Thoucentric, leading AI-driven projects in healthcare, supply chain, and cybersecurity. He is currently working on an AI-powered platform to streamline patient recruitment and discovery for clinical trials. His past work includes developing graph-based AI systems that integrate patient, drug, and symptom data. He also led an NVIDIA Inception incubator-backed AI startup focused on medical imaging. Beyond his professional work, Krishnendu is committed to mentorship, research, and volunteering. He has served as a section leader[ Cohort 2024, Cohort 2025 ] for Stanford University’s Code in Place initiative to teach programming voluntarily. He also served as a mentor for the UN SDG Hackmaker program, and a research volunteer at PathCheck Foundation. He has also been a mentor and judge at HackMIT, a “Mentor of Change” for NITI Aayog’s Atal Innovation Mission, and played a role in MIT Hacking Medicine’s collaboration with the Maharashtra Innovation Society in 2020. Additionally, he has contributed as a technical reviewer for Apress and Springer Nature on AI and machine learning publications. He is also a reviewer for the Journal of Computer Sciences And Informatics, and Journal Of Engineering Research And Reviews . Krishnendu is an alumnus of 5th Cohort of Entrepreneurship and Innovation Bootcamp , held by Massachusetts Institute of Technology , in the year 2018 at Brisbane, Australia. His research at Axonvertex AI, includes robotics, healthcare AI, and decentralized computing, including MAPLE-DeCoDe, an AI-driven platform for early detection of cognitive decline. He has also been a panel speaker and delegate for organizations such as AICRA and PGIMER. His independent research explores collaborative intelligence, AI security guardrails, and distributed inference. As an independent Principal Investigator, he has contributed to AI risk assessment and generative AI model evaluations in collaboration with the National Institute of Standards and Technology (NIST), United States. Krishnendu also won a category award ( Molypix AI sponsor award ) at AI in film making Hackathon, held by Massachusetts Institute of Technology Film Association, held in February 2025. Krshnendu Dasgupta has also been selected in the United Nations Development Programme as a vetted Consultant for Artificial Intelligence Tracks under ExpRes Roster for GPN deployments in the year 2025. Krishnendu recently presented at the Linux Foundation Summit about an AI framework focused on Privacy and Decentralized Approach – Agents of S.E.A.L.E.D Krishnendu remains dedicated to advancing AI in healthcare while ensuring its ethical and impactful application across industries.