Learning Healthcare System Podcast

Clinical Trial Matching

How do we find the right patients for the right clinical trials? In this episode, James Green (CEO, Cognome) and Dr. Parsa Mirhaji (Albert Einstein College of Medicine) discuss the complexities of clinical trial matching and how AI-driven learning health systems can transform patient recruitment. They explore: ✅ The role of Agentic AI in understanding trial criteria ✅ Challenges of data silos, redundancy, and quality in hospitals ✅ oTESSA, an AI-powered tool enhancing trial matching with justification & transparency ✅ How soft criteria can improve trial eligibility over time ✅ The impact of reinforcement learning in making trial matching more effective From oncology to breast cancer, this conversation dives deep into how AI, domain knowledge, and institutional context shape the future of clinical research. Tags: #ClinicalTrialMatching, #AIinHealthcare, #LearningHealthSystem, #AgenticAI, #ClinicalTrialRecruitment, #OncologyTrials, #BreastCancerResearch, #HealthcareData, #PatientEligibility, #ReinforcementLearning, #AITransparency, #TESSA, #MedicalAI, #HealthcareInnovation, #ClinicalResearch, #AIforGood, #PatientMatching, #DataSilos, #AIinMedicine, #HealthTech Chapters: Why Clinical Trial Matching is So Complex The Role of AI in Identifying the Right Patients Understanding Inclusion & Exclusion Criteria with AI Tackling Data Silos, Redundancy & Quality Issues Transparency, Justification & Eliminating AI Hallucination Soft vs. Hard Criteria: Preparing Patients for Future Trials The Future of AI in Healthcare & Just-in-Time Matching Closing Thoughts & Next Steps for Clinical Trial AI

The Learning Health System Maturity Model (S1, E2)

In this episode, we discuss what it takes to build a Learning Health System. Dr. Parsa Mirhaji has devised an eight level maturity model that we analyze in depth.Join us as we dive deep into the transformative power of advanced data and AI technologies in healthcare. This engaging conversation covers key topics such as: Master entity indexing and data lineage Real-time data ingestion and natural language processing (NLP) Leveraging large language models (LLMs) for healthcare innovation Ensuring data quality, privacy, and compliance Scalable, equitable access to data for a data-driven culture Responsible, explainable AI/ML and generative AI Integration of EHR and translation of research into practice The HIMSS Healthcare Analytics Maturity Model Pragmatic clinical trials, patient-reported outcomes, and precision medicine Explore how these innovations create a continuous learning and quality-improving health system, driving patient-centered and personalized medicine. Don’t miss this insightful discussion on the future of healthcare! tags: #HealthcareAI, #HealthcareAnalytics, #HIMSSMaturityModel, #DataQualityInHealthcare, #NLPHealthcare, #GenerativeAIHealthcare, #ExplainableAI, #PrecisionMedicine, #PersonalizedMedicine, #EHRIntegration, #PatientCenteredCare, #DataPrivacyHealthcare, #ComplianceEnforcementAI, #PragmaticClinicalTrials, #PopulationGenetics, #EquitableDataAccess, #PatientReportedOutcomes, #ResponsibleAI, #ScalableDataSystems, #HealthcareInnovation, #DrParsaMirhaji, #CognomeJamesGreen, #RemoteHealthcare, #RealTimeDataIngestion, #DataLineageHealthcare, #TrustableAI, #AIInMedicine, #HealthcareResearchTranslation, #KnowledgeSystems, #ScalableAISolutions Chapters: 0:00 Introduction 3:20 Maturity Level 1: The Foundational Layer 9:34 Comparison with HIMSS Analytic Maturity Model 11:08 Maturity Level 2: Open Science & Collaborative Research 15:05 Maturity Level 3: Equitable scalable access to and training 19:00 Maturity Level 4: Machine Learning & AI 20:34 Maturity Level 5: Translation to Practice 24:47 Maturity Level 6: Patient Empowerment 25:55 Maturity Level 7: Precision Medicine 27:45 Maturity Level 8: Learning Health System

Going Beyond Atlas: Building a Learning Health System with Dr. Parsa Mirhaji (S1,E3)

In this episode of our podcast, Dr. Parsa Mirhaji and James Green, CEO of Cognome, discuss the evolving landscape of healthcare data management. From real-world evidence generation to patient empowerment, they cover: Why OHDSI's Atlas falls short for learning health systems. Challenges with identified, de-identified, and limited-identified datasets. The implications of reidentification, IRB regulations, and compliance. Building a single-source dataset for better integration. Interoperable data ecosystems and frameworks for healthcare. The role of multimodal datasets: Bio repositories, PACS, Notes, and EMR. Self-service data extraction and auto-generated OHDSI OMOP datamarts. Patient-centered consent, privacy, and transparency in research. This episode is packed with insights on data quality, ontology management, and the future of healthcare interoperability. #real-world-evidence, #OHDSI, #Atlas-limitations, #learning-health-systems, #healthcare-data, #Dr-Parsa-Mirhaji, #James-Green, #Cognome, #IRB-regulations, #compliance, #data-privacy, #interoperability, #integration-frameworks, #multimodal-datasets, #patient-consent, #patient-empowerment, #Bio-repository, #PACS, #Notes, #EMR, #data-enclaves, #OHDSI-OMOP-datamarts, #audit-trails, #data-transparency, #data-quality, #ontology-management, #single-source-dataset, #healthcare-innovation

Transforming Care with Learning Health Systems

Dive into the inspiring journey of Dr. Parsa Mirhaji, a pioneer in healthcare data integration and Learning Health Systems. From building early Electronic Health Records (EHRs) to contributing to the OMOP Common Data Model, and his groundbreaking work in population health, Dr. Mirhaji’s vision has reshaped modern healthcare. Learn how he predicted respiratory failure, supported providers during COVID-19, and advanced federated learning networks like INSIGHT CDRN [https://insightcrn.org/]. Discover the foundation of Learning Health Systems and how predictive models are solving complex healthcare challenges today. Explore his incredible story—from his background in cardiology, to his expertise in semantic web and data integration. Witness how his efforts have saved lives using distributed, heterogeneous datasets. Watch now to understand the future of healthcare analytics and patient care. * #LearningHealthSystem * #HealthDataIntegration * #SemanticWebHealthcare * #PopulationHealth * #PredictiveAnalytics * #FederatedLearning * #DrParsaMirhaji * #COVID19 * #Healthcare * #HealthcareInnovation