Delta: HealthTech Innovators

Why do 30% of patients take medications differently than what's in their medical records? Dr. Eve Cunningham, Chief Medical Officer at Cadence, reveals the shocking gaps in traditional healthcare—and how remote patient monitoring is revolutionizing chronic disease management for 70,000+ patients across 20 health systems.In this episode, we dive deep into:✅ The hidden cost of episodic vs. continuous care✅ How a practicing OB-GYN broke into healthtech leadership✅ Why 20% of medication changes are actually DOWN-titrations✅ The future of AI-powered clinical decision support✅ Real outcomes: 18% fewer hospitalizations, $183/month savings per patientTimeStamps:Dr. Cunningham spent 20 years leading physician groups at Kaiser Permanente, CommonSpirit, and Providence before joining Cadence—a remote patient monitoring company backed by $141M from General Catalyst and Thrive Capital. She shares candid insights on physician leadership, technology transformation, and why clinicians MUST develop technical competency.🎯 Perfect for healthcare entrepreneurs, medtech founders, physicians exploring innovation, and anyone building the future of digital health.KEY TOPICS COVERED:Remote patient monitoring at scale (70,000+ patients)Clinical AI and machine learning in chronic disease managementBreaking into healthtech from clinical practiceValue-based care and Medicare reimbursement (CPT codes 99453, 99454, 99457, 99458)Medication reconciliation and polypharmacy managementVirtual care infrastructure: telehealth, virtual nursing, hospital-at-homeTechnology adoption in large health systemsThe emerging clinician-engineer hybrid roleDeprescribing and down-titration opportunitiesSocial determinants of health and caregiver engagementPUBLISHED OUTCOMES:📊 New England Journal of Medicine: Catalyst validates Cadence's model: https://catalyst.nejm.org/doi/abs/10.1056/CAT.24.0521CONNECT WITH DR. EVE CUNNINGHAM:LinkedIn: https://www.linkedin.com/in/evecunninghammd/🔗 CONNECT WITH CADENCE:Company LinkedIn: https://www.linkedin.com/company/cadencerpmWebsite: https://www.cadence.care/Published Research: https://www.cadence.care/outcomes-report-2024

Malke Assad, a plastic surgery resident and the founder of Rank RX, shares his inspiring journey from war-torn Aleppo to prominent U.S. medical institutions. He reveals the shocking shortcomings of the residency application system, including how Nobel laureates can fall victim to arbitrary cutoffs. Malke discusses how Rank RX uses AI and large language models to efficiently screen thousands of applications, promoting fairness. He also shares insights on building a tech team without coding skills and offers valuable advice to aspiring clinician-entrepreneurs.

Discover how Sahil and his brother turned a simple ear cleaning device into a viral sensation, surpassing 1 billion views on social media. They share their journey of obtaining FDA clearance, which became a key competitive advantage. Hear about their pivot from a B2B model to a direct-to-consumer healthcare network serving millions. Explore innovative marketing strategies, including influencer partnerships and organic content, that propelled their success. They also reflect on the importance of credibility and mentorship in scaling their business.

A Stanford PhD researcher reveals alarming truths about AI in medicine, highlighting the stark contrast between claimed accuracy and real-world performance. She discusses how models can dramatically fail when faced with questions that have no definitive answer. The conversation emphasizes the need for more realistic evaluations of AI tools and advises clinicians to approach AI as a supportive co-pilot rather than a replacement. With cautionary insights on model performance and patient safety, this discussion reshapes our understanding of AI deployment in healthcare.

Charlene, CEO of Ember, dives into how AI is transforming healthcare by tackling revenue integrity. She reveals that hospitals lose millions from inefficient billing, but her platform recovers over 51% of denied claims. Discover the impact of ambient listening on accurate clinical documentation and how startup focus strategies help navigate regulated industries. Charlene shares insights on the $10B healthcare fraud problem and the vital role of smart AI tools in detecting fraud. Perfect insights for healthcare executives and aspiring entrepreneurs!

Can AI forecast ICU risk from the first 36 hours of EHR data?University of Washington researcher Sihan explains TrajSurv, a survival-prediction model that converts noisy, irregular ICU time series into interpretable latent trajectories using Neural Controlled Differential Equations (NCDEs) and time-aware contrastive learning aligned to SOFA. We cover how trajectories outperform snapshots, handle missingness without heavy imputation, and remain clinically legible via vector-field feature importance and trajectory clustering.Validated on MIMIC-III and eICU with reported C-index ≈0.80 and cross-cohort ≈0.76, TrajSurv points to safer escalation, de-escalation, and bed allocation in the ICU.In this episode: survival prediction basics; limits of Cox/RSF vs deep time-series models; NCDE explained in plain language; first-36h feature set (53 labs/vitals/demographics); metrics (C-index, Brier, dynamic AUC); interpretable clustering linked to outcomes; and what’s next—adding interventions for counterfactual simulation and extending to oncology.Link to the paper: https://arxiv.org/abs/2508.00657Timestamps00:00 Why trajectories beat snapshots in EHR01:00 Guest intro: Sihan, UW Biomedical Informatics01:40 Survival prediction 101 and clinical use03:40 From Cox/RSF to deep learning on time-varying data05:03 What is TrajSurv (pronounced “traj-surf”)?06:16 NCDE explained with the “ship + weather” analogy08:14 Handling irregular sampling and missing data09:14 Time-aware contrastive learning aligned to SOFA10:47 Datasets: MIMIC-III and eICU; first 36h features (labs, vitals, demo)12:40 Results: C-index ≈0.80; cross-cohort ≈0.76; interpretability14:30 Workflow: CDS, monitoring, escalation, de-escalation16:15 Why humans miss multi-variable long-horizon trends18:21 Latent trajectory clustering and survival differences23:18 Next: interventions, counterfactuals, oncology applications25:40 ClosingRoupen Odabashian LinkedIn: https://www.linkedin.com/in/roupen-odabashian-md-frcpc-abim-183aaa142/Sihang Zeng: https://www.linkedin.com/in/zengsh/#HealthcareAI #ClinicalDecisionSupport #EHR #ICU #SurvivalAnalysis #DeepLearning #NCDE #MIMICIII #eICU #SOFA

Medical documentation errors cost U.S. hospitals over $70 billion in denied claims and $55 billion in lawsuits every year. In this episode, we sit down with Dimitri, Founder & CEO of WorkDone Health, a Y Combinator-backed startup that’s building the "Grammarly for medical records."WorkDone Health automates chart review, compliance checks, and billing validation in real-time, preventing errors before they cost hospitals money—or compromise patient safety. We explore:Why CFOs are the first to feel the pain of documentation errorsHow AI-powered compliance and quality checks reduce denialsLessons from Y Combinator and scaling a healthcare startupWhy WorkDone could be the antidote to insurance AI denialsIf you’re a healthcare leader, investor, or builder in healthtech, this episode shows the future of clinical documentation.Timestamps:0:00 – Intro: The cost of documentation errors ($70B in denials, $55B lawsuits)1:00 – Dimitri’s journey: From physics to healthcare AI3:00 – The problem: Reactive vs. proactive documentation review5:15 – Real-world example: Left vs. right shoulder conflict7:00 – Sepsis bundle case study9:00 – How WorkDone Health prevents denials in real time12:00 – Impact on CFO metrics: denials, lawsuits, billing cycle14:30 – The “antidote” to insurance AI claim denials18:00 – How the tool works: real-time vs. batch checks22:00 – Prioritization of alerts: reducing physician burden27:00 – Vision: “Grammarly for medical documentation”29:00 – Lessons from Y Combinator for healthtech startups32:00 – HIPAA compliance and why it matters from Day 137:00 – Future of WorkDone: API integrations with EMRsDimtry Karpov: https://www.linkedin.com/in/dmitrykarpov/WorkDone: https://www.linkedin.com/company/workdonehealth/WorkDone: https://www.wrkdn.com/Roupen Odabashian: https://www.linkedin.com/in/roupen-odabashian-md-frcpc-abim-183aaa142/

In this episode, we sit down with Chuck Feerick, founder and CEO of Latitude Health, a MedTech startup tackling one of the most overlooked — yet critically expensive — problems in healthcare: prior authorization and utilization management.Chuck shares how a personal experience in his early 20s inspired him to transform the way health plans make care decisions, using AI to reduce administrative burdens and accelerate patient access to treatment. With a background spanning health plan operations, venture capital, and startups, Chuck brings a 360° perspective on what it really takes to build a successful health tech company.We dive into:The $1 trillion administrative crisis in U.S. healthcareWhy prior authorization delays hurt patients and providersHow Latitude Health uses AI to empower—not replace—cliniciansThe real challenges of selling to health plansWhat every health tech founder must understand about procurement, ROI, and building painkiller productsThe future of AI in care decision-makingWhether you're a health tech entrepreneur, investor, or healthcare executive, this conversation is full of practical insights on solving big, unsexy problems with massive impact.00:00 – Intro: Can AI Fix Healthcare?01:03 – Meet Chuck Feerick, Founder of Latitude Health02:15 – A Personal Story That Sparked a HealthTech Mission04:10 – The Broken Prior Authorization Process Explained06:32 – Automating Utilization Management with AI08:44 – What Latitude Health Actually Does10:05 – How Patients, Providers & Payers Benefit12:20 – Chuck’s Journey: Operator, Investor, Founder14:15 – Lessons from VC for Startup Fundraising in MedTech16:01 – How to Sell to Payers: Complex Sales in Healthcare18:30 – The Role of AI vs. Human in Clinical Decision Making21:04 – How Latitude Uses LLMs to Structure Medical Data23:19 – Training AI with Clinicians: Nurses, Doctors, CMO Input25:12 – Building a HealthTech Startup the Right Way27:00 – Tackling Long Sales Cycles in Healthcare28:42 – AI is Moving Fast — Building for Flexibility30:18 – The Unsexy Problem That Needed Solving33:07 – Why Utilization Management Is the Key to Controlling Costs35:45 – Administrative Waste: The $1 Trillion Opportunity37:02 – Why Latitude Focuses on High-Impact Painkiller Tools38:49 – Consumers, Behavior, and the ROI of Innovation41:00 – Closing Thoughts: What Founders Must Understand About HealthcareRoupen Odabashian:LinkedIn: https://www.linkedin.com/in/roupen-odabashian-183aaa142/X: https://twitter.com/RoupenMDEmail: roupen@deltahealth.techTigran (Tiko) Bdoyan:LinkedIn: https://www.linkedin.com/in/chuckfeerickWatch Our Podcast at:https://youtu.be/Xj89GFyPpxw#MedicalStartup #Telehealth #SimulatedPatients #Fundraising #MedicalSchoolTools #CME #AIinMedicalEducation #CasperExam

Tikran Bdoyan, co-founder of SimAI, discusses how his AI-driven platform is revolutionizing medical education with realistic virtual patients. He highlights the urgent need to address training bottlenecks, the limitations of traditional medical exams, and the global demand for AI in clinical training. Tikran shares insights from their journey with Y Combinator and the unique challenges of fundraising in healthcare. Discover how SimAI supports medical schools, enhances student feedback, and customizes training for international students and telehealth teams.

Unlock proven strategies for HealthTech & MedTech startups to raise capital efficiently—from designing a lean deck and model to implementing AI powered outreach. In this episode, Jeff Fidelman, Harvard trained banker turned venture advisor, reveals why "Fundraising as a Service" is the next game changer in investor relations.Dive into:• Common funding mistakes founders make (like skipping the ask 😳)• Structuring your pitch (deck + model + valuation = 🟢)• Navigating SAFE vs. convertible notes• How AI reduces your MVP time & fundraising cost👉 Ideal for startup founders, HealthTech entrepreneurs, and media tech innovators ready to scale with smart capital strategies.Timestamps:00:00 Why fundraising execution matters01:06 Meet Jeff Fidelman – HealthTech fundraising guru02:03 Jeff’s path: from Morgan Stanley to venture banking05:03 Why founders fail at decks & modeling07:00 What "Fundraising as a Service" really means10:42 Don’t forget to ASK for money13:00 How investors evaluate your ROI14:28 Customer vs. investor psychology19:06 Equity dilution: how much you should give22:18 SAFE vs. Convertible Notes—founder friendly?23:50 The 3 critical slides: Problem, Market, Solution27:43 Use anecdotes to sell your story30:42 Funding sources in 2025: VC, angels, family offices35:27 How AI is accelerating MVPs & fundraising processRoupen Odabashian:LinkedIn: https://www.linkedin.com/in/roupen-odabashian-183aaa142/X: https://twitter.com/RoupenMDEmail: roupen@deltahealth.techJeffrey Fidelman:LinkedIn: https://www.linkedin.com/in/jeffreyfidelman/Watch Our Podcast at YouTube#HealthTech, #MedTech, #StartupFundraising, #VentureCapital, #PitchDeck, #StartupTips, #Founders, #SAFEvsConvertible, #StartupEquity, #StartupDilution, #RaisingCapital, #HealthcareStartups, #FundraisingStrategy, #InvestorRelations, #StartupMVP, #AIForStartups, #SeedFunding, #SeriesA, #StartupMistakes, #JeffFidelman