『Signal and Symptoms Podcast』のカバーアート

Signal and Symptoms Podcast

Signal and Symptoms Podcast

著者： Harvey Castro MD Junaid Kalia MD & Edward Marx
無料で聴く

Three healthcare AI experts who've watched millions wasted on failed projects. Dr. Harvey Castro, Dr. Junaid Kalia, Edward Marx, and guest experts cover all things healthcare AI - from digital transformation to clinical reality. Every Tuesday, we diagnose real failures, reveal what actually works, and help you avoid the expensive mistakes we've seen repeated everywhere. Because when AI decisions affect patient care, getting it right isn't optional.Copyright 2026 Harvey Castro MD, Junaid Kalia MD, & Edward Marx 政治・政府 衛生・健康的な生活 身体的病い・疾患
エピソード
  • Built Without Us: Physician Led AI Governance — Dr. Ryan Walsh (CMIO, Memorial Hermann)

    Built Without Us: Physician Led AI Governance — Dr. Ryan Walsh (CMIO, Memorial Hermann)
    2026/09/01

    Technology keeps getting built for clinicians and too often without them. This episode of Signal & Symptoms is about closing that gap. Dr. Junaid Kalia is joined by co-hosts Ed Marx, DR GPT™ Harvey Castro, and now officially on the roster Dr. Isha Mannering, with guest Dr. Ryan Walsh, Chief Medical Information Officer at Memorial Hermann. Ryan calls his path “the Forrest Gump of health IT”: a family physician and residency educator who raised his hand when someone asked “does anyone know about computers?” and ended up double-board-certified as a “human + machine” leader.

    The conversation is a working clinician’s field guide to living with AI: what actually excites a CMIO right now, how to de risk AI so you can use it without getting burned, why residents trust an AI summary inside Epic more than an outside source (and why that’s dangerous), and the med-legal reality that governance and law are being outpaced by the technology. Ed lands the episode’s sharpest line that the real leading cause of preventable death in a hospital might not be sepsis, but governance that keeps good tools out. Ryan’s answer isn’t to skip the guardrails: it’s a physician-led clinical AI governance council, piloting carefully, and refusing to throw the baby out with the bathwater “but we do need to test the bathwater.”

    What You Will Discover:

    [00:00] “nothing is foolproof,” and the EHR-trust trap

    [00:21] Welcome + meet Dr. Ryan Walsh (CMIO, Memorial Hermann), Isha joins as co-host

    [00:57] The “Forrest Gump of health IT” origin story

    [02:03] What excites a CMIO now: the tech finally catching up

    [03:23] AI as a thinking partner

    [04:42] “All technology is deflationary” (Junaid)

    [05:02] Advice for clinicians: use it, learn the limits, de-risk it

    [06:29] Do residents trust AI? The EHR summary surprise

    [07:43] Fear, soul, and choosing love over 150 years of tech (Ed)

    [08:13] The bridge: balance, not sides (Isha)

    [08:42] Med-legal reality + the clinical AI governance council

    [09:29] “The real leading cause of preventable death? Governance.”

    [10:07] Don’t throw the baby out with the bathwater test the bathwater

    Referenced in the show:

    🖇️ Dr. Ryan Walsh — CMIO, Memorial Hermann Health System; family physician + informaticist (“human + machine”)

    🖇️ Memorial Hermann’s overarching clinical AI governance council

    🖇️ AI summaries inside the EHR (Epic) — and the automation-bias / implicit-trust risk

    🖇️ 21st Century Cures Act era of health data + interoperability Connect with us:

    Dr. Junaid Kalia, Neurocritical Care Specialist and Founder of SaveLife.AI™ (host) 💼 LinkedIn — https://www.linkedin.com/in/junaidkaliamd

    🔗 Website — https://www.junaidkalia.com/

    📹 YouTube — https://www.youtube.com/@junaidkaliamd

    Edward Marx, CEO, Advisor (co-host)

    💼 LinkedIn — https://www.linkedin.com/in/edwardmarx/

    🔗 Website — https://www.marxadvisory.com/

    📹 YouTube — https://www.youtube.com/@EdwardMarx

    DR GPT™ Harvey Castro, ER Physician, #DrGPT™ (co-host)

    💼 LinkedIn — https://www.linkedin.com/in/harveycastromd/

    🔗 Website — https://www.harveycastromd.com/

    Visit our website: https://signalandsymptoms.com/

    Special Guest:

    Dr. Ryan Walsh — Chief Medical Information Officer, Memorial Hermann Health System

    💼 LinkedIn — https://www.linkedin.com/in/ryanwalshmd/

    Visit our website: https://signalandsymptoms.com/

    Get advisory insights about Healthcare AI — at zero cost: https://junaidkaliamd.substack.com/

    Medical disclaimer: This conversation is for general informational purposes and is not medical advice. Listening does not create a doctor–patient relationship. Views expressed are Their own and do not represent the employer. Tools and methods discussed are decision-support and research infrastructure with a clinician in the loop — not autonomous or cleared diagnostic devices. No PHI is shared.
    続きを読む 一部表示
    11 分
  • The Decision, Not the Model: Lessons from Oncology AI — Dr. Agata Krasoń

    The Decision, Not the Model: Lessons from Oncology AI — Dr. Agata Krasoń
    2026/08/27

    “AI alone is very rarely the real breakthrough.” That’s how Dr. Agata Krasoń a Senior Clinical & Imaging Data Scientist at Roche, joining from Switzerland opens the conversation, and it reframes the entire episode. The breakthrough, she argues, happens when the right data, the right model, the workflow, the validation, and the clinical decision are all connected. The model is the easy part.

    In this episode of Signal & Symptoms, Dr. Junaid Kalia and co-host Ed Marx dig into the unglamorous middle layer where medical imaging actually becomes clinical AI: data standardization, harmonization, and the FAIR foundations that decide whether a model can be trusted at all. Agata makes the case for starting with the decision, not the model; Junaid shares how SaveLife.AI™’s “VisionOps” flywheel compressed grounded-data prep from months to hours; and Ed brings the hard governance truth in his words, when we don’t share the right data, “people die, and that’s criminal.” They close on precision medicine, the AI “mirage” (models that fake the read), planning one year instead of five, and why patients should own their health data like a bank account.

    What You Will Discover:

    [00:00] “AI alone is rarely the real breakthrough”

    [00:47] Welcome + meet Agata Krasoń (Roche, Switzerland)

    [01:35] Start with the decision, not the model

    [02:58] Work backwards from the problem (Ed Marx)

    [03:29] Data standardization: the foundation you build the house on

    [04:23] VisionOps & the AI flywheel months to hours

    [05:32] Precision medicine: the right therapy for the right patient

    [06:06] The “mirage”: when AI fakes the read

    [06:58] Plan one year, not five

    [07:36] Switzerland vs. the US: 500+ EMRs, no single data source

    [08:48] Regulation, data-sharing, and who really drives the rules

    [09:15] Own your health data like your bank account (+ the $500 private-AI box)

    Referenced in the show:

    🖇️ Agata Krasoń’s May 2026 LinkedIn post — “AI alone is never the real breakthrough”

    🖇️ FAIR data principles (Findable, Accessible, Interoperable, Reusable)

    🖇️ SaveLife.AI™ “VisionOps” — Vision-Language Model (VLM) analysis pipeline

    🖇️ Sergey Brin, paraphrased — “If you cannot measure it, you cannot improve it”

    🖇️ The imaging-AI “mirage” — foundation models producing reads without truly using the image

    🖇️ Signal & Symptoms Ep 33 (Martin Willemink) — radiology AI

    Connect with us:

    Dr. Junaid Kalia, Neurocritical Care Specialist and Founder of SaveLife.AI™ (host) 💼 LinkedIn — https://www.linkedin.com/in/junaidkaliamd

    🔗 Website — https://www.junaidkalia.com/

    📹 YouTube — https://www.youtube.com/@junaidkaliamd

    Edward Marx, CEO, Advisor (co-host)

    💼 LinkedIn — https://www.linkedin.com/in/edwardmarx/

    🔗 Website — https://www.marxadvisory.com/

    📹 YouTube — https://www.youtube.com/@EdwardMarx

    DR GPT™ Harvey Castro, ER Physician, #DrGPT™ (co-host)

    💼 LinkedIn — https://www.linkedin.com/in/harveycastromd/

    🔗 Website — https://www.harveycastromd.com/

    Visit our website: https://signalandsymptoms.com/

    Special Guest:

    Dr. Agata Krasoń — Senior Clinical & Imaging Data Scientist, Roche (Basel, Switzerland)

    💼 LinkedIn — https://www.linkedin.com/in/agatakrason

    Visit our website: https://signalandsymptoms.com/

    Get advisory insights about Healthcare AI — at zero cost: https://junaidkaliamd.substack.com/

    Medical disclaimer: This conversation is for general informational purposes and is not medical advice. Listening does not create a doctor–patient relationship. Tools and methods discussed are decision-support and research infrastructure with a clinician in the loop — not autonomous or cleared diagnostic devices. No PHI is shared.
    続きを読む 一部表示
    11 分
  • Run the Model Yourself: A Clinician’s Guide to Local AI

    Run the Model Yourself: A Clinician’s Guide to Local AI
    2026/08/19
    This one is a roundtable no guest, just the three of us. Dr. Junaid Kalia sits down with co-hosts Ed Marx and DR GPT™ Harvey Castro for a hands on, slightly geeky conversation about something most clinicians have never been told they can do: run capable AI models yourself, on your own hardware, without ever sending a patient’s data to someone else’s cloud.It starts with a provocation Junaid running a local model on a $2,000 Mac at ~100 tokens/second and asking why he’d keep paying Azure for the privilege. From there the three of them walk through the whole terrain: why Harvey now updates his emergency medicine book with an AI agent every month, what “edge vs. near-edge vs. far-edge” actually means, whether an Apple laptop can really keep pace with a data center, and the uncomfortable catch that the best cheap open models right now come out of China, which opens a security and standards question the U.S. hasn’t answered. They close on the part that matters most in medicine: what a model can never show the FDA, and why a rural clinic with no road to it might be the best argument for local AI there is.What You Will Discover:[00:00] A $2,000 Mac at ~80–100 tokens/second (why bother going local?)[00:28] Welcome + why write a book when an AI can rewrite it every month[01:37] Who the book is really for: patients (and why the ER is a lot of people’s primary care)[02:34] 13 minutes with your doctor, how AI fills the gap (and visits trending down)[03:08] The home setup: 3 Macs, 128 GB unified memory, one tailnet[03:30] The model onslaught: what you can run for free (routers, Qwen, Kimi K2)[04:09] Edge, near-edge, or cloud, where should the model actually run?[05:00] Can an Apple laptop out-run a data center? (Apple Silicon + MLX + Core ML)[05:30] The catch: the best cheap models are Chinese and who then owns the standard[06:37] Boeing vs. Airbus: the same fight, now national, now for AI[07:11] What a model can never show the FDA (SBOM + prompt injection)[08:15] The rural clinic more advanced than any academic center[09:19] Three things you can do with AI todayReferenced in the show:🖇️ DR GPT™ Harvey Castro’s AI in Emergency Medicine book + the “Pivot or Perish” series — https://www.harveycastromd.com/🖇️ Open-weight model families discussed: Qwen (Alibaba), Kimi K2 (Moonshot AI), DeepSeek🖇️ Apple MLX + Core ML on Apple Silicon; Tailscale for a private multi-Mac “tailnet”🖇️ Inkling (referenced by Junaid) — a fine-tuning/infrastructure approach for bring-your-own-data models🖇️ Signal & Symptoms Ep 38 — “Why Will Digital Twins Change the Way We Treat Patients?”Connect with us:Dr. Junaid Kalia, Neurocritical Care Specialist and Founder of SaveLife.AI™ (host)💼 LinkedIn — https://www.linkedin.com/in/junaidkaliamd 🔗 Website — https://www.junaidkalia.com/ 📹 YouTube — https://www.youtube.com/@junaidkaliamdEdward Marx, CEO, Advisor (co-host)💼 LinkedIn — https://www.linkedin.com/in/edwardmarx/ 🔗 Website — https://www.marxadvisory.com/ 📹 YouTube — https://www.youtube.com/@EdwardMarxDR GPT™ Harvey Castro, ER Physician, #DrGPT™ (co-host)💼 LinkedIn — https://www.linkedin.com/in/harveycastromd/ 🔗 Website — https://www.harveycastromd.com/Visit our website: https://signalandsymptoms.com/Get advisory insights about Healthcare AI — at zero cost: https://junaidkaliamd.substack.com/Medical disclaimer: This conversation is for general informational purposes and is not medical advice. Listening does not create a doctor–patient relationship. The tools and models discussed are general-purpose technology, not cleared medical devices; nothing here is an endorsement of any specific vendor or model for clinical use. Do not enter protected health information into consumer AI tools.
    続きを読む 一部表示
    11 分
adbl_web_anon_alc_button_suppression_t1
まだレビューはありません