Podcasts by Category

LEVELS – A Whole New Level

LEVELS – A Whole New Level

Levels

Levels helps you understand your metabolic health with personalized data, expert guidance, and tools that connect your daily choices to measurable changes in your body. Our goal is to help you make better decisions about food, exercise, sleep, and long-term health. Connect with us: Become a Member: https://levels.link/wnl YouTube: https://youtube.com/@levels Instagram: https://instagram.com/levels Twitter: https://twitter.com/levels LinkedIn: https://linkedin.com/company/levels TikTok: https://tiktok.com/@levels

318 - #317 - What It Takes to Build Medical AI Doctors Will Trust | Dr. Suchi Saria & Mike Haney
0:00 / 0:00
1x
  • 318 - #317 - What It Takes to Build Medical AI Doctors Will Trust | Dr. Suchi Saria & Mike Haney

    Medical AI is full of impressive models that work on retrospective datasets. The much harder problem is turning one into a tool that can operate continuously inside a hospital, earn clinicians’ trust, fit into an overloaded workflow, stay reliable across different health systems, and ultimately improve patient outcomes.

    Mike Haney talks with Johns Hopkins researcher and Bayesian Health founder Dr. Suchi Saria about the decade-long journey from an academic sepsis-prediction algorithm to AI that clinicians are using in hospitals today. Her experience is a reality check on what it actually takes to make medical AI useful, and an argument for aiming higher than documentation and billing: toward systems that continuously watch patients, catch deterioration earlier, and help prevent avoidable harm.


    Free course: Improve your metabolic health

    Get our free email course on how glucose, nutrition, exercise, sleep, and measurement can help you build habits that support better energy and long-term health: ⁠⁠https://levels.link/wnl


    What We Cover:

    Why sepsis fits continuous AI monitoringHow causal reasoning separates signal from a noisy alertWhy real-time access to the full record mattersWhen a working algorithm still failed to get attentionHow adoption and human-machine teaming became engineering problemsWhat happened when the system went liveHow the same infrastructure extends beyond sepsisWhy healthcare is too conservative about medical AI


    🎙️ About the Guest:

    Dr. Suchi Saria is the John C. Malone Associate Professor at Johns Hopkins University, where she directs the Machine Learning and Healthcare Lab, and is the founder and CEO of Bayesian Health. Her work focuses on building and deploying machine-learning systems that use real-world clinical data to improve diagnosis, treatment, and patient safety.


    📍What Dr. Suchi Saria & Mike Haney discussed:

    04:30 - Why the real AI risk is what it is allowed to do08:32 - Why sepsis is a race against organ failure11:57 - From checklists to reading the full medical record16:30 - How causal reasoning finds a patient’s baseline18:50 - Using uncertainty to avoid another noisy alert22:11 - Why an hour-late warning is already too late25:06 - Reading Epic in real time without slowing it down32:35 - A working algorithm still couldn’t get clinicians’ attention35:53 - What happened when the system went live45:32 - Human-machine teaming, and who still makes the call54:17 - The same infrastructure, beyond sepsis58:35 - Why billing and coding is too small a target


    🔗 Helpful Links:

    Suchi Saria — Johns HopkinsResearch, publications, and academic background.Bayesian Health:Saria’s company commercializing real-time clinical AI.TREWScore —Science Translational Medicine(2015):The original real-time early warning model for septic shock.TREWS patient outcomes —Nature Medicine(2022):Prospective multisite evaluation after deploying the sepsis warning system in clinical care. TREWS clinician adoption —Nature Medicine(2022):Study of provider adoption and effects on sepsis treatment timing.Human-machine teaming —npj Digital Medicine(2022):Clinician interviews on what made the deployed AI system trustworthy and usable.Bayesian Health Sepsis Flagging Device — FDA (2026):FDA 510(k) clearance for the sepsis prediction software discussed in the episode.


    Watch the conversation: https://youtu.be/uVEKgSvei4s

    Find us on YouTube: ⁠⁠https://youtube.com/levelshealth?sub_confirmation=1⁠


    👋 Who we are:

    Levels helps you understand your metabolic health with personalized data, expert guidance, and tools that connect your daily choices to measurable changes in your body. Our goal is to help you make better decisions about food, exercise, sleep, and long-term health.


    Look for new shows every month on A Whole New Level, where we have in-depth conversations with thought leaders about metabolic health.

    Thu, 29 Oct 2026 - 1h 01min
  • 317 - #316 - What Should You Actually Do About High Cholesterol? | Dr. Seth Martin & Mike Haney

    Heart disease is the leading cause of death, but it’s also one of the most preventable. Decades of research have established a strong causal role for LDL and other ApoB-containing particles in atherosclerosis, and we now have multiple proven ways to lower them. The harder question is how to turn that evidence into a decision for an individual person.

    Mike Haney talks with Johns Hopkins cardiologist Dr. Seth Martin, a co-author of the new 2026 dyslipidemia guidelines, about what the latest evidence says we should actually measure and act on. The throughline is pragmatic: lower exposure to atherogenic particles earlier and for longer, use additional tests when they can change a decision, and distinguish interesting new measurements from ones that have actually been shown to improve outcomes.


    Free course: Improve your metabolic health

    Get our free email course on how glucose, nutrition, exercise, sleep, and measurement can help you build habits that support better energy and long-term health: ⁠https://levels.link/wnl


    What We Cover:

    Why the evidence that LDL and ApoB-containing particles cause atherosclerosis is so strongWhat “lower for longer” means and how the new LDL and ApoB goals change with cardiovascular riskWhen ApoB adds useful information beyond a standard lipid panelWhy the guidelines recommend against routine LDL particle-size testingHow PREVENT risk scores and coronary calcium scans can help decide when treatment makes senseWhat decades of statin research tell us about benefits, muscle symptoms, and diabetes riskHow much lifestyle changes typically move cholesterol, and when non-statin drugs enter the pictureWhy common heart-health supplements don’t have the evidence behind proven lipid-lowering therapies


    🎙️ About the Guest:

    Dr. Seth Martin is a professor of medicine and preventive cardiologist at Johns Hopkins, where he directs the Advanced Lipid Disorders Program and Digital Health and AI Lab at the Ciccarone Center for the Prevention of Cardiovascular Disease. He is a co-developer of the widely used Martin-Hopkins LDL cholesterol equation and served on the writing committee for the 2026 ACC/AHA dyslipidemia guideline.


    📍What Dr. Seth Martin & Mike Haney discussed:

    00:04 - LDL and ApoB are causal. Lower for longer07:10 - Guidelines set the standard. Not your doctor11:40 - 2026 shift: earlier treatment, PREVENT, lower goals17:01 - LDL near zero does not eliminate cholesterol19:59 - Hard numbers are back, and lower23:05 - ApoB if a high result changes treatment27:42 - No trial says treat particle size instead of LDL34:51 - PREVENT is for people not already high risk38:52 - Calcium 300 can push the goals. Zero can mean lifestyle first44:29 - The 3% statin line, and the choice just under it51:22 - Muscle symptoms uncommon. Statin can move prediabetes diagnosis earlier56:21 - Lifestyle often lowers LDL about 10%, not the whole benefit59:05 - Other proven drugs when a statin is not enough1:05:31 - Statin beat the supplements. Fish oil can raise AFib risk


    🔗 Helpful Links:

    2026 Guideline on the Management of Dyslipidemia:⁠Read the guideline and supporting materials⁠The New Cholesterol Guideline: What to Know — Johns Hopkins:Read the Johns Hopkins summaryPREVENT-ASCVD Calculator.: ⁠Use the PREVENT calculator⁠Martin-Hopkins LDL Equation: Learn about the Martin-Hopkins methodSPORT Trial —JACC(2022): Read the SPORT trial


    Watch the conversation: https://youtu.be/vRfhof5dOZw

    Find us on YouTube: ⁠https://youtube.com/levelshealth?sub_confirmation=1⁠


    👋 Who we are:

    Levels helps you understand your metabolic health with personalized data, expert guidance, and tools that connect your daily choices to measurable changes in your body. Our goal is to help you make better decisions about food, exercise, sleep, and long-term health.


    Look for new shows every month on A Whole New Level, where we have in-depth conversations with thought leaders about metabolic health.

    Thu, 22 Oct 2026 - 1h 08min
  • 316 - #315 - Can We Treat Disease Through the Nervous System? | Dr. Kevin Tracey & Mike Haney

    Most of NextLevel starts with a measurement problem: we can see more biology than ever, but we still have to figure out what to do with it. Bioelectronic medicine flips that sequence. We already know how to send electrical signals into the nervous system to change biology, including an FDA-approved vagus nerve treatment for rheumatoid arthritis, even though we still can’t map or read most of the individual nerve fibers carrying those signals.


    Mike Haney talks with Dr. Kevin Tracey, a pioneer of neuroimmunology and bioelectronic medicine, about what becomes possible when nerves become a therapeutic target. The opportunity is not simply vagus nerve stimulation, but learning which signals control specific organs, then building systems that can read and write them. That is still some distance away, and Tracey separates it from looser claims about vagal tone and vagus nerve hacks.


    Free course: Improve your metabolic health

    Get our free email course on how glucose, nutrition, exercise, sleep, and measurement can help you build habits that support better energy and long-term health: https://levels.link/wnl


    What We Cover:

    Why the vagus nerve is not one wireHow one minute a day became an FDA-approved rheumatoid arthritis treatmentWhy a nerve target can be more precise than a drugWhy mapping the vagus fiber by fiber is only beginningWhy CRP and cytokines are not a true inflammation readoutWhat HRV, breathing, humming, and cold plunges can and cannot show


    🎙️ About the Guest:

    Dr. Kevin Tracey is a neurosurgeon, scientist, and President and CEO of the Feinstein Institutes for Medical Research. His work helped establish how the vagus nerve regulates inflammation and helped launch bioelectronic medicine. He is also co-founder of SetPoint Medical and author of The Great Nerve.


    📍What Dr. Kevin Tracey & Mike Haney discussed:

    00:00 - A nerve can treat one organ. A pill cannot04:43 - The vagus nerve is 160,000 fibers, not one wire07:53 - Why the first fiber-by-fiber map of the human vagus is only months old10:29 - FDA-approved vagus nerve stimulation for rheumatoid arthritis14:33 - Why one minute a day can quiet inflammation for 12 to 24 hours17:39 - Why it took 30 years to get from the mouse finding to patients31:53 - How one minute of current reaches millions of immune cells41:19 - Why arthritis has a known mechanism and epilepsy and depression do not49:16 - What single fibers could change in diabetes, the liver, the gut, and stroke recovery52:59 - Why CRP and cytokine levels still fall short of a true readout1:04:18 - Resting heart rate, not HRV, is the cleaner vagus signal1:09:55 - Why deep breathing and humming are not vagus nerve stimulation1:16:35 - A cold plunge is fight-or-flight first, vagus second1:20:23 - The spleen signal he would measure if he could


    🔗 Helpful Links:

    The Great Nerve - Kevin J. Tracey (2025)RESET-RA - Nature MedicineSetPoint System - FDAThe inflammatory reflex - Nature (2002)Vagus nerve stimulation in rheumatoid arthritis - PNAS (2016), early human studyVagus nerve stimulation after stroke, paired with rehab - The Lancet (2021)


    Watch the conversation: https://youtu.be/x_h6Dd_Ap_o

    Find us on YouTube: https://youtube.com/levelshealth?sub_confirmation=1


    📲 Connect:

    Connect with Dr. Kevin Tracey at Feinstein Institutes for Medical Research


    👋 Who we are:

    Levels helps you understand your metabolic health with personalized data, expert guidance, and tools that connect your daily choices to measurable changes in your body. Our goal is to help you make better decisions about food, exercise, sleep, and long-term health.


    Look for new shows every month on A Whole New Level, where we have in-depth conversations with thought leaders about metabolic health.

    Thu, 15 Oct 2026 - 1h 21min
  • 315 - #314 - How to Make Health Decisions When the Science Is Unclear | Dr. Anupam Jena & Mike Haney

    Most health decisions happen before the science is settled. A study points one way, another points somewhere else, experts disagree about what matters, and even strong population-level evidence may not tell you what will happen to you.


    In this episode, Mike Haney talks with physician and economist Dr. Anupam Jena about how to make decisions under that kind of uncertainty. The goal isn’t to find a single hierarchy of evidence or a perfect source to trust. It’s to understand how much weight to put on any one piece of information, when personal experimentation can actually teach you something, and how the potential downside of an intervention should change the amount of evidence you demand before trying it.


    Free course: Improve your metabolic health

    Get our free email course on how glucose, nutrition, exercise, sleep, and measurement can help you build habits that support better energy and long-term health: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://levels.link/wnl⁠


    What We Cover:

    Why even a high-quality study should rarely change your mind by itselfWhy a meta-analysis is only as useful as the studies that go into itWhat randomized trials can establish, and where they can still fail to apply to real lifeHow to judge whether a study’s outcome is actually meaningful, not merely statistically significantWhen N-of-1 experiments can help, and how they can fool youA practical framework for deciding whether an intervention is worth trying: potential harm, quality of evidence, biological plausibility, and cost


    🎙️ About the Guest:

    Dr. Anupam Jena is the Joseph P. Newhouse Professor of Health Care Policy at Harvard Medical School, a physician at Massachusetts General Hospital, and an economist whose research uses natural experiments to uncover unexpected influences on health and medical care. He is also the host of Freakonomics, M.D. and co-author of Random Acts of Medicine.


    📍What Dr. Anupam Jena & Mike Haney discussed:

    04:04 - Why taxi and ambulance drivers die least often of Alzheimer's09:20 - Why half of people still skip a free heart medication13:02 - Why the headlines on coffee keep reversing14:55 - Judge the study on its merits, not on who funded it17:43 - Why even a high-quality study should rarely change your mind23:04 - Why a cold plunge trial cannot separate the bath from the belief26:19 - Why a meta-analysis is only as useful as the studies inside it27:15 - What a randomized trial can establish, and where it still fails in real life33:53 - The coin-flip test for whether a study shows cause and effect36:25 - Absolute risk, relative risk, and what "significant" leaves out43:06 - When an N-of-1 experiment can teach you what a trial cannot46:02 - Getting better does not mean the experiment worked53:55 - Harm, evidence, plausibility, cost: is it worth trying?


    🔗 Helpful Links:

    Dr. Anupam Jena — Harvard Medical School profileRandom Acts of Medicine — Anupam B. Jena & Christopher WorshamFreakonomics, M.D. https://freakonomics.com/series/bapuAlzheimer’s mortality among taxi and ambulance drivers (BMJ, 2024). Hypothesis-generating, not evidence that driving prevents Alzheimer’s: Read the BMJ studyMarathon road closures and cardiac mortality (NEJM, 2017): New England Journal of Medicine


    Watch the conversation:https://youtu.be/k9XI7ym7iP8

    Find us on YouTube: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://youtube.com/levelshealth?sub_confirmation=1⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠


    📲 Connect:

    Connect with Dr. Anupam Jena on https://x.com/AnupamBJena


    👋 Who we are:

    Levels helps you understand your metabolic health with personalized data, expert guidance, and tools that connect your daily choices to measurable changes in your body. Our goal is to help you make better decisions about food, exercise, sleep, and long-term health.


    Look for new shows every month on A Whole New Level, where we have in-depth conversations with thought leaders about metabolic health.

    Thu, 08 Oct 2026 - 57min
  • 314 - #313 - What Happens When We Start Imaging Healthy People? | Dr. Daniel Durand & Mike Haney

    Most medical imaging happens after a symptom, injury, or abnormal test gives a clinician a reason to look. But what changes if imaging becomes a more routine measurement, creating a record of the body before something goes wrong?

    In this episode of Next Level, Mike Haney talks with Dr. Daniel Durand, chief medical officer at Prenuvo, about whole-body MRI as a test case for a broader shift from episodic medicine toward longitudinal health data. Whole-body MRI is controversial, and Durand is clearly an advocate. The conversation takes the skepticism seriously, then asks a larger question: as measurement gets cheaper, more frequent, and increasingly visible to patients themselves, how should medicine decide what is worth knowing?


    Free course: Improve your metabolic health

    Get our free email course on how glucose, nutrition, exercise, sleep, and measurement can help you build habits that support better energy and long-term health: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://levels.link/wnl⁠


    What We Cover:

    How X-rays, CT scans, ultrasound, and MRI differ, and why radiation matters when you start thinking about repeated imagingWhat whole-body MRI sees well, and where CT, colonoscopy, or blood-based approaches may still be betterThe concerns around incidental findings, overdiagnosis, anxiety, and unnecessary follow-up, and Durand’s response to themWhat the current cancer-detection evidence for whole-body MRI does, and does not, establishWhy having prior scans could help distinguish a stable abnormality from something genuinely newHow faster scans and AI interpretation could eventually connect imaging with genomic, proteomic, and other health data


    🎙️ About the Guest:

    Dr. Daniel Durand is chief medical officer at Prenuvo and president of the Prenuvo Medical Group. He trained at Johns Hopkins, is board-certified in adult and pediatric radiology, and previously served as chief clinical officer and chief innovation officer at LifeBridge Health.


    📍What Dr. Daniel Durand & Mike Haney discussed:

    03:32 - Why imaging belongs in a series about continuous measurement15:32 - Imaging 101: X-rays, CT, ultrasound, and MRI28:57 - How AI is shortening MRI scan times38:52 - Screening versus surveillance40:26 - Which cancers whole-body MRI can miss46:39 - The case against scanning healthy people52:40 - What the cancer-detection data actually shows54:39 - "We're all going to get a body scan"1:03:31 - What would make routine imaging more useful?1:11:49 - Building a baseline of the healthy body1:17:43 - When AI can see more than a radiologist1:21:28 - Is it better to know, even when you can't treat it?


    🔗 Helpful Links:

    Dr. Daniel Durand, Prenuvo: Prenuvo medical leadershipMeta-analysis behind the ~9,000 participants and ~1.6% detection figures. It notes limits, including incidental findings (European Radiology, 2026): PubMedPrenuvo-associated study of 1,011 people, 2.2% confirmed cancer detection (Cancer Research/AACR, 2025): AACR abstractIncidental findings in whole-body MRI and their psychosocial effects (European Journal of Radiology, 2021): PubMedPrenuvo's research overview, including Polaris data (company-reported): Prenuvo clinical research


    Watch the conversation:https://youtu.be/rFZVbzUPSaA

    Find us on YouTube: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://youtube.com/levelshealth?sub_confirmation=1⁠⁠⁠⁠⁠⁠⁠⁠⁠


    📲 Connect:

    Connect with Dr. Daniel Durand at LinkedIn


    👋 Who we are:

    Levels helps you understand your metabolic health with personalized data, expert guidance, and tools that connect your daily choices to measurable changes in your body. Our goal is to help you make better decisions about food, exercise, sleep, and long-term health.


    Look for new shows every month on A Whole New Level, where we have in-depth conversations with thought leaders about metabolic health.

    Thu, 01 Oct 2026 - 1h 25min
Show More Episodes