Compounded Ozempic is everywhere, and most doctors have no idea what's actually in the vial. Semaglutide and tirzepatide got compounded and sold for a fraction of the brand-name price during the shortage, and it turned into a multi-billion-dollar market almost overnight. But the FDA shortage is over, Novo Nordisk sued Hims & Hers, and the whole compounded GLP-1 model is heading for a reckoning. I walk through how we got here and what it means for the person sitting across from you in the exam room. I'm Dr. Ajay Balaram, a physician and surgeon. This one hit my radar the hard way. One of my patients had their surgery canceled because they never mentioned they were on Ozempic. They didn't think a mail-order subscription counted as a real prescription. That disclosure gap is exactly what this video is about. What we get into: - What a compounding pharmacy actually is, and how 503A and 503B facilities differ (no jargon, I promise) - How a genuine drug shortage suspended the FDA's "essentially a copy" rule, and why the door never closed when the shortage ended - Why roughly 80% of compounded GLP-1s now have B12 or L-carnitine added, and what that's really about - The Novo Nordisk vs. Hims & Hers lawsuit, and how one ruling could reshape the entire market - The real safety risks: inconsistent potency, sterility in multi-dose vials, foreign-sourced active ingredient, and outright counterfeits - The four questions every patient should ask before they buy CHAPTERS 0:00 What's Actually in Compounded Ozempic? 1:26 Why It Matters for Doctors & Patients 3:01 What Is a Compounding Pharmacy? (503A vs 503B) 5:30 The Shortage Loophole: Why It's So Cheap 8:03 Is It Legal? Novo Nordisk vs Hims & Hers 11:01 Is Compounded Semaglutide Safe? The Risks 12:31 What Good Access Looks Like + What to Ask 13:47 Subscribe & What's Next Physicians: if you take one thing from this, ask the open-ended question at every visit. You can't monitor what you don't know about. And if you're a patient watching, the cheapest option isn't always the safest one, and your primary care doctor should know what you're on. Drop a comment. If you're a doctor, how are you handling patients who show up already on a compounded GLP-1? If you're a patient, what made you choose the route you chose? I read them. SOURCES & FURTHER READING - Omada Health survey of primary care physicians on third-party telehealth GLP-1 prescribing: https://www.omadahealth.com/resource-center/survey-report-primary-care-perspectives-on-glp-1-prescriptions - Novo Nordisk v. Hims & Hers (filed Feb 2026): https://www.novomedlink.com/content/dam/novomedlink/semaglutide/02-09-2026-company-statement.pdf - FDA drug shortage list + compounding guidance (503A / 503B): https://www.fda.gov/drugs/drug-safety-and-availability/drug-shortages CONNECT Subscribe: https://www.youtube.com/@UCJ0cJ1pGnm4z24PIAIl5HVQ More SpeakMD reviews: https://www.youtube.com/@SpeakMD/videos SpeakMD.com This channel is for education and is not medical advice. Talk to your own physician about your specific situation and medications. #Ozempic #Semaglutide #GLP1 #CompoundingPharmacy #Tirzepatide #Wegovy #Telehealth #SpeakMD Practice Smarter. Not Harder.
Online Compounding Pharmacies: What Doctors Need to Know
Everyone is calling Google's new release the AI doctor. Google is going out of its way not to call it that, and the reason why is the whole story. Last week Google DeepMind dropped its AI Co-Clinician, and the headlines wrote themselves: "AI matches doctors." The actual data is more interesting than that. In this breakdown I walk through what Google actually built, the dual-agent architecture running underneath it, and the three studies behind the announcement. I get into the one number every clinician should sit with, which is a single critical error in 98 cases, and what that looks like scaled across a real patient panel. Then I cover the part nobody else is talking about: the gap between the marketing and the medical-legal reality. If you treat patients, that gap is where your liability lives. Chapters 0:00 - The "AI Doctor" Google Won't Call a Doctor 1:24 - Why This Is a Research Announcement, Not a Product 2:27 - The Dual-Agent Architecture (Talker + Planner) 3:00 - What It Can Actually Do 3:48 - The Three Studies: Where Marketing Meets Science 3:57 - Study 1: Evidence Synthesis and the "One Error in 98" Problem 5:08 - Study 2: Pharmacology, the Strongest Claim 5:59 - Study 3: Multimodal Telemedicine Consultations 6:40 - PCPs Win All Seven Domains 7:12 - A Surgeon's Take on the Shoulder Exam Demo 8:03 - No Patient Outcomes, Just Demoware 9:00 - Triadic Care and the Supervision Question 11:21 - The Physician Shortage Argument 12:31 - The Malpractice Reality: Who Holds the Bag? 14:25 - Hallucinations and Sycophancy 15:30 - Three Takeaways 16:42 - Final Thoughts Disclosure This video is for educational and informational purposes only. It is not medical, legal, or investment advice. I have no financial relationship with Google or DeepMind. All product names and trademarks belong to their respective owners. AI Co-Clinician is a research announcement and is not FDA cleared or intended for diagnosis, treatment, or prevention of disease. Google Blog Post - https://deepmind.google/blog/ai-co-clinician/ 📩 contact@speakmd.com #SpeakMD #ClinicalAI #MedTech #GoogleDeepMind #HealthcareAI #PhysicianLife #MedicalLegal #AIinMedicine #DigitalHealth #Telemedicine
Google AI Co-Clinician: What Doctors Need to Know
After a year of using ambient AI scribes across thousands of patient encounters, I've figured out what actually works and what doesn't. I've tested or advised on at least 10 different platforms (DAX, Abridge, Doximity, Iscribe, Nabla, and more), and the gap between what these tools can do and what most physicians are actually getting out of them is huge. In this video, I'm sharing 15 practical tips that will get you the most out of whatever ambient scribe you're using. These come from peer-reviewed research, conversations with colleagues across specialties, and a year of trial and error in my own clinic. Whether you're already using an AI scribe or you've tried one and thought "this isn't for me," there's something in here for you. ⏱️ TIMESTAMPS 0:00 What I've learned in a year of ambient AI scribes 1:46 The 15 tips 2:28 Tip 1: Map it to your phone's action button 3:06 Tip 2: Figure out your consent 3:57 Tip 3: Nail your microphone setup 5:09 Tip 4: Stop talking over your patients 5:50 Tip 5: Chart review out loud in the hallway 7:23 Tip 6: Stop over-narrating in the room 7:54 Tip 7: Verbalize the assessment and plan to the patient 8:40 Tip 8: Dictate the exam as an addendum 9:30 Tip 9: Coach the AI like a junior resident 10:26 Tip 10: Use the structuring keywords 11:23 Tip 11: Customize your template 12:17 Tip 12: Go hybrid with dot phrases 13:31 Tip 13: Verbalize non-verbal findings 13:57 Tip 14: Pause the scribe for sensitive topics 14:34 Tip 15: Never sign without reviewing 15:48 The honest take 16:26 What's next on the channel 📌 MENTIONED IN THIS VIDEO Dr. Christian Pean's article on ambient scribe workflow: https://techysurgeon.substack.com/p/youre-using-your-clinics-ambient 🎥 WATCH NEXT SRT-H, the autonomous surgical robot out of Johns Hopkins Open Evidence breakdown 🔔 SUBSCRIBE for honest, physician-first takes on medical technology. No hype, no sales pitch, just the stuff I'd actually tell my colleagues. 💬 Drop your own ambient scribe tips in the comments. I read them all and I'm always looking to improve my workflow.
What I Learned Using Ambient AI Scribes Daily for a Year
Autonomous robot surgery just crossed a line most people thought was decades away — and as a practicing surgeon, I’m breaking down exactly how an AI-driven robot can now perform a procedure with no human hand on the controls. I cover how systems like the da Vinci platform and the Johns Hopkins SRT-H robot actually work, what “levels of surgical autonomy” really mean, and whether this is safe for patients. If you’ve wondered whether robots will replace surgeons, this is the honest answer from inside the operating room. Timestamps: 00:00 The Headlines 00:56 Welcome to SpeakMD 01:52 How SRT-H Actually Works 04:10 Training Data and Results 05:24 Hype vs. Reality 06:54 The Science Robotics Pushback 09:04 Levels of Surgical Autonomy 10:04 Regulation and Liability 11:17 What This Realistically Means 11:53 Final Thoughts Paper reference: Kim et al., SRT-H: A hierarchical framework for autonomous surgery via language-conditioned imitation learning. Science Robotics, July 2025. https://www.science.org/doi/10.1126/scirobotics.adt5254 If you want physician-first breakdowns of the tech that is actually going to affect your practice, hit subscribe. And if you disagree with anything I said, drop it in the comments. That is how we all get smarter. #SurgicalRobotics #AutonomousSurgery #SpeakMD #MedicalAI #RoboticSurgery #DaVinci #SRTH #MedTech #Intuitivesurgical
Fully Autonomous Robot Surgery with No Human Surgeon Controller?
Most clinical AI tools fail at establishing trust needed for actual patient care. Doximity's Ask is attempting to gain that trust, and it might be the closest any company has come to getting the physician-AI relationship right. In this video, I break down the three competing philosophies in clinical AI right now and Doximity's middle-ground approach that layers human physician verification on top of AI-generated answers. Doximity Ask routes its outputs to the actual authors of the cited studies for peer review and expert commentary. A system that's only possible because 85% of U.S. physicians are already on the Doximity platform. I walk through how the peer check and expert commentary features work, cover the built-in drug reference safeguards, the free journal access for physicians, and the fact that Doximity is compensating the doctors who verify its AI. I also cover the limitations you need to know — including unresolved liability questions for peer reviewers and the inherent subjectivity of expert opinion. **Timestamps:** 0:00 - Intro: The Trust Problem in Clinical AI 0:47 - How Physicians Actually Make Decisions 1:14 - What We're Covering Today 1:40 - Welcome to SpeakMD 2:04 - Disclosure on Doximity's AI Summit 2:37 - Three Competing Philosophies in Clinical AI 4:04 - Doximity's Middle Ground Approach 4:30 - The Bobby Flay Analogy 5:32 - How Dox AI Works in Practice 6:05 - Peer Check: Matching Experts to Queries 7:02 - Expert Commentary: Authors Review Their Own Papers 7:32 - Doximity's 85% Physician Network Advantage 8:15 - Drug Reference Safeguards 8:49 - Free Journal Access for Physicians 9:21 - Should AI Companies Compensate Researchers? 10:03 - The Compensation Model 10:27 - The Bigger Picture: Human Expertise Rising in Value 12:00 - Limitations: Liability Concerns 12:58 - Limitations: Defining Expertise 13:53 - Final Verdict 15:00 - Advice for Med Students & Residents 15:15 - Subscribe & Comment Related Videos: • Open Evidence Review: https://youtu.be/lxTqyQOUiqM • Full Doximity Platform Review: https://youtu.be/FSYzDvN3TtQ #ClinicalAI #Doximity #DoxAI #MedTech #PhysicianAI #SpeakMD #MedicalTechnology #HealthcareAI
Doximity Ask: Medical AI With Real Physician Oversight
In this episode of SpeakMD, we explore the concept of vibe coding—using plain English prompts with AI (like Claude Code) to build custom software without knowing a single line of code. We’ll look at how a practicing cardiologist recently used this exact method to beat 13,000 software engineers at an Anthropic hackathon, proving that clinical domain expertise along with AI tools can allow doctors to solve healthcare pain points. Then, I’ll walk you through how I "vibe coded" a fully functional, highly specific call-scheduling app tailored to the exact quirks, PTO requests, and weekend rules of a medical group. No hype, no marketing jargon—just a practical look at how physicians can finally take back control of their digital environment and eliminate daily friction. Subscribe to SpeakMD for unbiased, physician-first analysis of healthcare tech: @SpeakMD ⏱️ Chapters: 0:00 - The Nightmare of Making a Call schedule 1:07 - Can Doctors Make Software? 2:26 - What is "Vibe Coding"? 2:40- How a Cardiologist Won the Anthropic Hackathon 4:11- Doctors Have Domain Expertise 5:18 - Walkthrough: Building a Call Schedule App with Zero Code 6:49 - The Prompts: Translating Clinical Rules to AI 8:49 - App Demonstration and free for all Doctors 11:02 - Patient Safety and HIPAA Considerations 12:25 - What Else Can Physicians Build? (Micro-tools & Calculators) 13:31 - The SpeakMD Reality Check: Tradeoffs & Limitations 14:11 - Taking Back Control of Our Workflows Mentioned in this video: Claude Code (Anthropic) Free Call Scheduling App - Click Here! www.speakmd.com/callschedulemaker My Prompt: I'm looking to build a call schedule maker. This is for doctors in a group that have to decide who is on call on specific days of the week. The important things associated with this are to ensure that the doctors have calls that are evenly divided, as well as that holidays and weekends are evenly divided throughout the year. It should have questions like: * How many doctors are in the group * Considerations for equal amounts of call * Exclusions: these are certain days where doctors need to not be on call, so they list these as their exclusions and this gets factored into the call schedule. whenever there is a conflict and no one is able to take call this is flagged for in person determination. This should be a web app that people can interact with. Any doctors' group in the country could go on there, put their number of doctors along with the doctor's names, and churn out a calendar-like call schedule. Please help me code this web app. Disclaimer: The content provided on SpeakMD is for informational and educational purposes only and does not constitute medical, legal, or financial advice.
A Cardiologist Beat 13,000 Coders. Here's How.
Stop drowning in the noise. Here is the high-yield "Information Diet" for the modern physician. As clinicians, we are constantly bombarded with AI hype and marketing fluff that doesn't help us in the clinic. In this video, I’m sharing the 5 specific sources I use to separate the signal from the noise and figure out what’s actually going to impact my practice. **The Links:** 1. **Ground Truths (Eric Topol)** - For the actual science and mortality data. No fluff. [https://erictopol.substack.com/](https://erictopol.substack.com/) 2. **Out of Pocket (Nikhil Krishnan)** - To understand the "business physics" and absurdity of why our system is the way it is. [https://www.outofpocket.health/](https://www.outofpocket.health/) 3. **Fierce Healthcare** - The industry ticker tape. Good for knowing which hospital system is buying what. [https://www.fiercehealthcare.com/](https://www.fiercehealthcare.com/) 4. **Doximity Feed** - I use this to "read the room" and see what other physicians are saying in the comments. [https://www.doximity.com/](https://www.doximity.com/) 5. **The Healthcare AI Guy** - A great catalog of what the tech giants (Google/Amazon) are up to. [https://thehealthcareaiguy.com/](https://www.google.com/search?q=https://thehealthcareaiguy.com/) **Timestamps:** 0:00 The information problem 01:40 The data deep-dive ( Ground Truths) 02:53 Why things are so expensive/weirdm (Out of Pocket) 04:53 The "Game of Thrones" side of medicine (Fierce) 05:40 The digital doctors' lounge ( Doximity Feed) 06:31 Tracking the tech giants ( AI Healthcare Guy) 07:25 Summary 07:47 Protecting your cognitive load **Join the community:** Subscribe to join the community of forward-thinking clinicians. #MedicalAI #Doctors #SpeakMD #HealthcareTech
The Only 5 Healthcare Tech Sources I Rely On
UPDATE!!!: https://www.axios.com/2026/03/04/doctronic-utah-prescriptions-ai-jailbreak In Utah, an AI is now legally authorizing and signing prescription renewals without a human doctor in the loop. Welcome to a new era in medicine. In this video, we look at Doctronic.ai—a multi-agent AI system that claims to perform at the level of a board-certified physician in urgent care scenarios, with zero clinical hallucinations. Is it actually safe, or is it just a liability trap waiting to happen? More importantly, is this a tool designed to cure your burnout, or is it a direct competitor for low acuity visits? We put Doctronic through the SpeakMD framework to answer the four practical questions that actually matter to working physicians: 1. Does it work? (Looking at the actual medRxiv data and their multi-agent architecture). 2. Will I get paid? (How it impacts Fee-for-Service vs. the new $39 AI gig economy). 3. Will I get sued? (Deconstructing their "AI Malpractice" insurance and the Utah legal sandbox). 4. How does it fit into a real practice? (Is this what patients want?). If you want to understand how these tools actually impact your liability, your workflow, and your paycheck, you're in the right place. 👇 **Timestamps** 0:00 - The Autonomous Threshold (It's Already Here) 2:25 - What is Doctronic AI? (Multi-Agent Systems explained) 3:33 - Doctronic Research Paper Review 8:40 - Who is liable when AI makes mistakes? 11:31 - How.will this changes medical practice? 12:24 - Is this what patient's want? 13:19 - The SpeakMD Verdict **Join the SpeakMD Community:** If you're a physician trying to navigate the business and reality of modern medicine, hit subscribe. We’re building a community focused on practicing better medicine with less friction. **Resources Mentioned:** * Doctronic.ai UCSF medRxiv preprint study (March 2025) https://www.medrxiv.org/content/10.1101/2025.07.14.25331406v1 * Utah Department of Commerce: Office of Artificial Intelligence Policy (OAIP) Regulatory Sandbox * Notebook LM *Disclaimer: This video is for educational and informational purposes only and does not constitute medical or legal advice. SpeakMD is not affiliated with or sponsored by Doctronic.ai.*
The first AI legally authorized to sign prescriptions.
The "Stack of Shame" is a real thing. Whether it’s the physical pile of medical journals on your desk or the folder on your desktop titled "To Read," we’re all drowning in a medical literature explosion that doubles every 78 days. In this video, I’m breaking down how I’ve changed my approach to staying current using Google’s NotebookLM. We’re moving away from passive, linear reading and moving toward actively investigating papers. I’ll show you how I use this free tool to turn dense clinical guidelines into: * An AI-generated podcast for my morning commute. * Active recall quizzes for board prep or resident teaching. * Simplified patient handouts (that still need a doctor's eyes, of course). - Ajay **Timestamps:** 0:00 - The Stack of Shame 1:20 - A new way to learn 2:40 - What is NotebookLM? 3:49 - Demonstration of How it works: 5:54 - The "Killer App": Turning journals into podcasts 8:40 - Using AI for Active Recall & Quizzes 10:27 - What is the Cost? (Free) 11:28 - The Legal Guardrails (HIPAA & Liability) 12:34 - How I use it in practice 14:36 - My challenge to you If you're interested in the intersection between tech and medicine, hit subscribe. We focus on tools and workflows that help physicians practice smarter, not harder. www.speakmd.com
Stop Reading Medical Journals (Do This Instead)
Subscribe