Nelly MD

Nelly Tan
  • 5.0 (1)
  • Medicine

What happens when a radiologist gets curious about… pretty much everything? Welcome to Nelly MD — my podcast about the ideas, papers, technologies, and projects that make me stop and think. I’m a radiologist, but this show goes well beyond radiology. Expect a hodgepodge of peer-reviewed research, my own publications, artificial intelligence, quality improvement, healthcare innovation, interesting blog posts, lessons from projects, and whatever else catches my attention. Some episodes will unpack a research paper: Why did we do the study? What did we actually find? What surprised us? And does any of it matter in the real world? Others may explore AI, process improvement, new technology, patient care, or an idea I simply want to understand better. A quick note about AI: this podcast is intentionally co-created with AI. I choose the topics, papers, source material, questions, and overall direction. I bring the medical context, experience, interpretation, and judgment—and I decide what ultimately gets published. AI tools including ChatGPT, Claude, and Gemini help me explore ideas, summarize and synthesize information, organize material, and draft or refine content. I review, edit, and take responsibility for the final product. In other words: human curiosity and judgment, amplified by AI. You can find more of my writing, projects, experiments, and assorted interests at nellymd.com. Connect with me on LinkedIn: https://www.linkedin.com/in/nelly-tan-092b5bb/ Follow me on Bluesky: @nellytan.bsky.social Nelly MD is curious by design. Papers, radiology, AI, quality improvement, research, ideas—and probably a few things that don’t fit neatly into any category. This podcast is for educational and informational purposes only. It is not medical advice and does not represent the official position of any institution.

Episodes

  1. 1d ago

    The Question I Didn't Know to Ask

    Hey! I'd love to hear your thoughts, send me a voice note. Palliative care is not hospice In this deep dive, we explore how specialized palliative care works in parallel with active, curative treatment to relieve the physical and emotional stress of serious illness from day one[1]. 💡 Key Takeaways Parallel Care Model: Palliative care is given alongside disease-directed treatment, rather than replacing it when treatment stops[1][2].The Awareness Gap: An estimated 71% of U.S. adults have never heard the term "palliative care," and globally only about 14% of people who need it receive it[3].Beyond Cancer: Cancer accounts for only 34% of people who need palliative care; the majority have cardiovascular disease (38.5%), chronic respiratory disease (10.3%), or other chronic conditions[3][4].Clinical Evidence: A landmark 2010 study published in the New England Journal of Medicine showed that early palliative care significantly improved patient quality of life and reduced depressive symptoms[1][5].Telehealth Accessibility: Recent research confirms that video visits can deliver equivalent quality-of-life benefits as in-person appointments, making care far more accessible[6][7].📋 Questions to Ask Your Care Team If you or a loved one are facing a chronic or serious diagnosis, bring these practical questions to your next appointment: "Can we request a palliative care consult alongside our ongoing treatment plan?"[7]"Can we focus on targeting specific symptoms like pain, cough, nausea, and sleep disruption?"[8]"Are virtual/telehealth visits available for routine symptom check-ins?"🔗 Links & Resources Read the Full Article: Explore the original story and deeper analysis on the Blog PostFind a Local Provider: Search for palliative care specialists by ZIP code at GetPalliativeCare.orgConnect with the Author:LinkedIn Profile: https://www.linkedin.com/in/nelly-tan-092b5bb/Bluesky Profile: https://bsky.app/profile/nellytan.bsky.social🎙️ Audio Disclosure: This podcast deep dive was generated by Gemini Notebook based on the source analysis and medical literature review[10]*.*

    The Question I Didn't Know to Ask

  2. Sep 28

    How AI Frees Doctors for Patients

    Hey! I'd love to hear your thoughts, send me a voice note. 🤖 AI is not replacing my clinical judgment. It is clearing the ground so I can focus on the work that actually needs me. In this episode, I share what a year of building AI workflows in radiology really looks like: 🩻 Faster reporting when the tool fits the task 🔍 A systematic second review of prior findings 📚 Less friction in teaching and research 📅 Automated scheduling and administrative work ❤️ More time and attention for patients, and for life outside medicine ⚖️ Why AI still requires measurement, oversight, and human judgment The biggest lesson? 🎯 Workflow fit matters more than hype. AI worked well for standardized CT reporting, but the benefit was unclear for complex MRI. The goal is not automation for its own sake. It is giving clinicians more capacity for the work only they can do. 📝 Read the original blog post: https://www.nellymd.com/2026/08/what-year-of-building-ai-workflows.html 📚 References 1️⃣ Tan N. Large language model-assisted radiology reporting in a single-radiologist implementation: a retrospective cohort study interpreted through a UTAUT lens. Abdominal Radiology. 2026. 🔗 https://doi.org/10.1007/s00261-026-05524-y 2️⃣ Mayes CJ, Reyes C, Truman ME, et al. Improving radiology reporting accuracy: use of GPT-4 to reduce errors in reports. Abdominal Radiology. 2025;51(1):513-520. 🔗 https://doi.org/10.1007/s00261-025-05079-4 3️⃣ Twilt JJ, Saha A, Bosma JS, et al. Evaluating an AI-driven Triaging Workflow for MRI-based Clinically Significant Prostate Cancer Diagnosis: A Simulation Study. Radiology: Imaging Cancer. 2026;8(3):e250461. 🔗 https://doi.org/10.1148/rycan.250461 💬 Opinions are my own. This episode is for educational purposes and does not constitute medical advice. 🎙️ AI disclosure: This podcast episode was generated using Google's NotebookLM by Gemini, based on my original blog post and the referenced research. I reviewed the episode before publication.

    How AI Frees Doctors for Patients

  3. Sep 14

    Can AI Hear What Patients Love?

    Hey! I'd love to hear your thoughts, send me a voice note. Can AI make sure great care gets noticed? Patient compliments often remain buried in thousands of survey responses. This episode explores how natural language processing can identify positive feedback and quickly deliver it to the healthcare professionals who earned it. The results: praise could be shared in a median of 0.7 minutes per case, while 94% of surveyed staff felt appreciated and 90% felt valued. 📚 Featured research 🤖 Automating patient praise. Sharing Patient Praises With Radiology Staff: Workflow Automation and Impact on Staff. A hybrid NLP workflow made sharing patient compliments faster and supported staff recognition and morale. 🔗 DOI: 10.1016/j.jacr.2023.12.024 🧲 What shapes the MRI experience? Effects of Patient Demographics and Examination Factors on Patient Experience in Outpatient MRI Appointments. Longer waits and examinations were associated with worse ratings, while service, communication, and comfort mattered. 🔗 DOI: 10.1016/j.jacr.2023.02.032 💡 The takeaway: AI does not replace gratitude. It helps make sure gratitude reaches the right people. 🤖 AI disclosure: I selected the source papers and shaped the framing for this episode. Google NotebookLM generated the podcast audio. I reviewed and approved the audio and this episode listing before publication.

    Can AI Hear What Patients Love?

  4. Sep 7

    Hospital Care in Your Living Room

    Hey! I'd love to hear your thoughts, send me a voice note. My mother needed hospital care, and she got it. But the hospital also took her sleep, her movement, and every last bit of control over her day. Then she qualified for a hospital-at-home program, which brought hospital-level care into her home. In this episode, I describe what changed when the medicine stayed the same but the environment changed: scheduled visits, more movement, uninterrupted sleep, and the ability for our family to care for her without living in a hospital room. I also examine the evidence on hospital-at-home programs, including their safety, patient experience, costs, caregiver burden, and equity challenges. Hospital at home is not for every patient or every family. But for carefully selected patients, it offers a compelling alternative: keep the medicine and give people back more control over their lives. Read the full blog post: https://www.nellymd.com/2026/09/when-hospital-came-home.html Sources mentioned: Maniaci MJ, et al. J Hosp Med. 2025. https://doi.org/10.1002/jhm.70076 Levine DM, et al. Ann Intern Med. 2020. https://doi.org/10.7326/M19-0600 Edgar K, et al. Cochrane Database Syst Rev. 2024. https://doi.org/10.1002/14651858.CD007491.pub3 Krumholz HM. N Engl J Med. 2013. https://doi.org/10.1056/NEJMp1212324 Duhamel S, et al. J Am Geriatr Soc. 2026. https://doi.org/10.1111/jgs.70573 AI disclosure: I wrote the blog post from my own experience and point of view and co-drafted it with Claude (Anthropic), which helped research, organize, and edit the piece. Google NotebookLM generated the podcast audio from the blog post. ChatGPT (OpenAI) created the episode-cover illustration and prepared and scheduled the episode on RSS.com. I reviewed and approved the final blog post, audio, artwork, and episode listing before publication.

    Hospital Care in Your Living Room

  5. Aug 30

    How A Health System Improves Care

    Hey! I'd love to hear your thoughts, send me a voice note. How do you improve healthcare without blaming the people working inside it? In this episode, I explore how a large academic health system turns systems problems into measurable change, using DMAIC, root cause analysis (RCA), simulation, frontline observation, and an institutional culture of quality improvement. Drawing on four recent quality improvement projects, we look at: • how structured education, participation tracking, and simulated RCA increased radiology residents' participation in safety-event investigations by 33%; • how a one-hour simulated RCA improved residents' comfort with RCA participation, understanding of what to expect, and ability to identify system issues; • how low-cost, workflow-embedded changes to privacy, wait-time communication, and physical comfort raised top-box nuclear medicine waiting-area comfort scores from 76% to 85% while the check-in wait-time measure remained stable; and • what 1,106 Quality Academy projects involving 10,063 team members reveal about teamwork, efficiency, multidisciplinary collaboration, and sustainable improvement. References and access: Reyes C, Ponce LM, Hannafin CL, et al. Improving patient safety education for radiology residents: Using a quality improvement approach. Current Problems in Diagnostic Radiology. 2025;54(5):568-573. https://pubmed.ncbi.nlm.nih.gov/40517116/Fishleder MH, Hannafin CL, Ponce LM, et al. Exploring the feasibility and effectiveness of simulated root cause analysis for radiology training. Current Problems in Diagnostic Radiology. 2026;55(2):181-184. https://pubmed.ncbi.nlm.nih.gov/41177709/Tan N, Hannafin CL, Ponce LM, et al. Improving comfort in the nuclear medicine waiting area: A quality improvement initiative. Current Problems in Diagnostic Radiology. 2026;55(4):501-504. https://pubmed.ncbi.nlm.nih.gov/41912369/Tan N, Rohila V, Reyes C, et al. Cultivating a Quality Improvement Culture With Mayo Clinic Quality Academy. American Journal of Medical Quality. 2026;41(3):133-138. https://pubmed.ncbi.nlm.nih.gov/41961077/AI disclosure: This episode was co-created with AI. I supplied a brain dump and the source papers; ChatGPT, Claude, and Gemini helped create and shape the final content.

    How A Health System Improves Care
  • 5 Episodes

About

What happens when a radiologist gets curious about… pretty much everything? Welcome to Nelly MD — my podcast about the ideas, papers, technologies, and projects that make me stop and think. I’m a radiologist, but this show goes well beyond radiology. Expect a hodgepodge of peer-reviewed research, my own publications, artificial intelligence, quality improvement, healthcare innovation, interesting blog posts, lessons from projects, and whatever else catches my attention. Some episodes will unpack a research paper: Why did we do the study? What did we actually find? What surprised us? And does any of it matter in the real world? Others may explore AI, process improvement, new technology, patient care, or an idea I simply want to understand better. A quick note about AI: this podcast is intentionally co-created with AI. I choose the topics, papers, source material, questions, and overall direction. I bring the medical context, experience, interpretation, and judgment—and I decide what ultimately gets published. AI tools including ChatGPT, Claude, and Gemini help me explore ideas, summarize and synthesize information, organize material, and draft or refine content. I review, edit, and take responsibility for the final product. In other words: human curiosity and judgment, amplified by AI. You can find more of my writing, projects, experiments, and assorted interests at nellymd.com. Connect with me on LinkedIn: https://www.linkedin.com/in/nelly-tan-092b5bb/ Follow me on Bluesky: @nellytan.bsky.social Nelly MD is curious by design. Papers, radiology, AI, quality improvement, research, ideas—and probably a few things that don’t fit neatly into any category. This podcast is for educational and informational purposes only. It is not medical advice and does not represent the official position of any institution.

Information

  • Creator
    Nelly Tan
  • Years Active
    2026
  • Episodes
    5
  • Rating
    Clean
  • Copyright
    © Nelly Tan
  • Show Website
    Nelly MD