Clinicians + AI = Building Better Tools For Patient Care

What's Next: Preparing for the AI-Enhanced Future of Medicine

Welcome to Hippo Education's Practicing with AI, conversations about medicine, AI, and the people navigating both. Over the past seven episodes, we have explored many facets of AI and medicine, from AI documentation support to the pitfalls of AI in medicine, including hallucinations and potential bias. But now, we are looking to the future. What might medicine look like with AI woven into the way we diagnose and treat patients? What tools are currently being developed that clinicians should watch for? What concerns lie ahead as AI becomes more integrated into care? And where could AI push medicine forward in ways we never thought possible? Dr. John Casey joins us to answer these questions. John is an emergency medicine physician in Columbus, Ohio. He serves as Program Director for the emergency medicine residency at OhioHealth Doctors Hospital in Columbus, and as EMS medical director for multiple EMS agencies. He also works in medical informatics and has been a thought leader in AI and medicine. While we take a brief break, we're already gearing up for Season Two — and your voice might be featured in an upcoming episode. Visit speakpipe.com/hippoed [http://speakpipe.com/hippoed] to leave a voice message about anything related to AI and medicine: your excitement, your concerns, your own experiences with AI…anything.

Medicolegal Considerations with AI and Medicine

Welcome to Hippo Education's Practicing with AI, conversations about medicine, AI, and the people navigating both. This month, Rob and Vicky cover a highly requested topic: the medicolegal issues of AI in medicine. Are clinically-related searches in an LLM like Open Evidence admissible? Who is liable if there is a bad outcome when a clinician uses an AI tool in their decision-making? What really happens to all of the data and transcripts that is generated by an AI-scribbling tool? These questions (and many more!) are answered by our resident legal expert, Pete Heidepriem. Note: Pete's comments are not intended as legal advice, and they are not intended to form any type of attorney-client relationship. Visit speakpipe.com/hippoed [http://speakpipe.com/hippoed] to leave a voice message about anything related to AI and medicine: your excitement, your concerns, your own experiences with AI… anything. Your voice might even make it onto a future episode.

Bias and Fairness

Welcome to Hippo Education's Practicing with AI, conversations about medicine, AI, and the people navigating both. This month, Rob and Vicky address a common concern of clinicians when it comes to AI and medicine: bias and fairness. How might AI perpetuate health disparities that are rooted in bias? Or could AI help to mitigate bias in medicine? To learn more about this issue, Vicky interviews data journalist, author, and NYU professor Dr. Meredith Broussard [https://meredithbroussard.com/] on the topic of bias in technology. They explore how and why bias exists in technology and what can be done about it. Visit speakpipe.com/hippoed [http://speakpipe.com/hippoed] to leave a voice message about anything related to AI and medicine: your excitement, your concerns, your own experiences with AI… anything. Your voice might even make it onto a future episode. References: 1. Broussard M. More Than A Glitch: Confronting Race, Gender, and Ability Bias in Tech. The MIT Press; 2023. 2. Broussard M. Artificial Unintelligence: How Computers Misunderstand the World. The MIT Press; 2018. 3. Bhakta NR, et al. Race and Ethnicity in Pulmonary Function Test Interpretation: An Official American Thoracic Society Statement. Am J Respir Crit Care Med. 2023;207(8):978-995. PMID: 36973004 [https://pubmed.ncbi.nlm.nih.gov/36973004/] 4. Liu M, et al. Early detection of sexually transmitted infections from skin lesions with deep learning: a systematic review and meta-analysis. Lancet Digit Health. 2025;7(7):100894. PMID: 40769792 [https://pubmed.ncbi.nlm.nih.gov/40769792/] 5. Rao P. SCIN: A new resource for representative dermatology images. Google Research Blog. 2024. Available at: https://research.google/blog/scin-a-new-resource-for-representative-dermatology-images/ [https://research.google/blog/scin-a-new-resource-for-representative-dermatology-images/]. Accessed on September 25, 2025. 6. The Monk Skintone Scale [https://skintone.google/the-scale] 7. Good Machine Learning Practice for Medical Device Development: Guiding Principles. US Food & Drug Administration. 2025. Available at: https://www.fda.gov/medical-devices/software-medical-device-samd/good-machine-learning-practice-medical-device-development-guiding-principles [https://www.fda.gov/medical-devices/software-medical-device-samd/good-machine-learning-practice-medical-device-development-guiding-principles]. Accessed on September 25, 2025. 8. Rickman S. Evaluating gender bias in large language models in long-term care. BMC Med Inform Decis Mak. 2025;25(1):274. PMID: 40784946 [https://pubmed.ncbi.nlm.nih.gov/40784946/] 9. Challapally A, Pease C, Raskar R, Chari P. The GenAI Divide: State of AI in Business 2025. MIT NANDA. 2025. https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Business_2025_Report.pdf [https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Business_2025_Report.pdf]

Clinicians + AI = Building Better Tools For Patient Care

Welcome to Hippo Education's Practicing with AI, conversations about medicine, AI, and the people navigating both. This month, Rob and Vicky talk with Caroline (Carrie) Hodge, a PA and the co-founder and CEO of Dimer Health [https://www.dimerhealth.com/]. Dimer Health leverages clinical expertise and an AI-powered platform to facilitate a seamless transition for patients from hospital to home. We discuss how clinician-entrepreneurs are leveraging technology to address age-old problems in medicine. For more information on the organizations highlighted in this episode: 1. https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html [https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html] 2. https://thehealthcaretechnologyreport.com/how-one-key-encounter-helped-shiv-rao-create-abridge/https://thehealthcaretechnologyreport.com/how-one-key-encounter-helped-shiv-rao-create-abridge/ [https://thehealthcaretechnologyreport.com/how-one-key-encounter-helped-shiv-rao-create-abridge/] 3. https://www.viz.ai/our-story [https://www.viz.ai/our-story] 4. https://www.aapa.org/news-central/2025/03/pas-transform-post-discharge-care-reduce-readmissions-with-the-support-of-ai/ [https://www.aapa.org/news-central/2025/03/pas-transform-post-discharge-care-reduce-readmissions-with-the-support-of-ai/] Visit speakpipe.com/hippoed [http://speakpipe.com/hippoed] to leave a voice message about anything related to AI and medicine: your excitement, your concerns, your own experiences with AI… anything. Your voice might even make it onto a future episode.

When The Machine Gets It Wrong: Hallucinations

Welcome to Hippo Education's Practicing with AI, conversations about medicine, AI, and the people navigating both. This month, Rob and Vicky tackle a common pitfall of AI: hallucinations. What are hallucinations (and is that even the right term)? Why do these types of errors happen? And what can individuals do to reduce the hallucination rate? Plus, Rob and Vicky dive into OpenAI's most recent model release, ChatGPT 5, and analyze its performance against older GPT models. For those who want to dive deeper into OpenAI's HealthBench benchmark: 1. OpenAI's white paper on HealthBench outlines the benchmark's components and delivers performance data on older AI models. https://openai.com/index/healthbench/ [https://openai.com/index/healthbench/] 2. Drs. Liu and Liu performed a systematic analysis and outlined HealthBench's strengths and limitations in this paper [https://pubmed.ncbi.nlm.nih.gov/40719790/] published in the Journal of Medical Systems in July 2025. Visit speakpipe.com/hippoed [http://speakpipe.com/hippoed] to leave a voice message about anything related to AI and medicine: your excitement, your concerns, your own experiences with AI… anything. Your voice might even make it onto a future episode.