Dev and Doc: AI For Healthcare Podcast

<p>What does it mean for a doctor to diagnose a patient? Can an AI (GPT model) learn to diagnose a patient, and even out-diagnose a doctor? Can we use AI to predict the future?</p> <p>Try the Foresight GPT demo here: <a href="https://foresight.sites.er.kcl.ac.uk/">foresight.sites.er.kcl.ac.uk</a></p> <p>Like what you're hearing? Support us by subscribing and reaching out to us. We want to encourage open discussion between clinicians and developers.</p> <p>Dev&Doc is a podcast where doctors and developers deep dive into the potential of AI in healthcare.<br> 👨🏻‍⚕️Doc - <a href="https://www.linkedin.com/in/dr-joshua-auyeung/">Dr. Joshua Au Yeung</a><br> 🤖Dev - <a href="https://twitter.com/zeljkokr">Zeljko Kraljevic</a><br> <a href="https://www.linkedin.com/build-relation/newsletter-follow?entityUrn=7216474068085026817">LinkedIn Newsletter</a><br> <a href="https://youtube.com/@DevAndDoc">YouTube</a><br> <a href="https://podcasters.spotify.com/pod/show/devanddoc">Spotify</a><br> <a href="https://podcasts.apple.com/gb/podcast/dev-and-doc-ai-for-healthcare-podcast/id1751495120">Apple</a><br> <a href="https://aiforhealthcare.substack.com/">Substack</a><br> For enquiries - 📧 <a href="mailto:Devanddoc@gmail.com">Devanddoc@gmail.com</a> </p> Timestamps: 00:00 Start 00:49 Intro 02:18 How does a doctor diagnose? 06:27 LLM trained on medical school vs real clinical scenarios 10:54 Do you have time to see every patient (in detail)? 13:44 A doctor's day 22:28 Which doctor's jobs can be automated? 27:41 When you train models on the wrong goal (misalignment) 31:01 Low hanging fruit - GPT / LLM text summarisation , administrative tasks 37:25 What tools are helping doctors right now? 40:35 How does a doctor prognosticate? How are risk scores created? 49:05 Foresight- Using AI to Predict the Future 58:31 GPT graduates from medical school. GPT starts working in a hospital 1:02:25 Why are big tech not building the next real-world medical LLM? 1:04:44 Using AI to predict the future. Foresight GPT demo 1:10:18 predict diagnosis respiratory infections, COVID-19 1:11:40 predicting obstructive sleep apnoea 1:14:12 predicting polycystic kidney disease 1:18:01 wrap up <p>🎞️ Editor - <a href="https://www.instagram.com/dragan_kraljevic/">Dragan Kraljević</a></p> <p>🎨 Brand design and art direction - <a href="https://www.behance.net/anagrigorovici027d">Ana Grigorovici</a></p>

Discover the potential and pitfalls of large language models in healthcare. The hosts share their eye-opening experiences with AI chatbots, weighing their capabilities against their limitations. Delve into the evolution of language models and explore the critical importance of high-quality training data. The conversation also touches on the philosophical implications of AI behavior and the ongoing challenges in medical diagnostics. Join the exploration of how AI could transform clinical interactions while addressing pressing concerns.

Dr. Joshua Au Yeung, a doctor delving into AI's healthcare potential, and Zeljko Kraljevic, a developer at the tech-med intersection, dive into Named Entity Recognition (NER). They discuss its exciting applications like clustering a million hospital patients and improving pandemic monitoring. The duo highlights challenges faced by NER in clinical audits, the role of neural networks, and the importance of clinician collaboration. Insights shared also reveal resistance to AI in the NHS, hinting at a transformative future for healthcare.

Dev&Doc is a podcast where doctors and developers deep dive into the potential of AI in healthcare. 👨🏻‍⚕️Doc - Dr. Joshua Au Yeung 🤖Dev - Zeljko Kraljevic The podcast 🎙️ 🔊Spotify- https://sptfy.com/OMmV Join the Dev&Doc movement: 🏃 https://aiforhealthcare.substack.com/ Timestamps: Start 00:00 Introduction 00:28 The idea 01:20 Target audience 2:46 Start of the AI journey 04:15 Medical school and Computer science degrees 05:25 Background of Dev and Doc 05:51 Dev goes into healthcare 07:17 Doc goes into AI 09:20 Neurology, a second love 12:22 What to expect, NLP, large language models, NER, generative AI 13:16 The main goal of the podcast 16:11 🎞️ Editor- Dragan Kraljević https://www.instagram.com/dragan_kraljevic/ 🎨Brand design and art direction - Ana Grigorovici Reach out - 📧Devanddoc@gmail.com LinkedIn - https://shorturl.at/esEKO