we always, at least in, in, in the medical and the science part we have to have a a human in the equation because we have to remember that even if we use the prompts that help you get the same results. because chat GPT is a black box model that we don't know what it is trained about and they're always changing the weights
Dr. Shaaban's team at Utah State University is creating a virtual patient connected to generative AI, using local generative AI fed with virtual cases to make the patient act as if they have a medical condition, then injecting that into virtual reality.
Genie AI is an academic model fine-tuned with research papers that can generate paper outlines, provide in-house chatbot assistance, cite papers, and format citations according to preferred specifications
When creating AI-generated content and dealing with patient information, it is very important to use local generative AI models instead of large language models that share information externally.
Practical applications of generative AI in medical research and education
▶Ep 29 · 7:12
opinionAI models help increase efficiency, which can lead to productivity, but a human must always be in the equation for medical and scientific work↗
▶Ep 29 · 7:30
quotewe always, at least in, in, in the medical and the science part we have to have a a human in the equation because we have to remember that even if we use the prompts that help you get the same results. because chat GPT is a black box model that we don't know what it is trained about and they're always changing the weights↗
▶Ep 29 · 7:46
clinicalChatGPT is a black box model with unknown training data and changing weights, requiring human oversight to direct it and interpret its outputs↗
▶Ep 29 · 8:03
clinicalGenie AI is an academic model fine-tuned with research papers that can generate paper outlines, provide in-house chatbot assistance, cite papers, and format citations according to preferred specifications↗
▶Ep 29 · 9:46
clinicalAcademic AI models like Genie AI are mostly on par with latest published research, though users must verify which library the model searches↗
▶Ep 29 · 10:59
clinicalOpenEvidence was developed by Harvard team and Mayo Clinic, focuses on Elsevier library, provides conversational answers while summarizing latest papers, and suggests related topics↗
▶Ep 29 · 19:09
quoteWe have to have these talks. We have to learn how to use it because it, it's, it's here to stay↗
▶Ep 29 · 23:25
clinicalChatGPT can generate medical cases in USMLE Step 1 or Step 2 format with step-by-step progression and end-of-case feedback when given appropriate prompts↗
Dr. Ramy Shaaban - Best of the Best in Pediatric Surgery 2025
▶Ep 11 · 0:33
clinicalChatGPT is already being used to assist in clinical decision making, ensuring clinicians have the right information at their fingertips when they need it.↗
▶Ep 11 · 0:33
clinicalMachine learning is already being used in diagnostic imaging, helping doctors detect diseases like cancer earlier and more accurately.↗
▶Ep 11 · 0:33
clinicalPredictive analytics using machine learning helps forecast health risks, allowing doctors to intervene before problems become severe, resulting in better and more customized care for patients.↗
▶Ep 11 · 0:33
opinionKey ethical questions for AI in healthcare include how to protect patient privacy, ensure AI decisions are fair and unbiased, and keep the human touch in medicine.↗
▶Ep 11 · 0:33
opinionAI is a tool, not a replacement for human expertise; continuous education and responsible implementation are key to making AI work for everyone.↗
▶Ep 11 · 0:33
opinionPrompt engineering is a rising field; doctors need to understand how to accurately prompt AI to get the best results, treating AI as an assistive tool instead of a competitor.↗
▶Ep 11 · 0:33
clinicalGenerative AI can create content including text, images, audio, and video; tools like ChatGPT, DALL-E, and others are opening new doors in medical education, research, and patient engagement.↗
▶Ep 11 · 0:33
opinionThe goal of generative AI is not to replace healthcare professionals but to support them as a brainstorming partner, helping generate ideas and solutions faster.↗
▶Ep 11 · 0:33
opinionAI is not here to replace doctors; it is here to assist by processing vast amounts of data in seconds, suggesting diagnoses, summarizing research, and streamlining workflow.↗
▶Ep 11 · 0:33
opinionMedicine is about human connection, listening, empathizing, and making complex decisions that require experience and intuition; AI works best when paired with human expertise.↗
▶Ep 11 · 0:33
clinicalAI is streamlining administrative tasks like clinical documentation; AI can generate patient summaries instantly, saving hours of paperwork and giving healthcare professionals more time to focus on patient care.↗
▶Ep 11 · 0:33
opinionAI, machine learning, and large language models are transforming healthcare by improving diagnosis, personalizing treatment, and making the system more efficient, but they are here to assist, not replace human expertise.↗
▶Ep 11 · 0:33
opinionThe future of medicine is a collaboration between humans and technology, not just AI-driven.↗
▶Ep 11 · 0:33
quotemedicine is about human connection, listening and empathizing and making complex decisions that require experience and intuition.↗
▶Ep 11 · 0:33
quoteAI is a powerful tool, but it works best when paired with human expertise.↗
▶Ep 11 · 0:33
quoteThe future of medicine is not just AI driven, it is a collaboration between humans and technology.↗
▶Ep 11 · 0:33
clinicalGoogle's DeepMind AlphaFold is solving one of biology's biggest puzzles by predicting protein structures, helping researchers develop new treatments faster.↗
▶Ep 11 · 0:33
clinicalIBM Watson Health analyzes complex patient data to assist doctors in making better decisions.↗
▶Ep 11 · 0:33
opinionAI technologies are not replacing doctors; they are giving them superpowers by accelerating drug discovery, personalizing treatment, and handling administrative tasks more effectively.↗
▶Ep 11 · 0:33
clinicalLarge language models like OpenAI's ChatGPT are changing the way medical professionals access information, providing real-time evidence-based insights, summarizing medical literature, and offering diagnostic suggestions.↗
▶Ep 11 · 0:33
quoteartificial intelligence is a tool, not a replacement for human expertise.↗
▶Ep 11 · 0:33
quoteinstead of resisting AI. I think doctors need to understand how to accurately prompt AI to get the best results, that way we treat AI as a tool that assists us instead of a competitor that is coming to replace us.↗
▶Ep 11 · 0:33
quotethe goal is not to replace uh healthcare professional, it is to support them.↗
▶Ep 11 · 0:33
quoteA common fear of AI in healthcare is, well, it replaces doctors, and the answer is no. AI, AI is not here to take over. It is here to assist.↗
▶Ep 11 · 0:33
quoteAI in healthcare isn't just a futuristic idea, it is happening right now.↗
▶Ep 11 · 0:33
quoteThese technologies are not replacing doctors, they are giving them superpowers.↗
▶Ep 11 · 0:33
quotewith great power comes great responsibility.↗
▶Ep 11 · 6:59
opinionWhen creating AI-generated content and dealing with patient information, it is very important to use local generative AI models instead of large language models that share information externally.↗
▶Ep 11 · 6:59
opinionDisclosing the AI platform being used and ensuring local data handling are potential solutions to authenticity and security concerns.↗
▶Ep 11 · 6:59
clinicalDr. Shaaban's team at Utah State University is creating a virtual patient connected to generative AI, using local generative AI fed with virtual cases to make the patient act as if they have a medical condition, then injecting that into virtual reality.↗
▶Ep 11 · 6:59
opinionIt is becoming harder to differentiate between AI-generated and human-generated content because AI is getting better.↗
