Smart Scribe, Novel Proteins and Up To Date Health Professionals

Hello, and welcome to this edition of?The Med AI Capsule! ??????

I am thrilled to have you on board as we embark on a journey into the fascinating world of Medical AI. In this newsletter, I'll be your trusted source for the latest updates, breakthroughs, and thought-provoking insights in the ever-evolving field of artificial intelligence in healthcare.

Whether you're a healthcare professional, a tech enthusiast, or simply curious about the future of medicine,?'The Med AI Capsule'?is your compass to navigate the dynamic world of AI in healthcare.

Here are three of the latest developments in the field of AI in healthcare:

1.?AWS Announces AWS HealthScribe, a New Generative AI-Powered Service that Automatically Creates Clinical Documentation

• AWS HealthScribe is a new HIPAA-eligible service by Amazon Web Services that leverages speech recognition and generative AI to automatically create clinical documentation from patient-clinician conversations.
• It allows healthcare software providers to build clinical applications quickly, saving clinicians time by generating accurate clinical notes and summaries from doctor-patient discussions that can be entered into electronic health record (EHR) systems.

"Documentation is a particularly time-consuming effort for healthcare professionals, which is why we are excited to leverage the power of generative AI in AWS HealthScribe and reduce that burden." - Bratin Saha, vice president of Machine Learning and Artificial Intelligence Services at AWS

• While AWS HealthScribe offers significant benefits in streamlining documentation and improving the consultation experience, potential counterarguments may include concerns about the accuracy and reliability of AI-generated clinical notes and the potential for over-reliance on AI, potentially reducing the level of personalization and human touch in patient care.
• It is important to strike a balance between leveraging the efficiency of AI-powered solutions like AWS HealthScribe and preserving the essential role of human clinicians in providing personalized and high-quality healthcare to patients. Responsible use of AI and continuous validation by healthcare professionals will be crucial in harnessing the full potential of generative AI in the medical field.

2.?Generative-AI inventing proteins is changing medicine

• Protein folding problem solved by AI: AlphaFold, an AI tool developed by DeepMind, accurately predicts the 3D structure of proteins from their amino acid sequences, revolutionizing biology and various technology sectors.
• Generative AI tools for protein design: Genie, a generative AI model, can create entirely new proteins that have never existed in nature. These tools have the potential to transform scientific understanding, medical science, and environmental applications.
• Limitations of current AI tools: Existing AI tools can only design static and rigid proteins, while real proteins in nature can change shape and adapt to different conditions. Future advancements in AI could overcome this limitation and lead to even greater applications in various fields.

Counterarguments:

• Safety and ethical concerns: The creation of entirely new proteins through AI raises questions about safety and potential unintended consequences. Introducing synthetic proteins into living organisms may have unpredictable effects that require careful examination and regulation.
• Practical challenges: Despite the promise of AI-generated proteins, the translation of these designs into real-world applications and therapies may face practical hurdles and regulatory scrutiny. The complex nature of proteins and their interactions within living systems demands rigorous testing and validation before widespread implementation.

3.?This Health AI Startup Aims To Keep Doctors Up To Date On The Latest Science

• Large language models, like ChatGPT, suffer from a knowledge cutoff, being frozen in time and lacking access to real-time data.
• This limitation hinders their usefulness, especially in critical fields like medicine, where access to the latest research and information is crucial.
• OpenEvidence aims to address this problem by developing a solution that allows AI chatbots to access and incorporate up-to-date data and scientific studies into their responses, making them more relevant and valuable in real-world applications, particularly in medical settings.
• The founder, Daniel Nadler, seeks to enable chatbots to access the latest medical research by "marrying" language models with a real-time firehose of clinical documents.
• OpenEvidence's approach involves "retrieval augmented generation," allowing the AI chatbot to answer questions with up-to-date information from recent scientific studies. It aims to compete with established medical databases like UpToDate and offers interactive, tailored responses to precise patient scenarios.

Antonio Forte, a professor of plastic surgery at Mayo Clinic who is on OpenEvidence’s medical advisory board, says he uses UpToDate on a regular basis. Forte says the biggest difference using OpenEvidence over the past few weeks has been the time savings. Rather than having to read through the equivalent of a book chapter, he can get an answer “within 30 seconds, not within 10 minutes.”

• While OpenEvidence's approach shows promise in reducing inaccuracies ("hallucinations") by providing citations to sourced information, it still faces challenges in assessing the quality of retrieved data. The revenue model is yet to be determined, and the startup focuses on serving licensed medical professionals rather than becoming a chatbot for the average patient. Ethical considerations remain significant, as the technology is meant to assist healthcare professionals, not replace their human judgment.

Stay tuned for our upcoming editions where we'll uncover the latest breakthroughs and explore the potential of AI to shape a healthier tomorrow.

PS: If you are a medical professional who is interested in artificial intelligence but confused about where to start, feel free to check out my?CPD-accredited course on Bionabu?and my?Whatsapp Community. For 1:1 help or guidance, please visit?HERE.

Best regards,

Dr Avneesh