David Levy’s Post

𝐂𝐡𝐚𝐧 𝐙𝐮𝐜𝐤𝐞𝐫𝐛𝐞𝐫𝐠 𝐒𝐜𝐢𝐞𝐧𝐜𝐞 𝐭𝐨 𝐁𝐮𝐢𝐥𝐝 𝐀𝐈 𝐆𝐏𝐔 𝐂𝐥𝐮𝐬𝐭𝐞𝐫 𝐭𝐨 𝐌𝐨𝐝𝐞𝐥 𝐂𝐞𝐥𝐥 𝐒𝐲𝐬𝐭𝐞𝐦𝐬 The Chan Zuckerberg Initiative has announced the funding and building of one of the largest computing systems dedicated to nonprofit life science research in the world. The effort will provide the scientific community with access to predictive models of healthy and diseased cells, leading to groundbreaking new discoveries that could help cure, prevent, or manage all diseases by the end of this century. Read More: https://lnkd.in/eFCHcB5p #AsiaOneMagazine #media #news #dailynews #newsfeed #dailyupdates

#Cancer #patients undergoing #Radiotherapy shift, move, swallow, digest, pass gas, settle, and breathe over the course of treatment #delivery. These movements change the actual location of the #tumor being treated compared to what is expected, risking either under-treating the tumor or over-radiating the surrounding, healthy tissue. Techniques like respiratory gating and new technologies such as #MRI-guided radiation therapy improve the effectiveness of tumor tracking and minimize the impact of both small and large body movements on the delivery of radiation. They achieve this largely by not delivering radiation when the target is not in its expected position. Unfortunately, this has the effect of making treatments last longer, which is both an inconvenience to the patient and a limit on the number of patients who can be treated per day on a given linear accelerator. This approach is somewhat different from techniques associated with what we normally call #adaptive #radiotherapy, where physicians address changes that take place in the body over a longer period, such as changes in tumor size or shape, or the patient's hydration level or weight that often accompany both disease and treatment. In adaptive radiotherapy, a patient is scanned before each treatment, and the plan is potentially adjusted based on these macro changes to each patient's individual #physiology. The "holy grail" of introducing massively increased computational power and #machine #learning would be to combine both of these techniques into a unified approach, allowing #AI-enhanced software controlling the accelerator to adapt in real-time to actual and predictive movement. This would enable targeting tumors more precisely, at higher doses, over less time, and with lower collateral damage to adjacent structures. The safety protocols and guardrails around allowing machines more #autonomy in adapting plans and their #constraints to the delivery of real-time therapy are almost inconceivably perilous and equally complex. One thing is certain: the technology will get there before we are ready for it, and that means the time for these conversations is now.

We are thrilled to announce the award of a multi-national, multi-institutional collaborative research and AI development project between University of Cambridge, Asher Orion Group, Mass General Brigham, and Rhino Health. We are working to develop an AI model that will assist physicians with the diagnosis of a rare disease. “This is a unique opportunity to combine expertise from across the globe, both clinicians and computer science expertise. We strive for the day when all physicians and care-teams can access and use the power of computational innovations for patients’ quality of life regardless of their geographical location and socio-economic status.” Said John Kalafut PhD F Kalafut, PhD, CEO of Asher Orion Group. “Birt-Hogg-Dube syndrome is a complex disease that can be challenging to diagnose,” said Stefan Marciniak, from Cambridge University. “By leveraging federated learning, we hope to develop accurate and efficient diagnostic tools that can be used by both specialists and non-specialists alike.” “Federated learning offers a powerful solution to the challenge of data scarcity in rare disease research,” said Dr. Ittai Dayan MD Dayan, co-founder & CEO of Rhino Health. “By scaling data between different academic and non-academic centers, we can unlock the potential of this data to develop new diagnostics”. Learn more about the important work be supported by the The Myrovlytis Trust. #Raredisease #clinicalAI #researchaward #BHD #federatedlearning

A timely and relevant discussion on AI in healthcare! The possibilities are colossal and so are the responsibilities to ensure we get this right as we look to AI in tranformaing the delivery and practice of 21st century healthcare #ai #healthcare #mshmi

Awesome initiative Gianrico Farrugia, M.D. , Roy Jakobs and Bakul Patel ! As a globalist, I’m always encouraged when trailblazing US initiatives think broader than US only… thanks for the below. I’m sure ex-US key thinkers around how to consciously use AI in health care would love to become affiliated! “ Is this for the U.S. only? The work will draw primarily from the U.S. experience but will be informed by international efforts to ensure the inclusion of best practices, and to support global AI guideline harmonization efforts for health, medical care, and health research. The stakeholder groups involved in the AICC project and developing the Code include patients and families; providers; privacy, security and ethics experts; equity experts; health systems; tech companies, government agencies; biomedical scientists and researchers; health plans; pharma and health care product manufacturers; professional societies; medical societies; and health care AI collaborations. In addition, the NAM will work with these stakeholder groups to embed the Code into their own sets of guidelines and principles and develop their specific implementation guides. The project will be guided by a Steering Committee of national thought leaders representing all key stakeholders.” #StayCuriousStayHungry

Congratulations Dr. Gianrico Farrugia, M.D., Dr. Roy Jakobs, and Dr. Bakul Patel for leading the National Academy of Medicine discussion on #HealthcareAI! I echo my continued support of this approach and methodology to developing the framework for better outcomes. About NAM - The rapid development of artificial intelligence technology presents both exciting opportunities and ethical challenges for the healthcare sector. Recognizing this complex landscape, the prestigious National Academy of Medicine has undertaken a groundbreaking new initiative - the Artificial Intelligence Code of Conduct project. Led by the NAM's Leadership Consortium, this effort aims to establish guiding principles and best practices for the responsible and ethical use of AI in health-related fields. By bringing together experts from medicine, computer science, law, and ethics, the NAM seeks to create a rigorous framework that ensures AI algorithms perform safely, accurately, and fairly for all patients. The Code of Conduct will reflect core values such as transparency, accountability, and equity. It will provide standards to test AI systems before deployment, monitor for harms, and continuously improve algorithms. This pioneering code will enable AI innovation while building public trust through an emphasis on ethical design. With this project, the NAM asserts its leadership in shaping a future where AI enhances healthcare access and quality. Guided by the Code of Conduct, we can harness AI's potential while upholding our moral commitment to "first, do no harm." The NAM invites stakeholders nationwide to join in this urgent work to develop AI that serves humanity's well-being. For more information about NAM, visit: https://lnkd.in/gq_Dq3zi Cc: Dr. Gisele Waters, Ph.D., Dr. Ashokakumar Patel, Dr. Takeshi Utsumi, Dr. Maria Luciana A., Dr. Prashant Nayak, Dr. Wigdan Farah, Dr. Ken Potts, Dr. Renaldo C. Blocker, Ph.D. #AICC #AIethics #healthcareAI #responsibleAI #NAMedicine #AIcodeofconduct #ethicalAI #transparentAI #trustworthyAI #AIforgood #AIfairness #patientprivacy #AIaccountability #AItransparency #equitableAI #AIstandards #AIprinciples #AIinnovation #AIoversight #AIsafety #medtech #digitalhealth #futureofhealth #AI4health

We all need people in our lives who aren’t afraid to be honest, even when it means putting us — and themselves — in an uncomfortable position. Without them, how would we recognize our faults and grow? Healthcare organizations are no different, especially ones pursuing AI. They need someone to warn against the devastating outcomes of an unchecked arms race to build new solutions. They need to listen to Dr. Leo Anthony Celi. Dr. Celi’s resume reads like a survey of the world’s top institutions. He earned his medical degree at the University of the Philippines, completed fellowships at Harvard Medical School and Stanford University, and then earned master’s degrees in public health from Harvard University and biomedical informatics from Massachusetts Institute of Technology. Today, he is the Clinical Research Director and Principal Research Scientist at the Laboratory for Computational Physiology at MIT and a practicing intensivist at the Beth Israel Deaconess Medical Center in Boston. Dr. Celi champions open data and software as a building block for more inclusive healthcare. But that doesn’t stop him from calling out biases in AI that endanger underserved communities. At SameSky Health, we took those lessons to heart as we developed AI through a health equity lens. We trained our solution on a dataset of health-related conversations with diverse communities collected over a decade. And our dedicated team continuously monitors the solution for potential biases. We couldn’t have done it without leaders like Dr. Celi. He helps the healthcare industry understand that it can’t sacrifice equity for the sake of speed — the health of too many people is at stake. I look forward to speaking with Dr. Celi during our upcoming Under the Same Sky discussion. You can find more information about the event: https://lnkd.in/gU-2csQ4 #HealthEquity #ArtificialIntelligence #AI #Data

Excited to see the birth of AI Governance! There is EU AI Act (a more prescriptive product-safety style law), while the UK looks to adopt a flexible and 'proportionate' approach to AI regulation. Let's #aiforgood

This year’s Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence (AAAI-24) accepted two publications (https://lnkd.in/gFXvFpAx) from our team: - Towards Remote Differential Diagnosis of Mental and Neurological Disorders Using Automatically Extracted Speech and Facial Features presents an analysis of the utility, as measured by sensitivities and specificities, of multimodal features for the assessment of different health conditions.  - On The Feasibility of Multimodal Dialog Based Remote Balance Assessment analytically validates a novel, dialog-driven methodology for remote balance assessment, important for movement disorders like Parkinson’s disease. This demonstrates that Modality can measure yet another important modality of health information, i.e., body pose and movement.  Modality’s Chief Science Officer, Vikram Ramanarayanan was also invited to be a part of an expert panel on Future Directions in ML/AI for Health at the Machine Learning for Cognitive and Mental Health Workshop. https://lnkd.in/duUqYA8t AAAI-24 promotes AI research and fosters scientific exchange between researchers, practitioners, scientists, students, and engineers across AI and affiliated disciplines. #aaai2024

🎉 Exciting News to Share! 🎉 I'm thrilled to announce that my latest paper, "RespiroDynamics: A Multifaceted Dataset for Enhanced Lung Health Assessment Using Deep Learning," has been accepted for publication in the prestigious IEEE Access Q1 journal! This work represents a significant step forward in leveraging advanced deep learning techniques for the betterment of lung health diagnostics. By introducing the RespiroDynamics dataset, we aim to bridge critical gaps in current methodologies and offer a comprehensive tool for researchers and medical professionals to enhance lung disease detection and analysis. A culmination of relentless effort, collaboration, and innovation, this paper embodies our commitment to pushing the boundaries of medical technology. It wouldn't have been possible without the support of my incredible team, mentors, and peers who have contributed their expertise and insights throughout this journey. Muhammad Sharshar Hosam ElHady Ahmed Hesham Youssef Nafea Yasser Ashraf Mohammad Yaqub and Prof.Mohsen Guizani I hope our findings will inspire further research and development in this vital area of healthcare, opening new avenues for early diagnosis and treatment strategies for lung-related ailments. For anyone interested in diving deeper into our research, I'm more than happy to connect, discuss our work, and explore potential collaborations. Here's to advancing healthcare through technology! 🚀 #DeepLearning #LungHealth #MedicalResearch #IEEEAccess #InnovationInHealthcare https://lnkd.in/dd7wHayE