Applications of Machine Learning in Biomedicine

🚀 AI Video Analysis in Healthcare: A Glimpse Into the Future The latest study from my colleague Anaïs Rameau and her team explores how Google Gemini—one of the only commercial AI models capable of video analysis—can interpret laryngoscopy videos. This work highlights the growing role of multimodal large language models (LLMs) in processing real-world medical video data. 💡 Key insight: Unlike traditional AI trained on static medical images, multimodal LLMs like Gemini can analyze real-time video without task-specific training, demonstrating strong procedure recognition but variable accuracy across diagnostic tasks. Notably, it could also generate procedural narrations, correctly describing key surgical steps while leaving room for refinement. Beyond video interpretation, the true power of multimodal LLMs lies in their ability to integrate multiple types of data—combining video, text, and even structured patient records to provide richer insights than single-modality AI models. 📌 What’s next for AI video analysis in healthcare? There are many potential applications: 🔷 ICU patient monitoring – Detecting respiratory distress, seizures, or patient deterioration. 🔷 Surgical AI – Identifying key steps in procedures and generating post-op summaries. 🔷 Neurology & movement disorders – Tracking Parkinson’s progression or tremor severity. 🔷 Rehabilitation & physical therapy – AI-powered motion tracking to personalize recovery plans. 🔷 Endoscopy & colonoscopy AI – While specialized AI solutions already exist for polyp detection, multimodal LLMs could take this further by combining real-time analysis with text-based insights, such as clinical notes or prior reports. As AI models continue improving, video analysis could become an important tool in clinical decision support and procedural automation. This study provides a compelling example of how AI can engage with dynamic medical data, with applications well beyond laryngoscopy. 🔗 Read the full study here (paywalled, DM for PDF): https://lnkd.in/emYp-8fJ

Google unveils AI-powered healthcare innovations spanning drug discovery, enhanced search, and integrated medical records: 💊In drug discovery, new open AI models (TxGemma) are designed to understand both text and molecular structures to help predict the safety and efficacy of potential therapies 💊An AI co-scientist tool built on Gemini 2.0 assists biomedical researchers by parsing scientific literature, generating novel hypotheses, and proposing experimental approaches 💊These tools will be available through the Health AI Developer Foundations program, aiming to streamline the early stages of drug development 🔎 In search, expanded health knowledge panels now cover thousands more topics and use AI to provide quick, credible answers to health-related queries 🔎 The "What People Suggest" feature aggregates user discussions from online platforms to offer personalized insights based on shared experiences with specific health conditions 🔎 These enhancements support multiple languages, including Spanish, Portuguese, and Japanese, and are initially rolling out on mobile devices in the U.S. 💿The global launch of Medical Records APIs for the Health Connect platform on Android enables apps to read and write standardized medical data, such as allergies, medications, immunizations, and lab results 💿The APIs support over 50 data types, integrating everyday health tracking with official medical records from healthcare providers 👇Links to source articles in comments #DigitalHealth #AI #Google

At Biogen, cutting-edge technologies like AI and Generative AI are transforming how the firm develops therapies for complex neurological diseases like Alzheimer’s, Parkinson’s, and ALS. 🌟 From accelerating drug discovery to optimizing clinical trials and advancing personalized medicine, AI is making a profound impact. 💡 Here’s what they are doing: ✅ Drug Discovery: Using AI to analyze massive datasets and design new molecules faster than ever. ✅ Clinical Trials: AI-powered patient recruitment and real-time monitoring through wearables are improving trial efficiency. ✅ Personalized Medicine: Tailoring therapies to individual patients with machine learning insights. ✅ Supply Chain Excellence: Predictive analytics to forecast demand, optimize inventory, and enhance efficiency. 🌐 Why it matters: AI has the power to bring therapies to market faster, improve patient outcomes, and drive operational efficiency across the biopharma industry. It’s not just about innovation—it’s about transforming lives. 💙 📈 The future of healthcare is being shaped by AI, and Biogen is leading the way. But we’re also mindful of the challenges—data privacy, model transparency, and evolving regulations are critical areas we’re navigating to ensure ethical and impactful AI use. 🛡️ 💬 What are your thoughts on AI’s role in biopharma? Let’s discuss how these technologies can unlock new possibilities in healthcare! #AI #GenerativeAI #Biopharma #Innovation #HealthcareTechnology #Neurology #FutureOfMedicine #Biogen 🌟🧬

Generative AI in Drug Discovery 🌟 Just like how ChatGPT crafts texts and DALL-E 2 creates lifelike images from prompts, generative AI is now transforming drug discovery. Imagine AI generating new drugs for diseases like cancer, Alzheimer's, and fibrosis! Some notable examples: → AI-driven platforms like Insilico Medicine's PharmaAI are designing drugs for complex conditions. For instance, a USP1 inhibitor for solid tumors is in clinical trials, and a QPCTL inhibitor for malignant tumors is being developed with Fosun Pharma. Their lead drug for idiopathic pulmonary fibrosis has reached phase II trials! → Recursion is using AI to develop treatments for rare diseases like cerebral cavernous malformation and neurofibromatosis type 2, both in phase II trials. → Healx is repurposing existing drugs for rare diseases, targeting conditions like Fragile X syndrome and cancers like plexiform neurofibroma. Over the years, AI's role in drug discovery has grown exponentially. Traditional methods take 10-15 years and billions of dollars to bring a drug to market. Generative AI accelerates this process, identifying targets, designing drugs, and even predicting clinical trial outcomes with tools like inClinico, boasting a 79% accuracy rate! The synergy between vast datasets, expert knowledge, and AI capabilities is reshaping the future of medicine. Companies like GSK, Novartis, and Roche are building in-house AI capabilities, while collaborations between biotechs and pharma giants are on the rise. From 4 partnerships in 2015 to 27 in 2020, the trend is clear! In the image, we see how Machine Learning algorithms are utilized in the biomedical field, closely related to drug discovery, to innovate new treatments and therapies. As we witness this pivotal moment, the potential for AI-designed drugs to reach the market is within sight. The journey of integrating AI in drug discovery is just beginning, promising a future where medicine is more precise, efficient, and innovative. #productivity #machinelearning #technology #artificialintelligence #drugdiscovery #healthcare #biotech #pharma

Earlier this year, I witnessed how AI and machine learning can enhance patient care in cardiology in practical, impactful ways.   A speaker at the AI Cures conference at MIT shared how ML can be applied to data from minimally invasive home monitoring devices like ECGs.   A patient’s hemodynamic measures are incredibly useful in monitoring a patient, however given the equipment involved, can only be done in the hospital. With this new algorithm that was presented, the model can actually infer a patient's hemodynamic measurements, like pressures, fairly accurately from the ECG waveform data alone. I found that rather amazing. And useful!   This means patients could be monitored closely at home, with the ML model providing cardiologists with clinical indicators like pressure risks they wouldn't otherwise have without bringing the patient in.   Examples like this, where ML provides incremental advantages and empowers clinicians, excite me most about AI in healthcare.   The technology is maturing to the point where we can apply it to increase access to care, fill in gaps, and connect disparate data sources - rather than pursue AI applications for their own sake.   What other opportunities exist where AI/ML could provide an extra layer of insight to improve clinicians' abilities? I'd love to hear your ideas! #AI #artificialintelligence #codetocare

5 Ways Google Brain and DeepMind Reshaping Healthcare using AI Google DeepMind and Google Brain are not just using AI in healthcare; they're fundamentally changing how we approach medicine. Here are 5 unique examples of their groundbreaking work: 1. AlphaFold: Predicting Protein Interactions for Novel Therapies: Beyond just predicting protein structures, AlphaFold is being used to map protein-protein interactions. This is crucial for understanding how diseases develop and identifying potential drug targets. Imagine designing drugs that precisely disrupt harmful protein interactions, leading to more effective and targeted therapies. 2. Isomorphic Labs: Designing AI-Powered "Digital Twins" for Personalized Medicine. Isomorphic Labs is developing AI models that can create personalized "digital twins" of patients. These virtual representations incorporate an individual's genetic makeup, medical history, and lifestyle factors. This allows for highly personalized treatment plans, predicting how a patient will respond to different drugs and interventions. 3. AlphaQubit & Willow Chip: Accelerating Drug Discovery with Quantum Simulations: Quantum computers, powered by AlphaQubit error correction and the Willow chip, can simulate molecular interactions with unprecedented accuracy. This opens up possibilities for designing entirely new drugs and materials, tackling diseases that have been resistant to traditional approaches. 4. MedLM: Summarizing Complex Medical Literature for Faster Diagnosis: MedLM can analyze vast amounts of medical literature, identifying relevant research and summarizing key findings. This empowers doctors to make faster and more informed diagnoses, especially for rare or complex conditions where staying up-to-date on the latest research is crucial. 5. AMIE: Empowering Patients with AI-Driven Health Insights: AMIE, an AI-powered health assistant, can analyze personal health data, identify potential risks, and provide personalized recommendations. Imagine receiving proactive alerts about potential health issues, personalized exercise and nutrition plans, and even early detection of diseases based on your unique health profile. Google DeepMind and Google Brain are not just developing AI; they're building a future where healthcare is more precise, personalized, and accessible to all. #Healthcare #AI #DeepMind #GoogleBrain #AlphaFold #DrugDiscovery #QuantumComputing #MedLM #PersonalizedMedicine #FutureofHealth