Farzana Rahman’s Post

Great point from Judith Reece. She has brilliantly highlighted a crucial perspective on #GenerativeAI: its potential for positive change despite current shortcomings. A common mistake is to evaluate new technologies based on their present capabilities rather than considering their evolutionary trajectory.  Generative AI brings one more change - redefining the meaning of the ‘short term’, 'near term' and 'long term'. #GenAI

A pediatric ophthalmologist encounters a baby girl with a pronounced crossed eye, prompting questions about potential underlying neurologic causes. Assessing the risk of a brain problem is crucial before deciding between surgery or an MRI. Read more about this medical scenario and the complexities of infantile esotropia in the healthcare system: [Link to Article] Artificial Intelligence (AI) is revolutionizing decision-making processes in healthcare. At MultiCare in Washington State, we are harnessing the power of Large Language Models (LLMs) to enhance performance. By leveraging this cutting-edge technology, we aim to optimize patient care and outcomes. Learn more about the impact of AI in healthcare informatics: [Link to Article]

Thrilled to announce a major leap forward at Retnovi AI! 🚀 We've just upgraded from GPT-3.5 Turbo to the cutting-edge GPT-4o, enhancing our AI capabilities in ophthalmology like never before. In our latest blog post, we delve into how this upgrade will revolutionize our approach in diagnosing eye diseases, personalized treatment plans, patient care, etc. The advanced capabilities of GPT-4o promise to elevate accuracy, efficiency, and patient outcomes, marking a significant milestone in our journey. 👁️🗨️ Curious about the technology driving our innovations? Dive into the details and discover how we're leveraging the latest in AI to redefine standards in ophthalmology: https://lnkd.in/dBf8dmMw Join us in celebrating this achievement and stay tuned for more updates as we continue to push boundaries in AI-driven healthcare! 🌐 #AIinOphthalmology #HealthTechInnovation #GPT4o #StartupJourney #ArtificialIntelligence #Ophthalmology #HealthcareAI

GE HealthCare and Mass General Brigham Evolve its AI Collaboration with Medical Imaging Foundation Models Orlando, Fla. — March 12, 2024 — Based on its long-term artificial intelligence (AI) partnership, GE HealthCare and Mass General Brigham plan to integrate medical imaging foundation models into their AI research work, with a strong focus on responsible AI practices. Both organizations have been working closely on AI solutions since announcing their 10-year commitment in 2017 to explore the use of AI across a broad range of diagnostic and treatment paradigms through sustainable AI development. “The relationship between Mass General Brigham’s commercial AI business (Mass General Brigham AI) and GE HealthCare has helped accelerate the introduction of AI into a range of product offerings and digital health solutions. With foundation models, we are witnessing the next wave of AI innovation, and it is already reshaping how we build, integrate and use AI,” said Dr. Keith Dreyer, Chief Data Science Officer, Mass General Brigham. “I think we are all optimistic that foundation models may actually complement and enhance the work we have been doing with convolutional neural networks over the past few years. Hopefully, this work will help make healthcare delivery more efficient for our practitioners, more accessible for our patients and more equitable for our diverse communities.” The traditional approach to integrating AI into healthcare systems requires the retraining of models to accommodate the unique requirements of different patient populations and hospital settings. This can lead to increased costs and complexity, and in addition, hinder the broad adoption of AI technologies in the healthcare industry. Foundation models have the potential to transform healthcare by improving workflow efficiency and imaging diagnosis, since they have demonstrated strong capabilities in solving a diverse set of tasks. Foundation models have emerged as a reliable and adaptable foundation for developing AI applications tailored to the healthcare sector. “GE HealthCare and Mass General Brigham have a long-standing AI collaboration that has produced AI-powered tools which help increase operational effectiveness and productivity. Now, with adding foundation models to our research work, we will be able to take the next step of digital and AI transformation to develop technology innovations that provide better patient care and outcomes,” said Parminder Bhatia, Chief AI Officer, GE HealthCare. "Incorporating responsible AI practices into this phase, we are committed to ensuring these innovations adhere to guidelines, prioritize patient safety and privacy, and promote fairness and transparency across all applications."

The AI Revolution in Healthcare: From Science Fiction to Reality AI healthcare is steadily climbing to outer space levels of extraordinary. Pre-AI, diagnoses often relied solely on a doctor's expertise and sometimes fallible human judgment. Treatments were largely one-size-fits-all, and predicting health issues before they occurred seemed sci-fi impossible. Today? AI is transforming healthcare beyond our wildest dreams. Here's how this revolution unfolded: 1. Early Detection Superpowers 🦸♀️   Remember when early detection meant frequent, often invasive screenings? Now, AI tools like IBM Watson Health and PathAI are changing the game. These systems can analyze vast amounts of medical data, identifying patterns that human eyes might miss.   ▶ IBM Watson Health: Born from the famous Jeopardy!-winning AI, it's now assisting in medical diagnosis and treatment recommendations.   ▶ PathAI: Founded in 2016, it's improving pathology diagnostics, potentially catching diseases before they become life-threatening. 2. Personalized Treatment Genies 🧞♂️   Gone are the days of one-pill-fits-all. Enter the era of personalized medicine, powered by AI.   ▶ Tempus: Founded in 2015, it's analyzing genetic data to tailor cancer treatments to individual patients.   ▶ Deep Genomics: Since 2015, they've been using AI to develop personalized genetic therapies, potentially revolutionizing treatment for rare diseases. 3. Efficiency Optimization Ninjas 🥷   Remember the long wait times and inefficient hospital operations? AI is tackling these too.   ▶ Qventus: Founded in 2012, it's using AI to streamline hospital operations, reducing wait times and improving patient flow.   ▶ LeanTaaS: Since 2010, they've been enhancing healthcare efficiency, optimizing everything from operating room schedules to infusion center management. 4. 24/7 Health Companions 🤖   Imagine having a doctor available anytime, anywhere. That's now a reality.   ▶ Buoy Health: Launched in 2014, it's your AI-powered health assistant, available 24/7 to discuss symptoms and provide guidance.   ▶ Babylon Health: Since 2013, it's been offering AI-powered health consultations, making healthcare more accessible globally. 5. Robotic Surgeons with Superhuman Precision 🦾   Science fiction? Not anymore.   ▶ Da Vinci Surgical System: Introduced in 2000, it's now performing surgeries with incredible accuracy, minimizing invasiveness and improving recovery times. This AI revolution in healthcare is the perfect encapsulation of what it takes to achieve remarkable milestones in technology. Shows how relentless innovation and a thirst for progress can transform an entire industry. What do you think the future holds for AI in healthcare? What's your boldest prediction for the future of AI in medicine? Here's one: AI will be our primary healthcare provider by 2030! Agree or Disagree? Love to read your thoughts in the comments ❤️❤️ #AIRevolution #FutureOfHealthcare #HealthTech #InnovationInMedicine

While most in the healthcare industry understand AI's potential—or perhaps some of its history—to improve diagnostics, I suspect many will be surprised to learn just how far and wide AI is already wildly innovating in this space 💡 • The UK gov't says that analysis of brain scans by e-Stroke, developed by Brainomix, has reduced the time b/w hospital admits and Tx for stroke patients by >60 min • Capio Saint Göran Hospital in 🇸🇪 uses an AI system from Lunit Global as the 'second pair of eyes' in its radiography department • In 🇩🇰 Transpara, a product provided by ScreenPoint Medical, is used as a first reader of mammograms in low-risk cases • FUJIFILM Corporation has built a 3.5kg, battery-powered x-ray machine which, paired with AI algorithms from Qure.ai is being used to screen for tuberculosis in rural 🇳🇬. It can also assess a host of other diseases incl pneumonia, COPD and heart failure • Butterfly Network, Inc. produces a hand-held ultrasound which, thanks to built-in AI, can be used to assess high-risk pregnancies and to estimate due dates, fetal weights and the amount of amniotic fluid—measurements otherwise not possible outside a clinic • Similar AI-enhanced systems from Philips and GE HealthCare in the market have contributions to make in cardiology, ED medicine and orthopaedics. 100s of Butterfly’s systems are being used in 🇺🇦 to help first responders assess the wounds of war • PCPs in 🏴󠁧󠁢󠁥󠁮󠁧󠁿 are evaluating an AI-enabled stethoscope to see if it can improve the diagnosis of some sorts of heart disease. Trials in Oxford are comparing measurements of lung function made using an AI-driven spirometer with previous techniques for picking up COPD • Hyperfine, Inc., is the maker of an innovative portable MRI called Swoop. Its AI capabilities allow it to assess what is going on using data gathered with the use of comparatively weak magnetic fields. Because low fields are easier to generate, Swoop can be taken to the patient’s bedside, rather than having to sit in a room of its own like high-field MRI machines • Ezra is using AI to drive down the cost of full-body MRI as a cancer-screening tool. Using high-field magnets and proprietary AI it has made scans quicker and thus cheaper; it offers a 30-minute scan for $1,350 and is aiming to bring the cost down to $500 • Microsoft is collaborating with Paige, a firm that develops AI for pathologists, to build an image-based AI tool for diagnosing cancer that will be fed billions of images • Cognoa, trained on footage from hundreds of thousands of kids, has built an AI-powered tool to assess children for autism • In September [researchers] from UCL published a foundation model for retinal images produced with Google DeepMind. retFound can match the performance of experts when making decisions to refer patients for a # of eye diseases. By picking up tiny changes in the eye’s blood vessels it also appears to predict health conditions such as Parkinson’s disease and stroke

🔍 Are we ready for personalized AI in healthcare? Resurfacing a study from earlier this year that revealed that AI affects radiologists in varied ways, highlighting the need for tailored AI solutions. Key takeaways: - Over 140 radiologists evaluated chest X-rays with and without AI, showing significant performance differences. - Contrary to expectations, experience and AI familiarity didn't consistently enhance performance. - AI errors significantly impacted diagnostic accuracy, stressing the need for precision. LVLMs or foundation models significantly will address these issues by providing capability to incorporate AI in the existing workflows and existing tools that radiologists are already using. We will be showcasing @hoppr's API based solution at the RSNA AIAP showcase exhibit at the Radiological Society of North America (RSNA) annual meeting in December — Come have a look and give us feedback? 🔍 Recommended read. Link to the paper 👉 https://lnkd.in/gK2e-5Tx #OpenAccess #HumanAISymbiosis #AIassistance #HealthcareAI #RadiologyAI #ImagingAI #AI

It's remarkable to reflect on the journey of this paper, which began its inception four years ago. Throughout its development, our research underwent several transformative phases of ideation. Initially, our focus was on exploring ways to streamline the deployment of AI models for radiologists, aiming to reduce friction in the process. As our research evolved, we considered conducting a comprehensive survey to identify the key bottlenecks in deploying AI models within hospital settings. We were particularly interested in examining the economic aspects of these deployments in healthcare institutions. After thorough deliberation and multiple iterations, we ultimately decided to concentrate on the deployment of AI models using open-source tools. This final direction proved to be both innovative and practical. I'd like to express my sincere gratitude to all the co-authors who contributed their expertise and insights at various stages of this paper's development. Your collective efforts have been instrumental in shaping this research into its current form. For context, this is the initial survey we conducted. https://lnkd.in/eYM8bnvv Thanks to Richard D. White, MD, MS (FACR,FACC) for pushing me to complete the paper when I was giving up hope on this. Also special thanks to the unsung hero of this paper Garima Saraowgi for putting up with me while writing this paper. I hope the medical imaging community will find this paper useful. #MONAI #MONAIDeploy #Radiology #OpenSource #Healthcare #AI

AI does Not Necessarily Lead to more Efficiency in Clinical Practice Although AI is often seen as a solution for handling routine tasks such as monitoring patients, documenting care tasks and supporting clinical decisions, the actual effects on work processes are unclear. Particularly in data-intensive specialties such as genomics, pathology and radiology, where AI is already being used to recognise patterns in large amounts of data and prioritise cases, there is a lack of reliable data on efficiency gains. The results of this analysis makes clear that the use of AI in everyday clinical practice that local conditions and individual work processes have a major influence on the success of AI implementation. #AI #healthcare #workflows #efficiency #improvement https://lnkd.in/eB6SDgnZ

Efficient care starts with smart predictions. Machine Learning drives smarter #healthcare by analyzing #patientdata to optimize surgery schedules, admissions and emergency triaging, and to improve care delivery and reduce delays. Via https://lnkd.in/ecw3Pkmv #machinelearning #artificialintelligence #ai #healthcareinnovation