Healthcare

This is my face finishing the last pieces of my documentation after my #ER shift. It's a face of frustration after spending way too much time documenting in a less-than-intuitive, inefficient EMR. It's the face of frustration from endless clicks, digital pop-up blockades, and seek-and-find missions for clicking the correct checkbox in an electronic health record to simply discharge a patient. The ultimate price of this inefficiency: compromised patient care, delays, errors, skyrocketing stress for healthcare professionals, and an overall decline in the system's effectiveness. It's time to streamline our processes for the sake of our clinicians and, most importantly, our patients. The problem: EMRs were made as billing platforms with patient care and clinical workflows as secondary considerations. The solution: 1. Put frontline clinicians back in the boardroom to fix these inefficiencies. 2. Reduce and eliminate unnecessary administrative tasks. 3. Utilize trainers to perform frequent check-ins with clinicians to ensure clinicians use the best and most efficient documentation methods. 4. Leverage new technologies (like AI, dictation software, ambient listening software) to reduce screen and keyboard time for clinicians. 5. Create standardized workflows for documentation. The more ways to do the same thing, the more challenging it is to teach and build efficiencies across a team. 6. EMR companies should use practicing, specialty-specific clinicians to guide design decisions. #HealthcareSystem #ClinicianBurnout #TimeForChange Cerner Corporation Epic MEDITECH #EMR ABIG Health #frontlineclinicians #nurses #physicians #hospitals

Motivation is the least reliable driver of behaviour change. It fluctuates. A good morning, a bad week, a stressful month, motivation moves with all of it. And most people experience this. They wanted something, started, fell off, and concluded they didn't want it enough. Wendy Wood, a psychologist at USC, studied this for 30 years. She found that the people who changed most durably were the ones who changed their environment until the behaviour became automatic. It had nothing to do with how motivated they were. The gym on the commute home. The kitchen with healthy food in it. Small contextual shifts that made the right behaviour easier to do than avoid. 43% of what people do every day isn't a decision. It's a context firing. Same place, same time, same cues, the brain automatically starts executing. Once a behaviour crosses that threshold, motivation becomes largely irrelevant. The context carries it. The people who relied on motivation alone kept cycling. High intention, inconsistent follow-through, same conclusion every time. The ones who lasted stopped trying to sustain motivation and started building situations where they won't need to rely on it. Motivation will get you started, but your environment will decide what stays. #rajshamani #figuringout

With top medical degrees in hand, they could have gone anywhere. But they went where 1 in 3 children never reached their fifth birthday. This is the story of Dr. John Oommen and Mercy John, and how 30 years of determination transformed a community. The year was 1987, and Dr. John Oommen, fresh out of Christian Medical College (CMC), Vellore, reached Bissam Cuttack, a remote block surrounded by over 300 tribal villages. Six years later, his wife Mercy, who had a postgraduate in nursing, declined a job offer in America to join him. What they saw when they walked in was heartbreaking. → There was one 80 bed hospital with 5 doctors serving 300 villages → Infant mortality was 200 per thousand → Under-five mortality was 350 per thousand → Parents had four children, hoping at least two would survive → Malaria infected 59% of children Mercy took charge of the nursing school, which had almost no faculty. She taught six hours a day, did all the admin work, and built a college that eventually produced some of the best nurses in the region. Meanwhile Dr. John took charge of the hospital. Inspired by a mentor’s words, he built the hospital on a radical belief: A patient will not pay before seeing a doctor, because if the poor couldn’t see the doctor, the hospital was meaningless. But the real transformation began in the villages. John kept a notebook in every village to track births and deaths, and trained tribal women as health workers, which earned him the villagers’ trust. Then came a night that made him rethink his approach. A health worker he had trained died in childbirth while waiting for “Doctor Johnny” to arrive. Her last words to her family: “He will come.” He came, but it was too late. That night, sitting beside her body, he had a painful realization: If everything depended on him, he was part of the problem. So he changed the way he worked. He stepped back, trained others, and built systems where the community trusted the role, not the individual. Mercy turned the nursing college into a pipeline of local talent who understood the culture and stayed. Their work became a community movement. + John pioneered a people's movement against malaria. + Child deaths dropped sharply. + Mercy's nurses became the backbone of care. + A tribal elder challenged John to build a school "like the one you studied in," and 16 villages mobilized to make it happen. + Female literacy climbed from 1% to nearly 50%. By 2017, their malaria work was adopted by the Government of Odisha. Within months, malaria cases dropped by 80%. When they retired in 2024, the Bissam Cuttack railway station was packed with people who came to say thank you. They believe that they didn’t sacrifice anything, they received far more in love, learning, and meaning than they ever gave. - I recently had the privilege of having Dr. John and Mercy on The Health Worker Podcast by Azim Premji Foundation. The podcast link is in the comments. #DrJohnOommen #MercyJohn #BoundlessWithRamG

𝗥𝗲𝗺𝗲𝗺𝗯𝗲𝗿 𝘀𝗽𝗲𝗻𝗱𝗶𝗻𝗴 𝘄𝗲𝗲𝗸𝘀 𝗳𝗶𝗴𝘂𝗿𝗶𝗻𝗴 𝗼𝘂𝘁 𝗵𝗼𝘄 𝘁𝗼 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 𝘆𝗼𝘂𝗿 𝗳𝗶𝗿𝘀𝘁 𝗠𝗮𝗿𝗸𝗼𝘃 𝗺𝗼𝗱𝗲𝗹? That struggle doesn't have to exist anymore! I reached out to Raymond Henderson, who along with Chris Sampson, Xavier Pouwels, Stephanie Harvard, Ron Handels, Talitha Feenstra, Dr. Ramesh Bhandari, Aryana Sepassi, PharmD, MAS, and Renée Arnold, published an excellent systematic review identifying 182 open-source health economic models. With Raymond's support, I've turned their research into a searchable database with 200+ models you can download and learn from. It's great to come across researchers who share the same goal: make health economic modelling more transparent and accessible. I remember how hard it was to learn this stuff, and neither of us want others to face the same barriers. Filter by 🔍 🔹 Disease area (oncology, infectious disease, cardiovascular, etc.) 🔹 Model type (Markov, partitioned survival, decision trees, DES) 🔹 Software (Excel, R, Python, and more) Download a model, open it up, and see exactly how it's structured. The database is free on my Discord community server, "𝗧𝗵𝗲 𝗣𝗵𝗮𝗿𝗺𝗮 𝗣𝗲𝗿𝘀𝗽𝗲𝗰𝘁𝗶𝘃𝗲". I've also created a video walking through the entire collection. What modelling resource do you wish had existed when you were starting out? #OpenSource #HEOR #HealthEconomics #CostEffectiveness #HealthTechnologyAssessment #EconomicModeling #ISPOR ♻️ If you found this useful, consider sharing it so others in your network can benefit too. 👉 Follow Mirko von Hein for more posts and videos about health economics, market access, cost-effectiveness modelling, global health and consulting in the pharmaceutical industry.

🔬 New evidence on how small lifestyle changes could add years to your life A new UK Biobank study followed 59,000 adults to find the minimum combined improvements in sleep, physical activity, and diet needed for meaningful gains in lifespan and healthspan. Key findings: → +1 year of life: Just 5 extra minutes of sleep, 2 minutes more physical activity, and half a serving of vegetables daily → +4 years disease-free: 24 minutes more sleep, 4 minutes more activity, plus modest diet improvements (one cup of vegetables, one serving of whole grains, two servings of fish weekly) → Optimal behaviors (7-8 hours sleep, 42+ min daily activity, quality diet) were linked to ~9.4 additional years of both lifespan and healthy years Practical takeaway: Small, simultaneous changes across sleep, movement, and nutrition may be more effective and sustainable than dramatic changes in any single area. Caveat: This is observational data showing associations, not causation. Diet was self-reported. Ref: Koemel et al. Minimum combined sleep, physical activity, and nutrition variations associated with lifeSPAN and healthSPAN improvements: a population cohort study. eClinicalMedicine, 2026

After losing my dad to cancer, I became a cancer researcher at MIT – looking for answers. What I learned surprised me: it’s not the science that’s failing us. It’s the system that pays for it. A founder I know built AI that detects cancer on radiology scans earlier than any human can — early enough to cure it. He pitched a major health insurance exec: ✅ “Catch cancer early, when it’s cheaper to treat. Cut costs. Save lives. Everyone wins.” His reply? ❌ “We’ll never pay for it.” Why? 👉 “The average person switches jobs every ~2.5 years. We’d pay for the test and the treatment… But their next insurer would get the benefit.” Let that sink in. We’ve built a system where saving lives is a bad business decision. The root problem? Health insurance is tied to your job. Which means insurers think short-term. They have no reason to invest in your long-term health. But imagine if you owned your insurance — and took it with you job to job, like a 401(k). Suddenly, long-term thinking could win. Cancer rates are rising — especially in young people. We don’t just need better treatments. We need better incentives. It’s time to rewire the system: ✅ Where saving lives is good business ✅ Where insurers think long-term ✅ Where healthcare actually makes people healthy This isn’t theoretical. It’s personal. And it’s why I’m building Thatch.

Two years ago, I watched a brilliant health tech startup burn through $2M in 6 months. Their AI could predict patient readmissions with 94% accuracy. Incredible technology. Their GTM strategy? "Hospitals will obviously want this." Here is what really happened: Month 1️⃣: 23 demos with hospital CMOs who loved the concept Month 2️⃣: Procurement asked for ROI projections they couldn't provide Month 3️⃣: IT wanted integration specs that didn't exist Month 4️⃣: Finance needed justification for an "experimental" AI tool Month5️⃣: Clinical teams pushed back b/c workflows weren't designed with clinician input Month 6️⃣: Cash ran out during a "promising" pilot negotiation The lesson that changed everything for this client (that I ended up terminating) 🙃 : 1. Healthcare doesn't buy technology. It buys solutions to specific financial problems with proven implementation paths. 2. That startup could have survived if they'd started with: "We'll reduce your readmission costs by $400K annually, guaranteed, with 90-day implementation." 3. Instead of selling AI predictions, they needed to sell cost reduction with success metrics. Now when founders ask me about GTM strategy, I ask them this: "What specific dollar amount will you save your customer, and what happens if you don't deliver?" If you can't answer both parts confidently, you're not ready to sell. You ARE ready to refine your GTM strategy so when you do start selling, you win... #HealthTech #GTM #Entrepreneurship #HealthcareAI

How can we make genomic foundation models actually useful to biology?! Teach them to REASON!! 🧬 Excited to share BioReason - the first model to successfully integrate DNA foundation models (eg, Evo 2) with LLMs (eg, Qwen3) for biological reasoning! 🔬 What we built: • Novel multimodal architecture that lets LLMs directly process genomic sequences as input • Trained with supervised fine-tuning + GRPO reinforcement learning for sophisticated multi-step reasoning • Generates interpretable step-by-step biological reasoning traces from genomic data 📊 Benchmarks & Performance: • KEGG pathway reasoning: 97% accuracy on mechanistic variant-to-disease prediction • Variant effect prediction: 80-88% accuracy on pathogenic/benign classification • Evaluated on 1,449 KEGG entries + 86K+ ClinVar variants across coding/non-coding regions • Consistent 15%+ performance gains over DNA-only or LLM-only baselines 🎯 What this truly means: This enables AI systems to provide mechanistic biological insights comparable to domain experts - bridging the gap between "black box" DNA foundation models and interpretable scientific reasoning. Could fundamentally accelerate hypothesis generation and biological discovery by making genomic AI transparent and actionable. 🙏 Thanks to our amazing team: Adib Fallahpour , Andrew Magnuson, Purav Gupta, Rex Ma, Jack Naimer, Arnav Shah, Haonan Duan, Omar Ibrahim, Hani Goodarzi , Chris Maddison Across institutions: University of Toronto Vector Institute University Health Network Arc Institute Cohere Google DeepMind 🗒️ Paper: https://lnkd.in/gCdWT5mb 🌐 Website: https://lnkd.in/gzh4cFYV 💻 Code: https://lnkd.in/gfQfNytK 🤗 Datasets: https://lnkd.in/gCnbvHM2 #AI #MachineLearning #Genomics #Biology #Research #BioAI

📢 The World Health Organization's Genomics Programme has officially launched the new principles for ethical human genome data collection, access, use, and sharing! 🌍🧬 These guidelines set a global standard for responsible genomic data practices, developed with input from the WHO Technical Advisory Group on Genomics (TAG-G) and international experts. As genomic technologies continue to advance, it’s crucial to have a robust framework to: 🔍 Ensure Informed Consent and Privacy Protect individual rights by promoting transparency and clear communication about data use. 🤝 Promote Equity and Inclusivity Address disparities in genomic research and ensure fair representation of diverse populations, especially from low- and middle-income countries (LMICs). 🌐 Foster Global Collaboration Encourage partnerships across borders and sectors to maximize the benefits of genomic data sharing, while upholding strict standards for privacy and security. 💡 Support Capacity Building Strengthen local infrastructure and enhance genomic literacy to make genomic data practices more inclusive and sustainable worldwide. These principles aim to guide researchers, policymakers, and healthcare providers in aligning their practices with WHO’s commitment to ethical genomics. The document provides actionable recommendations to address the key ethical, social, and legal challenges in the field. 📥 Ready to dive in? Download the full document here: https://lnkd.in/eNQpxNn2 🗓️ Stay tuned for an upcoming webinar to learn more about these new guidelines and how they can be applied in practice. #Genomics #GlobalHealth #Equity #DataEthics #Collaboration #WHO #Research Sara Niedbalski, Ph.D. Sergio Carmona Ciara Staunton Elena Ambrosino raffaella casolino Zilfalil Alwi Mascalzoni Deborah Tiffany Boughtwood Marc Abramowicz Michele Ramsay Gabriela Repetto Ahmad Abou Tayoun, PhD, FACMG Iscia Lopes-Cendes Yosr Hamdi Kazuto Kato Sherry Taylor PhD, FCCMG, ErCLG Tim Hubbard Rokhaya Ndiaye

"Your mother seems fine when I examine her." This is what the doctor told my patient's daughter after a 15-minute office visit. The daughter knew something was wrong. Mom was getting lost driving to familiar places, struggling with her checkbook, and repeating the same stories. But in the clinic, mom was charming, articulate, and passed the basic cognitive screening. The problem? We're looking for dementia in the wrong places. After diagnosing 1000+ cases, here's the #1 early sign missed in medical visits: Loss of executive function in complex daily activities Not memory loss. Not confusion. Executive function. What this looks like in real life: 1. Financial management becomes impossible ↳ Checkbook balancing that took 10 minutes now takes 2 hours ↳ Bills get paid twice or not at all despite good intentions ↳ Complex financial decisions get avoided or delegated suddenly 2. Driving skills deteriorate in subtle ways ↳ Getting lost in familiar neighborhoods ↳ Difficulty with left turns or parking ↳ Family notices increased anxiety about driving 3. Multi-step tasks become overwhelming ↳ Cooking elaborate meals they've made for decades ↳ Managing multiple medications correctly ↳ Planning and executing social events Why providers miss this: 1. Office cognitive tests don't capture real-world complexity ↳ MoCA and MMSE test basic cognitive functions ↳ Patients can pass these while struggling at home ↳ Executive function requires complex task assessment 2. Patients compensate during medical visits ↳ Motivated to appear competent to providers ↳ Spouses often answer questions for them ↳ Social skills remain intact longer than cognitive abilities 3. Providers focus on obvious red flags ↳ Severe memory loss that hasn't developed yet ↳ Clear confusion that comes in later stages ↳ Behavioral changes that family hasn't reported A better approach: 1. Ask about specific functional changes - "Has bill-paying become more difficult in the past year?" - "Do you feel less confident planning dinner parties?" - "Have you stopped doing activities you used to enjoy?" 2. Include caregivers in the assessment Family members notice functional decline months before cognitive tests detect problems. 3. Use technology that tests executive function Digital cognitive assessments can capture complex decision-making deficits that paper tests miss. When families say "something's not right," they're detecting executive function changes that our medical system isn't designed to measure. The most important question for early detection: "What activities have become more difficult in the past year?" Executive function decline predicts future cognitive decline better than memory complaints. And it's detectable years before traditional dementia symptoms appear. ⁉️ What early changes did you notice that providers initially dismissed? ♻️ Share if you think we need better ways to detect early dementia signs 👉 Follow me (Reza Hosseini Ghomi, MD, MSE) for insights on dementia