Health Services Research Initiatives

Disruption is fast. Adoption isn’t. In health care, truly disruptive tech rarely “goes viral.” Morris, Wooding & Grant (https://lnkd.in/ga6Xb2Pm) reviewed 23 studies that measured translational time lags. Results varied widely by method and stage, but the most repeated figure was ~17 years from research to routine clinical practice. Measuring from product launch, it is not uncommon for widespread commercial adoption to unfold over a decade. The first 2–3 years belong to pioneers running pilots; clinician "friends and family" are the primary adopters. This is the moment the management team realizes that all their launch forecasts are wildly optimistic and it's time to sheepishly inform the VCs that a Series D is in their near future. The cycle can only be broken by reimbursement. Only when payment arrives is sustainable growth possible.  Years 4–7 are mostly linear: training, workflow fit, financial clarity, an established revenue model, progressive product improvements, and early clinical evidence accumulate. These are the "hard slogging" years: one-on-one meetings educating and instructing care teams about an evolving value proposition. The product doesn't "sell itself" - the sales and clinical teams sell the product. This pattern isn’t just anecdotal. Foundational work in health-care diffusion shows that translating discoveries into routine care is slow and social, not purely technical. What you put in is what you get out. Years 8–10 are where the S-curve steepens, as guidelines catch up, KOLs normalize use, and publications coalesce into clinical consensus. The resulting run through the bell curve leads pundits to comment that widespread product uptake was "inevitable" - it wasn't. If you’re building or adopting disruptive tech: pilot early, publish relentlessly, design for workflow (not just efficacy), and make reimbursement & training first-class features. Two high profile examples: • Intuitive Surgical (da Vinci robotic surgery): FDA clearance arrived in 2000 for general laparoscopy. Adoption then compounded over the 2000s and 2010s, with robotic techniques ultimately capturing a dominant share in procedures like radical prostatectomy—illustrating a long, stepwise shift from early pilots to mainstream practice. • Dexcom (continuous glucose monitoring): First FDA-approved system in 2006 (STS). A major inflection came with Medicare coverage in 2017 for “therapeutic” CGM and continued guideline endorsement by the ADA—moving CGM from early adopters to the standard toolkit for insulin-treated patients. When it comes to disruptive product adoption in medicine, I try to remember Atul Gawande's wise words from “Slow Ideas” (The New Yorker): “We yearn for frictionless, technological solutions. But people talking to people is still the way that norms and standards change.”

We don’t build world-class healthcare alone. Collaboration is the real engine of progress. This week proved it again. When Dr. JW (JONG-WOO) CHOI and his team from Asan Medical Center (AMC) visited Doha, something special happened. They didn’t just tour The View Hospital and the Korean Medical Center. They brought with them decades of experience from one of the world’s most respected hospitals. They shared insights that can’t be found in textbooks. They opened up about what works—and what doesn’t—when it comes to patient care, technology, and leadership. Here’s what stood out from their visit: → Shared Learning ↪ Every conversation sparked new ideas. From advanced surgery techniques to patient safety, both teams left with fresh perspectives. → Cultural Exchange ↪ Healthcare is not just science. It’s also about understanding people. The Korean and Qatari teams learned how culture shapes care, trust, and healing. → Innovation in Action ↪ Asan Medical Center’s approach to digital health and connected care is years ahead. Their real-world examples showed us what’s possible when you blend technology with compassion. → Building Bridges ↪ This partnership is more than a handshake. It’s a living bridge—connecting Korea and Qatar, East and West, tradition and innovation. → Raising the Bar ↪ When top minds come together, standards rise. The visit set a new benchmark for what’s possible in international healthcare collaboration. Here’s the truth: No hospital, no matter how advanced, can solve every challenge alone. The best breakthroughs happen when borders disappear and knowledge flows freely. That’s why these visits matter. That’s why we keep building this bridge. Because the future of healthcare belongs to those who work together. And every patient, in every country, deserves nothing less.

Linking health data to location data sounds straightforward. It took years of specialist work to make it possible without compromising either the data or the people behind it. We were brought in to work on one of the most ambitious data integration programmes in the UK public sector. The platform was designed to help researchers and analysts discover, join, and analyse data. Previously, that data existed in separate silos across government departments. The challenge was not a shortage of data. The UK holds extraordinary datasets covering health, labour markets, demographics, and geography. The challenge was that each dataset had been built with different definitions, geographies, and privacy requirements. Linking them without careful architecture risked exposing personal information. It also produced analysis that was fundamentally unreliable. Neither was acceptable. Here's what we delivered. We built privacy-preserving anonymisation workflows for every dataset ingested into the platform. Each workflow included differential risk controls and automated disclosure checks. Not as a compliance layer applied afterwards. As a core architectural component built into the ingestion process from the start. We implemented a reference data hub that unified geospatial codes, health lookups, labour market data, and demographic classifications. Everything was brought into a single governed catalogue. This solved a problem that had prevented meaningful cross dataset analysis for years. Every dataset now carries a common location spine. This allowed health outcomes to be examined alongside labour market data and census boundaries. The analysis could be performed using consistent geographies that did not drift between sources. We built APIs enabling analysts to combine datasets in ways that were previously manual, error prone, and slow. The platform was designed to scale to billions of records as participation from additional departments grows. The outcomes. Researchers can now discover and analyse previously siloed data to accelerate evidence based policy design. Robust anonymisation and governance frameworks reduced the risks associated with data sharing. As a result, departments that previously held back are now participating. Geospatial alignment means every analysis carries consistent national and regional context rather than fragmentary local snapshots. The hardest data problems are rarely about storage or processing power. They are about the invisible barriers between datasets. Different codings, different boundary definitions, different privacy thresholds. Building the infrastructure that lets disparate data speak a common language is painstaking, specialist work. But it is what transforms individual datasets into genuine analytical capability. What siloed data in your organisation could generate transformative insight if it could reliably connect to other sources? #DataIntegration #PrivacyPreserving #PublicSector

Right now, the Learning Health System (LHS) remains more of a concept than a common practice. But a new perspective in npj Health Systems reframes this challenge: to fully unlock AI’s potential in healthcare, we must operationalize the LHS. The article outlines pragmatic strategies to embed LHS frameworks in health systems, covering: 1️⃣ Health Information Technology (HIT) and Biomedical Informatics (BMI) integration for ambidextrous leadership 2️⃣ Data readiness as a non-negotiable for AI readiness 3️⃣ Workforce development gaps in digital fluency and informatics 4️⃣ Financial models that reward pragmatic, translational research 🔑 Key takeaways: 👉 The synergy between biomedical informatics and health IT is foundational for scalable AI adoption. 👉 Quality improvement and translational research must co-evolve, guided by adaptive governance and ethics. 👉 AI isn’t just a technology play—it’s a systems strategy requiring infrastructure. The institutions that align operational, clinical, and research priorities around continuous learning will lead the next healthcare transformation. #HealthcareAI #LearningHealthSystem #DigitalHealth #ClinicalInformatics #BiomedicalInformatics #HealthIT #AIinHealthcare #TranslationalResearch #HealthTechLeadership #ValueBasedCare

No data, no AI. Healthcare AI critically depends on large, high-quality datasets—yet historically, hospitals and medical centers have had limited incentives to share data widely. This has made developing generalizable and equitable health AI particularly challenging. That's why I'm excited about recent releases of large-scale, ethically-sourced datasets designed to break this barrier: 📌 NIH All of Us (Feb 2025): Massive recent expansion—now featuring genomic data from 414,000+ participants and wearable data from nearly 60,000 individuals, representing a milestone in precision medicine research. https://lnkd.in/eaXa8ipB 📌 CRITICAL Dataset (Jan 2025): Clinical records from over 400,000 ICU patients across multiple U.S. centers, now the largest publicly available critical-care dataset ever assembled. https://lnkd.in/enmQUYGm 📌 Stanford Longitudinal EHR (Feb 2025): Extensive clinical dataset capturing  25,991 unique patients, 441,680 visits, and 295 million clinical events over a decade per patient, ideal for modeling disease trajectories. https://lnkd.in/edNaDq5q 📌 Stanford MC-MED (Mar 2025): Detailed multimodal dataset from 118,385 emergency department visits, combining clinical records with continuous waveform monitoring. https://lnkd.in/esDSkHtN 📌 Bridge2AI initiative, including: 🎤 Voice as a Biomarker of Health (Jan 2025): Proud to be involved in creating this pioneering, ethically-sourced dataset linking 12,523 voice recordings to diverse health conditions. https://lnkd.in/e5Rm8cfh 📈 AI-READI Diabetes Dataset (Nov 2024): Rich multimodal data from 1,067 participants, enabling deeper AI-driven insights into diabetes progression and reversal. https://lnkd.in/eUiB78-d These datasets represent crucial progress toward a future of responsible, open, and inclusive health AI. Excited to see what innovations they will unlock !

CEPI and WHO urge broader #research strategy for countries to prepare for the next #pandemic. The CEPI (Coalition for Epidemic Preparedness Innovations) and the World Health Organization (WHO) called on researchers and governments to strengthen and accelerate global research to prepare for the next pandemic They emphasized the importance of expanding research to encompass entire families of #pathogens that can infect humans–regardless of their perceived pandemic risk–as well as focusing on individual pathogens The approach proposes using prototype pathogens as guides or pathfinders to develop the knowledge base for entire pathogen families At the Global Pandemic Preparedness Summit 2024 held in Rio de Janeiro, Brazil, WHO R&D Blueprint for Epidemics issued a report urging a broader-based approach by researchers and countries This approach aims to create broadly applicable knowledge, tools and #countermeasures that can be rapidly adapted to #emerging #threats This strategy also aims to speed up #surveillance and research to understand how pathogens transmit and #infect #humans and how the #immune #system responds to them The report’s authors likened its updated recommendation to imagining #scientists as individuals searching for lost keys on a street (the next pandemic pathogen) The area illuminated by the streetlight represents well-studied pathogens with known pandemic potential. By researching prototype pathogens, we can expand the lighted area, gaining knowledge and understanding of pathogen families that might currently be in the dark. The dark spaces in this metaphor include many regions of the world, particularly resource-scarce settings with high biodiversity, which are still under monitored and understudied. These places might harbor novel pathogens but lack the infrastructure and resources to conduct comprehensive research The prioritization work underpinning the report involved over 200 scientists from more than 50 countries, who evaluated the #science and evidence on 28 #virus families and one core group of #bacteria, encompassing 1652 pathogens. The #epidemic and pandemic risk was determined by considering available information on #transmission patterns, #virulence, and availability of #diagnostic #tests, #vaccines, and #treatments    CEPI and WHO also called for globally coordinated, #collaborative research to prepare for potential pandemics History teaches us that the next pandemic is a matter of when, not if. It also teaches us the importance of science and political resolve in blunting its impact,” said Tedros Adhanom Ghebreyesus, WHO DG. We need that same combination of science and political resolve to come together as we prepare for the next pandemic. Advancing our knowledge of the many pathogens that surround us is a global project requiring the participation of scientists from every country https://lnkd.in/ehrFV87i

Safeguarding information while enabling collaboration requires methods that respect privacy, ensure accuracy, and sustain trust. Privacy-Enhancing Technologies create conditions where data becomes useful without being exposed, aligning innovation with responsibility. When companies exchange sensitive information, the tension between insight and confidentiality becomes evident. Cryptographic PETs apply advanced encryption that allows data to be analyzed securely, while distributed approaches such as federated learning ensure that knowledge can be shared without revealing raw information. The practical benefits are visible in sectors such as banking, healthcare, supply chains, and retail, where secure sharing strengthens operational efficiency and trust. At the same time, adoption requires balancing privacy, accuracy, performance, and costs, which makes strategic choices essential. A thoughtful approach begins with mapping sensitive data, selecting the appropriate PETs, and aligning them with governance and compliance frameworks. This is where technological innovation meets organizational responsibility, creating the foundation for trusted collaboration. #PrivacyEnhancingTechnologies #DataSharing #DigitalTrust #Cybersecurity

We solved half the problem & thought we bridged the gap. Ever worked on a solution that looked perfect on paper… but ended up creating more problems than it solved? That’s exactly what happened when I was called in to review a telehealth solution. It was well-designed, checked all the cybersecurity boxes, & allowed patients to consult doctors remotely. The project requirement was clear: enable remote consultations. And the solution delivered exactly that. But here’s the thing: While healthcare systems often operate in silos, patients experience their care as one continuous journey. And this solution missed critical parts of that journey: 🔸 No easy way to book follow-ups. Patients had to call, leading to missed care. 🔸 Medication collection still required hours of travel, making the platform’s convenience meaningless. 🔸 Administrative staff were overloaded, causing delays in care coordination. We solved one problem & unintentionally created three more. The solution was designed for the system’s convenience, not the patient’s journey. To shift the perspective, we expanded the conversation to include voices we hadn’t considered: 🔸 Pharmacists: To integrate medication delivery into the process 🔸 Community Health Workers: To provide local, hands-on support 🔸 Family Caregivers: To highlight logistical & emotional challenges at home 🔸 IT Teams: To automate follow-ups & reduce administrative burden 🔸 Local Transport Providers: To enable last-mile delivery of medications With these insights, we redesigned the solution into a comprehensive care experience: ✅ Patients could book follow-ups easily & get automated reminders ✅ Medications were delivered directly to their homes ✅ Caregivers & community workers ensured patients didn’t fall through the cracks I later learned that: 🔸 Missed follow-ups dropped by 40%. 🔸 Medication adherence & health outcomes improved significantly. The redesigned platform didn’t just connect patients to doctors, it completed the care journey. Next time you’re working on a solution, consider these points: 1️⃣ Patients see one journey While systems operate in silos, patients experience care as a unified process. 2️⃣ Identify all stakeholders Both direct & indirect voices like caregivers, pharmacists & community workers, are essential to closing gaps. 3️⃣ Design for continuity Address every touchpoint in the patient’s journey, ensuring nothing falls through the cracks. Have you worked on solutions where overlooked stakeholders made all the difference? What’s one gap you discovered that changed everything? #DigitalHealth #Innovation #HealthcareTransformation #PatientExperience #Collaboration 💡This post is part of 'Rethinking Digital Health Innovation' (RDHI), empowering professionals to transform digital health beyond IT and AI myths. 💡Find the ongoing series and resources on our companion website (URL in comments). 💡 Repost if this message resonates with you!

🌍 𝗪𝗵𝗮𝘁 𝗱𝗼𝗲𝘀 𝗢𝗻𝗲 𝗛𝗲𝗮𝗹𝘁𝗵 𝗶𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗹𝗼𝗼𝗸 𝗹𝗶𝗸𝗲 𝗶𝗻 𝗽𝗿𝗮𝗰𝘁𝗶𝗰𝗲? We often talk about the importance of collaboration across human, animal, and environmental health sectors, but how are countries actually making it work? We are happy to launch WOAH's new One Health case study series "𝘐𝘮𝘱𝘭𝘦𝘮𝘦𝘯𝘵𝘪𝘯𝘨 𝘖𝘯𝘦 𝘏𝘦𝘢𝘭𝘵𝘩: 𝘊𝘰𝘶𝘯𝘵𝘳𝘺 𝘌𝘹𝘱𝘦𝘳𝘪𝘦𝘯𝘤𝘦𝘴 𝘢𝘯𝘥 𝘓𝘦𝘴𝘴𝘰𝘯𝘴 𝘓𝘦𝘢𝘳𝘯𝘵". Drawing on real-world experiences from different regions, these case studies showcase how the One Health approach is being translated into action at national and local levels. This initiative was a collaborative effort that I was fortunate to help develop and bring to finalization alongside my colleagues across the global One Health community of WOAH. 📖 The first batch features experiences from: ✅ Argentina: Tackling Mycobacterium bovis in Wildlife–Human Interface Areas of Iguazú National Park of Argentina: https://lnkd.in/e5WCfDd4 ✅ NAOHUN: Strengthening One Health Leadership Across North America’s Universities: https://lnkd.in/e-7-RVXu ✅ Japan's Fukuoka Prefecture: Advancing One Health at the sub-national level: https://lnkd.in/eeyZsv3b ✅ Netherlands: Signaling and responding to zoonotic disease threats using a One Health approach: the Zoonotic disease structure: https://lnkd.in/e7UaYiGa ✅ Bhutan’s One Health Journey Addressing Zoonoses and Other Threats Through Integrated Action: https://lnkd.in/egixmTne ✅ Argentina: Responsible Hunting and Invasive Species Control in El Palmar National Park, Argentina: https://lnkd.in/eRvgsqfR These examples illustrate how countries and institutions are strengthening surveillance, improving risk management, fostering multisectoral collaboration, and supporting evidence-based decision-making to address complex health challenges. For policymakers, practitioners, researchers, and partners working at the human-animal-environment interface, these case studies offer valuable insights into operationalizing the One Health Joint Plan of Action (OH JPA) and advancing health security through integrated approaches. 📚Knowledge sharing is essential if we want to move from commitment to implementation. I hope these experiences inspire learning, adaptation, and collaboration across sectors and countries. 🔗 Explore the case studies and share which example resonates most with your work. 📤 Please also don’t hesitate to share these useful resources within your networks! #OneHealth #HealthSecurity #PublicHealth #OneHealthInAction

Drug Design for Global Health (#dd4gh) is live 💖 We've been working with Medicines for Malaria Venture to build an AI drug discovery platform for global health researchers — and it's free! Most AI tools that accelerate drug discovery are expensive and need lots of data to work. For researchers in low- and middle-income countries working on malaria, TB, and neglected tropical diseases, both are out of reach. dd4gh changes that. It gives eligible researchers free access to predictive and generative AI trained on data from years of global health research. Scientists can identify the most promising compounds faster, reducing the time and cost it takes to find new treatments for diseases that affect their communities. The platform was co-created with researchers during workshops in Ghana and Switzerland to make sure it actually meets the needs of scientists on the front lines. Access to advanced AI systems shouldn't depend on where a scientist works or their lab's budget. 🔗 link in comments 😊