Healthcare Technology Consulting

Researchers at Yale University using Curiosity—Epic's generative medical event model, which simulates a patient's likely future course from their record — looked at adults discharged from the ED with abdominal pain, one of the most common and most uncertain presentations in emergency medicine. Traditional risk models answer a binary question: will this patient come back? Curiosity answers a richer one: if they return, when, and will that return end in discharge or admission? Two patients can carry the same overall revisit probability but face very different paths—one headed toward a quick outpatient follow-up, another toward an early admission. A binary score flattens that difference. A trajectory surfaces it. A single pretrained model, like Curiosity, can generate calibrated predictions across many outcomes without retraining. As a result, the focus and time shift away from building a bespoke model for every clinical question and toward deciding which questions are worth asking. The team moved from idea to results in a matter of weeks. It also highlights an emerging skillset: clinicians who pair deep clinical reasoning with real fluency in generative AI. The questions they choose to ask are the key ingredient. Check out the full post from lead author Kent McCann: https://lnkd.in/eeVBxRB4 Preprint: https://lnkd.in/guNssvvc More on Curiosity: https://lnkd.in/gGunqeby

AI is only as smart as its data. Bad data breaks everything. Good data builds the future. AI in healthcare is not magic. It is math, logic, and trust—stacked on a backbone of clean, connected data. Here’s the truth: • AI can’t fix broken data. • Automation fails if the data is a mess. • Connected care needs a solid data foundation. Think of data as the bones of a body. If the bones are weak, nothing stands. If the bones are strong, you can build muscle, move fast, and stay healthy. To build smarter AI and real connected care, start with these pillars: 1/ Data Quality:   Garbage in, garbage out.   Every record, every field, every update must be right.   No duplicates. No missing info. No errors.   Clean data is the first rule. 2/ Interoperability:   Systems must talk to each other.   Break down silos.   Use standards like HL7, FHIR, and APIs.   If your data can’t move, your care can’t connect. 3/ Privacy and Security:   Trust is everything.   Encrypt data.   Control access.   Follow HIPAA and GDPR.   Patients own their data—protect it. 4/ Governance:   Set the rules.   Who can see what?   Who can change what?   Audit trails, clear roles, and strong policies keep data safe and useful. 5/ Infrastructure Flexibility:   Cloud, on-prem, or hybrid—pick what fits.   Scale up as you grow.   Don’t get locked in.   Your data backbone must bend, not break. 6/ Continuous Improvement:   Data is never “done.”   Check, clean, and update all the time.   Train your team.   Make data quality a habit, not a project. When you get these right, you unlock: • Smarter automation • Real-time insights • Scalable AI that learns and adapts • Seamless patient care across systems The best AI in the world can’t save bad data. But with the right data backbone, you build care that connects, scales, and lasts. Start with better data. Build the future of healthcare—one clean record at a time.

Miss a deadline, and you're out of compliance. Miss the trend behind the deadline, and patients get hurt.   Medical device incidents happen every day. Most teams chase deadlines and miss the bigger picture.   Every report has a clock. But knowing when to report is only the start.   What experienced vigilance teams know:   Meeting deadlines keeps you compliant.   Managing patterns keeps patients safe.   Those 2-day, 5-day, 10-day, and 30-day clocks?   They’re not just regulatory requirements. They’re early warning signals.   High-performing companies treat vigilance deadlines as data collection points.    Here are 4 ways you can start today:    1. Master Your Reporting Timelines   • 10 days for EU deaths and public health threats • 5 days for FDA events needing remedial action • 10 days for serious incidents in Canada and Australia   Each deadline reflects a severity tier.  Track them to see your risk profile trend over time.   2. Document Your Classification Logic   • Record criteria for “serious deterioration.” • Define what constitutes a “public health threat.” • Set clear thresholds for “remedial action.”   Auditors check consistency.  Clear logic shows you understand the rules and apply them the same way every time.   3. Align Your Global Reporting   • Japan: 15-day reports for serious injuries • Brazil: 30-day submissions for malfunctions posing serious risk • Australia: 10-day notifications for deaths   Different clocks for similar events = opportunities to standardize internally.   4. Build Systems Around Deadlines   • Set alerts for 2-, 5-, 10-, and 30-day triggers. • Create templates for each timeline (required fields, attachments, sign-offs). • Map submission portals to deadline categories (EUDAMED, MedWatch, NOTIVISA, etc.).   When vigilance management is systematic, compliance follows naturally.   And when compliance runs on rails, your team can prevent the next incident. Not just report the last one. ⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡⬡ MedTech regulatory challenges can be complex, but smart strategies, cutting-edge tools, and expert insights can make all the difference. I'm Tibor, passionate about leveraging AI to transform how regulatory processes are automated and managed. Let's connect and collaborate to streamline regulatory work for everyone! #automation #regulatoryaffairs #medicaldevices

☕ Sunday at The HIT Academy. Tomorrow we begin Module 7: Data Strategy, Analytics, and Population Health — five lessons on the gap that defines modern healthcare. 🎯 Why this module matters. Healthcare has invested for a decade in better data infrastructure. The data warehouses are built. The dashboards are deployed. The analytics teams are hired. The predictive models are running. And yet, ask any senior leader honestly how many of their most consequential decisions are actually informed by analytics, and the answer is fewer than the investment would suggest. The decisions that matter most: strategic investments, executive hires, service line strategy, capital allocation, partnership choices. They still get made on intuition, anecdote, and the loudest voice in the room. The technology problem is largely solved. The decision problem is not. 📖 What's coming this week. 🔸 **Monday — Lesson 34.** From data to decisions. Why most healthcare analytics programs underdeliver, and the disciplines that distinguish the few that succeed. 🔸 **Tuesday — Lesson 35.** Data warehouse, lakehouse, data mesh. The architectural choice behind every modern analytics program, and how to make it strategically rather than by vendor selection. 🔸 **Wednesday — Lesson 36.** Population health management. Promise, reality, and the operational disciplines that turn infrastructure into outcomes. 🔸 **Thursday — Lesson 37.** Analytics talent. The roles healthcare actually needs, why the market is brutal, and what the best teams do differently. 🔸 **Friday — Lesson 38.** Data governance. The structural discipline that determines whether your data is an asset, a liability, or merely an expense. 🧭 A note on what I am writing from. I have led data and analytics organizations through warehouse builds, lakehouse migrations, population health program launches, and the talent battles that determine whether the work compounds or stalls. The consistent pattern I have observed: the technology is the easy part. The operational discipline of converting data into decisions is the hard part. The organizations that take that work seriously outperform their peers consistently. The organizations that treat analytics as an infrastructure problem stay stuck on infrastructure. This module is for the leaders who want to close the gap between investment and outcome. If you know a peer who sits in a CIO, CHIO, CDO, or analytics leadership role, forward this. The HIT Academy is free, and it stays free. Stay curious AF, my friends. ☕ Khalid Turk, FCHIME, CHCIO #TheHITAcademy #HealthcareAnalytics #PopulationHealth #DataStrategy #HealthIT

Europe just CE marked its first LLM-powered medical device. Prof. Valmed, a clinical decision-support system built on a retrieval-augmented generation (RAG) architecture, has been certified as a Class IIb medical device under EU MDR (2017/745). That classification places it in the same risk category as infusion pumps and ventilators meaning it requires Notified Body review, a full ISO 13485 quality management system, software lifecycle documentation under IEC 62304, and a robust post-market surveillance plan. This is a notable precedent for generative AI in clinical care. For those of us building regulated healthtech products, a few takeaways: --RAG architectures are viable, but only with traceability, curation, and grounding. Prof. Valmed queried over 2.5 million validated sources and preserved retrieval paths, prompt logic, and model state for auditability. --Evidence requirements are tightening. Generic model benchmarks won’t cut it. The review demanded indication-specific performance data, bias mitigation strategies, and plans for continuous monitoring. --Dual-framework compliance is the new norm. The EU AI Act adds layers of transparency, human oversight, and data governance to what MDR already requires. The FDA’s PCCP guidance is converging in similar ways. Teams will need harmonized documentation across all three. --Enterprise buyers and payers are factoring in compliance maturity. Cost-effectiveness, audit trails, and fairness metrics are making their way into procurement criteria, especially for clinical AI. If you’re an early-stage team, this is less about racing to certification and more about structuring your product, data, and validation strategy with these expectations in mind. Compliance isn't the goal, it’s the baseline for clinical credibility and long-term defensibility. Happy to compare notes if you're navigating MDR, the AI Act, or FDA alignment. https://lnkd.in/g7rkk97b

Artificial Intelligence (AI) is rapidly transforming Clinical Data Management (CDM) from a transactional function into a strategic enabler of faster, higher-quality clinical research. Traditionally, data management has relied on manual processes for data cleaning, query generation, reconciliation, coding, and database review. AI is reshaping these activities by automating repetitive tasks, identifying hidden patterns, and enabling proactive risk detection throughout the clinical trial lifecycle. Organizations are increasingly adopting AI-powered capabilities such as intelligent data review, automated discrepancy detection, predictive query management, medical coding assistance, protocol deviation identification, and anomaly detection across clinical datasets. Generative AI is further enhancing productivity by assisting with documentation, standard operating procedures, study metadata creation, programming support, and natural language interaction with clinical data repositories. The adoption of AI delivers significant benefits, including reduced cycle times, improved data quality, lower operational costs, enhanced regulatory compliance, and faster database lock. AI also enables data managers to focus on higher-value activities such as risk-based data review, cross-functional collaboration, and strategic oversight rather than manual data processing. However, successful AI adoption requires more than deploying technology. Organizations must establish robust governance frameworks, ensure data privacy and regulatory compliance, validate AI models, maintain human oversight, and build trust through transparent and explainable AI. Investment in workforce upskilling is equally important, enabling clinical data professionals to develop competencies in AI, analytics, and digital technologies. Looking ahead, AI will become a foundational capability within Clinical Data Management, supporting integrated, intelligent, and adaptive clinical operations. Combined with Risk-Based Quality Management (RBQM), real-world data, decentralized clinical trials, and advanced analytics, AI has the potential to accelerate drug development while improving patient safety and data integrity. Organizations that strategically embrace AI with a clear governance model and strong change management approach will be well positioned to deliver more efficient, scalable, and patient-centric clinical trials. The key objectives achieved through this AI adoption summary are: 1. Establish the strategic vision 2. Highlight business value 3. Showcase practical use cases 4. Emphasize operational transformation 5. Address governance and compliance 6. Promote organizational readiness 7. Align with industry trends 8. Support executive decision-making #AI #Innovation #DataManagement #Transformation #Future

𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗖𝗼𝘂𝗹𝗱 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺 𝗖𝗹𝗶𝗻𝗶𝗰𝗮𝗹 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗦𝘂𝗽𝗽𝗼𝗿𝘁. 𝗛𝗲𝗿𝗲'𝘀 𝗪𝗵𝗮𝘁 𝗧𝗵𝗮𝘁 𝗠𝗶𝗴𝗵𝘁 𝗟𝗼𝗼𝗸 𝗟𝗶𝗸𝗲. This week, OpenAI released a visual tool for building multi-agent workflows(1). I've been curious about agents for a while, but never had time to learn. Playing with this tool got me thinking about a longstanding challenge: how do we translate complex clinical pathways into effective CDS tools? 𝗧𝗵𝗲 𝗣𝗿𝗼𝗯𝗹𝗲𝗺 𝘄𝗶𝘁𝗵 𝗖𝘂𝗿𝗿𝗲𝗻𝘁 𝗖𝗗𝗦 Today's EHR-based decision support faces a fundamental tradeoff. Tightly scripted rules are reliable but inflexible. Loosely scripted ones give clinicians room to adapt but sacrifice consistency. Multi-agent AI workflows might offer a way out of this bind. 𝗔 𝗣𝗿𝗼𝗼𝗳 𝗼𝗳 𝗖𝗼𝗻𝗰𝗲𝗽𝘁 To explore this, I translated Children's Hospital of Philadelphia's Suicide Risk Assessment Pathway (2) into a multi-agent workflow. Here's how it works: • Input: Clinician's risk formulation, screening results, risk and protective factors • Acuity script: Determines patient acuity level • Intervention agent: Recommends response level • Response agents: Four specialized agents provide tailored clinical guidance based on severity 𝗔 𝗗𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝗞𝗶𝗻𝗱 𝗼𝗳 𝗖𝗗𝗦 Now imagine this in your EHR. Instead of rigid decision trees, you'd have multiple specialized LLMs that can: • Access relevant patient data • Provide contextual guidance • Answer follow-up questions in real time • Adapt to clinical nuance while maintaining evidence-based standards Some extras that make this promising are the ability to use MCP and RAG! This isn't just automation. It's augmentation that preserves clinical judgment while providing robust support.   Bimal Desai MD, MBI, FAAP, FAMIA

The future of laboratory medicine isn't another test. It's connecting the tests we already have. Another inspiring presentation from our Laboratory Medicine trainee program at King's College Hospital London, Jeddah This project didn't introduce a new biomarker. It introduced a new way of thinking. Instead of looking at a patient's CBC... ...or CRP... ...or blood cultures... ...or coagulation profile... ...or blood bank support... ...as separate reports, our trainee followed one patient through the entire sepsis journey, integrating every laboratory result into a single clinical pathway. That changed everything. Because patients don't experience disease one laboratory test at a time. The laboratory shouldn't either. One of the biggest limitations of today's laboratory reporting is that we report individual results, while the body produces #interconnected biology. Every day, our laboratories generate enormous amounts of information. Much of it never reaches the clinician in a meaningful way. A slight rise in neutrophils. A gradual fall in platelets. A subtle increase in lactate. A coagulation trend suggesting early DIC. A microbiology report showing emerging antimicrobial resistance. A blood bank request indicating increasing transfusion requirements. Individually... many of these observations never trigger an alert. Some are not even formally reportable. Yet when these pieces are integrated, they suddenly begin telling the same story. That is where the future begins. Imagine laboratory systems that no longer deliver isolated reports, but continuously integrate information across: 🔹 Hematology 🔹 Clinical Chemistry 🔹 Microbiology 🔹 Molecular Diagnostics 🔹 Blood Bank 🔹 Clinical history 🔹 Previous laboratory trends Suddenly, the laboratory is no longer reporting numbers. It is recognizing patterns. This is exactly where artificial intelligence will have its greatest impact. Not by replacing laboratorians. But by connecting thousands of data points that no human can realistically synthesize in real time. The result is earlier recognition of deterioration... earlier prediction of sepsis... better #antimicrobial #stewardship... more #personalized treatment... and ultimately better patient #outcomes. What impressed me most was that this insight came from one of our trainees. The project reminded all of us that innovation doesn't always come from buying a new analyzer or introducing another biomarker. Sometimes #innovation comes from asking a simple question: "What happens if we allow all our laboratory data to speak to each other?" That is the laboratory I believe we will build over the next decade. Congratulations to our trainee and the entire laboratory team for demonstrating that the future of healthcare is not just digital. It is integrated. Because patients are never divided into departments. Their laboratory data shouldn't be either.

The Hidden Backbone of Modern Healthcare: Data Management Hospitals don’t run on machines. They run on data. Every patient record, lab report, prescription, and diagnosis generates information but here’s the uncomfortable truth: Most hospitals are drowning in data and starving for insight. In the rush to go “digital,” many systems ended up fragmented different departments storing data in silos, outdated EHRs (Electronic Health Records) that don’t talk to each other, and mountains of manual entries that erode both time and trust. The result? Delayed decisions. Incomplete patient histories. Burnout for staff who spend more time typing than treating. But hospitals that invest in structured data management are seeing a quiet revolution. Here’s what they do differently: Unified Data Architecture - One connected ecosystem across departments (no more 12 login screens for one patient). Real-Time Dashboards - Doctors and admins get instant insights on patient flow, diagnostics, and resource allocation. AI-Driven Analysis - Predictive models that flag high-risk patients before emergencies happen. Data Governance - Clear policies that ensure security, privacy, and accuracy -not as afterthoughts, but as foundations. The outcome isn’t just operational efficiency. It’s better care, fewer errors, and more trust. When hospitals treat data as a clinical asset, not just a digital record, patient outcomes improve. Healthcare isn’t just about curing illness anymore it’s about managing information intelligently. If you work in healthcare tech or hospital operations: What’s the biggest challenge you’ve faced with data management integration, quality, or adoption? #Healthcare #DataManagement #HealthTech #HospitalInnovation #DigitalTransformation

This editorial provides a crucial, actionable framework for healthcare organizations to navigate the mandatory requirements of the new EU AI Act, ensuring the safe and compliant integration of AI into critical care settings. • What? It proposes a checklist-based methodology for the structured implementation of Artificial Intelligence (AI) policies within high-acuity healthcare settings like anaesthesia and intensive care units. • Why? To address the upcoming European Union AI Act, which imposes binding legal obligations on healthcare organizations to ensure AI is used in a safe, transparent, and governable manner, and to navigate the complex ethical and operational challenges of integrating AI into patient care . • How? By providing a comprehensive, two-part checklist that guides healthcare professionals in systematically evaluating AI systems. The checklist covers Clinical/Technical Validation (e.g., performance, safety, regulatory compliance) and Governance/Compliance (e.g., adherence to the AI Act, GDPR, and establishing clear organizational responsibility). #AIinHealthcare #HealthTech #AIpolicy #DigitalHealth #PatientSafety #EUAIAct #MedicalAI #ClinicalAI