MASLD/MASH Assessment for Next Steps in Care

Generating Real-World Evidence (RWE) in SMA faces hurdles due to evolving standard of care with recent treatments, inconsistent outcomes measurement due to age at treatment initiation and severity baseline, and the need for long-term follow-up. The PHARMO Institute, part of Lumanity, is uniquely positioned to deliver clinically rich insights into SMA disease history, treatment patterns, and outcomes, and invite you to test your research objectives with us, including with: - Patient characteristics and long-term outcomes - Neurodevelopment and pathophysiology - Evolving standard of care and treatment - Long-term safety and durability - Healthcare resource utilization (HCRU) Access our one-pager at https://lnkd.in/eRNUXp4r and connect with us at contact@lumanity.com. #SpinalMuscularAtrophy #SMA #GeneticTesting #SMAScreening

Conclusion: There has been an increasing trend toward the use of PSMA PET/CT for staging mCSPC in recent years, identifying a population with more favourable disease characteristics and a more favourable prognosis. This shift in patient characteristics, driven by stage migration (the Will Rogers phenomenon), influences clinical management by enabling more refined patient selection for conservative or targeted therapies. Consequently, accounting for lead-time and selection bias is essential when comparing survival outcomes in the PSMA PET/CT era.

Every patient's journey is different. Clinical decisions shouldn't rely on assumptions. Patients with MASLD progress at different rates, and no two clinical pathways are exactly alike. From identifying patients at increased risk to further evaluation, management, and longitudinal monitoring, each step depends on having meaningful clinical information at the right time. LIVERFASt™ provides biopsy-aligned assessment of fibrosis, steatosis, and inflammatory activity, helping clinicians better understand disease severity and support informed patient management. Because every clinical decision shapes the next step in a patient's journey. Learn more about the clinical evidence behind LIVERFASt™: https://lnkd.in/g52CHnaV #ClinicalPathways #ClinicalDecisionMaking #MASLD #MASH #LIVERFASt #LiverHealth #RiskStratification #Fibronostics

What should happen after identifying a patient at increased risk of advanced fibrosis? Identifying the right patient is only the first step.The real value of liver assessment lies in what happens next. Should the patient be referred for specialist evaluation? Would additional assessment provide greater clinical clarity? Should follow-up be scheduled sooner? Or is longitudinal monitoring the most appropriate course? LIVERFASt™ was designed to support these clinical decisions by providing biopsy-aligned fibrosis staging, together with steatosis and activity assessment, helping clinicians better understand where a patient sits on the disease spectrum and what action may be appropriate next. Because a test result should do more than report a finding. It should help guide patient management. Learn more about the clinical evidence behind LIVERFASt™: https://zurl.co/rd5Wt #ClinicalPathways #ClinicalDecisionMaking #MASLD #MASH #LIVERFASt #RiskStratification #LiverHealth #ClinicalEvidence #Fibronostics

Real-world impact begins with the clinicians and healthcare organizations using the technology every day. We're grateful to The Diabetes Centre for sharing their experience with Ophthalytics AI - Nsight360™ and their commitment to advancing earlier detection for patients at risk of diabetic eye disease. By combining AI-assisted retinal analysis with human clinical oversight, Nsight360™ helps healthcare organizations expand access to diabetic eye screening, support earlier identification of high-risk patients, and strengthen preventive care programs. As the global burden of diabetes continues to grow, scalable screening solutions have an important role to play in helping patients receive timely eye exams and appropriate follow-up care. Interested in learning how Nsight360™ can support your screening program? We'd love to connect. 📧 info@ophthalytics.com 📞 +1 (862) 222-6880 #Nsight360 #DiabeticRetinopathy #PrimaryCare #PopulationHealth #PreventiveCare #HealthcareInnovation #ArtificialIntelligence #DigitalHealth #Ophthalytics

$50B in RHTP funding is on the table. AI diagnostics at the point of care is exactly the kind of project that wins these applications. Breakdown below 👇 #RuralHealth #DiabeticRetinopathy #ValueBasedCare #PrimaryCare 

Successful implementation will depend on workflow integration, staff training, quality execution, and measurable outcomes. Autonomous point-of-care diagnostics can be a practical way for rural primary care settings to close diabetic eye care gaps without adding unnecessary burden to patients or clinics.

Over 60% of patients with diabetes skip their annual diabetic eye exam. In rural America, that gap is often even wider because the nearest retina specialist can be hours away, transforming a routine check-up into a full day off work. That’s where the $50B Rural Health Transformation Program (RHTP) comes in, helping you close that care gap. Several states are already directing this funding to chronic disease prevention and technology innovation, exactly where autonomous, point-of-care AI diagnostics can fit. Best of all, RHTP funding covers the setup and subscription rather than the clinical exam itself.  Individual screenings are billed separately under CPT code 92229, turning a grant-funded initiative into a self-funding revenue engine. One caveat: RHTP is a competitive, scored application through your state - not an entitlement. The states reward high-impact projects that plug into existing primary care workflows. Given that, it's worth building a case that shows clear, measurable impact. We broke down how to position AI diagnostics against your state's outcome targets, navigate the RFP process, and improve your HEDIS and MIPS Measure 117 scores. You can read the full analysis here: https://lnkd.in/d6cFB_Ga

Strategic Interests, LLC is helping many providers and vendors capture a share of the $50 billion in RHTP funding available from CMS and all 50 states, by aligning your strategy with innovation and collaboration with partners to transform rural healthcare Vendors already participating can grow faster with our help Contact us at: https://lnkd.in/gGWND4pn

Three patient subtypes. Zero treatment history. One question: 𝗰𝗮𝗻 𝘆𝗼𝘂 𝗳𝗹𝗮𝗴 𝘁𝗵𝗲 𝗵𝗶𝗴𝗵𝗲𝘀𝘁-𝗿𝗶𝘀𝗸 𝗽𝗮𝘁𝗶𝗲𝗻𝘁 𝗯𝗲𝗳𝗼𝗿𝗲 𝘆𝗼𝘂 𝗸𝗻𝗼𝘄 𝗮𝗻𝘆𝘁𝗵𝗶𝗻𝗴 𝗮𝗯𝗼𝘂𝘁 𝘁𝗵𝗲𝗶𝗿 𝘁𝗿𝗲𝗮𝘁𝗺𝗲𝗻𝘁 𝗽𝗮𝘁𝗵? Working with synthetic EHR data (1,763 type 2 diabetes patients), I first let unsupervised clustering find natural patient groups. Three emerged: a mild majority, a small dyslipidemic subgroup, and a multimorbid group ⇾ older patients, high comorbidity burden, the ones who carry the most clinical risk if missed. Then came the harder question. Clustering after the fact is useful for research. But in practice, 𝘆𝗼𝘂 𝘄𝗮𝗻𝘁 𝘁𝗼 𝗸𝗻𝗼𝘄 𝗲𝗮𝗿𝗹𝘆, 𝗮𝘁 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝘃𝗶𝘀𝗶𝘁, 𝗯𝗲𝗳𝗼𝗿𝗲 𝗮𝗻𝘆 𝗺𝗲𝗱𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗵𝗶𝘀𝘁𝗼𝗿𝘆 𝗲𝘅𝗶𝘀𝘁𝘀. So I deliberately stripped the model down: no comorbidity index, no treatment data, no follow-up history. Just what's available on day one: age, labs, BMI. The result on a held-out test set: 𝟵𝟮% 𝗼𝗳 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗿𝗯𝗶𝗱 𝗽𝗮𝘁𝗶𝗲𝗻𝘁𝘀 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗹𝘆 𝗳𝗹𝗮𝗴𝗴𝗲𝗱, using only baseline information. The model wasn't optimized for the best overall accuracy, it was optimized to catch the group that matters most clinically. That distinction, choosing what to optimize for not just how, is where a biotech background changes the questions you ask a dataset. #DataScience #MachineLearning #HealthcareAnalytics #RealWorldEvidence