At CU Anschutz, our researchers are unlocking biological insights from incomplete datasets by providing guidelines to achieve near scRNA-seq accuracy in bulk deconvolution, enabling deeper insight into cell types and states within complex tissues ➡️ https://cudbmi.info/rna-guidelines-1

A new Pediatric Sepsis Event (PSE) definition from CU Anschutz enables large-scale surveillance, shedding light on the true prevalence of pediatric sepsis and guiding better care and prevention nationwide.

Pseudomonas aeruginosa is a pathogen that often dominates infections in vulnerable tissues or hosts. CU Anschutz researchers found resistance only in clinical strains, identifying how antibiotic pressure can increase its threat and complicate treatment ➡️ https://cudbmi.info/pseudomonas-aeruginosa-1

No code, no downloads—just insights. The pedbp app makes it easy to explore and visualize pediatric blood pressure percentiles (BPPs) in a user-friendly web app. @cuanschutz.bsky.social researchers designed this tool give consistent access to BPPs.

A global study of genetic data from 2.9 million people uncovered hundreds of new variants linked to thyroid cancer. CU Anschutz researchers found DNA patterns that may help predict cancer aggressiveness, and guide earlier, more precise care.

Pediatric blood pressure isn't the simple 120/80 'healthy' ceiling we learn for adults—it's a function of age, sex and more. Led by @peteredewitt.bsky.social researchers @@cuanschutz.bsky.social developed pedbp: a tool for pediatric blood pressure percentiles. Learn more➡️ https://cudbmi.info/pedbp1

Resarchers @cuanschutz.bsky.social developed MUSE, one of the first multi-LLM uncertainty algorithms grounded in information-theoretic principles. Instead of relying on a single model’s output, MUSE leverages a subset of models. Learn more➡️ https://cudbmi.info/muse1

🥧 Pi Day isn’t just about math—it’s also a reminder that precision matters. Researchers at CU Anschutz are using multi-omics to study how hormones, metabolism, genetics, and the gut microbiome work together to shape obesity treatment.

Enjoyed working w/ Stephen & Agnes on this! Gave me a chance to think systematically about where AI 🤖 can backstop human 🧑🏼‍🔬 fallibilities in peer review (fatigue, ordering effects, bias) vs. where human judgment remains essential (novelty, feasibility, creative leaps) while grappling w/ the risks.

Using a familiar correlational coefficient like Spearman’s or Pearson’s on molecular data may miss some complex patterns that exist. To overcome this, researchers at @cuanschutz.bsky.social including @miltondp.bsky.social developed CCC—a new statistical framework ➡️ https://cudbmi.info/ccc-1

LLMs show promise for supporting clinicians, but there are still challenges with their implementation. Researchers @cuanschutz.bsky.social established a foundation for evaluating LLMs' abilities with multi-modal data and temporal reasoning.

Sparse data and lack of reliable models are challenges in estimating biological systems. Researchers at @cuanschutz.bsky.social introduced a multi‑objective data assimilation framework for complex biological systems➡️ https://cudbmi.info/multiobjective-optimization1

Clinicians have a lot to consider for patient medications. LLMs could support medication management, but medications pose unique challenges for these LLMs. @cuanschutz.bsky.social researchers developed a benchmark suite to evaluate these implementations: https://cudbmi.info/rx-llm-1

How your body breaks down medication is more unique than you think. Researchers at CU Anschutz’s Claw Lab are mapping the genetic and metabolic differences that shape drug responses, and building models that could help clinicians personalize dosing with greater equity and precision.

Researchers developed a model that leverages EHRs to predict which children with severe TBI will go on to receive ICP monitoring. The findings can inform the design of a clinical decision support tool. Learn more ➡️ https://cudbmi.info/icp_monitor_tbi1

PhD programs worldwide face an urgent question: How should trainees use ChatGPT, Claude & similar tools? Now online: two resources on thoughtfully integrating generative AI into research training. 📄 Conceptual framework: zenodo.org/records/18649847 📋 Practical guide: zenodo.org/records/18452319 🧵

Jenna Tomkinson from CU Anschutz led a hands-on Cell Painting workshop at National Jewish Health, showing how image-based profiling can reveal disease-linked patterns and open the door to new partnerships in discovery.

Researchers at @cuanschutz.bsky.social are examining methods to overcome challenges in personalized oncology. In a recent perspective, the researchers explore hybrid models (mechanistic + ML) to improve model fits and potentially prediction. Learn more➡️ https://cudbmi.info/personal-oncology-JAMIA-1

You may not know what NLP is, but it's very prevalent in our lives. @compbiologist.bsky.social, PhD, associate professor @cuanschutz.bsky.social explains NLP and how he uses it to help biomedical data be reused for new discoveries. Learn more➡️ https://cudbmi.info/natural-language-processing-1

Interdisciplinary research is challenging but vital for innovation and better patient outcomes. The latest JAMIA issue highlights this approach, with @cuanschutz.bsky.social researcher David Albers, PhD, as associate guest editor. Read more➡️ https://academic.oup.com/jamia/article/33/1/1/8408480

AI is rapidly reshaping clinical care. CU Anschutz researcher Yanjun Gao, PhD, explores how we can ensure these AI tools are safe, transparent and aligned with human needs. Learn more here ➡️ https://cudbmi.info/health-ai-2026-1

phoenix supports researchers in implementing Phoenix & Phoenix-8 pediatric sepsis scoring—providing more reproducible research and findings that translate into better care over time. Learn more about the tool developed by researchers @cuanschutz.bsky.social➡️ https://cudbmi.info/phoenix-package-1

Computational methods are improving how we translate discoveries from model organisms to humans. Researchers including @compbiologist.bsky.social propose agnology: “agnostic” to evolutionary history, driven by data. Learn more➡️ https://cudbmi.info/computational-methods-human-disease-1

Computational methods are improving how we translate discoveries from model organisms to humans. Researchers including @compbiologist.bsky.social propose agnology: “agnostic” to evolutionary history, driven by data. Learn more➡️ https://cudbmi.info/computational-methods-human-disease-1

Meet the Claw Lab, where researchers partner with the community to build a stronger foundation for ethical, collaborative and adaptive personalized medicine ➡️ https://cudbmi.info/claw-lab-1

Every breakthrough in 2025, from new ICU guidelines to building one of the most complete human genome maps, reflects the power of working together to improve lives. Discover the stories behind the impact ➡️ https://cudbmi.info/top-stories-2025-1

Researchers at CU Anschutz created an automated system that continuously collects ventilator waveforms and links them with patient health records. Explore what this means for ICU care ➡️ https://cudbmi.info/data-pipeline-ventilator-waveforms-1

📢 CCPM Seminar Alert! Join us Tuesday, Dec. 9 at noon for an insightful session with Katrina Claw, PhD, and Randi Johnson, PhD, MPH. ➡️ Details here: https://cudbmi.info/ccpm-seminar-2025-1

Personalized medicine isn’t the future—it’s happening now. The Claw Lab at CU Anschutz is delivering culturally tailored, science-driven healthcare solutions that honor both biology and community knowledge. Meet the team behind the research ➡️ https://cudbmi.info/claw-lab-1

If you knew your DNA hinted at a higher risk for future disease, would it change how you live today? By analyzing thousands of genetic variants, Polygenic Risk Scores provide a snapshot of your potential disease risk.

Joel Stoddard, MD, is on a mission to catch mood disorders before they take hold. His research at CU Anschutz combines brain imaging, behavioral insights and machine learning to identify patterns that could predict mood disorders early, opening the door to faster and more effective interventions.

🔍 What if the key to managing disease isn’t just in your DNA? CU Anschutz researcher Maggie Stanislawski is utilizing multi-omics and microbiome science to investigate how genes, microbes, and molecules interact to influence health.

Patients trust chatbots for more than scheduling. A CU Anschutz study found many use UCHealth’s Livi for sensitive topics like mental health and billing, citing anonymity.

A new study of nearly 10,000 COVID-19 survivors in Colorado and Utah found that patients who received remdesivir during hospitalization had: ✅ 27% lower risk of death after discharge ✅ Fewer hospital and ER readmissions within 28 days Explore the study ➡️ https://cudbmi.info/covid-rdv-2025-1

Mechanical ventilation saves lives, but can also cause ventilator-induced lung injury (VILI). A new study from CU Anschutz introduces a computer model that predicts VILI using early lung function data, outperforming traditional measures ➡️ https://cudbmi.info/vent-lung-injuries-1

Thrilled to see our primary and secondary faculty sharing their expertise at #AMIA2025! From AI in health to genomics and clinical informatics, their work is shaping the future of healthcare. Check out their sessions and join the conversation ➡️ https://cudbmi.info/amia-2025-1

CU Anschutz researchers are utilizing synthetic data to train open-source AI models that automate radiology reporting, ensuring patient privacy is not compromised. Their new tool, AIDA, is already helping radiologists save time and focus on patient care.

Yanjun Gao, AI researcher at CU Anschutz, shares a critical insight: AI chatbots often mirror user input without verifying it against the literature. Her insights featured in @natureportfolio.nature.com ➡️ cudbmi.info/ai-sycophancy-1

🌱 Dave Bunten and the DBMI software engineering team presented the Software Gardening Almanack at #USRSE2025. This tool was built to support sustainable research software. Learn how DBMI is cultivating reusable, renewable software for science ➡️ cudbmi.info/softwaregarden-1

Golden hour? More like golden season.

Carving out time for creativity! DBMI’s annual pumpkin carving brought together our team for some seasonal, spooky fun 🎃

“What frontier AI technologies can do is amazing, but very few have made their way into the clinic.” — Jayashree Kalpathy-Cramer, PhD At the 29th Annual Eye Center Symposium, CU ophthalmologists explored how AI is reshaping eye care.

🍫 Is your sweet tooth genetic? Turns out your love for chocolate may be written in your DNA ➡️ https://bit.ly/3JkF2f2

Catch up on the latest from the CU Anschutz Department of Biomedical Informatics. Dive into the stories ➡️ https://bit.ly/4kWhASd 🧬 Asthma genetics in African-ancestry populations 🧠 ML insights into NF1 cell changes 💊 ICU pharmacists recognized in new national guidelines

Tellen Bennett, MD, MS, is heading to @jhu.edu ACCM Grand Rounds! On Oct. 23, he’ll share insights on “Human in the Loop: Critical Care, Informatics, and Mentorship.”

Congratulations @audreyhendricks.com for being honored with the 2025 @geneticssociety.bsky.social Education Award for her transformative work in genetics education. Hendricks accepted the award and shared her insights during a featured presentation at the ASHG Annual Meeting.

🌟 @geneticssociety.bsky.social 2025 takeover! Matthew, Davyd and Keshav brought the energy, the science and the posters. Representing the labs of @compbiologist.bsky.social, Joanne Cole, and @audreyhendricks.com, they’re pushing the boundaries of genomics.

DYK that many research software tools never make it beyond their original lab—even ones that can support other researchers and transform patient care? 🧵⬇️

What if AI could help personalize autoimmune disease treatments? At CU Anschutz, Fan Zhang, PhD, is using single-cell tech and AI to uncover immune cell interactions that could lead to better therapies for rheumatoid arthritis and other autoimmune conditions ➡️ https://bit.ly/4nMHidW

🎉 Big congrats to David Albers, PhD, on being elected to the 2025 class of ACMI fellows! His work in computational modeling is shaping the future of health informatics.