(@peteredewitt) — Bluesky Profile

5 days ago

Diagram comparing longitudinal vs encounter-level comorbidity detection using ICD-10 codes across five patient encounters.

Top panel (Longitudinal): The patient initially has uncomplicated diabetes (E11.9). Later an encounter includes E11.22 and K72.10, indicating complex diabetes and severe liver disease. Using longitudinal logic, these conditions persist in later encounters even when only E11.9 appears, preserving severity and correctly flagging severe liver disease.

Bottom panel (Encounter-level): Each encounter is evaluated independently. Diabetes changes from uncomplicated → complex → back to uncomplicated when E11.9 reappears, and severe liver disease is never flagged because its code does not repeat.

Message: Ignoring patient history can downgrade severity or fail to identify comorbidities.

Same ICD codes. Same patient. Different risk profiles.

Encounter-level comorbidity logic assumes ICD codes are re-reported every visit. They usually aren’t.

medicalcoder handles this

📦install.packages("medicalcoder")

#rstats #HealthInformatics #EHR #ClinicalResearch #RiskAdjustment #PublicHealth

3 3 0 0

1 week ago

GUESS WHO’S BACK, BACK AGAIN 👀

130 22 7 4

2 weeks ago

Thanks! I would love to hear what you think about the package after using it.

0 0 0 0

5 months ago

CU Anschutz Makes Research Tools Available Worldwide The Department of Biomedical Informatics at CU Anschutz presents the Wall of Software: a growing gallery of open-source tools that support medical research

Read more about how DBMI built the Wall of Software and why it’s important for the research community: news.cuanschutz.edu/dbmi/wall-of...

0 1 0 0

2 months ago

A collage of diverse professional fields including genetics, digital technology with a person at a workstation, laboratory research, and medical review with text labeled "Softcare Almonds."

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

1 1 0 0

2 weeks ago

a lot of medication blister packs in a pile containing medications of different color, size, and shape suggesting comprehensive medication management (CMM)

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

0 1 0 0

1 month ago

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

3 2 0 0

2 weeks ago

📦 medicalcoder v0.8.0 is now on CRAN.

medicalcoder is a unified and longitudinally aware framework for ICD-based comorbidity assessment in #rstats

CRAN: cran.r-project.org/package=medi...

GitHub: github.com/dewittpe/med...

Website: peteredewitt.com/medicalcoder/

12 5 1 0