Central line-associated blood stream infection (CLABSI) surveillance is mandated and publicly reported in United States hospitals but requires manual chart review. Generative artificial intelligence (AI) may facilitate CLABSI identification.MethodsWe performed a retrospective cohort study of CLABSI surveillance using standardized prompts, clinical data, and Centers for Disease Control and Prevention definitions. In 11 hospitals, 24 infection control (IC) nurses and physicians retrospectively reviewed 220 CLABSI/non CLABSI bacteremias. Three methods of review were compared to original facility expert review: 1) AI-assist review, 2) AI-alone review, and 3) repeat expert review. Disagreement between any method of review was adjudicated by a 2-expert physician referee panel.ResultsAI-assist review had a 93.2% (205/220, 95% CI: 89.0–96.1) overall accuracy (agreement with facility reporting or refereeing panel) vs. AI-alone review, 90.0% (198/220, 95% CI: 85.3–93.6) overall accuracy or repeat expert review, 88.2% (97/110, 95% CI: 80.1–93.6) overall accuracy. Inter-site variability was greater for repeat expert review than AI-assist. AI-assist review required a median of 14 minutes (interquartile range, IQR 6-25.5) vs. 25 minutes (IQR 11-43) for repeat expert (p = 0.0001). AI-assist review was reported as low effort in 52% of cases vs. 21% of repeat expert cases (p < 0.0001). AI-assist review was reported as somewhat or very objective in 72% of cases vs. 61% of repeat expert cases (p=0.092).ConclusionsCLABSI detection by AI methods was at least as accurate as traditional methods, better liked by experts, faster and less variable. AI-assisted review could improve healthcare-associated infection reporting.

Staphylococcus aureus colonization predisposes to skin and soft tissue infection (SSTI). Given the waning effectiveness of decolonization, we evaluated periodic personal decolonization and household environmental decontamination to reduce SSTIs among households affected by S. aureus.MethodsHouseholds of children with community-associated S. aureus SSTI participated in an open-label randomized trial. After baseline decolonization, households were randomized 1:1:1 to a 3-month decolonization intervention: 1) Periodic-Personal (twice weekly chlorhexidine bathing and monthly intranasal mupirocin application); 2) Environmental-Hygiene (weekly household surface disinfection and enhanced laundry measures); or 3) Integrated-Approach of both Periodic-Personal and Environmental-Hygiene. Over 9 months, participants and household surfaces were sampled at 5 study visits to detect S. aureus; SSTI incidence was recorded. The primary outcome was household-level cumulative SSTI at 3 months, comparing the Integrated-Approach to the combined Personal-Periodic and Environmental-Hygiene groups.ResultsBetween 2015-2021, 196 index patients and their household contacts (n=623) were enrolled. Cumulative SSTI incidence did not differ between groups during the 3-month intervention. In index patients and household contacts with SSTI in the year prior to enrollment, SSTI incidence was lower among the Integrated-Approach at 6- and 9-months compared to the combined Periodic-Personal and Environmental-Hygiene groups. In multivariable analyses, prior year SSTI was associated with subsequent SSTI; intervention group was not significant. All interventions reduced MRSA, but not MSSA, personal colonization over 9 months.ConclusionsWhile an Integrated-Approach of prolonged personal and environmental decolonization reduced SSTIs among participants with prior year SSTI, prior SSTI strongly predicted SSTI incidence longitudinally. Novel prevention strategies are needed.

Finally understood TMLE's "doubly robust" property through simulation. Works well when either outcome OR treatment model is correct. XGBoost + TMLE captured complex relationships without manual specif...

IDWeek2025 had the lowest post count since 2022 (1,272 posts). While top posters shifted to Bluesky, X remained on par—the key difference was engagement rates favoring Bluesky. Grateful to learn so mu...

Ever wondered what M184V, K65R actually mean? I learnt it from rebuilding Stanford's HIV resistance algorithm from scratch to find out. Spoiler: it took tons of code to match their 3-line tool. But th...

Learned RNA-seq workflow using C. difficile data from a published study 🧬. Processed raw reads through fastp → kallisto → DESeq2 pipeline. Results matched the original paper's findings, with clear dif...

Hands-on with Oxford Nanopore workflow: pod5 → BAM → assembly! Processed M. tuberculosis from raw signals to complete genome using dorado + flye. Fascinating how thousands of contigs became one 4M+ bp...

We learnt how to assemble DNA fragments from a recently published *N. meningitidis* outbreak study using SKESA 🧬, practiced using BLAST for species identification and MLST for strain typing, and explo...

Ever wondered how DNA alignment actually works under the hood? 🧬 We coded the Needleman-Wunsch algorithm from scratch, working through scoring matrices by hand with simple examples like "CAT" vs "CT" ...

This report describes 41 cases of Neisseria meningitidis conjunctivitis among military trainees living in a communal setting in Texas.

🧬🔬 Explore phylogenetic analysis from genome to tree! Basic workflow with R/Bioconductor. Learnt to work with large genomic dataset. Extract 16S rRNA from 10K+ E.coli strains using dataset dehydrate, ...

Instead of flashcards, we Rube Goldberg'd this with Bioconductor! Analyzed 3,280 E. coli genomes from NCBI, detecting ESBL genes in 84.4% of samples. CTX-M-15 was most common. Helped us understand gen...

Learn how to build a flash-card style question bank using Google Sheets as storage, R’s Plumber API, and host it on a Digital Ocean droplet—step-by-step setup, deployment, and tips.

Hierarchical composite endpoints (HCEs) are increasingly being used in infectious diseases research. In this review aimed at educating the clinical reader,

Enjoyed learning penalized GAM math. Built penalty matrices, optimized λ using GCV, and implement our own GAM function. Confusing? Yes! Rewarding? Oh yes!

I finally understood B-splines by working through the Cox-deBoor algorithm step-by-step, discovering they're just weighted combinations of basis functions that make non-linear regression linear. What ...

We learnt to derive the Newton-Raphson algorithm from Taylor series approximation and implements it for logistic regression in R. We'll show how the second-order Taylor expansion leads to the Newton-R...

Refreshed my rusty calculus skills lately! 🤓 Finally understand what happens during complete separation and why those coefficient SE get so extreme. The math behind maximum likelihood estimation makes...

In my simulations of Response Adaptive Randomization, I discovered it performs comparably to fixed 50-50 allocation in identifying treatment effects. The adaptive approach does appear to work! However...

Note: Since your browser does not support Javascript, you must press the Continue button once to proceed.