Software
Open-source code behind my papers.
Everything below is public on GitHub.
isitfair
Fairness evaluation for clinical prediction models. You bring a trained model’s predicted probabilities and the patient groups to compare. isitfair reports subgroup-stratified discrimination, calibration and decision-curve analysis, states which estimates the data can support, and writes a single HTML report aligned with TRIPOD+AI.
pip install git+https://github.com/HugoGuillen/isitfair.git
Companion paper: Subgroup deployment-readiness audit of calibration and clinical utility in perioperative infection prediction. JAMIA (2026), in press.
MAP-CARE
A pipeline that translates Swiss procedure codes (CHOP) with a local large language model, embeds them, and maps them to other classifications such as the German OPS by semantic similarity. Companion paper: LLM-augmented semantic embeddings enable cross-lingual mapping of medical procedure terms. Scientific Reports (2026), doi:10.1038/s41598-025-34778-7.
Code and data for papers
- postsurgicalinfections: pretrained model and notebook for Prediction of postoperative infections by strategic data imputation and explainable machine learning, JAMIA (2025).
- microbialcomposition: the InSSIght dashboard notebook for exploring the microbiology of surgical-site infections.
- riboswitch2018: datasets for Classification of riboswitch sequences using k-mer frequencies, Biosystems (2018).
- imorns: supplementary material for Accurate classification of immunomodulatory RNA sequences, IJCNN (2017).
Earlier tools
- genehtracker: traces the GENCODE annotation history of Ensembl gene IDs and symbols, and maps retired IDs. Presented at ECCB 2022.
- refractiveindex.info-sqlite: an SQLite wrapper for the refractiveindex.info optical-constants database.
- ezTracks: plots a GTF annotation with grouped BED tracks.
- arff2pandas: loads ARFF files as pandas DataFrames.