Toolkit for evaluating and monitoring AI models in clinical settings
-
Updated
Jun 19, 2024 - Python
Toolkit for evaluating and monitoring AI models in clinical settings
🧪Yet Another ICU Benchmark: a holistic framework for the standardization of clinical prediction model experiments. Provide custom datasets, cohorts, prediction tasks, endpoints, preprocessing, and models. Paper: https://arxiv.org/abs/2306.05109
MIMIC Code Repository: Code shared by the research community for the MIMIC family of databases
Small footprint info panel that listens, talks and shows useful info on an e-Paper display. 100% local speech transcription and generation.
OMOP standardization pipeline for ICU databases
Companion code repository to Marcou et al. 2024, Creating a computer assisted ICD coding system: Performance metric choice and use of the ICD hierarchy
MIMIC III Corpus Parsing
[arXiv'24] The official implementation code of LEADER.
MIMIC-III corpus parsing and section prediction with MedSecId (COLING paper)
Used MIMIC III database, an Open Data Kit (ODK), and hospital admissions data from the UK.gov HES data. Various investigations as per hospital requirements have been done, including ICU and hospital LOS investigations for patients with cardiac devices.
📄 Preprint submitted to Artificial Intelligence in Medicine 🏥 - "MediCARE: Medical Collaborative Agents REasoning over Interpretable Heterogeneous Graphs" 💊📊 - University of Naples "Federico II" 🎓
Provenience of discharge summaries Pythonic access (BioNLP paper)
🔎 DSML researcher : Detection of medical biomarkers affecting mortality in patients with intensive care unit EMR pneumonia
Mapping the MIMIC-III database to the OMOP schema
KDD'23 | MedLink: De-Identified Patient Health Record Linkage
Master's thesis work aims to develop a tool for the analysis and prediction of data from the MIMIC-III database, using sepsis as a case study. Two specific prediction tasks have been selected: sepsis mortality and mortality within 30 days of sepsis diagnosis.
Established ML benchmark for 48-mortality prediction using MIMIC-III data and the FIDDLE Preprocessing Technique
A program to create RDF and RDF* knowledge graphs from the clinical database MIMIC-III, where a hospital layout has been created and patients move within the hospital.
Repository for the Paper: „On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series“
Add a description, image, and links to the mimic-iii topic page so that developers can more easily learn about it.
To associate your repository with the mimic-iii topic, visit your repo's landing page and select "manage topics."