missedSampleLib 0.0.2

missedSampleLib

This repository contains the Python-based machine learning model developed as part of the study titled: “Development and Validation of a CDS-Based Machine Learning Model for Accurate Detection of Misidentified Samples in Hospitalized Patients”. The model, built using the XGBoost algorithm, was trained on real-world clinical data from hospitalized patients to detect sample misidentification errors (MIS), including: • MIS cases: confirmed errors (25%) and randomly simulated sample reordering (25%) • Properly identified control samples (50%) This package was specifically designed for integration into a Clinical Decision Support System (CDS) to automate the detection of analytical inconsistencies and enhance patient safety in routine clinical workflows. Repository contents: • Trained model script (.py) • Brief documentation for implementation This file is part of the technical supplementary material associated with the manuscript, and is provided to support transparency, reproducibility, and practical deployment.