arXiv subjects

Davide Chicco

Publications and source records attributed to Davide Chicco.

4 recordsLinked to original sources

arXiv2026

An unsupervised clustering analysis of breast cancer data derived from electronic health records enhanced through UMAP dimensionality reduction

Breast cancer is one of the most widespread types of cancer, affecting approximately 8 million women worldwide. Electronic health records of patients diagnosed with this disease can serve as valuable datasets for computational analyses, enabling the discovery of new insights about the pathology. Unsupervised clustering, in particular, can identify groups of patients with medically significant features, revealing data trends that might otherwise go unnoticed by medical doctors. In this study, we first applied the DBSCAN density-based clustering method to three independent datasets derived from electronic medical records of patients with mammary carcinoma. Subsequently, to enhance our results, we preceded the DBSCAN application with a dimensionality reduction phase using UMAP. We evaluated our clustering outcomes using three statistical indices (DBCV, DCSI, and DISCO). Our results confirm the effectiveness of combining UMAP with DBSCAN for clustering data derived from electronic health records, paving the way for the medical interpretation of the patient groups identified by our approach.

cs.LG↗

arXiv2024

Interactive Classification Metrics: A graphical application to build robust intuition for classification model evaluation

Machine learning continues to grow in popularity in academia, in industry, and is increasingly used in other fields. However, most of the common metrics used to evaluate even simple binary classification models have shortcomings that are neither immediately obvious nor consistently taught to practitioners. Here we present Interactive Classification Metrics (ICM), an application to visualize and explore the relationships between different evaluation metrics. The user changes the distribution statistics and explores corresponding changes across a suite of evaluation metrics. The interactive, graphical nature of this tool emphasizes the tradeoffs of each metric without the overhead of data wrangling and model training. The goals of this application are: (1) to aid practitioners in the ever-expanding machine learning field to choose the most appropriate evaluation metrics for their classification problem; (2) to promote careful attention to interpretation that is required even in the simplest scenarios like binary classification. Our application is publicly available for free under the MIT license as a Python package on PyPI at https://pypi.org/project/interactive-classification-metrics and on GitHub at https://github.com/davhbrown/interactive_classification_metrics.

cs.LG↗

arXiv2024

EHRs Data Harmonization Platform, an easy-to-use shiny app based on recodeflow for harmonizing and deriving clinical features

Electronic health records (EHRs) contain important longitudinal information on individuals who have received medical care. Traditionally, EHRs have been used to support a wide range of administrative activities such as billing and clinical workflow, but, given the depth and breadth of clinical and demographic data they contain, they are increasingly being used to provide real-world data for research. Although EHR data have enormous research potential, the full realization of that potential requires a data management strategy that extracts from large EHR databases, that are collected from a range of care settings and time periods, well-documented research-relevant data that can be used by different researchers. Having a common well-documented data management strategy for EHR will support reproducible research and sharing documentation on research variables that are derived from EHR variables is important to open science. In this short paper, we describe the EHRs Data Harmonization Platform. The platform is based on an easy to use web app a publicly available at https://poxotn-arian-aminoleslami.shinyapps.io/Arian/ and as a standalone software package at https://github.com/ArianAminoleslami/EHRs-Data Harmonization-Platform, that is linked to an existing R library for data harmonization called recodeflow. The platform can be used to extract, document, and harmonize variables from EHR and it can also be used to document and share research variables that have been derived from those EHR data.

cs.DB↗

arXiv2020

The MCC-F1 curve: a performance evaluation technique for binary classification

Many fields use the ROC curve and the PR curve as standard evaluations of binary classification methods. Analysis of ROC and PR, however, often gives misleading and inflated performance evaluations, especially with an imbalanced ground truth. Here, we demonstrate the problems with ROC and PR analysis through simulations, and propose the MCC-F1 curve to address these drawbacks. The MCC-F1 curve combines two informative single-threshold metrics, MCC and the F1 score. The MCC-F1 curve more clearly differentiates good and bad classifiers, even with imbalanced ground truths. We also introduce the MCC-F1 metric, which provides a single value that integrates many aspects of classifier performance across the whole range of classification thresholds. Finally, we provide an R package that plots MCC-F1 curves and calculates related metrics.

stat.ML↗