medical-7

Patient Phenotyping

3260 papers • 126 benchmarks • 313 datasets

Classifying patients after 24h regarding their admission diagnosis, using the APACHE group II and IV labels.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in patient-phenotyping-7

Trend

Dataset

Best Model

Actions

HiRID

Libraries

i

Use these libraries to find patient-phenotyping-7 models and implementations

Datasets

HiRID

Subtasks

No subtasks available.

Most implemented papers

Benchmarking machine learning models on multi-centre eICU critical care dataset

Seyedmostafa Sheikhalishahi, Vevake Balaraman, V. Osmani•Tue Oct 01 2019

This is the first public benchmark on a multi-centre critical care dataset, comparing the performance of clinical gold standard with the authors' predictive model and investigating the impact of numerical variables as well as handling of categorical variables on each of the defined tasks.

87

Content

0

Paper Graph

Visualization of Emergency Department Clinical Data for Interpretable Patient Phenotyping

N. Hurley, B. Mortazavi, A. Haimovich, R. A. Taylor•Thu Jul 04 2019

This work uses the newly-described non-linear embedding technique called uniform manifold approximation and projection (UMAP) to identify clusters in the embedded data and uses the adjusted Rand index to establish stability in the discovery of these clusters, describing the emergent properties of discovered clusters.

8 0

Paper Graph

Temporal Phenotyping using Deep Predictive Clustering of Disease Progression

M. Schaar, Changhee Lee•Sun Jun 14 2020

A deep learning approach for clustering time-series data, where each cluster comprises patients who share similar future outcomes of interest (e.g., adverse events, the onset of comorbidities).

65 0

Paper Graph

A methodology based on Trace-based clustering for patient phenotyping

Antonio Lopez-Martinez-Carrasco, J. Juarez, M. Campos, Bernardo Cánovas-Segura•Sun Oct 31 2021

A new unsupervised machine learning technique, denominated as Trace-based clustering, and a 5-step methodology in order to support clinicians when identifying patient phenotypes are proposed, showing that the proposed methodology allows physicians to identify consistent patient phenotype.

13 0

Paper Graph

Adding a benchmark result helps the community track progress.