Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 8, 2022The Journal of Heart and Lung TransplantationOpen Access

A novel interpretable machine learning model identified patients needing advanced heart failure therapies with an F1 score of 43.8%, recall of 51.1%, and precision of 46.9%.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Systems-level barriers limit access to advanced heart failure therapies, creating a need for automated systems to help clinicians evaluate patients at the appropriate time.

Does an interpretable machine learning model accurately identify potential candidates for advanced heart failure therapies in patients with heart failure?

Population

4,694 HF patients from the REVIVAL and INTERMACS registries

Comparison

Novel machine learning model vs other commonly used machine learning models

Design

Retrospective registry-based model development and validation study

Key result

A novel interpretable machine learning model identified patients needing advanced heart failure therapies with an F1 score of 43.8%, recall of 51.1%, and precision of 46.9%.

Authors

HYHeming YaoJGJessica R. GolbusJGJonathan Gryak

Discussion

Loading...

Member takes

Overview

Offers a proof-of-concept tool for predicting advanced HF therapy needs; leaves open whether prospective validation.

Study Design

Type

Observational (n=4,694)

Multicenter

Yes

Structured PICO

Does an interpretable machine learning model accurately identify potential candidates for advanced heart failure therapies in patients with heart failure?

P
Population
4,694 patients with heart failure from the REVIVAL and INTERMACS registries used to train and validate an interpretable machine learning model.
E
Exposure
Novel interpretable machine learning model based on principles of tropical geometry and fuzzy logic
C
Comparator
Other commonly used machine learning models
O
Outcome
Model performance (F1 score, recall, and precision) for identifying need for advanced therapies evaluations

A novel, interpretable machine learning model can identify heart failure patients who may need evaluation for advanced therapies while providing transparent clinical rules for clinicians.

Cite This Study

Yao et al. (2022) conducted an observational in Heart failure (n=4,694). Interpretable machine learning model based on tropical geometry and fuzzy logic vs. Other commonly used machine learning models was evaluated on F1 score for identifying need for advanced therapies. A novel interpretable machine learning model identified patients needing advanced heart failure therapies with an F1 score of 43.8%, recall of 51.1%, and precision of 46.9%.

synapsesocial.com/papers/6a8dce2ddafbba8333315b0fhttps://doi.org/10.1016/j.healun.2022.08.028
View Full Paper
Ask AI
Bookmark
Share