A Machine Learning Case Study for AI-empowered echocardiography of Intensive Care Unit Patients in low- and middle-income countries

TL;DR

This study demonstrates the development and validation of lightweight machine learning models for real-time echocardiography classification in ICU patients within low- and middle-income countries, highlighting challenges and future needs.

Contribution

It presents a case study on deploying thinner neural networks for echocardiography classification in resource-limited settings, including data curation, model validation, and deployment considerations.

Findings

Thinner neural networks can classify echocardiography views with limited data.

The models show promise for real-time clinical use in low-resource environments.

Further work is needed to improve dataset diversity and hardware implementation.

Abstract

We present a Machine Learning (ML) study case to illustrate the challenges of clinical translation for a real-time AI-empowered echocardiography system with data of ICU patients in LMICs. Such ML case study includes data preparation, curation and labelling from 2D Ultrasound videos of 31 ICU patients in LMICs and model selection, validation and deployment of three thinner neural networks to classify apical four-chamber view. Results of the ML heuristics showed the promising implementation, validation and application of thinner networks to classify 4CV with limited datasets. We conclude this work mentioning the need for (a) datasets to improve diversity of demographics, diseases, and (b) the need of further investigations of thinner models to be run and implemented in low-cost hardware to be clinically translated in the ICU in LMICs. The code and other resources to reproduce this work are available at https://github.com/vital-ultrasound/ai-assisted-echocardiography-for-low-resource-countries.