Il deep machine learning rivoluziona la valutazione dell’invecchiamento e delle malattie cardiache utilizzando i moscerini della frutta

A breakthrough from the University of Alabama at Birmingham, which uses deep learning to speed up the evaluation of cardiac health in fruit flies, could pave the way for new insights into human heart disease.

In an impressive leap forward for biomedical research, a team at the University of Alabama at Birmingham (UAB) has employed deep learning technology to transform how scientists study heart aging and disease using fruit flies, known scientifically as Drosophila. This technological advancement can significantly accelerate cardiac research and reduce human error, promising new frontiers in heart disease studies that could eventually benefit human health.

Fruit flies have long served as a reliable model for researching human cardiovascular diseases. However, measuring heart functions such as expansion and contraction traditionally required time-consuming human intervention. Led by Girish Melkani, an associate professor in the UAB Department of Pathology, Division of Molecular and Cellular Pathology, the UAB researchers have developed a method using deep learning and high-speed video microscopy to automate these measurements.

“Our machine learning method is not just fast; it minimizes human error because you don’t have to manually mark each heart wall under systolic and diastolic conditions,” Melkani said in a comunicato stampa. “Furthermore, you can run the analyses of several hundred hearts and look at the analyses when done for all the hearts.”

This approach unlocks the potential for more extensive testing on how various environmental and genetic factors influence heart aging and pathology. Potential models for future studies include zebrafish and mice, which, like fruit flies, are invaluable for cardiovascular research.

“Additionally, our techniques could be adapted for human heart models, providing valuable insights into cardiac health and disease,” Melkani added. “Moreover, the machine learning approach can predict cardiac aging with high accuracy.”

The UAB team’s research tested their model on both aging hearts and a fruit fly model of dilated cardiomyopathy, caused by the knockdown of a critical enzyme, oxoglutarate dehydrogenase. They trained their automated model using 54 hearts and validated it with an additional 177 hearts, successfully recreating expected cardiac aging trends.

Melkani highlighted that their model could be implemented with consumer-grade hardware. The analysis code generated by the team can compute a range of vital cardiac statistics, including diastolic and systolic diameters, fractional shortening, ejection fraction, heart rate and heartbeat arrhythmicity.

“To our knowledge, this innovative platform for deep learning-assisted segmentation is the first of its kind to be applied to standard high-resolution high-speed optical microscopy of Drosophila hearts while also quantifying all relevant parameters,” said Melkani.

This pioneering technique holds the promise of transforming how researchers study heart function in fruit flies and beyond.

“By automating the process and providing detailed cardiac statistics, we pave the way for more accurate, efficient and comprehensive studies of heart function in Drosophila. This method holds tremendous potential — not only for understanding aging and disease in fruit flies — but also for translating these insights into human cardiovascular research,” Melanie added.

L' studio, titled “Automated assessment of cardiac dynamics in aging and dilated cardiomyopathy Drosophila models using machine learning,” was published in Communications Biology.