A collaborative team from the University of California, San Diego, and Stanford University has unveiled a groundbreaking noninvasive approach to monitor electrical activity inside heart muscle cells without penetrating them. This innovation, powered by artificial intelligence, offers a safer and more efficient way to study cardiac functions and test drugs.
As reported by economictimes, the method involves correlating extracellular signals—captured from the cell’s surface—with intracellular signals, which provide detailed insights into cellular activity. “Extracellular signals are like hearing a conversation through a wall, while intracellular signals are akin to being in the room,” explained Professor Zeinab Jahed, a senior author of the study. The research team developed a deep learning model that reconstructs intracellular signals with high accuracy using extracellular data.
To achieve this, researchers engineered an array of nanoscale, platinum-coated silica electrodes, each 200 times smaller than a heart muscle cell. Heart cells derived from stem cells were cultured on this electrode array, generating a large dataset of extracellular-intracellular signal pairs, including responses to various drugs. This data enabled the AI model to predict intracellular activity solely from extracellular recordings.
The innovation holds significant potential for drug development, particularly in cardiotoxicity testing, where detailed intracellular data is crucial. “This method allows us to screen drugs on human heart cells directly, offering a more accurate and cost-effective alternative to traditional animal models,” said Jahed. The approach could also pave the way for personalized medicine, enabling drugs to be tested on patient-specific cells.
While the study focused on heart cells, researchers aim to expand the method to other cell types, including neurons, to better understand cellular activity across different tissues. This breakthrough promises to revolutionize how we study cell behavior and develop new treatments.