AI-powered BeatProfiler revolutionises heart research

A breakthrough in heart cell function analysis and drug testing


Researchers at Columbia Engineering have introduced BeatProfiler, a revolutionary software that leverages artificial intelligence (AI) to automate the analysis of heart cell function from video data. This transformative tool integrates the analysis of various heart function indicators, including contractility, calcium handling, and force output, into a single platform, significantly expediting the process and minimizing the margin for errors. Moreover, BeatProfiler not only facilitates the differentiation between different diseases and their severity levels but also enables the rapid and objective testing of drugs affecting heart function.

Dr. Gordana Vunjak-Novakovic, the project leader and University Professor at Columbia, expressed her enthusiasm, stating, "This is truly a transformative tool. It's fast, comprehensive, automated, and compatible with a broad range of computer platforms, making it easily accessible to investigators and clinicians."

In a bid to maximize the impact of their research, the team has opted to offer the AI software as open-source, allowing any lab to utilize it free of charge. This move is driven by the belief that widespread dissemination and user feedback from academic, clinical, and commercial labs will further refine the software, enhancing its utility in diverse research settings.

The genesis of this project lies in the urgent clinical need to swiftly and accurately diagnose heart diseases. Over several years, the team progressively incorporated different features to develop a tool that could capture the function of cardiac models, facilitating the study of cardiac diseases and the assessment of potential therapeutics. With the escalation of cardiac tissue capabilities through innovations such as milliPillar and multiorgan tissue models, the researchers recognized the necessity to rapidly quantify the function of cardiomyocytes and tissues to facilitate studies exploring genetic cardiomyopathies, cosmic radiation, immune-mediated inflammation, and drug discovery.

Lead author Youngbin Kim and his coauthors have played a pivotal role in the development of BeatProfiler. They have meticulously crafted a graphical user interface (GUI) to enable biomedical researchers with no coding expertise to analyze data effortlessly. This collaborative effort has brought together experts in software development, machine learning, signal processing, and engineering, culminating in the creation of a tool that surpasses existing methods by delivering analyses up to 50 times faster and with enhanced reliability. Kim emphasized, "This level of analysis speed and versatility is unprecedented in cardiac research. Using machine learning, the functional measurements analyzed by BeatProfiler helped us to distinguish between diseased and healthy heart cells with high accuracy and even to classify different cardiac drugs based on how they affect the heart."

The unveiling of BeatProfiler marks a pivotal moment in heart research, heralding a new era where AI and machine learning are leveraged to accelerate the pace of discovery and drive transformative advancements in the field of cardiology.

Join our WhatsApp Channel to get the latest news, exclusives and videos on WhatsApp