This week, our BEATNET team dedicated efforts to building a solid foundation for our ECG deep learning project. We dived into the required documentation, mapping out the project’s scope, stakeholders, and benefits, while drafting weekly status reports and project diagrams to guide our process. A key focus was clarifying our data situation through a detailed session with our company liaison. We learned that Aventusoft’s proprietary ECG data is largely unlabeled, with annotations and clinical info available for only a fraction of patients—and with columns varying across different datasets. Most of the annotated data supports seismocardiogram (SCG) research rather than the ECG deep learning tasks we’re pursuing.
Given these findings, our immediate priorities are twofold: designing robust ECG landmark detection algorithms resilient to noise and diverse conditions, and developing models to identify arrhythmias and conduction abnormalities. To accomplish this, we’ll use well-annotated public datasets like PTB-XL and MIT-BIH as our starting point. Next week, we’ll shift into hands-on exploration of these public datasets, refining our preprocessing pipelines, and aligning our workflow with industry best practices. With the planning phase wrapping up, we’re eager to start coding and build out the core baseline models for BEATNET.
This week, our team officially kicked off Project BEATNET with a meeting attended by Aventusoft’s liaisons, Dr. Keider Hoyos and Dr. Diego Pava, along with our faculty advisor, Prof. Kejun Huang. The meeting established the foundation for our collaboration by clearly defining the project’s objectives and expectations. Aventusoft highlighted three key focus areas for our work: landmark detection, disease state classification, and system deployment. Our task is to develop AI models that can accurately identify PQRS-T waveforms in both normal and abnormal ECG signals, as well as classify various conditions, including arrhythmias, conduction abnormalities, pacemaker types, and signs of electrolyte imbalance. A distinctive feature of the project is to create both comprehensive models for cloud-based inference and streamlined models optimized for mobile device performance.
At the beginning of the meeting, the liaisons highlighted the importance of data. Ultimately, we will receive single-lead, 30-second ECG recordings in periodic batches, provided in MATLAB or NumPy formats, along with limited demographic details. Meanwhile, our team is expected to actively search for and use publicly available datasets, such as those from PhysioNet and MIT-BIH, to start initial model development while Aventusoft finalizes data sharing agreements. We are fully responsible for cleaning and preprocessing all the data.
From a technical standpoint, Aventusoft instructed us to use Python as our main programming language and PyTorch for all deep learning tasks, explicitly advising against TensorFlow due to previous compatibility issues. Our approach will begin with an extensive review of the latest research on single-lead, short-duration ECG analysis, adapting and fine-tuning existing models to fit the specific requirements of our project. We are also encouraged to apply semi-supervised learning methods to utilize unlabeled data for improved results.
A particularly important topic discussed was documentation. Aventusoft requires FDA-style documentation from all team members, including specifications of requirements, descriptions of system and algorithm designs, risk assessments, and verification and validation procedures. They emphasized that the quality of documentation is just as critical as the quality of the code for the project’s success and regulatory compliance.
Looking ahead, the immediate priorities for the upcoming week are to identify and evaluate suitable public ECG datasets, start an in-depth literature review of methodologies relevant to our project, brainstorm and document preprocessing strategies, and thoughtfully assign sub-tasks among team members. With clear direction from our liaisons and defined next steps, our team is excited to move from the planning phase into concrete research and development. We look forward to sharing our progress in the coming weeks!
Hello everyone, welcome to our team’s blog! We are excited to collaborate with Aventusoft on the ECG Deep Learning project, which sits at the crossroads of artificial intelligence and healthcare technology. Our main goal is to create deep learning algorithms that can precisely analyze electrocardiogram (ECG) data, focusing on detecting key landmarks, classifying diseases, and deploying solutions on both cloud and mobile platforms. This groundbreaking work aims to enhance digital health tools and aid in the early detection and diagnosis of heart conditions like heart failure.
This week, we focused on understanding the project’s scope by carefully reviewing Aventusoft’s Statement of Work (SOW). The SOW highlights our objectives: building highly accurate models to identify important landmarks across different ECG patterns and developing strong disease classification algorithms. These models will be deployed as efficient cloud services and lightweight mobile apps, all while complying with FDA design control documentation standards to prepare for future regulatory approval.
To get ready technically, we held internal discussions with Professor Kejun Huang. Looking ahead, our next step is to have our first meeting with Aventusoft’s liaison engineers. This meeting will be essential to clarify details about dataset access, structure, and project priorities. We also plan to finalize our choice of software tools and create a detailed checklist of dataset requirements. Meanwhile, we will begin outlining our data preprocessing strategy and continue refining the framework for FDA-required documentation. Additionally, we are working on scheduling regular weekly meetings with our industry mentors to maintain smooth communication throughout the project.
At this point, our team is on track and motivated, with clear next steps outlined. Once we receive the ECG dataset and detailed project guidance from Aventusoft, we will proceed with data processing and developing baseline models. We look forward to sharing updates as we advance in this important project!
