Detecting underlying paroxysmal atrial fibrillation for Zenicor
Detecting underlying paroxysmal atrial fibrillation in ECG
Together with Zenicor Medical Systems AB, we trained a deep learning model to predict an underlying paroxysmal atrial fibrillation (AF) condition in patients by using single-lead electrocardiogram (ECG) time series of the patients’ sinus ECG as input. The project was funded in part by Vinnova.
Zenicor has become one of the leading Medtech companies in Europe in the fields of early diagnosis of arrhythmias and stroke prevention for health care. They have developed a unique system, Zenicor-ECG, for the early detection and diagnosis of arrhythmias easily and cost-effectively. Zenicor’s products and solutions enable a simple and effective diagnosis of atrial fibrillation and other cardiac arrhythmias.
Every day, thousands of people suffer from stroke due to an underlying undiagnosed AF condition. Stroke often results in conditions such as paralysis or, in many cases, death. For this reason, a precise and early diagnosis of AF is an essential part of stroke prevention. Paroxysmal AF occurs when a rapid, erratic heart rate begins suddenly and then stops on its own within seven days. It is also known as intermittent AF and often lasts for less than 24 hours. In the early stages of patients with AF, AF sequences are short and sometimes hard to notice for the patient. As the disease progresses, sequences become longer and more frequent, thus gradually increasing the risk of stroke. Detecting AF in-sequence is not a difficult task since it comes out as clear patterns in an ECG. However, detecting patients with an underlying AF condition given an ECG that is not in an AF sequence is a much more challenging task.
Working together with the client and leading cardiologists at Karolinska Institutet as domain experts, the Modulai team tested different and modified versions of state-of-the-art CNN architectures for raw time series data. We were able to create a model to detect underlying AF in normal-looking ECGs.
To further gain insight into the model, explainability methods were employed to find out how the model was able to predict the condition.
Data were processed using various open-source libraries in Python. Model architectures were developed in TensorFlow and, the model was wrapped in a Flask API and dockerized.