Completed phase one of NODE.Health’s validation process for an e-consent platform. The solution is a software platform that improves pre-and post-care education by using high-quality medical animations to explain treatment options, a survey to test for comprehension, and a video-based informed consent process to capture the doctor-patient conversation.

The platform will support patients in receiving the information they require prior to their respective procedures, especially those who are not able to attend multiple appointments due to social constraints.

Low-Cost Cardiac Output Monitor

Provided phase two support for a cardiac output monitoring tool, which is easier to operate and more cost-effective compared to current offerings in the market. This tool, which has been FDA approved, will enable patients to understand their cardiac issues in a more accurate manner, while reducing their long-term spending.

Neural Network Development for ECGs

Provided third phase support to help validate a new artificial intelligence platform called a ‘convolution neural network classifier’. The study evaluated the platform’s performance on various arrhythmias diagnosed on 12-lead ECGs and single-lead Holter monitors. The solution focused on identifying the correct arrhythmia at the time of a significant clinical event, including a cardiac arrest.

This tool aims to automate accurate ECG readings, especially among more sinister arrhythmias, to aid clinicians in their workup of patients lacking access to modern healthcare services. 


AI CT Imaging

Provided phase one support for an artificial intelligence application related to non-contrast head/brain CT imaging for patients with head trauma or stroke symptoms. The technology provides a triage aid to prioritize and notify critical head CT scans, a TBI progress monitoring tool, and a reporting assistance mode that pre-populates radiologist templates. NODE.Health evaluated the critical end-points that should be prioritized as part of a validation effort.

This application can aid clinicians in rural and non-academic settings to better diagnose different types of head injuries. Using AI, the software can detect changes in radiological images to quicken the diagnostic process in patients with head injuries, which allows for treatment to begin sooner.