The Fast and the Furiously Accurate

By: The Zebra-Med Product Team

Gandhi_smiling_R

“There is more to life than simply increasing its speed.” – Mahatma Gandhi
“Increasing speed can lead to more life” – Zebra Medical Vision

We at Zebra Medical Vision are constantly thinking about ways AI can have a real impact on patient care. To achieve this, it is important to strike a delicate balance with physicians, finding the path where their work can be augmented through the use of our products. One such way is by focusing on acute conditions that, when left undiagnosed can get progressively worse and increasingly dangerous for the patient. Currently, such cases suffer from the inherent “fairness” of the “first in, first out” workflow of radiology departments. To these patients, waiting in line with all the other exams means a greater price in terms of their health. To us, this problem represents a real opportunity for our AI to make a difference and save lives. With this in mind, we set out to develop a suite of triage-focused products. This week we are introducing the first multi-modality AI triage solution to address two life-threatening conditions – intracranial hemorrhage (or brain-bleed), and pneumothorax.

pneumotorax_with-1.png

Pneumothorax, the presence of gas within the pleural space between the lung and the chest wall, is generally diagnosed by a radiologist from a chest x-ray exam. In many healthcare systems in the world, chest x-ray exams can wait a significant amount of time before they are read by radiologists. When the diagnosis is delayed, and without prompt management, pneumothorax can lead to total lung collapse and other potentially fatal complications. With an estimated incidence rate of 18-28 cases per 100,000 population, there are between 130,000 – 207,000 cases of pneumothorax in Europe every year. Misdiagnosis or late-diagnosis of Pneumothorax impacts around 74,000 americans per year.

Screen Shot 2019-02-26 at 11.49.24.png

Brain bleed is a devastating condition impacting almost 3.6 million Americans each year. Someone experiences a stroke or traumatic brain injury every 9 seconds, and diagnostic brain scans (head CTs) can cost $150,000 per patient. The high 30-day mortality rate ranges from 35% to 52% and about 50% of this mortality occur within the first 24 hours, emphasizing the importance of early detection and effective treatment in the Emergency Department.

Our acute-insights triage system we announce today is the first multi-modality AI triage system in the market. Our system integrates into the existing workflow, sending out a message when it detects a suspected acute finding. This message can then inform the caregiver by upgrading the priority of the suspected cases in the worklist, reducing the time to diagnosis by 80%, and thereby increasing the likelihood of timely treatment.

 

pneu_worklist.png

 

We are already implementing these systems in Israeli healthcare systems and abroad, and are humbled and excited at the opportunity to contribute to improved clinical care. “In a clinical validation study we performed, Zebra-med’s acute CXR pneumothorax and CT Brain bleed products demonstrated a promising potential to substantially reduce turn around time and increase the radiologist’s confidence in making these diagnoses” said Dr. Terry Matalon, MD, FACR, FSIR Chairman, Diagnostic Radiology at Albert Einstein Medical Center. “Seeing the software in action emphasized key aspects AI solutions must address in order to impact our field. High accuracy, speed, seamless integration and the ability to work on multi-modalities – both X-ray and CT”

The two solutions (pneumothorax and brain bleed) are CE cleared and pending FDA 510(K) clearance (not yet available for sale in the US).

The Zebra-Med Product Team

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s