FDA Clears Aidoc's AI Algorithm To Detect Brain Aneurysm

“In the US a brain aneurysm ruptures every 18 minutes. It’s an acute condition that can quickly turn fatal so time is of the essence."

Elad Walach, Co-founder and CEO, Aidoc

On April 6, 2022 Aidoc received its 9th FDA 510(k) clearance. This FDA-clearance was granted for Aidoc's AI algorithm for triage and notification of brain aneurysm. Aidoc's AI based decision support software analyzes medical imaging data, flags findings, and alerts radiologists, surgeons, and neurologists of suspected positive cases. In 2018 Aidoc was granted FDA clearance for an algorithm to flag acute intracranial hemorrhage in CT?scans, and in 2019 the company received FDA clearance for its?pulmonary embolism?system. Aidoc has also obtained?FDA clearance for algorithms to detect pneumothorax,?stroke, cervical fracture,?intra-abdominal free gas, and?incidental pulmonary embolism.

Aidoc was founded in 2016 and has raised over $140 million from investors including TLV Partners and Squarepeg Capital. The company's software is used in hospitals, level 1 trauma centers, and outpatient imaging centers. The following hospitals and imaging centers use Aidoc's algorithms: Montefiore Nyack Hospital,?Yale New Haven Hospital, Cedars-Sinai Medical Center,?University of Rochester Medical Center, Sheba Medical Center, and Antwerp University?Hospital.

Brain Aneurysms

Most brain aneurysms are very small - measuring 1/8 inch to one inch. Since they are difficult to detect, 25% of people with aneurysms are misdiagnosed. Ruptured brain aneurysms are fatal in about 50% of cases and 66% of survivors have permanent neurological damage. Intracranial hemorrhage is the most common sign of brain aneurysm and detecting it promptly is critical.

• An estimated 6.5 million people in the US have an brain aneurysm and 20% of people diagnosed with a brain aneurysm have more than one aneurysm.
• When brain aneurysms rupture there's a 50% chance of death
• There are almost 500,000 deaths worldwide each year caused by ruptured brain aneurysms, and half the victims are younger than 50.
• In one study in patients evaluated in a hospital ER for headaches, approximately 1 in 100 had a ruptured aneurysm. In another study the number was 4 in 100.
• Women are more likely than men to have a brain aneurysm (3:2 ratio).
• Women, particularly those over the age of 55, have a higher risk of brain aneurysm rupture than men (about 1.5 times the risk).
• African-Americans and Hispanics are about twice as likely to have a brain aneurysm rupture compared to whites.

* Source: Brain Aneurysm Foundation

Clinical Study Highlights

• A clinical study on the accuracy of deep?convolutional neural networks?for the detection of pulmonary embolism on CT pulmonary angiograms was performed by the University Hospital of Basel. The results, presented at the European Congress of Radiology, showed that the Aidoc algorithm reached 93% sensitivity and 95% specificity.
• Clinical research performed to test the diagnostic performance of Aidoc's deep learning-based triage system for the flagging of acute findings in abdominal CT scans achieved 93% sensitivity (91/98, 7 false-negative) and 97% specificity (93/96, 3 false-positive) in the detection of acute abdominal findings.
• Clinical research on Aidoc's Intracranial Hemorrhage algorithm accuracy was presented at the European Congress of Radiology by Antwerp University Hospital. The research evaluated the use of Aidoc's deep learning algorithm for the detection of intracranial hemorrhage on non-contrast enhanced?CT?of the?brain. The University of Washington also completed a study on the accuracy of Aidoc's intracranial hemorrhage algorithm.

Regulatory Clearances

Aidoc has multiple regulatory clearances. It's intracranial hemorrhage, vessel occlusion, pulmonary embolism and cervical-spine fracture algorithms are FDA (510k) cleared. Aidoc’s algorithm for notification and triage of incidental pulmonary embolisms and its free-air algorithm and rib fracture are available under investigational use in the US.

1. Intracranial Hemorrhage - 510(k) Triage and notification software indicated for use in the analysis of non-enhanced head CT images; flags and communicates suspected positive findings of pathologies in head CT images, namely Intracranial Hemorrhage.
2. Large Vessel Occlusions - 510(k) Triage and notification software indicated for use in the analysis of head CTA images; flags and communicates suspected positive findings of M1 Large Vessel Occlusion.
3. Acute C-Spine Fractures - 510(k) Triage and notification software indicated for use in the analysis of cervical spine CT images; flags and communicates suspected positive findings of linear lucencies in the cervical spine bone in patterns compatible with fractures.
4. Pulmonary Embolism - 510(k) Triage and notification software indicated for use in the analysis of CTPA images; flags and communicates Pulmonary Embolism.
5. Intra-Abdominal Free Gas - 510(k) Triage and notification software indicated for use in the analysis of abdomen CT images; flags and communicates suspected positive cases of Intra- Abdominal Free Gas.
6. Incidental PE - 510(k) Triage and notification software indicated for use in the analysis of CT images; flags and communicates incidental Pulmonary Embolism.
7. Rib Fractures - 510(k) Triage and notification software indicated for use in the analysis of chest CTs (with or without contrast); flags and communicates suspected cases of three or more acute Rib fracture pathologies.
8. Pneumothorax - 510(k) Pneumothorax triage and notification on x-ray.
9. Brain Aneurysm - 510(k) Brain Aneurysm triage and notification.

Subscribe, Comment, Join Group

I'm interested in your feedback - please leave your comments.

To subscribe to the AI in Healthcare Milestones newsletter please click here .

To join the AI in Healthcare Milestones Group please click here .

Copyright ? 2022 Margaretta Colangelo. All Rights Reserved.

This article was written by Margaretta Colangelo. Margaretta is a leading AI analyst who tracks significant milestones in AI in healthcare. She consults with AI healthcare companies and writes about some of the companies she consults with. Margaretta serves on the advisory board of the AI Precision Health Institute at the University of Hawai?i?Cancer Center @realmargaretta