Stroke is a leading cause of death in the US, with more than 795,000 strokes resulting in more than 100,000 deaths each year. It is estimated that up to a third of the most common type of stroke are caused by LVO, when a clot blocks the circulation of the blood in the brain. Around 1 in 10 strokes are thought to be caused by ICH, or bleeding that occurs inside the skull.

Blackford Partner Avicenna.AI develops medical imaging AI solutions for pathologies with a high occurrence. Its FDA-cleared CINA Head triage AI solution uses a combination of deep learning and machine learning technologies to automatically detect and prioritize acute ICH and LVO cases within 20 seconds, seamlessly alerting the radiologist within their existing systems and workflow.

We spoke to Cyril Di Grandi, co-founder and CEO of Avicenna.AI to find out more.

Blackford: How did Avicenna.AI get started?

Cyril Di Grandi: I was looking for a new challenge after co-founding Olea Medical in 2008. The emergence of AI really resonated with me and I wanted to work on new AI applications that could save lives. Then I met with the radiologist and healthcare AI specialist Peter Chang at RSNA 2017 and he showed me his work in this area. We immediately realized we could create something useful together and officially started Avicenna two years ago.

Blackford: Tell us about your technology.

Cyril Di Grandi: We focus on developing AI applications that use CT scanner imaging – especially for emergency pathologies. We ultimately hope to build a full suite of products that can detect every life-threatening condition from head to toe. Our first application, CINA Head, targets the brain and starts with detection of ICH and LVO.

Blackford: How do you deliver clinical value to your customers?

Cyril Di Grandi: There are two key benefits of AI enabled diagnosis. First, in busy emergency rooms and stroke centers, our deep learning system is able to rapidly identify the key markers of stroke and alert a physician when a specific patient may need to be urgently evaluated. Second, in smaller community hospitals without 24-hour access to stroke experts, the AI system can be used to increase the confidence and objectivity of interpretation, and, if needed, identify patients whose care needs to be escalated to a dedicated stroke center.

Blackford: What sets you apart from everyone else?

Cyril Di Grandi: Peter Chang is both a radiologist and a recognized expert in deep learning, so his work has helped us develop high-performance AI algorithms that deliver results in critical environments. CINA’s ICH detection capability was validated using data from 814 cases conducted at more than 250 imaging centers across the United States, with 96% accuracy, 91.4% sensitivity and 97.5% specificity. The product’s LVO detection capability was validated based on 476 cases, with 97.7% accuracy 97.9% sensitivity and 97.6% specificity.

Blackford: Why partner with Blackford?

Cyril Di Grandi: Blackford has built a great reputation based on its curation of the best applications on the market, so partnering with the company is a great achievement for us. It is a recognition of the value of our technology and demonstrates our readiness to enter the competitive market.

Blackford: Tell us a fun fact about your company?

Cyril Di Grandi: In some ways it was harder for us to come up with a name for our company than to build an efficient algorithm! The name of the company is based on the great Persian doctor Ibn Sina (Avicenna) – though practising in medieval times, he is considered one of the founders of modern medicine.