AI-powered device delivers “amazing physiological information” to guide thrombectomy treatments

Hall Rice

The Clotild Smart Guidewire System (Sensome), which uses: artificial intelligence (AI) to provide real-time insights into clot composition shows promise in the first-in-human CLOT OUT study, according to Hal Rice (Gold Coast University Hospital, Southport, Australia). Rice discussed this new technology and the potential it offers in endovascular thrombectomy procedures using electrical impedance spectroscopy at LINNC Paris 2022 (May 30 – June 1, Paris, France).

The presenter began by noting that the first pass effect in this space is “very important”, increasing the likelihood of a thrombolysis in cerebral infarction (TICI) 3 score and a “great clinical outcome” for the patient. Rice noted that recent studies have also confirmed that the composition of the clot also has a significant impact on patient outcomes. For example, red blood cell-rich thrombi are more susceptible to distal embolization, while fibrin-rich and platelet-rich thrombi may be more difficult to remove, but also less likely to have distal embolization.

Moving on to discuss Clotild technology, Rice noted its unique, “very smart” microsensor, which is 2mm in size and takes impedance measurements that are sent via a Bluetooth transmitter to the Cloviz tablet, providing real-time insight into what’s going on. the clot looks like, and the length of the occlusion. This translates to the sensor providing higher impedance readings in red blood cell-rich clots and lower impedance readings for fibrin-rich clots, he added, reporting “really good differentiation” between the two.

Rice explained that thanks to the nine sensors on the device, arranged in three rows, it is also able to identify clots with a ‘mixed’ composition – which can have significant amounts of red blood cells, fibrin and platelets in their composition – whereby this is indicated. indicated by different impedance measurements between the different groups of sensors.

He then went on to state that the Clotild device uses a database centered around clots of known composition. This database has been used to train a machine learning model capable of recognizing different compounds, which can then predict composition in unknown clots, Rice reported. He also claimed that this use of electrical impedance spectroscopy provides a new means of characterizing occlusions in stroke, with the data demonstrating sustained coherence through ex vivoanimal and early human research to date.

The next part of Rice’s presentation focused on the CLOT OUT study, the first human study to evaluate the safety of the Clotild Smart Guidewire System. Training and validating the aforementioned prediction model through a database is also an important goal of CLOT OUT, he noted. The one-armed, multicentric study started at the end of 2021, is taking place in Australia and Europe and plans to enroll approximately 100 patients with acute ischemic stroke of M1 origin to collect a total of 60 blood clots. Providing a status update on CLOT OUT, Rice said the study has enrolled 11 patients to date with no observed device-related complications in these completed cases, and the inaugural meeting of the Data Safety Monitoring Board recently recommended continuation of the study.

Concluding his speech, Rice said this “exciting” technology is akin to other innovations in stroke care, such as robotics and the delivery of thrombolytics after thrombectomy. “In addition to what we see or feel on an angiogram in terms of resistance during a procedure, this wire means we’re also getting some amazing physiological information now,” he continued. “It also integrates very well into our current mechanical thrombectomy workflows, with very little delay for these time-critical procedures.” Here he reported that implementing the Clotild device adds less than five minutes to the overall thrombectomy workflow.

Rice also briefly hinted at future applications beyond clot composition and length, such as in vessel wall analysis to elucidate other important occlusion features such as smooth muscle content and cholesterol — potentially identifying clots that are actually intracranial atherosclerosis (ICAS) lesions, not thrombo- embolic occlusions.

“These parameters can really help guide the mechanical thrombectomy procedure and potentially increase the first-pass effect in the future,” he stated. “It’s early days, with 11 out of 100 patients enrolled, but the technology certainly shows promise.” The Clotild device and its potential have been well received at LINNC, with Jacques Moret (Bicêtre University Hospital, Paris, France) noting that it is a “fascinating” use of advanced technology that could help answer questions about what happens distally from it. a clot happens after its removal. This point was echoed by Vitor Pereira (St. Michael’s Hospital, Toronto, Canada), who added that the device has the potential to improve first-pass recanalization rates by “bringing personalized medicine to the world of thrombectomy.”

Presenting rice at LINNC Paris 2022

Leave a Comment

Your email address will not be published. Required fields are marked *