Robotically assisted transcranial Doppler with artificial intelligence for assessment of cerebral vasospasm after subarachnoid hemorrhage

Esmaeeli, Shooka; Hrdlicka, Courtney M.; Bastos, Andres Brenes; Wang, Jeffrey; Gomez-Paz, Santiago; Hanafy, Khalid A.; Lioutas, Vasileios‐Arsenios; Ogilvy, Christopher S.; Thomas, Ajith J.; Shaefi, Shahzad; Fehnel, Corey R.; Nozari, Ala

doi:10.18700/jnc.200002

Cited by 15 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…14 This case study found that the MCA mCBFV insonated by NovaGuide were comparable to those measured via an expert; in the evaluation of a patient with angiographically-confirmed vasospasm (concordance correlation coefficient, 0.83; 95% CI, 0.42-0.96; p=0.001). 13 This work is an important compliment to this study, showing equivalence in a pathological population.…”

Section: Discussionsupporting

confidence: 59%

“…4 Recent work has been done to present and evaluate possible solutions to these limitations of TCD, ranging from semi-autonomous insonation of healthy control subjects to fully-autonomous evaluation and indication of angiographic vasospasm after SAH. 12,13 For TCD to become more widely utilized, the limitations of both operation and analysis must be addressed. Here we sought to evaluate the performance of a novel, fully autonomous robotic TCD (rTCD) system, NovaGuide (NovaSignal Corp., Los Angeles, CA, USA).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Automated Transcranial Doppler Ultrasound for Middle Cerebral Artery Insonation

O’Brien¹,

Dorn²,

Ranjbaran³

et al. 2022

J Neurosonol Neuroimag

View full text Add to dashboard Cite

Background: Transcranial Doppler ultrasound (TCD) is utilized in the assessment of neurological conditions in clinical environments such as the intensive care unit and emergency department. However, obstacles for widespread use of TCD include a lack of trained registered vascular technologists (RVT) and operator variability. We present a study comparing RVT and a fully automated robotic TCD system (NovaGuide rTCD) for insonation of the middle cerebral artery (MCA).Methods: A trained RVT and rTCD sequentially collected bilateral MCA cerebral blood flow velocity (CBFV) from 86 healthy subjects. Mean CBFV (mCBFV) and the signal quality assessment (SQA) acquired manually by RVT and autonomously via rTCD were compared. Comparison metrics evaluated include mean accuracy ratio (MAR), and Bland-Altman mean-difference (MD) between rTCD and RVT with paired t-Test for significance. Bootstrapping was used in the accuracy ratio and mean-time to best signal computations to establish 95% confidence intervals.Results: The mCBFVs and SQAs found by rTCD compared to RVT had MAR of 99.7% (97.7-101.7%) and 102.7% (101.1-104.8%), respectively. The rTCD mean-time to best-quality signal was 0.87 min (0.71-1.05) (RVT was not timed). The mean-difference scores for mCBFV and SQA were MD=-0.43cm/s (<i>p</i>=0.053) and MD=-0.36 (<i>p</i>=0.61), respectively. The rTCD had a 3.5% no-window failure rate compared to RVT no-window rate of 4.1%.Conclusion: Comparison of bilateral TCD signals collected by rTCD and RVT demonstrated equivalence in mCBFV and signal quality, suggesting rTCD’s potential to expand utility of TCD in clinical settings that are resource-limited.

show abstract

Section: Discussionsupporting

confidence: 59%

Section: Introductionmentioning

confidence: 99%

Fully Automated Transcranial Doppler Ultrasound for Middle Cerebral Artery Insonation

O’Brien¹,

Dorn²,

Ranjbaran³

et al. 2022

J Neurosonol Neuroimag

View full text Add to dashboard Cite

show abstract

“…Interestingly, when we applied the mean CBFv threshold for mild vasospasm to the maximum CBFv (Max CBFv ≥ 120 cm/s) from the NovaGuide data we obtained a performance comparable to previous publications. A meta-analysis of 26 studies comparing TCD against angiography found that utilizing the criteria of mean CBFv > 120 cm/s TCD had a sensitivity of 67% (48–87%), specificity of 99% (99–100%), positive predictive value of 97% (95–98%), negative predictive value of 78% (65–91%), positive likelihood ratio of 17 (5–56) ,and negative likelihood ratio of 0.4 (0.2–0.7) 14 . Our metrics of sensitivity (83%), negative predictive value (90%), and positive likelihood ratio (8.75) are contained within these reported ranges.…”

Section: Discussionmentioning

confidence: 99%

“…This ensures the acquired velocities are representative of the current flow dynamics of the MCA. While the MCAs are the only vessel the robotic TCD will autonomously locate and measure, the internal carotid artery terminus anterior cerebral arteries, and posterior cerebral arteries, can be measured manually 14 .…”

Section: Methodsmentioning

confidence: 99%

Safety and efficacy of a novel robotic transcranial doppler system in subarachnoid hemorrhage

Clare

Stein

Damodara

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Delayed cerebral ischemia (DCI) secondary to vasospasm is a determinate of outcomes following non-traumatic subarachnoid hemorrhage (SAH). SAH patients are monitored using transcranial doppler (TCD) to measure cerebral blood flow velocities (CBFv). However, the accuracy and precision of manually acquired TCD can be operator dependent. The NovaGuide robotic TCD system attempts to standardize acquisition. This investigation evaluated the safety and efficacy of the NovaGuide system in SAH patients in a Neuro ICU. We retrospectively identified 48 NovaGuide scans conducted on SAH patients. Mean and maximum middle cerebral artery (MCA) CBFv were obtained from the NovaGuide and the level of agreement between CBFv and computed tomography angiography (CTA) for vasospasm was determined. Safety of NovaGuide acquisition of CBFv was evaluated based on number of complications with central venous lines (CVL) and external ventricular drains (EVD). There was significant agreement between the NovaGuide and CTA (Cohen’s Kappa = 0.74) when maximum MCA CBFv ≥ 120 cm/s was the threshold for vasospasm. 27/48 scans were carried out with CVLs and EVDs present without negative outcomes. The lack of adverse events associated with EVDs/CVLs and the strong congruence between maximal MCA CBFv and CTA illustrates the diagnostic utility of the NovaGuide.

show abstract

“…The incidences of morbidity and mortality due to vasospasm are both around 20% [ 8 , 9 ]. Vasospasm can be diagnosed by transcranial Doppler (TCD) ultrasonography and transcranial color-coded Doppler (TCCD) ultrasonography, albeit with limited accuracy [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

Vasospasm-Related Death after Aneurysmal Subarachnoid Hemorrhage: A Retrospective Case–Control Study

Khanafer

Bhogal

Hellstern

et al. 2022

JCM

View full text Add to dashboard Cite

Background: Vasospasm after the rupture of an intracranial aneurysm is a frequent phenomenon and is the main cause of morbidity and mortality in patients who have survived intracranial hemorrhage and aneurysm treatment. We analyzed the diagnosis and management of patients with aneurysmal subarachnoid hemorrhage who eventually died from ischemic brain damage due to vasospasm. Methods: Between January 2007 and December 2021 (15 years), a total of 1064 patients were diagnosed with an aneurysmal intracranial hemorrhage in a single comprehensive neurovascular center. Vasospasm was diagnosed in 408 patients (38.4%). A total of 187 patients (17.6%) died within 90 days of the aneurysm rupture. In 64 of these 187 patients (33.7%), vasospasm was considered to be the cause of death. In a retrospective analysis, demographic and clinical data for patients without, with non-fatal, and with fatal vasospasm were compared. The patients with fatal vasospasm were categorized into the following subgroups: “no diagnosis and treatment” (Group a), “delayed diagnosis” (Group b), “cardiovascular complications” (Group c), and “vasospasm-treatment complications” (Group d). Results: Among the patients with fatal vasospasm, 31 (48.4%) were assigned to group a, 26 (40.6%) to group b, seven (10.9%) to group c, and none (0%) to group d. Conclusion: The early recognition of severe posthemorrhagic vasospasm is a prerequisite for any treatment and requires routine diagnostic imaging in all unconscious patients. Aggressive endovascular vasospasm treatment may fail to prevent death but is infrequently the cause of a fatal outcome.

show abstract

Robotically assisted transcranial Doppler with artificial intelligence for assessment of cerebral vasospasm after subarachnoid hemorrhage

Cited by 15 publications

References 23 publications

Fully Automated Transcranial Doppler Ultrasound for Middle Cerebral Artery Insonation

Fully Automated Transcranial Doppler Ultrasound for Middle Cerebral Artery Insonation

Safety and efficacy of a novel robotic transcranial doppler system in subarachnoid hemorrhage

Vasospasm-Related Death after Aneurysmal Subarachnoid Hemorrhage: A Retrospective Case–Control Study

Contact Info

Product

Resources

About