Establishing a carotid artery stenosis disease cohort for comparative effectiveness research using natural language processing

A comparative effectiveness study of carotid intervention for long-term stroke prevention in patients with severe asymptomatic stenosis from a large integrated health system

OBJECTIVE

The results of current prospective trials comparing the effectiveness of carotid endarterectomy (CEA) vs standard medical therapy for long-term stroke prevention in patients with asymptomatic carotid stenosis (ACS) will not be available for several years. In this study, we compared the observed effectiveness of CEA and standard medical therapy vs standard medical therapy alone to prevent ipsilateral stroke in a contemporary cohort of patients with ACS.

METHODS

This cohort study was conducted in a large integrated health system in adult subjects with 70% to 99% ACS (no neurologic symptom within 6 months) with no prior ipsilateral carotid artery intervention. Causal inference methods were used to emulate a conceptual randomized trial using data from January 1, 2008, through December 31, 2017, for comparing the event-free survival over 96 months between two treatment strategies: (1) CEA within 12 months from cohort entry vs (2) no CEA (standard medical therapy alone). To account for both baseline and time-dependent confounding, inverse probability weighting estimation was used to derive adjusted hazard ratios, and cumulative risk differences were assessed based on two logistic marginal structural models for counterfactual hazards. Propensity scores were data-adaptively estimated using super learning. The primary outcome was ipsilateral anterior ischemic stroke.

RESULTS

The cohort included 3824 eligible patients with ACS (mean age: 73.7 years, 57.9% male, 12.3% active smokers), of whom 1467 underwent CEA in the first year, whereas 2297 never underwent CEA. The median follow-up was 68 months. A total of 1760 participants (46%) died, 445 (12%) were lost to follow-up, and 158 (4%) experienced ipsilateral stroke. The cumulative risk differences for each year of follow-up showed a protective effect of CEA starting in year 2 (risk difference = 1.1%, 95% confidence interval: 0.5%-1.6%) and persisting to year 8 (2.6%, 95% confidence interval: 0.3%-4.8%) compared with patients not receiving CEA.

CONCLUSIONS

In this contemporary cohort study of patients with ACS using rigorous analytic methodology, CEA appears to have a small but statistically significant effect on stroke prevention out to 8 years. Further study is needed to appropriately select the subset of patients most likely to benefit from intervention.

Comprehensive Review of Natural Language Processing (NLP) in Vascular Surgery

Objective

The use of Natural Language Processing (NLP) has attracted increased interest in healthcare with various potential applications including identification and extraction of health information, development of chatbots and virtual assistants. The aim of this comprehensive literature review was to provide an overview of NLP applications in vascular surgery, identify current limitations, and discuss future perspectives in the field.

Data sources

The MEDLINE database was searched on April 2023.

Review methods

The database was searched using a combination of keywords to identify studies reporting the use of NLP and chatbots in three main vascular diseases. Keywords used included Natural Language Processing, chatbot, chatGPT, aortic disease, carotid, peripheral artery disease, vascular, and vascular surgery.

Results

Given the heterogeneity of study design, techniques, and aims, a comprehensive literature review was performed to provide an overview of NLP applications in vascular surgery. By enabling identification and extraction of information on patients with vascular diseases, such technology could help to analyse data from healthcare information systems to provide feedback on current practice and help in optimising patient care. In addition, chatbots and NLP driven techniques have the potential to be used as virtual assistants for both health professionals and patients.

Conclusion

While Artificial Intelligence and NLP technology could be used to enhance care for patients with vascular diseases, many challenges remain including the need to define guidelines and clear consensus on how to evaluate and validate these innovations before their implementation into clinical practice.

Natural History of Asymptomatic Moderate Carotid Artery Stenosis in a Large Community-Based Cohort

Background:

Moderate carotid artery stenosis is a poorly defined risk factor for ischemic stroke. As such, practice recommendations are lacking. In this study, we describe the long-term risk of stroke in patients with moderate asymptomatic stenosis in an integrated health care system.

Methods:

All adult patients with asymptomatic moderate (50%–69%) internal carotid artery stenosis between 2008 and 2012 were identified, with follow-up through 2017. The primary outcome was acute ischemic stroke attributed to the ipsilateral carotid artery. Stroke rates were calculated using competing risk analysis. Secondary outcomes included disease progression, ipsilateral intervention, and long-term survival.

Results:

Overall, 11 614 arteries with moderate stenosis in 9803 patients were identified. Mean age was 74.2±9.9 years with 51.4% women. Mean follow-up was 5.1±2.9 years. There were 180 ipsilateral ischemic strokes (1.6%) identified (crude annual risk, 0.31% [95% CI, 0.21%–0.41%]), of which thirty-one (17.2%) underwent subsequent intervention. Controlling for death and intervention as competing risks, the cumulative incidence of stroke was 1.2% (95% CI, 1.0%–1.4%) at 5 years and 2.0% (95% CI, 1.7%–2.4%) at 10 years. Of identified strokes, 50 (27.8%) arteries had progressed to severe stenosis or occlusion. During follow-up, there were 17 029 carotid studies performed in 5951 patients, revealing stenosis progression in 1674 (14.4%) arteries, including 1614 (13.9%) progressing to severe stenosis and 60 (0.5%) to occlusion. The mean time to stenosis progression was 2.6±2.1 years. Carotid intervention occurred in 708 arteries (6.1%). Of these, 66.1% (468/708) had progressed to severe stenosis. The overall mortality rate was 44.5%, with 10.5% of patients lost to follow-up.

Conclusions:

In this community-based sample of patients with asymptomatic moderate internal carotid artery stenosis followed for an average of 5 years, the cumulative incidence of stroke is low out to 10 years. Future research is needed to optimize management strategies for this population.

Incidence of Ischemic Stroke in Patients With Asymptomatic Severe Carotid Stenosis Without Surgical Intervention

IMPORTANCE

Optimal management of patients with asymptomatic severe carotid stenosis is uncertain, due to advances in medical care and a lack of contemporary data comparing medical and surgical treatment.

OBJECTIVE

To estimate stroke outcomes among patients with medically treated asymptomatic severe carotid stenosis who did not undergo surgical intervention.

DESIGN, SETTING, AND PARTICIPANTS

Retrospective cohort study that included 3737 adult participants with asymptomatic severe (70%-99%) carotid stenosis diagnosed between 2008 and 2012 and no prior intervention or ipsilateral neurologic event in the prior 6 months. Participants received follow-up through 2019, and all were members of an integrated US regional health system serving 4.5 million members.

EXPOSURES

Imaging diagnosis of asymptomatic carotid stenosis of 70% to 99%.

MAIN OUTCOMES AND MEASURES

Occurrence of ipsilateral carotid-related acute ischemic stroke. Censoring occurred with death, disenrollment, or ipsilateral intervention.

RESULTS

Among 94 822 patients with qualifying imaging studies, 4230 arteries in 3737 (mean age, 73.8 [SD 9.5 years]; 57.4% male) patients met selection criteria including 2539 arteries in 2314 patients who never received intervention. The mean follow-up in this cohort was 4.1 years (SD 3.6 years). Prior to any intervention, there were 133 ipsilateral strokes with a mean annual stroke rate of 0.9% (95% confidence interval [CI], 0.7%-1.2%). The Kaplan-Meier estimate of ipsilateral stroke by 5 years was 4.7% (95% CI, 3.9%-5.7%).

CONCLUSIONS AND RELEVANCE

In a community-based cohort of patients with asymptomatic severe carotid stenosis who did not undergo surgical intervention, the estimated rate of ipsilateral carotid-related acute ischemic stroke was 4.7% over 5 years. These findings may inform decision-making regarding surgical and medical treatment for patients with asymptomatic severe carotid artery stenosis.