De-biased Disentanglement Learning for Pulmonary Embolism Survival Prediction on Multimodal Data.

Health disparities among marginalized populations with lower socioeconomic status significantly impact the fairness and effectiveness of healthcare delivery. The increasing integration of artificial intelligence (AI) into healthcare presents an opportunity to address these inequalities, provided that AI models are free from bias. This paper aims to address the bias challenges by population disparities within healthcare systems, existing in the presentation of and development of algorithms, leading to inequitable medical implementation for conditions such as pulmonary embolism (PE) prognosis. In this study, we explore the diversity of biases in healthcare systems, which highlights the need for a holistic framework to reduce bias by complementary aggregation. By leveraging de-biasing deep survival prediction models, we propose a framework that disentangles identifiable information from images, text reports, and clinical variables to mitigate potential biases within multimodal datasets. Our study offers several advantages over traditional clinical-based survival prediction methods, including richer survival-related characteristics and bias-complementary predicted results. By improving the robustness of survival analysis through this framework, we aim to benefit patients, clinicians, and researchers by improving fairness and accuracy in healthcare AI systems. The code is available at https://github.com/zzs95/fairPE-SA.

Transcarotid Arterial Revascularization of Symptomatic Internal Carotid Artery Disease: A Systematic Review and Study-Level Meta-Analysis.

BACKGROUND: Transcarotid artery revascularization (TCAR) is an interventional therapy for symptomatic internal carotid artery disease. Currently, the utilization of TCAR is contentious due to limited evidence. In this study, we evaluate the safety and efficacy of TCAR in patients with symptomatic internal carotid artery disease compared with carotid endarterectomy (CEA) and carotid artery stenting (CAS). METHODS: A systematic review was conducted, spanning from January 2000 to February 2023, encompassing studies that used TCAR for the treatment of symptomatic internal carotid artery disease. The primary outcomes included a 30-day stroke or transient ischemic attack, myocardial infarction, and mortality. Secondary outcomes comprised cranial nerve injury and major bleeding. Pooled odds ratios (ORs) for each outcome were calculated to compare TCAR with CEA and CAS. Furthermore, subgroup analyses were performed based on age and degree of stenosis. In addition, a sensitivity analysis was conducted by excluding the vascular quality initiative registry population. RESULTS: A total of 7 studies involving 24 246 patients were analyzed. Within this patient cohort, 4771 individuals underwent TCAR, 12 350 underwent CEA, and 7125 patients underwent CAS. Compared with CAS, TCAR was associated with a similar rate of stroke or transient ischemic attack (OR, 0.77 [95% CI, 0.33-1.82]) and myocardial infarction (OR, 1.29 [95% CI, 0.83-2.01]) but lower mortality (OR, 0.42 [95% CI, 0.22-0.81]). Compared with CEA, TCAR was associated with a higher rate of stroke or transient ischemic attack (OR, 1.26 [95% CI, 1.03-1.54]) but similar rates of myocardial infarction (OR, 0.9 [95% CI, 0.64-1.38]) and mortality (OR, 1.35 [95% CI, 0.87-2.10]). CONCLUSIONS: Although CEA has traditionally been considered superior to stenting for symptomatic carotid stenosis, TCAR may have some advantages over CAS. Prospective randomized trials comparing the 3 modalities are needed.

FLAIR signal intensity ratio predicts small subcortical infarct early neurologic deterioration: a cross-sectional study.

PURPOSE: Prior studies have used the fluid-attenuated inversion recovery sequence signal intensity ratio (FLAIR-SIR) to predict those with an incomplete infarct that may safely receive acute thrombolytics. Clinical early neurologic deterioration (END) of small subcortical infarcts (SSIs) is suspected to occur due to delayed infarct completion. We aimed to understand if a lower FLAIR-SIR, suggestive of an incomplete infarct, would have a higher likelihood of SSI-related END. METHODS: A cross-sectional retrospective study was performed of those with an acute SSI (anterior or posterior circulation) without significant parent vessel steno-occlusive disease. END was defined as a new or worsened disabling neurologic deficit during the index hospitalization. Standard-of-care brain MRIs were reviewed from the hospitalization, and a FLAIR-SIR cutoff of ≤ 1.15 was used based on prior studies. Adjusted logistic regression models were used for analysis. RESULTS: We identified 252 patients meeting inclusion criteria: median (IQR) age 68 (12) years, 38.5% (97/252) female, and 11% (28/252) with END. Tobacco use was more common in those without END (32%) compared with END (55%, p = 0.03). In adjusted analyses, a FLAIR-SIR cutoff of ≤ 1.15 yielded an odds ratio of 2.8 (95% CI 1.23-6.13, p = 0.012) of early neurological deterioration. CONCLUSION: Those with a FLAIR-SIR ≤ 1.15 are nearly threefold more likely to develop SSI-related END.

Borderzone Infarcts and Recurrent Cerebrovascular Events in Symptomatic Intracranial Arterial Stenosis: A Systematic Review and Meta-Analysis.

BACKGROUND AND PURPOSE: Intracranial arterial stenosis (ICAS)-related stroke occurs due to three primary mechanisms with distinct infarct patterns: (1) borderzone infarcts (BZI) due to impaired distal perfusion, (2) territorial infarcts due to distal plaque/thrombus embolization, and (3) plaque progression occluding perforators. The objective of the systematic review is to determine whether BZI secondary to ICAS is associated with a higher risk of recurrent stroke or neurological deterioration. METHODS: As part of this registered systematic review (CRD42021265230), a comprehensive search was performed to identify relevant papers and conference abstracts (with ≥20 patients) reporting initial infarct patterns and recurrence rates in patients with symptomatic ICAS. Subgroup analyses were performed for studies including any BZI versus isolated BZI and those excluding posterior circulation stroke. The study outcome included neurological deterioration or recurrent stroke during follow-up. For all outcome events, corresponding risk ratios (RRs) and 95% confidence intervals (95% CI) were calculated. RESULTS: A literature search yielded 4,478 records with 32 selected during the title/abstract triage for full text; 11 met inclusion criteria and 8 studies were included in the analysis (n=1,219 patients; 341 with BZI). The meta-analysis demonstrated that the RR of outcome in the BZI group compared to the no BZI group was 2.10 (95% CI 1.52-2.90). Limiting the analysis to studies including any BZI, the RR was 2.10 (95% CI 1.38-3.18). For isolated BZI, RR was 2.59 (95% CI 1.24-5.41). RR was 2.96 (95% CI 1.71-5.12) for studies only including anterior circulation stroke patients. CONCLUSION: This systematic review and meta-analysis suggests that the presence of BZI secondary to ICAS may be an imaging biomarker that predicts neurological deterioration and/or stroke recurrence.

Pulmonary hypertension associated with cardiopulmonary bypass and cardiac surgery.

BACKGROUND AND AIM: Pulmonary hypertension (PH) is frequently associated with cardiovascular surgery and is a common complication that has been observed after surgery utilizing cardiopulmonary bypass (CPB). The purpose of this review is to explain the characteristics of PH, the mechanisms of PH induced by cardiac surgery and CPB, treatments for postoperative PH, and future directions in treating PH induced by cardiac surgery and CPB using up-to-date findings. METHODS: The PubMed database was utilized to find published articles. RESULTS: There are many mechanisms that contribute to PH after cardiac surgery and CPB which involve pulmonary vasomotor dysfunction, cyclooxygenase, the thromboxane A2 and prostacyclin pathway, the nitric oxide pathway, inflammation, and oxidative stress. Furthermore, there are several effective treatments for postoperative PH within different types of cardiac surgery. CONCLUSIONS: By possessing a deep understanding of the mechanisms that contribute to PH after cardiac surgery and CPB, researchers can develop treatments for clinicians to use which target the mechanisms of PH and ultimately reduce and/or eliminate postoperative PH. Additionally, learning about the most up-to-date studies regarding treatments can allow clinicians to choose the best treatments for patients who are undergoing cardiac surgery and CPB.