Machine Learning Modeling to Predict Atrial Fibrillation Detection in Embolic Stroke of Undetermined Source Patients.

BACKGROUND: In patients with embolic stroke of undetermined source (ESUS), occult atrial fibrillation (AF) has been implicated as a key source of cardioembolism. However, only a minority acquire implantable cardiac loop recorders (ILRs) to detect occult paroxysmal AF, partly due to financial cost and procedural inconvenience. Without the initiation of appropriate anticoagulation, these patients are at risk of increased ischemic stroke recurrence. Hence, cost-effective and accurate methods of predicting AF in ESUS patients are highly sought after. OBJECTIVE: We aimed to incorporate clinical and echocardiography data into machine learning (ML) algorithms for AF prediction on ILRs in ESUS. METHODS: This was a single-center cohort study that included 157 consecutive patients diagnosed with ESUS from October 2014 to October 2017 who had ILR evaluation. We developed four ML models, with hyperparameters tuned, to predict AF detection on an ILR. RESULTS: The median age of the cohort was 67 (IQR 59-74) years old and the median monitoring duration was 1051 (IQR 478-1287) days. Of the 157 patients, 32 (20.4%) had occult AF detected on the ILR. Support vector machine predicted for AF with a 95% confidence interval area under the receiver operating characteristic curve (AUC) of 0.736-0.737, multilayer perceptron with an AUC of 0.697-0.708, XGBoost with an AUC of 0.697-0.697, and random forest with an AUC of 0.663-0.674. ML feature importance found that age, HDL-C, and admitting heart rate were important non-echocardiography variables, while peak mitral A-wave velocity and left atrial volume were important echocardiography parameters aiding this prediction. CONCLUSION: Machine learning modeling incorporating clinical and echocardiographic variables predicted AF in ESUS patients with moderate accuracy.

Risk of Liver Fibrosis Is Associated with More Severe Strokes, Increased Complications with Thrombolysis, and Mortality.

The Fibrosis (FIB)-4 index is an established non-invasive test to detect liver fibrosis. Liver fibrosis is postulated to be one of the predictors of the risk of symptomatic Intracranial Haemorrhage (SICH) after intravenous tissue plasminogen activator (IV tPA) therapy, the mainstay of treatment following acute ischemic stroke (AIS). However, SICH is a feared complication of thrombolytic therapy. We aimed to evaluate the association of FIB-4 with outcomes of AIS after IV tPA. Consecutive AIS patients receiving IV tPA from 2006 to 2018 at a single stroke centre were studied in a retrospective cohort study. Multivariable adjusted logistic regression was performed to assess associations of FIB-4 with outcomes. The primary outcome was SICH, and secondary outcomes included functional independence (mRS of 0−2) and mortality measured at 90 days. Among 887 patients (median age: 67 (IQR: 57−77)), 342 had FIB-4 < 1.3 and 161 had FIB-4 > 2.67. A greater proportion of moderate to severe strokes (NIHSS ≥10) occurred in the FIB-4 > 2.67 group (n = 142, 88.8%) compared to the FIB-4 < 1.3 group (n = 208, 61.2%). Amongst the different stroke subtypes, median FIB-4 was highest in cardioembolic stroke (CES) compared to the 3 other non-CES stroke subtypes (1.90 (IQR: 1.41−2.69)). Following IV tPA, having FIB-4 > 2.67 was associated with an increased rate of SICH (adjusted OR: 4.09, 95% CI: 1.04−16.16, p = 0.045) and increased mortality (adjusted OR 3.05, 95% CI: 1.28−7.26, p = 0.012). Advanced liver fibrosis was associated with an increased rate of SICH and increased 90-day mortality after IV tPA. The FIB-4 score may be useful for prognostication after IV tPA.

Impact of Traditional and Non-Traditional Lipid Parameters on Outcomes after Intravenous Thrombolysis in Acute Ischemic Stroke.

Contradicting evidence exists regarding the role of lipids in outcomes following intravenous (IV) thrombolysis with tissue plasminogen activator (tPA). Restricted cubic spline curves and adjusted logistic regression were used to evaluate associations of low-density lipoprotein cholesterol (LDL-C), non-high-density lipoprotein cholesterol (non-HDL-C), total cholesterol (TC), high-density lipoprotein cholesterol (HDL-C) and LDL-C/HDL-C ratio with poor functional outcome, symptomatic intracranial hemorrhage (SICH) and 90-day mortality, among 1004 acute ischemic stroke (AIS) patients who received IV tPA in a comprehensive stroke center. Quartile (Q) 1, Q2 and Q3 of HDL-C were associated with increased odds of poor functional outcome (adjusted odds ratio (adjOR) 1.66, 95% CI 1.06-2.60, p = 0.028, adjOR 1.63, 95% CI 1.05-2.53, p = 0.027, adjOR 1.56, 95% CI 1.01-2.44, p = 0.048) compared to Q4. Q2 and Q4 of non-HDL-C were associated with increased odds of SICH (adjOR 4.28, 95% CI 1.36-18.90, p = 0.025, adjOR 5.17, 95% CI 1.64-22.81, p = 0.011) compared to Q3. Q1 and Q2 of LDL-C was associated with increased odds of mortality (adjOR 2.57, 95% CI 1.27-5.57, p = 0.011 and adjOR 2.28, 95% CI 1.10-5.02, p = 0.032) compared to Q3. In AIS patients who received IV tPA, low LDL-C was associated with increased odds of mortality while HDL-C may be protective against poor functional outcome.

Association of triglyceride-glucose index with clinical outcomes in patients with acute ischemic stroke receiving intravenous thrombolysis.

Intravenous tissue plasminogen activator (tPA) remains the cornerstone of recanalization therapy for acute ischemic stroke (AIS), albeit with varying degrees of response. The triglyceride-glucose (TyG) index is a novel marker of insulin resistance, but association with outcomes among AIS patients who have received tPA has not been well elucidated. We studied 698 patients with AIS who received tPA from 2006 to 2018 in a comprehensive stroke centre. TyG index was calculated using the formula: ln[fasting triglycerides (mg/dL) × fasting glucose (mg/dL)/2]. TyG index was significantly lower in patients that survived at 90-days than those who died (8.61 [Interquartile Range: 8.27-8.99] vs 8.76 [interquartile range: 8.39-9.40], p = 0.007). In multivariate analysis, TyG index was significantly associated with 90-day mortality (OR: 2.12, 95% CI: 1.39-3.23, p = 0.001), poor functional outcome (OR: 1.41 95% CI: 1.05-1.90, p = 0.022), and negatively associated with early neurological improvement (ENI) (OR: 0.68, 95% CI: 0.52-0.89, p = 0.004). There was no association between TyG index and symptomatic intracranial hemorrhage. 'High TyG' (defined by TyG index ≥ 9.15) was associated with mortality, poor functional outcomes and no ENI. In conclusion, the TyG index, a measure of insulin resistance, was significantly associated with poorer clinical outcomes in AIS patients who received tPA.

Overlapping deletion regions at 11q23 in myelodysplastic syndrome and chronic lymphocytic leukemia, characterized by a novel BAC probe set.

Translocations or deletions involving the 11q23 region have been observed in acute lymphoblastic leukemia (ALL), acute myelocytic leukemia (AML), myelodysplastic syndrome (MDS), and chronic lymphocytic leukemia (CLL). BAC probes encompassing the D11S29 and D11S924 markers and flanking the MLL gene were used in dual color fluorescence in situ hybridization. Fifteen patients with hematologic malignancies and cytogenetic abnormalities of 11q23 were analyzed. The BAC and MLL probes demonstrated split signals in five of 7 ALL or AML cases with translocations of 11q23. Of the remaining 2 cases, one had normal signals for both probe sets and the other had a submicroscopic deletion of the MLL 3' region. In one case of AML with del(11)(q23), deletion of the MLL 3' region and the region telomeric to the MLL gene was seen. Three CLL cases with deletion of part or the entire 11q23 region showed deletion of one copy of MLL, but retention of the region telomeric to MLL. However, in four MDS cases with deletions involving the 11q23 region, deletions of both the MLL gene and the flanking regions of the MLL gene were observed. Hence, the deletions on 11q23 are different but overlapping for CLL and MDS, implicating different genes involved for these diseases.