Major cardiovascular events in patients presenting with acute stroke: a 5-year follow-up study in patients who had ischaemic stroke and stroke mimics

Choi

J Neurol Neurosurg Psychiatry

et al. 2023

BackgroundWhether deep learning models using clinical data and brain imaging can predict the long-term risk of major adverse cerebro/cardiovascular events (MACE) after acute ischaemic stroke (AIS) at the individual level has not yet been studied.MethodsA total of 8590 patients with AIS admitted within 5 days of symptom onset were enrolled. The primary outcome was the occurrence of MACEs (a composite of stroke, acute myocardial infarction or death) over 12 months. The performance of deep learning models (DeepSurv and Deep-Survival-Machines (DeepSM)) and traditional survival models (Cox proportional hazards (CoxPH) and random survival forest (RSF)) were compared using the time-dependent concordance index (Ctdindex).ResultsGiven the top 1 to all 60 clinical factors according to feature importance, CoxPH and RSF yieldedCtdindex of 0.7236–0.8222 and 0.7279–0.8335, respectively. Adding image features improved the performance of deep learning models and traditional models assisted by deep learning models. DeepSurv and DeepSM yielded the bestCtdindex of 0.8496 and 0.8531 when images were added to all 39 relevant clinical factors, respectively. In feature importance, brain image was consistently ranked highly. Deep learning models automatically extracted the image features directly from personalised brain images and predicted the risk and date of future MACEs at the individual level.ConclusionsDeep learning models using clinical data and brain images could improve the prediction of MACEs and provide personalised outcome prediction for patients with AIS. Deep learning models will allow us to develop more accurate and tailored prognostic prediction systems that outperform traditional models.

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning-based personalised outcome prediction after acute ischaemic stroke

Choi

J Neurol Neurosurg Psychiatry

et al. 2023

“…SOR is probably associated with poor functional recovery, a higher incidence of severe events either in hospital or short-term death and long term major adverse cardiovascular events (MACE) complications [5] . Therefore, we want a reliable risk stratification tool that reliably predicts the development of SOR on the basis of its complicated pathophysiology.…”

Section: Discussionmentioning

confidence: 99%

Predictors of Suboptimal Reperfusion and Short Term Mortality in Patients Presented With Acute ST-Segment Elevation Myocardial Infarction and Treated With Primary Percutaneous Coronary Intervention

Abdelmoneum¹,

Arafa²,

Mohamed³

et al. 2023

Background: Predictors of Suboptimal reperfusion are still unclear. Aim: This study aimed to determine the factors that may indicate suboptimal reperfusion and short-term mortality in patients who were diagnosed with acute ST-segment elevation myocardial infarction (STEMI) and underwent primary percutaneous coronary intervention (pPCI). Patients and methods: This multicenter prospective comparative study, conducted at Benha University hospitals and National Heart Institute, included 400 patients (age<18 years and both sex) with acute STEMI, who were treated with PPCI. They were divided equally into 2 groups; suboptimal and optimal reperfusion groups (TIMI < III Vs.TIMI III respectively). Clinical data was collected. ECG, laboratory investigations, echocardiographic study, PPCI and 6 months follow up were done to all patients included. Results: This study showed that advanced age (60.4±8.2), family history of CAD, dyslipidemia, being diabetic, prolonged Pain to PCI time, higher random blood sugar (RBG) at the time of presentation, Killip class >1, heavy thrombus burden, prediltation, multiple stents insertion and longer stent length are predictors of the SOR after PPCI. While, Patients on long term beta blockers (BB) and angiotensin-converting enzyme inhibitor (ACEI) are less likely to develop SOR. Furthermore, patients with SOR are more likely to develop in-hospital arrhythmias, heart failure, acute mitral regurge and inhospital mortality. Additionally, it increases 6-months risk of reischemia and mortality. Conclusions: Predicting the occurrence of no-reflow following pPCI can be achieved by considering various factors, such as clinical data, laboratory results, angiographic features, and procedural characteristics. Heavy thrombus burden, prediltation, dyslipidemia, longer stent length, pain to PCI time and RBG >300 (mg/dL) at the time of presentation were found to be the most predictable variables to SOR. Long term use of BB and ACEI were found to be significant independent factors that decreased the likelihood of TIMI9h were considered the most predictable variables to mortality in no reflow.

“…We excluded patients in whom the final diagnosis was either ICH or stroke mimics. The details of the stroke database have previously been published (22)(23)(24)(25)(26)(27). In brief, HGH is a Joint Commission International accredited 600-bed hospital, where ~95% of all strokes in Qatar requiring hospitalization are admitted.…”

Section: Methodsmentioning

confidence: 99%

How appropriate is use of antiplatelet medications in patients with transient ischemic attacks and stroke: an analysis of 9132 patients over eight years

Naveed¹,

Akhtar²,

Jerdi³

et al. 2023

Preprint

Self Cite

Background and purpose: Guidelines recommend patients with high-risk TIAs and minor stroke presenting within 1-3 days from onset be offered dual antiplatelet therapy (DAPT). There is little data on real-world adherence to these recommendations. We evaluated the appropriateness of DAPT use in TIA and stroke patients in a prospective Database. Methods: The Qatar Stroke Database began enrollment of patients with TIAs and acute stroke in 2014 and currently has ~ 16,000 patients. For this study we evaluated the rates of guideline-adherent use of antiplatelet treatment at the time of discharge in patients with TIAs and stroke. TIAs were considered high-risk with ABCD2 score of ? 4 and minor stroke was defined as NIHSS ? 3. Patient demographics, clinical features, risk factors, previous medications, imaging and laboratory investigations, final diagnosis, discharge medications, and discharge and 90-day modified Rankin Scale (mRS) were analyzed. Results: After excluding patients with ICH, mimics and rare secondary causes, 8082 patients available for final analysis (TIAs: 1357;stroke 6725). In high-risk TIAs, 282 of 666 (42.3%) patients were discharged on DAPT. In patients with minor stroke, 1207 of 3572 (33.8%) patients were discharged on DAPT. DAPT was inappropriately offered to 238 of 691 (34.4%) of low-risk TIAs and 809 of 3153 (25.7%) of non-minor stroke patients. Conclusions: This large database of prospectively collected patients with TIAs and stroke shows that, unfortunately, despite several guidelines, a large majority of patients with TIAs and stroke are receiving inappropriate antiplatelet treatment at discharge from hospital. This requires urgent attention and further investigation.