Initial in-hospital heart rate is associated with three-month functional outcomes after acute ischemic stroke

Kuo, Ya-Wen; Lee, Meng; Huang, Yen-Chu; Lee, Jiann-Der

doi:10.1186/s12883-021-02252-2

“…Higher heart rate at rest was associated with poorer functional status in the elderly and predicted subsequent functional decline independently of cardiovascular risk factors ( 46 ). Higher initial in-hospital heart rate also predicted poorer stroke outcomes ( 47 ). The potential influence of these additional predictors on the development of SAP may warrant further research.…”

Section: Discussionmentioning

confidence: 99%

Application of machine learning and natural language processing for predicting stroke-associated pneumonia

Tsai

¹

,

Hsieh

²

,

Sung

³

2022

Front. Public Health

View full text Add to dashboard Cite

BackgroundIdentifying patients at high risk of stroke-associated pneumonia (SAP) may permit targeting potential interventions to reduce its incidence. We aimed to explore the functionality of machine learning (ML) and natural language processing techniques on structured data and unstructured clinical text to predict SAP by comparing it to conventional risk scores.MethodsLinked data between a hospital stroke registry and a deidentified research-based database including electronic health records and administrative claims data was used. Natural language processing was applied to extract textual features from clinical notes. The random forest algorithm was used to build ML models. The predictive performance of ML models was compared with the A2DS2, ISAN, PNA, and ACDD4 scores using the area under the receiver operating characteristic curve (AUC).ResultsAmong 5,913 acute stroke patients hospitalized between Oct 2010 and Sep 2021, 450 (7.6%) developed SAP within the first 7 days after stroke onset. The ML model based on both textual features and structured variables had the highest AUC [0.840, 95% confidence interval (CI) 0.806–0.875], significantly higher than those of the ML model based on structured variables alone (0.828, 95% CI 0.793–0.863, P = 0.040), ACDD4 (0.807, 95% CI 0.766–0.849, P = 0.041), A2DS2 (0.803, 95% CI 0.762–0.845, P = 0.013), ISAN (0.795, 95% CI 0.752–0.837, P = 0.009), and PNA (0.778, 95% CI 0.735–0.822, P < 0.001). All models demonstrated adequate calibration except for the A2DS2 score.ConclusionsThe ML model based on both textural features and structured variables performed better than conventional risk scores in predicting SAP. The workflow used to generate ML prediction models can be disseminated for local adaptation by individual healthcare organizations.

show abstract

“…In fact, cardiac complications are frequently found in patients with acute stroke. Relevant studies mainly focused on ischemic stroke and subarachnoid hemorrhage, but few studies are on ICH [ 3 , 4 ]. A study has shown that cardiac complications may occur in 1% to 4% of patients with ICH [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Changes of Electrocardiogram and Myocardial Enzymes in Patients with Intracerebral Hemorrhage

Qin

¹

,

Dai

²

,

Shuang

³

et al. 2022

View full text Add to dashboard Cite

Purpose. Cardiac complications are common in patients with spontaneous intracerebral hemorrhage (ICH). The present study is aimed at observing the incidence of cardiac complications after ICH, so as at improving the understanding of the relationship between cardiac complications and ICH. Methods. This is a retrospective study on analyzing electrocardiogram (ECG) and serum myocardial enzyme of 208 patients with ICH admitted to a tertiary hospital from 2018 to 2019. For each patient, demographics, medical history, clinical presentation, ECG, serum myocardial enzyme, and head CT on admission were reviewed. Mortality was noted. Results. Among the 208 patients, 145 (69.71%) had one or more ECG abnormalities. The top three abnormalities were corrected QT interval (QTc) prolongation 52 (25%), ST depression 48 (23.08%), and T wave inversion 38 (18.27%). One hundred and thirty-nine patients (66.83%) had increased serum levels of at least one kind of myocardial enzyme, which were high-sensitive cardiac troponin T (hs-cTnT) 79 (37.98%), lactic dehydrogenase (LDH) 80 (38.46%), creatine kinase (CK) 57 (27.40%), and creatine kinase-myocardial subfraction (CKMB) 57 (27.40%). The logistic regression analysis showed the following: secondary intraventricular hemorrhage (SIVH) (odds ratio (OR) 5.32; 95% confidence interval (CI) 2.55–11.08; p < 0.001 ) and hematoma volume > 30 ml (OR 3.81; 95% CI 1.86–7.81; p < 0.001 ) were independent predictive factors of QTc prolongation; thalamus location (OR 5.79; 95% CI 1.94–17.28; p < 0.05 ), hematoma volume > 30 ml (OR 24.187; 95% CI 3.14-186.33; p < 0.05 ), insular involvement (OR 19.08; 95% CI 5.77-63.07; p < 0.001 ), and SIVH (OR 2.62; 95% CI 1.69-5.86; p < 0.05 ) were independent predictive factors of ST depression; insular involvement (OR 2.90; 95% CI 1.12–7.50; p < 0.05 ) and hematoma volume > 30 ml (OR 1.98; 95% CI 1.06–3.70; p < 0.05 ) were independent predictive factors of increase of CK; Glasgow Coma Scale (GCS) (OR 0.86; 95% CI 0.78–0.98; p < 0.05 ) and insular involvement (OR 5.56; 95% CI 1.98–15.62; p < 0.05 ) were independent predictive factors of increase of CKMB; SIVH (OR 2.05; 95% CI 1.07–3.92; p < 0.05 ) was independent predictive factor of increase of LDH; age (OR 1.03; 95% CI 1.01–1.06; p < 0.05 ), blood glucose on admission (OR 1.10; 95% CI 1.01–1.20; p < 0.05 ), and history of antiplatelet drug use (OR 3.50; 95% CI 1.01–12.12; p < 0.05 ) were independent predictive factors of hs-cTnT. All the injury indexes were not related to in-hospital mortality. Conclusion. The study suggests that insular involvement, hematoma volume > 30 ml, and SIVH are the strongest risk factors for ECG abnormalities and elevated myocardial enzymes after ICH followed which are the risk factors such as GCS, age, admission blood glucose, and ICH location in the thalamus.

show abstract

First post-discharge heart rate and long-term prognosis in patients with acute myocardial infarction

Li¹,

Zhang²,

Feng³

et al. 2022

Rev. Cardiovasc. Med.

View full text Add to dashboard Cite

Background: Elevated heart rate (HR) is associated with cardiovascular mortality and other events associated with acute myocardial infarction (AMI). The heart rate after discharge is likely superior to reflect the deteriorating heart function, which negatively responds to normal physical activity. This study aimed to explore the effect of HR at the first outpatient visit on clinical outcomes. Methods: We retrospectively identified 605 patients with AMI. HRs at admission, discharge, and first outpatient visits were measured. The primary endpoint was defined as major adverse cardiovascular events (MACEs), including cardiovascular (CV) death, readmission for worsening heart failure, recurrent nonfatal myocardial infarction (MI), repeated coronary revascularization, and ischemic stroke. Results: During the follow-up period, 145 cases of MACE occurred, including 34 CV deaths, 31 recurrent MI, 89 revascularizations, 41 heart failures, and 4 strokes. The event group displayed an elevated HR at the first outpatient visit compared to the event-free group (p < 0.001). After adjustment for confounding risk factors, Cox models showed that the outpatient HR had the best correlation with MACE [Hazard ratio (HR) = 1.33, 95% confidence interval (CI) = 10.8-59.3, p < 0.01 for increments of 1 standard deviation (SD) in the outpatient HR) and CV mortality (HR = 1.18, 95% CI = 1.052-1.325, p < 0.01) compared with the other two HRs. The restricted spline model indicated that HR at the first post-discharge above 71 bpm was associated with CV mortality. Conclusions: Elevated HR at the first outpatient visit over a period of 2-4 weeks is related to the adverse outcomes of AMI and may identify AMI patients at higher risk of CV mortality.

show abstract

Initial in-hospital heart rate is associated with three-month functional outcomes after acute ischemic stroke

Cited by 4 publications

References 41 publications

Application of machine learning and natural language processing for predicting stroke-associated pneumonia

Application of machine learning and natural language processing for predicting stroke-associated pneumonia

Changes of Electrocardiogram and Myocardial Enzymes in Patients with Intracerebral Hemorrhage

First post-discharge heart rate and long-term prognosis in patients with acute myocardial infarction

Contact Info

Product

Resources

About