Early Seizures Are Predictive of Worse Health-Related Quality of Life at Follow-Up After Intracerebral Hemorrhage

Phenotypes of Patients with Intracerebral Hemorrhage, Complications, and Outcomes

BACKGROUND

The objective of this study was to define clinically meaningful phenotypes of intracerebral hemorrhage (ICH) using machine learning.

METHODS

We used patient data from two US medical centers and the Antihypertensive Treatment of Acute Cerebral Hemorrhage-II clinical trial. We used k-prototypes to partition patient admission data. We then used silhouette method calculations and elbow method heuristics to optimize the clusters. Associations between phenotypes, complications (e.g., seizures), and functional outcomes were assessed using the Kruskal-Wallis H-test or χ2 test.

RESULTS

There were 916 patients; the mean age was 63.8 ± 14.1 years, and 426 patients were female (46.5%). Three distinct clinical phenotypes emerged: patients with small hematomas, elevated blood pressure, and Glasgow Coma Scale scores > 12 (n = 141, 26.6%); patients with hematoma expansion and elevated international normalized ratio (n = 204, 38.4%); and patients with median hematoma volumes of 24 (interquartile range 8.2-59.5) mL, who were more frequently Black or African American, and who were likely to have intraventricular hemorrhage (n = 186, 35.0%). There were associations between clinical phenotype and seizure (P = 0.024), length of stay (P = 0.001), discharge disposition (P < 0.001), and death or disability (modified Rankin Scale scores 4-6) at 3-months' follow-up (P < 0.001). We reproduced these three clinical phenotypes of ICH in an independent cohort (n = 385) for external validation.

CONCLUSIONS

Machine learning identified three phenotypes of ICH that are clinically significant, associated with patient complications, and associated with functional outcomes. Cerebellar hematomas are an additional phenotype underrepresented in our data sources.

Acute seizures after spontaneous intracerebral hemorrhage in young individuals: 11-year trends and association with mortality

BACKGROUND

The rate of spontaneous Intracerebral Hemorrhage (sICH) is rising among young Americans. Trends in acute seizure (AS) incidence in this age group is largely unknown. Further, the association of AS with mortality has not been reported in this age group. The aim of this study is to determine trends in AS among young individuals with sICH.

METHODS

The Merative MarketScan® Commercial Claims and Encounters database, for the years 2005 through 2015, served as the data source for this retrospective in-hospital population study. This period was chosen as spontaneous ICH incidence increased among young individuals between 2005 and 2015. Our study population included patients aged 18-64 years with ICH identified using the International Classification of Diseases, Ninth and Tenth Revision (ICD-9/10) codes 430, 431, 432.0, 432.1, 432.9, I61, I61.0, I61.1, I61.2, I61.3, I61.4, I61.5, I61.6, I61.8, and I61.9, excluding those with a prior diagnosis of seizures (ICD-9/10 codes 345.x,780.3x, G40, G41, and R56.8). We computed yearly AS incidence, mortality (in patients with and without seizures), and analyzed trends. We applied a logistic regression model to determine the independent association of AS with mortality accounting for demographic and clinical variables.

RESULTS

AS incidence increased linearly between 2005 (incidence rate: 8.1 %) and 2015 (incidence rate: 11.0 %), which represents a 26 % relative increase (P for trends <0.0001). In-hospital mortality rate was 14.3 % among those who developed AS and 11.5 % among those who did not have AS. Overall, between 2005 and 2015, in-hospital mortality decreased from 13.0 % to 9.7 % among patients without AS but remained unchanged among those with AS. Patients who developed AS were 10 % more likely to die than those who did not (OR: 1.10, 95 % confidence interval: 1.02-1.18).

CONCLUSIONS

Between 2005 and 2015, the incidence of AS increased by nearly 26 % among young Americans with sICH. In-patient mortality remained unchanged among those who developed seizures but declined among those who did not. The occurrence of AS was independently associated with a 10 % higher risk of in-hospital death.

Big Data in Stroke: How to Use Big Data to Make the Next Management Decision

The last decade has seen significant advances in the accumulation of medical data, the computational techniques to analyze that data, and corresponding improvements in management. Interventions such as thrombolytics and mechanical thrombectomy improve patient outcomes after stroke in selected patients; however, significant gaps remain in our ability to select patients, predict complications, and understand outcomes. Big data and the computational methods needed to analyze it can address these gaps. For example, automated analysis of neuroimaging to estimate the volume of brain tissue that is ischemic and salvageable can help triage patients for acute interventions. Data-intensive computational techniques can perform complex risk calculations that are too cumbersome to be completed by humans, resulting in more accurate and timely prediction of which patients require increased vigilance for adverse events such as treatment complications. To handle the accumulation of complex medical data, a variety of advanced computational techniques referred to as machine learning and artificial intelligence now routinely complement traditional statistical inference. In this narrative review, we explore data-intensive techniques in stroke research, how it has informed the management of stroke patients, and how current work could shape clinical practice in the future.

Impact of acute symptomatic seizures and their management on patient-reported outcomes after stroke

OBJECTIVE

Acute symptomatic seizures (ASyS) after stroke are not uncommon. However, the impact of ASyS and its management with anti-seizure medications (ASMs) on patient-reported outcome measures (PROMs) remains poorly investigated. The objective of our study is to evaluate the association between PROMs and ASyS and ASMs following stroke.

METHODS

We performed a retrospective cohort study of all stroke patients who underwent inpatient continuous EEG (cEEG) monitoring performed due to suspected ASyS, including the ones with observed convulsive ASyS, from 04/01/2012 to 03/31/2018, who completed PROMs within 6 months of hospital discharge. Patient-reported outcome measures, including one Neuro-QoL and six PROMIS v1.0 domain scales, were completed by patients as the standard of care in ambulatory stroke clinics. Since ASMs are sometimes used without clearly diagnosed ASyS, we performed group comparisons based on ASM status at discharge, irrespective of their ASyS status. T-tests or Wilcoxon rank sum tests compared continuous variables across groups and chi-square tests or Fisher's exact tests were used for categorical variables.

RESULTS

A total of 508 patients were included in the study [mean age 62.0 ± 14.1 years, 51.6% female; 244 (48.0%) ischemic stroke, 165 (32.5%) intracerebral hemorrhage, and 99 (19.5%) subarachnoid hemorrhage]. A total of 190 (37.4%) patients were discharged on ASMs. At the time of the first PROM, conducted a median of 47 (IQR = 33-78) days after the suspected ASyS, and 162 (31.9%) were on ASMs. ASM use was significantly higher in patients diagnosed with ASyS. Physical Function and Satisfaction with Social Roles and Activities were the most affected health domains. Patient-reported outcome measures were not significantly different between groups based on ASyS (electrographic and/or convulsive), ASM use at hospital discharge, or ASM status on the day of PROM completion.

SIGNIFICANCE

There were no differences in multiple domain-specific PROMs in patients with recent stroke according to ASyS status or ASM use suggesting the possible lack of the former's sensitivity to detect their impact. Additional research is necessary to determine if there is a need for developing ASyS-specific PROMs.

Predicting Early Seizures After Intracerebral Hemorrhage with Machine Learning

BACKGROUND

Seizures are a harmful complication of acute intracerebral hemorrhage (ICH). "Early" seizures in the first week after ICH are a risk factor for deterioration, later seizures, and herniation. Ideally, seizure medications after ICH would only be administered to patients with a high likelihood to have seizures. We developed and validated machine learning (ML) models to predict early seizures after ICH.

METHODS

We used two large datasets to train and then validate our models in an entirely independent test set. The first model ("CAV") predicted early seizures from a subset of variables of the CAVE score (a prediction rule for later seizures)-cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL-whereas early seizure was the dependent variable. We attempted to improve on the "CAV" model by adding anticoagulant use, antiplatelet use, Glasgow Coma Scale, international normalized ratio, and systolic blood pressure ("CAV + "). For each model we used logistic regression, lasso regression, support vector machines, boosted trees (Xgboost), and random forest models. Final model performance was reported as the area under the receiver operating characteristic curve (AUC) using receiver operating characteristic models for the test data. The setting of the study was two large academic institutions: institution 1, 634 patients; institution 2, 230 patients. There were no interventions.

RESULTS

Early seizures were predicted across the ML models by the CAV score in test data, (AUC 0.72, 95% confidence interval 0.62-0.82). The ML model that predicted early seizure better in the test data was Xgboost (AUC 0.79, 95% confidence interval 0.71-0.87, p = 0.04) compared with the CAV model AUC.

CONCLUSIONS

Early seizures after ICH are predictable. Models using cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL had a good accuracy rate, and performance improved with more independent variables. Additional methods to predict seizures could improve patient selection for monitoring and prophylactic seizure medications.