Machine Learning-Based Approaches for Prediction of Patients’ Functional Outcome and Mortality after Spontaneous Intracerebral Hemorrhage

Spontaneous intracerebral hemorrhage (SICH) has been common in China with high morbidity and mortality rates. This study aims to develop a machine learning (ML)-based predictive model for the 90-day evaluation after SICH. We retrospectively reviewed 751 patients with SICH diagnosis and analyzed clinical, radiographic, and laboratory data. A modified Rankin scale (mRS) of 0–2 was defined as a favorable functional outcome, while an mRS of 3–6 was defined as an unfavorable functional outcome. We evaluated 90-day functional outcome and mortality to develop six ML-based predictive models and compared their efficacy with a traditional risk stratification scale, the intracerebral hemorrhage (ICH) score. The predictive performance was evaluated by the areas under the receiver operating characteristic curves (AUC). A total of 553 patients (73.6%) reached the functional outcome at the 3rd month, with the 90-day mortality rate of 10.2%. Logistic regression (LR) and logistic regression CV (LRCV) showed the best predictive performance for functional outcome (AUC = 0.890 and 0.887, respectively), and category boosting presented the best predictive performance for the mortality (AUC = 0.841). Therefore, ML might be of potential assistance in the prediction of the prognosis of SICH.

Admission Dehydration Status Portends Adverse Short-Term Mortality in Patients with Spontaneous Intracerebral Hemorrhage

The impact of dehydration at admission of patients with spontaneous intracerebral hemorrhage (ICH) on short-term mortality remains ambiguous due to scarce data. All of the consecutive patients with spontaneous ICH, who were referred to our neurovascular center in 2018/19, were assessed for hydration status on admission. Dehydration was defined by a blood urea-to-creatinine ratio > 80. In a cohort of 249 patients, 76 patients (31%) were dehydrated at the time of admission. The following factors were significantly and independently associated with increased 30-day mortality in multivariate analysis: “signs of cerebral herniation” (p = 0.008), “initial midline shift > 5 mm” (p < 0.001), “ICH score > 3” (p = 0.007), and “admission dehydration status” (p = 0.007). The results of the present study suggest that an admission dehydration status might constitute a significant and independent predictor of short-term mortality in patients with spontaneous ICH.

Association of Socioeconomic Status With Ideal Cardiovascular Health in Black Men

Background Black men are burdened by high cardiovascular risk and the highest all‐cause mortality rate in the United States. Socioeconomic status (SES) is associated with improved cardiovascular risk factors in majority populations, but there is a paucity of data in Black men. Methods and Results We examined the association of SES measures including educational attainment, annual income, employment status, and health insurance status with an ideal cardiovascular health (ICH) score, which included blood pressure, glucose, cholesterol, body mass index, physical activity, and smoking in African American Male Wellness Walks. Six metrics of ICH were categorized into a 3‐tiered ICH score 0 to 2, 3 to 4, and 5 to 6. Multinomial logistic regression modeling was performed to examine the association of SES measures with ICH scores adjusted for age. Among 1444 men, 7% attained 5 to 6 ICH metrics. Annual income <$20 000 was associated with a 56% lower odds of attaining 3 to 4 versus 0 to 2 ICH components compared with ≥$75 000 ( P =0.016). Medicare and no insurance were associated with a 39% and 35% lower odds of 3 to 4 versus 0 to 2 ICH components, respectively, compared with private insurance (all P <0.05). Education and employment status were not associated with higher attainment of ICH in Black men. Conclusions Among community‐dwelling Black men, higher attainment of measures of SES showed mixed associations with greater attainment of ICH. The lack of association of higher levels of educational attainment and employment status with ICH suggests that in order to address the long–standing health inequities that affect Black men, strategies to increase attainment of cardiovascular health may need to address additional components beyond SES.

Elevated Red Cell Distribution Width to Platelet Ratio Is Associated With Poor Prognosis in Patients With Spontaneous, Deep-Seated Intracerebral Hemorrhage

Object: Inflammatory response is an important determinant of subsequent brain injury after deep-seated intracerebral hemorrhage (ICH). The ratio of red blood cell (RBC) distribution width to platelet count (RPR) has been established as a new index to reflect the severity of inflammation. To the best of our knowledge, no association between RPR and prognosis after spontaneous ICH has yet been reported.Methods: In all patients with deep-seated ICH treated at our Neurovascular Center from 2014 to 2020, initial laboratory values were obtained to determine RPR in addition to patient characteristics and known risk factors. Subsequent multivariate analysis was performed to identify independent risk factors for 90-day mortality after deep-seated ICH.Results: Hundred and two patients with deep-seated ICH were identified and further analyzed. Patients with an initial RPR &lt; 0.06 exhibited significantly lower mortality rate after 90 days than those with an initial RPR ≥ 0.06 (27 vs. 57%; p = 0.003). Multivariate analysis identified “ICH score ≥ 3” (p = 0.001), “anemia on admission” (p = 0.01), and “elevated RPR ≥ 0.06” (p = 0.03) as independent predictors of 90-day mortality.Conclusions: The present study constitutes the first attempt to demonstrate that the ratio of RBC distribution width to platelets—as an independent inflammatory marker—might serve for prognostic assessment in deep-seated ICH.

Abstract 1122‐000199: Real‐World Bridging with Intra‐Arterial Therapy is Safe After Tenectplase in Patients with Acute Ischemic Stroke

Introduction : The safety profile of IV tenecteplase (TNK) as a bridging therapy to Intra‐arterial therapy (IAT) is not well‐established in patients receiving acute ischemic stroke therapy. Our objective was to evaluate the incidence of hemorrhagic transformation in subjects who received TNK followed by IAT outside of clinical trial setting. Methods : Electronic medical records of subjects with stroke secondary to LVO who received TNK and IAT within 4.5 hours of last known normal were reviewed. CT head within 24 hours post‐TNK was evaluated for hemorrhagic transformation (HT). Severity was determined by ECASS III criteria Symptomatic intracranial hemorrhage was defined as an increase in NIHSS greater than or equal to 4. Clinical outcomes were assessed with NIHSS at admission, discharge and mRS scores at one month. Z score population proportions were used for subgroup analysis. Social Science Statistics was used for data analysis. Results : From October 2020 to April 2021, 20 subjects received IV tenecteplase. Four subjects did not have LVO or undergo IAT and were excluded from study. Four subjects (25%) developed hemorrhagic transformation. Of this subset, 2 subjects (12.5%) had asymptomatic HI‐1, 1 subject had symptomatic HI‐2, and 1 subject had asymptomatic PH‐1. One subject developed intracranial hemorrhage (ICH score 5) outside of stroke region (intraventricular, subarachnoid, infratentorial parenchymal) without evidence of hemorrhagic transformation of ischemic stroke. In subgroup analysis between subjects with HT and without HT, there was no statistically significant difference in intra‐arterial non‐thrombolytics (z = 0.1393, p = 0.44433); there was a trend towards significance in number of passes (z = 1.2534, p = .10565) and periprocedural IV heparin use for intracranial stenting and/or angioplasty (z = 0.9342, p = 0.17619). There was a statistically significant increase of HT when periprocedural IV integrilin (z = 1.6727, p = 0.04746) was used. Conclusions : Our small subset of early real‐world experience demonstrates a higher rate of symptomatic transformation in bridging with TNK when compared with alteplase. Larger prospective studies are needed to validate our findings.

Abstract 1122‐000215: Scheduled Head CT in Neurologically Stable Spontaneous ICH Patients May be Unnecessary

Introduction : Obtaining serial head computed tomography (CTH) imaging for patients with spontaneous intracerebral hemorrhage (sICH) is commonly utilized to monitor for hematoma expansion (HE), defined as an increase in ICH volume by 33%. Obtaining recurrent CTH in the ICU setting may burden nursing and transport staff, expose patients to radiation, and inflate healthcare costs. It remains unclear whether utilizing scheduled CTH for sICH patients is more advantageous than targeted CTH, which is prompted by a decline in neurological status. We reviewed clinical factors and imaging studies in patients with and without HE. Methods : This retrospective cohort study conducted over two years identified 171 sICH patients. Patient demographics, clinical and neuroimaging data were recorded (including the reason for repeat imaging). These variables were then compared and analyzed in relation to HE using SPSS version 26, chi‐square tests for categorical variables, and independent‐samples t‐tests were used for continuous variables. Results : Patients were predominantly male (65%), with a mean age of 65±14 years, a median GCS of 14, a median ICH score of 1, and a median ICH volume of 12.1 ccs. Repeat CTH was obtained within 14 hours after the initial imaging on average. Admission blood pressure (BP), BP‐lowering interventions, pre‐admission use of anticoagulant and antiplatelet therapy, GCS on admission, ICH volume, ICH score, and presence of spot signs were similar between the two groups. 15% of total patients (26/171) had HE. In the group that underwent scheduled repeat CTH, only 7% (9 patients) had HE, while the remaining 93% (119 patients) did not. Patients who underwent a second scan following a change in the neurologic assessment included 39% (17 patients) who had HE, compared to 61% (26 patients) that did not. HE detection was significantly lower in patients that underwent scheduled CTH (p < 0.0001). Conclusions : In patients with a stable exam, scheduled head CT only showed HE in 6% of patients; thus, the excess burden, radiation, and costs may not be necessary for these patients. Hematoma expansion is significantly lower in patients who underwent scheduled imaging than those prompted by a decline in neurologic status. However, our sample size is small and additional studies with larger population sizes are required to validate our findings.

Abstract 1122‐000024: Stereotactic IntraCerebral Underwater Blood Aspiration Improves Survival Following Intracerebral Hemorrhage as Compared to Predicted Mortality

Introduction : Intracerebral hemorrhage (ICH) is a devastating form of neurological injury with substantial mortality. Recent publications on minimal invasive surgery (MIS) for hematoma evacuation have suggested survival benefits in select patients. Since 2015, our center has been performing an MIS technique using continuous irrigation with aspiration through an endoscope (SCUBA). SCUBA does not require a stability scan and can be performed despite hematoma expansion, intraventricular hemorrhage or radiographic spot sign. We present the 30‐day mortality of our initial experience and compare it to predicted mortality by presenting ICH score. Methods : We performed a retrospective review of consecutively admitted patients with spontaneous non‐traumatic supratentorial ICH who underwent SCUBA between 12/2015 – 03/2019. The primary outcome was observed 30‐day mortality compared to predicted mortality by ICH score on presentation. Key secondary outcomes were operative markers, hospital length of stay, and discharge disposition. Results : One hundred and fifteen patients were identified, with mean (SD) ICH volume of 51.4mL (33.9mL) and median ICH score of 2. The median evacuation was 97% of the hematoma volume and 85% of patients had a residual clot burden of less than 15mL. Twelve patients died within one month of SCUBA for an overall mortality rate of 10.4%. This was significantly lower than the predicted mortality by ICH score of 35.1%, with an absolute risk reduction of 24.7%. When analyzed by presenting ICH score, significant mortality benefits were observed for all ICH scores > 2, with more pronounced differences at higher ICH scores (Table 1). Conclusions : This study suggests that MIS with the SCUBA technique for ICH may reduce predicted 30‐day mortality, with a number need to treat of 4 to prevent one mortality. Further evaluation of this technique in a randomized clinical trial is required.

Abstract P150: Sex Differences In Augmentation Index And Aortic Pulse Pressure Among Patients Diagnosed With Acute Primary Intracerebral Hemorrhage

Introduction: Intracerebral hemorrhage (ICH) is the second most common subtype of stroke. Hypertension is a major cause of primary spontaneous ICH. However, sex difference in blood pressure (BP) and arterial stiffness among ICH patients is not well characterized. Methods: A prospective pilot study to investigate the feasibility of measuring arterial stiffness in acute primary ICH patients was approved by the institutional research board at Wake Forest Baptist Health. Eligible subjects with primary ICH were enrolled in the study within 7 days of onset. Non-invasive measurements of brachial BP, aortic BP, augmentation index at heart rate of 75 beats per minute (AIx75), and carotid-femoral pulse wave velocity (cf-PWV) were measured at the patient’s bedside, using the SphygmoCor XCEL System v1 (AtCor Medical Pty Ltd., Sydney, Australia). Results: A total of 20 patients have been enrolled in the study over 5 months. Over half the patients enrolled were female (55%, n = 11), including 82% (n = 9) White, 9% (n = 1) Asian and 9% (n = 1) Hispanic. There was increased diversity in the male patients (45%, n = 9) including 44% (n = 4) Black, 22% (n = 2) White, 22% (n = 2) Hispanic, and 11% (n = 1) Asian. Men were significantly younger than women (57 ± 5 years vs 74 ± 3 years, respectively, P = 0.009). There were no significant differences in BMI or ICH score. At the time of measurement, there were no significant sex differences in brachial or aortic blood pressures (systolic and diastolic), however, females had significantly higher AIx75 (35 ± 4 vs 20 ± 6, P = 0.036) and aortic PP (53 ± 2 mm Hg vs 42 ± 4 mm Hg, P = 0.020) than males. Sex difference in cf-PWV was not statistically significant (p = 0.054). Conclusion: In the current feasibility pilot study, preliminary data show that females had higher arterial stiffness measured as AIx75 and aortic PP than males in the acute setting of ICH. Further study will be required to ascertain whether this is related to higher age at presentation in females. Whether sex differences in arterial stiffness predict differences in the outcome among ICH patients is not well characterized; thus, assessment of 30-day functional and neurological outcomes will be performed with NIHSS and modified Rankin Scores.

Trends in the seeking of emergency service for ischemic stroke and its risk factors during the COVID-19 pandemic, a study from Taiwan

Background & Objectives: COVID-19 may influence the health seeking behavior of acute ischemic stroke patients. This study aimed to determine the characteristics of the patients who visited the emergency room in a centre designated for stroke care in Taiwan. Methods: This was a retrospective database-based study comparing the severity of ischemic stroke, intracerebral hemorrhage (ICH), and risk factors of patients seen between 2019 and 2020 in the National Taiwan University Hospital Yunlin Branch. Patients with or without thrombolysis therapy were analysed. Results: The median NIHSS of ischemic stroke patients were lower in 2019 than in 2020 (p = 0.015). The difference was seen in non-thrombolysis patients (2019: 3[1-6] vs. 4 [2-7.5], p = 0.012) but not in thrombolysis patients. The frequency of minor stroke was higher in 2019 (45.1%) than in 2020 (37.9%, p = 0.038). The discharge mRS was lower overall (p = 0.004) and in non-thrombolysis patients (0.003), but not in thrombolysis patients in 2019. As for the ICH patients, the severity of ICH score (p = 0.021) and discharge mRS (p = 0.001) were also lower in 2019. The frequencies of risk factors of stroke were higher in 2019 than in 2020, including smoking (24% vs. 18.2%, p = 0.046), alcohol (11.9% vs. 7.5%, p = 0.039), hypertension (72.9% vs. 66.2%, p = 0.039), history of stroke (16.5% vs. 11.6%, p = 0.047), and atrial fibrillation (11.9% vs. 7.5%, p = 0.039). Conclusions: This study in Taiwan revealed a decline in the willingness to seek emergency services under the influence of COVID-19 among patients with lower stroke severity, especially those with more risk factors.

Methodological quality of multivariate prognostic models for intracranial haemorrhages in intensive care units: a systematic review

ObjectivesPatients with severe spontaneous intracranial haemorrhages, managed in intensive care units, face ethical issues regarding the difficulty of anticipating their recovery. Prognostic tools help clinicians in counselling patients and relatives and guide therapeutic decisions. We aimed to methodologically assess prognostic tools for functional outcomes in severe spontaneous intracranial haemorrhages.Data sourcesFollowing Preferred Reporting Items for Systematic Reviews and Meta-Analyses recommendations, we conducted a systematic review querying Medline, Embase, Web of Science, and the Cochrane in January 2020.Study selectionWe included development or validation of multivariate prognostic models for severe intracerebral or subarachnoid haemorrhage.Data extractionWe evaluated the articles following the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies and Transparent Reporting of multivariable prediction model for Individual Prognosis Or Diagnosis statements to assess the tools’ methodological reporting.ResultsOf the 6149 references retrieved, we identified 85 articles eligible. We discarded 43 articles due to the absence of prognostic performance or predictor selection. Among the 42 articles included, 22 did not validate models, 6 developed and validated models and 14 only externally validated models. When adding 11 articles comparing developed models to existing ones, 25 articles externally validated models. We identified methodological pitfalls, notably the lack of adequate validations or insufficient performance levels. We finally retained three scores predicting mortality and unfavourable outcomes: the IntraCerebral Haemorrhages (ICH) score and the max-ICH score for intracerebral haemorrhages, the SubArachnoid Haemorrhage International Trialists score for subarachnoid haemorrhages.ConclusionsAlthough prognostic studies on intracranial haemorrhages abound in the literature, they lack methodological robustness or show incomplete reporting. Rather than developing new scores, future authors should focus on externally validating and updating existing scores with large and recent cohorts.