Radiological features of brain hemorrhage through automated segmentation from computed tomography in stroke and traumatic brain injury.

Introduction: Radiological assessment is necessary to diagnose spontaneous intracerebral hemorrhage (ICH) and traumatic brain injury intracranial hemorrhage (TBI-bleed). Artificial intelligence (AI) deep learning tools provide a means for decision support. This study evaluates the hemorrhage segmentations produced from three-dimensional deep learning AI model that was developed using non-contrast computed tomography (CT) imaging data external to the current study. Methods: Non-contrast CT imaging data from 1263 patients were accessed across seven data sources (referred to as sites) in Norway and Sweden. Patients were included based on ICH, TBI-bleed, or mild TBI diagnosis. Initial non-contrast CT images were available for all participants. Hemorrhage location frequency maps were generated. The number of estimated haematoma clusters was correlated with the total haematoma volume. Ground truth expert annotations were available for one ICH site; hence, a comparison was made with the estimated haematoma volumes. Segmentation volume estimates were used in a receiver operator characteristics (ROC) analysis for all samples (i.e., bleed detected) and then specifically for one site with few TBI-bleed cases. Results: The hemorrhage frequency maps showed spatial patterns of estimated lesions consistent with ICH or TBI-bleed presentations. There was a positive correlation between the estimated number of clusters and total haematoma volume for each site (correlation range: 0.45-0.74; each p-value < 0.01) and evidence of ICH between-site differences. Relative to hand-drawn annotations for one ICH site, the VIOLA-AI segmentation mask achieved a median Dice Similarity Coefficient of 0.82 (interquartile range: 0.78 and 0.83), resulting in a small overestimate in the haematoma volume by a median of 0.47 mL (interquartile range: 0.04 and 1.75 mL). The bleed detection ROC analysis for the whole sample gave a high area-under-the-curve (AUC) of 0.92 (with sensitivity and specificity of 83.28% and 95.41%); however, when considering only the mild head injury site, the TBI-bleed detection gave an AUC of 0.70. Discussion: An open-source segmentation tool was used to visualize hemorrhage locations across multiple data sources and revealed quantitative hemorrhage site differences. The automated total hemorrhage volume estimate correlated with a per-participant hemorrhage cluster count. ROC results were moderate-to-high. The VIOLA-AI tool had promising results and might be useful for various types of intracranial hemorrhage.

Systolic blood pressure at age 40 and cognitive function 25 years later: the Akershus Cardiac Examination (ACE) 1950 Study.

OBJECTIVES: Hypertension in midlife is a risk factor for cognitive impairment. Still, the ideal midlife blood pressure (BP) remains unknown. We examined associations between different systolic blood pressure (SBP) levels at the age of 40-43 years and change in SBP over a 25-year period with cognitive function at age 62-65 years. METHODS: We included 2424 individuals born in 1950 who had participated both in the Age 40 Program (1990-1993) and the Akershus Cardiac Examination (ACE) 1950 Study (2012-2015). The exposure was SBP at age 40-43 years and the outcome was cognitive function at age 62-65 years, assessed with Montreal Cognitive Assessment, Delayed recall trial from the Consortium to Establish a Registry for Alzheimer's Disease Word List Memory Task, and Trail Making Test part B (TMT B). RESULTS: Participants were 40.1 ±â€Š0.3 years old with mean SPB 128 ±â€Š13 mmHg at the Age 40 Program, and 63.9 ±â€Š0.6 years old with mean SPB 138 ±â€Š18 at the ACE 1950 Study. Adjusted linear regressions showed no associations between SBP and subsequent cognitive function. In logistic regressions, individuals with SBP ≥140 mmHg, compared to individuals with SBP <120 mmHg (odds ratio 2.29, 95% confidence interval 1.28-4.10, P-value 0.005) had increased risk of an abnormal TMT B-score. Change in SBP during the 25-year follow-up was not associated with cognitive function. CONCLUSIONS: SBP ≥140 mmHg at age 40-43 was associated with reduced capacity on TMT B, a domain specific cognitive test sensitive to vascular impairment. No other associations were found between SBP, or change in SBP, and cognitive function.

The knowing-doing gap in acute stroke-Does stroke knowledge translate into action?

In this study, we suggest that there is a substantial knowing-doing gap in acute stroke, as increased stroke knowledge was not associated with earlier hospital admission.

The assessment of carotid atherosclerosis using a new multipurpose ultrasound probe.

BACKGROUND AND PURPOSE: Multipurpose ultrasound probes combined with ultra-mobile ultrasound instrumentation have the potential to increase the availability and use of ultrasound examinations in the assessment of atherosclerotic burden and cardiac disease. The aim of this study was to compare the agreement of a newly developed multipurpose probe to a standard linear carotid probe in detection of atherosclerosis of the precerebral arteries. METHODS: We examined 103 patients with a multipurpose probe (General Electric, G9L MPP-9 MHz) and a standard linear probe (General Electric, Vivid 7-M12L-14 MHz). Measurements included intima-media thickness (IMT) in the common carotid arteries (CCA), carotid bifurcations (BIF), internal carotid arteries (ICA), and detection of carotid plaques and stenoses. RESULTS: We found a significant level of agreement between the two probes for all IMT measurements with intraclass correlation coefficients (ICC) of: left CCA .91, left BIF .68, left ICA .75, right CCA .84, right BIF .74, and right ICA .59. Agreement with regard to carotid plaque and stenosis detection had kappa values of .94 and .93. CONCLUSION: The multipurpose probe showed agreement with a standard linear probe in detecting atherosclerosis of the carotid arteries and has therefore the potential for use in both cardiac and precerebral ultrasound examinations.

Stroke unit care benefits patients with intracerebral hemorrhage: systematic review and meta-analysis.

BACKGROUND AND PURPOSE: Patients with any type of stroke managed in organized inpatient (stroke unit) care are more likely to survive, return home, and regain independence. However, it is uncertain whether these benefits apply equally to patients with intracerebral hemorrhage and ischemic stroke. METHODS: We conducted a secondary analysis of a systematic review of controlled clinical trials comparing stroke unit care with general ward care, including only trials published after 1990 that could separately report outcomes for patients with intracerebral hemorrhage and ischemic stroke. We performed random-effects meta-analyses and tested for subgroup interactions by stroke type. RESULTS: We identified 13 trials (3570 patients) of modern stroke unit care that recruited patients with intracerebral hemorrhage and ischemic stroke, of which 8 trials provided data on 2657 patients. Stroke unit care reduced death or dependency (risk ratio [RR], 0.81; 95% confidence interval [CI], 0.471-0.92; P=0.0009; I2=60%) with no difference in benefits for patients with intracerebral hemorrhage (RR, 0.79; 95% CI, 0.61-1.00) than patients with ischemic stroke (RR, 0.82; 95% CI, 0.70-0.97; Pinteraction=0.77). Stroke unit care reduced death (RR, 0.79; 95% CI, 0.64-0.97; P=0.02; I2=49%) to a greater extent for patients with intracerebral hemorrhage (RR, 0.73; 95% CI, 0.54-0.97) than patients with ischemic stroke (RR, 0.82; 95%, CI 0.61-1.09), but this difference was not statistically significant (Pinteraction=0.58). CONCLUSIONS: Patients with intracerebral hemorrhage seem to benefit at least as much as patients with ischemic stroke from organized inpatient (stroke unit) care.

Poststroke epilepsy: occurrence and predictors--a long-term prospective controlled study (Akershus Stroke Study).

PURPOSE: The aims of the study were to assess the occurrence of poststroke epilepsy (PSE) in patients with ischemic strokes, to identify predictors, and to investigate whether treatment in a stroke unit (SU) influenced the long-term outcomes of epilepsy. METHODS: Patients with PSE, defined as those having two ore more unprovoked epileptic seizures > or = 1 week after an ischemic stroke, were identified from a cohort of 484 patients with ischemic strokes. The patients were prospectively assessed 7-8 years after stroke or until death. Different variables were studied to look for possible predictors. RESULTS: From 484 patients with ischemic strokes, PSE developed in 12 (2.5%) and 15 (3.1%) patients during the first year and 7-8 years after stroke, respectively. Eight (53%) of these patients were treated in a stroke unit (SU), and seven (47%) were treated in a general medical ward (GMW). The mean age of those who developed PSE and those who did not was 74.3 years and 76.3 years, respectively. In a multivariate analysis, a Scandinavian Stroke Scale (SSS) score < 30 on admission was a significant predictor for developing PSE [odds ratio (OR), 4.9; p = 0.004). CONCLUSIONS: The prevalence of PSE, 7 to 8 years after an ischemic stroke, was 3.1%. SSS scores < 30 on admission were a significant predictor for PSE. Neither treatment in SU versus GMW, cortical location, nor age at onset of stroke seemed to influence the risk of developing PSE.