Artificial Intelligence Transforms the Future of Health Care.

Life sciences researchers using artificial intelligence (AI) are under pressure to innovate faster than ever. Large, multilevel, and integrated data sets offer the promise of unlocking novel insights and accelerating breakthroughs. Although more data are available than ever, only a fraction is being curated, integrated, understood, and analyzed. AI focuses on how computers learn from data and mimic human thought processes. AI increases learning capacity and provides decision support system at scales that are transforming the future of health care. This article is a review of applications for machine learning in health care with a focus on clinical, translational, and public health applications with an overview of the important role of privacy, data sharing, and genetic information.

Cerebral Microbleeds are Associated with Higher Mortality Among Ischemic Stroke Patients.

BACKGROUND: Several studies have shown that cerebral microbleeds (CMBs) increase the risk of long-term stroke-related mortality. The purpose of this study was to determine if the existence and burden of CMBs are a predictor of in-hospital death among patients with acute ischemic stroke (AIS). METHODS: We studied consecutive ischemic stroke patients who admitted to our tertiary center over a 2-year period (2013-2014). Patients who underwent thrombolysis were excluded. Baseline characteristics of patients, number and topography of CMBs, white matter lesions, and spontaneous symptomatic hemorrhagic transformation were recorded. Outcome measure in our study was in-hospital death. RESULTS: Out of 1126 consecutive AIS patients evaluated in this study, 772 patients included in the study (mean age 61.9 ± 14.2years [18-95 years], 51.6% men, and 58.2% African American). CMBs were present on the magnetic resonance imaging (MRI) sequences of 124 (16.1%) patients. The overall rate of in-hospital mortality was 4.1%. The presence or absence of CMBs was not predictive of in-hospital mortality (P = .058). After adjusting for potential confounders, the presence of ≥4 CMBs on T2*-weighted MRI was independently (P = .004) associated with a higher likelihood of in-hospital death (odds ratio: 6.6, 95% confidential interval: 2.50 and 17.46) in multivariable logistic regression analyses. Older age, higher National Institute of Health stroke scale, and history of atrial fibrillation were also associated with greater chance of in-hospital death. CONCLUSIONS: The presence or absence of CMBs was not predictive of in-hospital mortality. However, the presence of multiple CMBs was associated with a higher in-hospital mortality rate among AIS patients.

Racial Difference in Cerebral Microbleed Burden Among a Patient Population in the Mid-South United States.

BACKGROUND: Although intracerebral hemorrhage (ICH) is more common among African-Americans, data on the burden of cerebral microbleeds (CMBs) among different races is limited. The purpose of this study is to compare the number, associated factors, and topography of CMBs between African-American and Caucasian populations in the Mid-South United States. METHODS: Using natural language processing, we extracted all brain MRIs performed during a 2-year period (2012-2013) when the report indicated the presence of CMB. All the extracted MRI studies were evaluated for number and location of CMBs, prior stroke, and deep white matter lesion. Negative binomial regression was used to model for the overdispersed count data. RESULTS: A total 167 patients (mean age was 63 ± 15 years, 49% men, 77% African-American, median CMB count: 8) with 1 or more CMBs on their brain MRI were included in this study. There was no significant difference between the 2 groups in terms of CMB locations (P = .086), but there was a significant difference between African-American and Caucasian patients in terms of number of CMBs (16.5 ± 18 versus 6.5 ± 5.5, P < .001). The prevalence of multiple CMBs (CMBs ≥ 5) was similar among African-Americans and Caucasians (72% versus 55%, P = .062). After adjusting for potential confounders, the African-American race was not independently associated with a higher CMB burden (P = .073). CONCLUSION: African-American race was not independently associated with a higher rate of CMB burden when compared to Caucasians after adjusting for potential confounders. We also did not observe a significant racial difference regarding the location and prevalence of multiple CMBs (CMBs ≥ 5).

Safety of Intravenous Thrombolysis in Chronic Intracranial Hemorrhage: A Five-Year Multicenter Study.

INTRODUCTION: Although the recently updated U.S. alteplase label removed "history of intracranial hemorrhage (ICH)" as a contraindication, there are very limited data on the safety of intravenous thrombolysis (IVT) in acute ischemic stroke (AIS) patients with chronic ICH. We sought to evaluate IVT safety in AIS patients with a history of ICH. METHODS: We analyzed consecutive AIS patients treated with IVT at 3 tertiary stroke centers during a 5-year period. We identified AIS treated with IVT with clinical history and neuroimaging confirmation of prior ICH. The safety measure was symptomatic ICH (sICH) defined according to European Cooperative Acute Stroke Study-III criteria combined with the clinical deterioration of 4 points or higher in the National Institutes of Health Stroke Scale (NIHSS) or death. RESULTS: Of the 1212 AIS patients treated with IVT, 7 (.6%) (mean age 72 ± 11 years, 57% men, median NIHSS: 5 points, interquartile range: 2-8) had a history of ICH (hematoma volume: 1-21 cm3, elapsed time between previous ICH and AIS: 1.5-12 years, 5 located in basal ganglia and 2 in periventricular white matter). Patients with previous ICH did not differ in terms of demographics and admission stroke severity in comparison with the rest. The 2 groups had similar rates of sICH (0% [0/7] versus 3.6%, P = .61) and in-hospital mortality (0% [0/7] versus 6.0%, P = .50). CONCLUSION: Our study indicates that IVT might be safe among AIS patients with a history of chronic ICH. Further research with a larger sample size is required to confirm our finding and define the shortest time interval between the hemorrhagic and ischemic events that can be associated with the safe administration of IVT.

Racial Difference in Cerebral Microbleed Burden among Ischemic Stroke Patients.

BACKGROUND AND AIMS: Data on the epidemiology of cerebral microbleeds (CMBs) among patients with ischemic stroke are limited. This study compared the number, associated factors, and topography of CMBs between African American and Caucasian ischemic stroke patients in the Mid-South United States. METHOD: We evaluated consecutive ischemic stroke patients admitted to our tertiary stroke center, University of Tennessee Health Science Center, Memphis, Tennessee, in a two-year period. We analyzed T2*-weighted magnetic resonance images for the number, location, and topography of CMBs, as well as patients' demographic and clinical information. RESULTS: Among 760 ischemic stroke patients who were included (mean age was 62.1 ± 13.9 years, 51.4% men), 450 (59.2%) were African American. In comparison with Caucasians, African Americans were about five years younger (P = .000) and had a higher rate of hypertension (80.9% vs. 74.5%, P = .036). Similarly, African Americans had a higher prevalence of diabetes mellitus (P = .001). There was no significant difference between African-Americans and Caucasians in terms of CMBs presence and location. African Americans had a higher number of CMBs in comparison with Caucasians, but the difference was not significant. African Americans were more likely to have CMBs ≥5 (P = .047). Although African American stroke patients had a higher rate of large confluent white matter lesions, there was no significant racial difference regarding the rate and severity of deep white matter lesions. CONCLUSION: We did not observe any differences between African American and Caucasian patients with ischemic stroke patients regarding the presence, number, and location of CMBs. However, our results suggested that the prevalence of multiple CMBs (CMBs ≥5) might be higher among African American stroke patients.

Uncommon Causes of Cerebral Microbleeds.

BACKGROUND: Cerebral microbleeds (CMBs) are small and round perivascular hemosiderin depositions detectable by gradient echo sequences or susceptibility-weighted imaging. Cerebral microbleeds are common among patients with hypertension, cerebral ischemia, or cerebral amyloid angiopathy. In this article, we describe uncommon causes of CMBs. METHODS: We searched Pubmed with the keyword CMBs for relevant studies and looked for different uncommon causes of CMBs. RESULTS: CMBs have several uncommon etiologies including posterior reversible encephalopathy syndrome, infective endocarditis, brain radiation therapy, cocaine abuse, thrombotic thrombocytopenic purpura, traumatic brain injury, intravascular lymphomatosis or proliferating angio-endotheliomatosis, moyamoya disease, sickle cell anemia/ß-thalassemia, cerebral autosomal dominant arteriopathy subcortical infarcts, and leukoencephalopathy (CADASIL), genetic syndromes, or obstructive sleep apnea. CONCLUSIONS: Understanding the uncommon causes of CMBs is not only helpful in diagnosis and prognosis of some of these rare diseases, but can also help in better understanding different pathophysiology involved in the development of CMBs.

Thrombotic Thrombocytopenic Purpura with Concomitant Progressive Cerebral Microbleeds.

Thrombotic thrombocytopenic purpura (TTP) is a disease caused by excessive platelet thrombi and multisystem vasculopathy. We report a young patient with refractory TTP who has developed multiple multifocal cerebral microbleeds on his brain magnetic resonance imaging scans. TTP-associated thrombotic microangiopathy resulting in diffuse microthrombi formation in the microcirculation and hypoperfusion might be an underlying etiology.