Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review.

This scoping review of randomised controlled trials on artificial intelligence (AI) in clinical practice reveals an expanding interest in AI across clinical specialties and locations. The USA and China are leading in the number of trials, with a focus on deep learning systems for medical imaging, particularly in gastroenterology and radiology. A majority of trials (70 [81%] of 86) report positive primary endpoints, primarily related to diagnostic yield or performance; however, the predominance of single-centre trials, little demographic reporting, and varying reports of operational efficiency raise concerns about the generalisability and practicality of these results. Despite the promising outcomes, considering the likelihood of publication bias and the need for more comprehensive research including multicentre trials, diverse outcome measures, and improved reporting standards is crucial. Future AI trials should prioritise patient-relevant outcomes to fully understand AI's true effects and limitations in health care.

Secondary Prevention in Patients With Stroke Versus Myocardial Infarction: Analysis of 2 National Cohorts.

BACKGROUND: The implementation of preventive therapies among patients with stroke remains inadequately explored, especially when compared with patients with myocardial infarction (MI), despite sharing similar vascular risk profiles. We tested the hypothesis that participants with a history of stroke have a worse cardiovascular prevention profile in comparison to participants with MI. METHODS AND RESULTS: In cross-sectional analyses within the UK Biobank and All of Us Research Program, involving 14 760 (9193 strokes, 5567 MIs) and 7315 (2948 strokes, 4367 MIs) participants, respectively, we evaluated cardiovascular prevention profiles assessing low-density lipoprotein (<100 mg/dL), blood pressure (systolic, <140 mm Hg; and diastolic, <90 mm Hg), statin and antiplatelet use, and a cardiovascular prevention score that required meeting at least 3 of these criteria. The results revealed that, within the UK Biobank, patients with stroke had significantly lower odds of meeting all the preventive criteria compared with patients with MI: low-density lipoprotein control (odds ratio [OR], 0.73 [95% CI, 0.68-0.78]; P<0.001), blood pressure control (OR, 0.63 [95% CI, 0.59-0.68]; P<0.001), statin use (OR, 0.45 [95% CI, 0.42-0.48]; P<0.001), antiplatelet therapy use (OR, 0.30 [95% CI, 0.27-0.32]; P<0.001), and cardiovascular prevention score (OR, 0.42 [95% CI, 0.39-0.45]; P<0.001). Similar patterns were observed in the All of Us Research Program, with significant differences across all comparisons (P<0.05), and further analysis suggested that the odds of having a good cardiovascular prevention score were influenced by race and ethnicity as well as neighborhood deprivation levels (interaction P<0.05 in both cases). CONCLUSIONS: In 2 independent national cohorts, patients with stroke showed poorer cardiovascular prevention profiles and lower adherence to guideline-directed therapies compared with patients with MI. These findings underscore the need to explore the reasons behind the underuse of secondary prevention in vulnerable stroke survivors.

Burden of Ischemic and Hemorrhagic Stroke Across the US From 1990 to 2019.

Importance: Stroke is a leading cause of death and disability in the US. Accurate and updated measures of stroke burden are needed to guide public health policies. Objective: To present burden estimates of ischemic and hemorrhagic stroke in the US in 2019 and describe trends from 1990 to 2019 by age, sex, and geographic location. Design, Setting, and Participants: An in-depth cross-sectional analysis of the 2019 Global Burden of Disease study was conducted. The setting included the time period of 1990 to 2019 in the US. The study encompassed estimates for various types of strokes, including all strokes, ischemic strokes, intracerebral hemorrhages (ICHs), and subarachnoid hemorrhages (SAHs). The 2019 Global Burden of Disease results were released on October 20, 2020. Exposures: In this study, no particular exposure was specifically targeted. Main Outcomes and Measures: The primary focus of this analysis centered on both overall and age-standardized estimates, stroke incidence, prevalence, mortality, and DALYs per 100 000 individuals. Results: In 2019, the US recorded 7.09 million prevalent strokes (4.07 million women [57.4%]; 3.02 million men [42.6%]), with 5.87 million being ischemic strokes (82.7%). Prevalence also included 0.66 million ICHs and 0.85 million SAHs. Although the absolute numbers of stroke cases, mortality, and DALYs surged from 1990 to 2019, the age-standardized rates either declined or remained steady. Notably, hemorrhagic strokes manifested a substantial increase, especially in mortality, compared with ischemic strokes (incidence of ischemic stroke increased by 13% [95% uncertainty interval (UI), 14.2%-11.9%]; incidence of ICH increased by 39.8% [95% UI, 38.9%-39.7%]; incidence of SAH increased by 50.9% [95% UI, 49.2%-52.6%]). The downturn in stroke mortality plateaued in the recent decade. There was a discernible heterogeneity in stroke burden trends, with older adults (50-74 years) experiencing a decrease in incidence in coastal areas (decreases up to 3.9% in Vermont), in contrast to an uptick observed in younger demographics (15-49 years) in the South and Midwest US (with increases up to 8.4% in Minnesota). Conclusions and Relevance: In this cross-sectional study, the declining age-standardized stroke rates over the past 3 decades suggest progress in managing stroke-related outcomes. However, the increasing absolute burden of stroke, coupled with a notable rise in hemorrhagic stroke, suggests an evolving and substantial public health challenge in the US. Moreover, the significant disparities in stroke burden trends across different age groups and geographic locations underscore the necessity for region- and demography-specific interventions and policies to effectively mitigate the multifaceted and escalating burden of stroke in the country.

Polygenic Susceptibility to Hypertension and Cognitive Performance in Middle-aged Persons Without Stroke or Dementia.

BACKGROUND AND OBJECTIVES: Mounting evidence indicates that hypertension leads to a higher risk of dementia. Hypertension is a highly heritable trait, and a higher polygenic susceptibility to hypertension (PSH) is known to associate with a higher risk of dementia. We tested the hypothesis that a higher PSH leads to worse cognitive performance in middle-aged persons without dementia. Confirming this hypothesis would support follow-up research focused on using hypertension-related genomic information to risk-stratify middle-aged adults before hypertension develops. METHODS: We conducted a nested cross-sectional genetic study within the UK Biobank (UKB). Study participants with a history of dementia or stroke were excluded. We categorized participants as having low (≤20th percentile), intermediate, or high (≥80th percentile) PSH according to results of 2 polygenic risk scores for systolic and diastolic blood pressure (BP) generated with data on 732 genetic risk variants. A general cognitive ability score was calculated as the first component of an analysis that included the results of 5 cognitive tests. Primary analyses focused on Europeans, and secondary analyses included all race/ethnic groups. RESULTS: Of the 502,422 participants enrolled in the UKB, 48,118 (9.6%) completed the cognitive evaluation, including 42,011 (8.4%) of European ancestry. Multivariable regression models using systolic BP-related genetic variants indicated that compared with study participants with a low PSH, those with intermediate and high PSH had reductions of 3.9% (ß -0.039, SE 0.012) and 6.6% (ß -0.066, SE 0.014), respectively, in their general cognitive ability score (p < 0.001). Secondary analyses including all race/ethnic groups and using diastolic BP-related genetic variants yielded similar results (p < 0.05 for all tests). Analyses evaluating each cognitive test separately indicated that reaction time, numeric memory, and fluid intelligence drove the association between PSH and general cognitive ability score (all individual tests, p < 0.05). DISCUSSION: Among nondemented, community-dwelling, middle-aged Britons, a higher PSH is associated with worse cognitive performance. These findings suggest that genetic predisposition to hypertension influences brain health in persons who have not yet developed dementia. Because information on genetic risk variants for elevated BP is available long before the development of hypertension, these results lay the foundation for further research focused on using genomic data for the early identification of high-risk middle-aged adults.

Higher Hospital Frailty Risk Score Is Associated With Increased Risk of Stroke: Observational and Genetic Analyses.

BACKGROUND: Frailty is a prevalent state associated with several aging-related traits and conditions. The relationship between frailty and stroke remains understudied. Here we aim to investigate whether the hospital frailty risk score (HFRS) is associated with the risk of stroke and determine whether a significant association between genetically determined frailty and stroke exists. DESIGN: Observational study using data from All of Us research program and Mendelian Randomization analyses. METHODS: Participants from All of Us with available electronic health records were selected for analysis. All of Us began national enrollment in 2018 and is expected to continue for at least 10 years. All of Us is recruiting members of groups that have traditionally been underrepresented in research. All participants provided informed consent at the time of enrollment, and the date of consent was recorded for each participant. Incident stroke was defined as stroke event happening on or after the date of consent to the All of Us study HFRS was measured with a 3-year look-back period before the date of consent for stroke risk. The HFRS was stratified into 4 categories: no-frailty (HFRS=0), low (HFRS ≥1 and <5), intermediate (≥5 and <15), and high (HFRS ≥15). Last, we implemented Mendelian Randomization analyses to evaluate whether genetically determined frailty is associated with stroke risk. RESULTS: Two hundred fifty-three thousand two hundred twenty-six participants were at risk of stroke. In multivariable analyses, frailty status was significantly associated with risk of any (ischemic or hemorrhagic) stroke following a dose-response way: not-frail versus low HFRS (HR, 4.9 [CI, 3.5-6.8]; P<0.001), not-frail versus intermediate HFRS (HR, 11.4 [CI, 8.3-15.7]; P<0.001) and not-frail versus high HFRS (HR, 42.8 [CI, 31.2-58.6]; P<0.001). We found similar associations when evaluating ischemic and hemorrhagic stroke separately (P value for all comparisons <0.05). Mendelian Randomization confirmed this association by indicating that genetically determined frailty was independently associated with risk of any stroke (OR, 1.45 [95% CI, 1.15-1.84]; P=0.002). CONCLUSIONS: Frailty, based on the HFRS was associated with higher risk of any stroke. Mendelian Randomization analyses confirmed this association providing evidence to support a causal relationship.

Association of Body Mass Index and Waist Circumference With Imaging Metrics of Brain Integrity and Functional Connectivity in Children Aged 9 to 10 Years in the US, 2016-2018.

Importance: Aside from widely known cardiovascular implications, higher weight in children may have negative associations with brain microstructure and neurodevelopment. Objective: To evaluate the association of body mass index (BMI) and waist circumference with imaging metrics that approximate brain health. Design, Setting, and Participants: This cross-sectional study used data from the Adolescent Brain Cognitive Development (ABCD) study to examine the association of BMI and waist circumference with multimodal neuroimaging metrics of brain health in cross-sectional and longitudinal analyses over 2 years. From 2016 to 2018, the multicenter ABCD study recruited more than 11 000 demographically representative children aged 9 to 10 years in the US. Children without any history of neurodevelopmental or psychiatric disorders were included in this study, and a subsample of children who completed 2-year follow-up (34%) was included for longitudinal analysis. Exposures: Children's weight, height, waist circumference, age, sex, race and ethnicity, socioeconomic status, handedness, puberty status, and magnetic resonance imaging scanner device were retrieved and included in the analysis. Main Outcomes and Measures: Association of preadolescents' BMI z scores and waist circumference with neuroimaging indicators of brain health: cortical morphometry, resting-state functional connectivity, and white matter microstructure and cytostructure. Results: A total of 4576 children (2208 [48.3%] female) at a mean (SD) age of 10.0 years (7.6 months) were included in the baseline cross-sectional analysis. There were 609 (13.3%) Black, 925 (20.2%) Hispanic, and 2565 (56.1%) White participants. Of those, 1567 had complete 2-year clinical and imaging information at a mean (SD) age of 12.0 years (7.7 months). In cross-sectional analyses at both time points, higher BMI and waist circumference were associated with lower microstructural integrity and neurite density, most pronounced in the corpus callosum (fractional anisotropy for BMI and waist circumference at baseline and second year: P < .001; neurite density for BMI at baseline: P < .001; neurite density for waist circumference at baseline: P = .09; neurite density for BMI at second year: P = .002; neurite density for waist circumference at second year: P = .05), reduced functional connectivity in reward- and control-related networks (eg, within the salience network for BMI and waist circumference at baseline and second year: P < .002), and thinner brain cortex (eg, for the right rostral middle frontal for BMI and waist circumference at baseline and second year: P < .001). In longitudinal analysis, higher baseline BMI was most strongly associated with decelerated interval development of the prefrontal cortex (left rostral middle frontal: P = .003) and microstructure and cytostructure of the corpus callosum (fractional anisotropy: P = .01; neurite density: P = .02). Conclusions and Relevance: In this cross-sectional study, higher BMI and waist circumference among children aged 9 to 10 years were associated with imaging metrics of poorer brain structure and connectivity as well as hindered interval development. Future follow-up data from the ABCD study can reveal long-term neurocognitive implications of excess childhood weight. Imaging metrics that had the strongest association with BMI and waist circumference in this population-level analysis may serve as target biomarkers of brain integrity in future treatment trials of childhood obesity.

Blood pressure-related white matter microstructural disintegrity and associated cognitive function impairment in asymptomatic adults.

BACKGROUND AND OBJECTIVES: We aimed to investigate the white matter (WM) microstructural/cytostructural disintegrity patterns related to higher systolic blood pressure (SBP), and whether they mediate SBP effects on cognitive performance in middle-aged adults. METHODS: Using the UK Biobank study of community-dwelling volunteers aged 40-69 years, we included participants without a history of stroke, dementia, demyelinating disease or traumatic brain injury. We investigated the association of SBP with MRI diffusion metrics: fractional anisotropy (FA), mean diffusivity (MD), intracellular volume fraction (a measure of neurite density), isotropic (free) water volume fraction (ISOVF) and orientation dispersion across WM tracts. Then, we determined whether WM diffusion metrics mediated the effects of SBP on cognitive function. RESULTS: We analysed 31 363 participants-mean age of 63.8 years (SD: 7.7), and 16 523 (53%) females. Higher SBP was associated with lower FA and neurite density, but higher MD and ISOVF. Among different WM tracts, diffusion metrics of the internal capsule anterior limb, external capsule, superior and posterior corona radiata were most affected by higher SBP. Among seven cognitive metrics, SBP levels were only associated with 'fluid intelligence' (adjusted p<0.001). In mediation analysis, the averaged FA of external capsule, internal capsule anterior limb and superior cerebellar peduncle mediated 13%, 9% and 13% of SBP effects on fluid intelligence, while the averaged MD of external capsule, internal capsule anterior and posterior limbs, and superior corona radiata mediated 5%, 7%, 7% and 6% of SBP effects on fluid intelligence, respectively. DISCUSSION: Among asymptomatic adults, higher SBP is associated with pervasive WM microstructure disintegrity, partially due to reduced neuronal count, which appears to mediate SBP adverse effects on fluid intelligence. Diffusion metrics of select WM tracts, which are most reflective of SBP-related parenchymal damage and cognitive impairment, may serve as imaging biomarkers to assess treatment response in antihypertensive trials.

A genome-wide association study of frailty identifies significant genetic correlation with neuropsychiatric, cardiovascular, and inflammation pathways.

Frailty is an aging-related clinical phenotype defined as a state in which there is an increase in a person's vulnerability for dependency and/or mortality when exposed to a stressor. While underlying mechanisms leading to the occurrence of frailty are complex, the importance of genetic factors has not been fully investigated. We conducted a large-scale genome-wide association study (GWAS) of frailty, as defined by the five criteria (weight loss, exhaustion, physical activity, walking speed, and grip strength) captured in the Fried Frailty Score (FFS), in 386,565 European descent participants enrolled in the UK Biobank (mean age 57 [SD 8] years, 208,481 [54%] females). We identified 37 independent, novel loci associated with the FFS (p < 5 × 10-8), including seven loci without prior described associations with other traits. The variants associated with FFS were significantly enriched in brain tissues as well as aging-related pathways. Our post-GWAS bioinformatic analyses revealed significant genetic correlations between FFS and cardiovascular-, neurological-, and inflammation-related diseases/traits, and subsequent Mendelian Randomization analyses identified causal associations with chronic pain, obesity, diabetes, education-related traits, joint disorders, and depressive/neurological, metabolic, and respiratory diseases. The GWAS signals were replicated in the Health and Retirement Study (HRS, n = 9,720, mean age 73 [SD 7], 5,582 [57%] females), where the polygenic risk score built from UKB GWAS was significantly associated with the FFS in HRS individuals (OR per SD of the score 1.27, 95% CI 1.22-1.31, p = 1.3 × 10-11). These results provide new insight into the biology of frailty by comprehensively evaluating its genetic architecture.

Emergent external ventricular drain placement in patients with factor Xa inhibitor-associated intracerebral hemorrhage after reversal with andexanet alfa.

BACKGROUND: Andexanet alfa (AA), a factor Xa-inhibitor (FXi) reversal agent, is given as a bolus followed by a 2-hour infusion. This long administration time can delay EVD placement in intracerebral hemorrhage (ICH) patients. We sought to evaluate the safety of EVD placement immediately post-AA bolus compared to post-AA infusion. METHODS: We conducted a retrospective study that included adult patients admitted with FXi-associated ICH who received AA and underwent EVD placement The primary outcome was the occurrence of a new hemorrhage (tract, extra-axial, or intraventricular hemorrhage). Secondary outcomes included mortality, intensive care unit and hospital length of stay, and discharge modified Rankin Score. The primary safety outcome was documented thrombotic events. RESULTS: Twelve patients with FXi related ICH were included (EVD placement post-AA bolus, N = 8; EVD placement post-AA infusion, N = 4). Each arm included one patient with bilateral EVD placed. There was no difference in the incidence of new hemorrhages, with one post-AA bolus patient had small, focal, nonoperative extra-axial hemorrhage. Morbidity and mortality were higher in post-AA infusion patients (mRS, post-AA bolus, 4 [4-6] vs. post-AA infusion 6 [5,6], p = 0.24 and post-AA bolus, 3 (37.5 %) vs. post-AA infusion, 3 (75 %), p = 0.54, respectively). One patient in the post-AA bolus group had thrombotic event. There was no difference in hospital LOS (post-AA bolus, 19 days [12-26] vs. post-AA infusion, 14 days [9-22], p = 0.55) and ICU LOS (post-AA bolus, 10 days [6-13] vs. post-AA infusion, 11 days [5-21], p = 0.86). CONCLUSION: We report no differences in the incidence of tract hemorrhage, extra-axial hemorrhage, or intraventricular hemorrhage post-AA bolus versus post-AA infusion. Larger prospective studies to validate these results are warranted.

Whole-Exome Sequencing Analyses Support a Role of Vitamin D Metabolism in Ischemic Stroke.

BACKGROUND: Ischemic stroke (IS) is a highly heritable trait, and genome-wide association studies have identified several commonly occurring susceptibility risk loci for this condition. However, there are limited data on the contribution of rare genetic variation to IS. METHODS: We conducted an exome-wide study using whole-exome sequencing data from 152 058 UK Biobank participants, including 1777 IS cases. We performed single-variant analyses for rare variants and gene-based analyses for loss-of-function and deleterious missense rare variants. We validated these results through (1) gene-based testing using summary statistics from MEGASTROKE-a genome-wide association study of IS that included 67 162 IS cases and 454 450 controls, (2) gene-based testing using individual-level data from 1706 IS survivors, including 142 recurrent IS cases, enrolled in the VISP trial (Vitamin Intervention for Stroke Prevention); and (3) gene-based testing against neuroimaging phenotypes related to cerebrovascular disease using summary-level data from 42 310 UK Biobank participants with available magnetic resonance imaging data. RESULTS: In single-variant association analyses, none of the evaluated variants were associated with IS at genome-wide significance levels (P<5×10-8). In the gene-based analysis focused on loss-of-function and deleterious missense variants, rare genetic variation at CYP2R1 was significantly associated with IS risk (P=2.6×10-6), exceeding the Bonferroni-corrected threshold for 16 074 tests (P<3.1×10-6). Validations analyses indicated that CYP2R1 was associated with IS risk in MEGASTROKE (gene-based test, P=0.003), with IS recurrence in the VISP trial (gene-based test, P=0.001) and with neuroimaging traits (white matter hyperintensity, mean diffusivity, and fractional anisotropy) in the UK Biobank neuroimaging study (all gene-based tests, P<0.05). CONCLUSIONS: Because CYP2R1 plays an important role in vitamin D metabolism and existing observational evidence suggests an association between vitamin D levels and cerebrovascular disease, our results support a role of this pathway in the occurrence of IS.

Polygenic Susceptibility to Hypertension and Blood Pressure Control in Stroke Survivors.

BACKGROUND AND OBJECTIVES: Blood pressure (BP) is often not at goal in stroke survivors, leaving individuals vulnerable to additional vascular events. Given that BP is a highly heritable trait, we hypothesize that a higher polygenic susceptibility to hypertension (PSH) leads to worse BP control in stroke survivors. METHODS: We conducted a study within the UK Biobank evaluating persons of European ancestry who survived an ischemic or hemorrhagic stroke. To model the PSH, we created polygenic risk scores (PRSs) for systolic and diastolic BP using 732 genetic variants. We divided the PRSs into quintiles and used linear/logistic regression to test whether higher PSH led to higher observed BP, uncontrolled BP (systolic BP > 140 mm Hg or diastolic BP > 90 mm Hg), and resistant BP (uncontrolled BP despite being on ≥3 antihypertensive drugs). We conducted an independent replication using data from the Vitamin Intervention for Stroke Prevention (VISP) trial. RESULTS: We analyzed 5,940 stroke survivors. When comparing stroke survivors with very low vs very high PSH, the mean systolic BP was 137 (SD 18) vs 143 (SD 20, p < 0.001), the mean diastolic BP was 81 (SD 10) vs 84 (SD 11, p < 0.001), the prevalence of uncontrolled BP was 42.8% vs 57.2% (p < 0.001), and the prevalence of resistant hypertension was 3.9% vs 11% (p < 0.001). Results remained significant using multivariable models (p < 0.001) and were replicated in the VISP study (all tests with p < 0.05). DISCUSSION: A higher PSH is associated with worse BP control in stroke survivors. These findings point to genetic predisposition as an important determinant of poorly controlled BP in this population.

Multimodal biomedical AI.

The increasing availability of biomedical data from large biobanks, electronic health records, medical imaging, wearable and ambient biosensors, and the lower cost of genome and microbiome sequencing have set the stage for the development of multimodal artificial intelligence solutions that capture the complexity of human health and disease. In this Review, we outline the key applications enabled, along with the technical and analytical challenges. We explore opportunities in personalized medicine, digital clinical trials, remote monitoring and care, pandemic surveillance, digital twin technology and virtual health assistants. Further, we survey the data, modeling and privacy challenges that must be overcome to realize the full potential of multimodal artificial intelligence in health.

Association of Chronic Kidney Disease With Risk of Intracerebral Hemorrhage.

Importance: The evidence linking chronic kidney disease (CKD) to spontaneous intracerebral hemorrhage (ICH) is inconclusive owing to possible confounding by comorbidities that frequently coexist in patients with these 2 diseases. Objective: To determine whether there is an association between CKD and ICH risk. Design, Setting, and Participants: A 3-stage study that combined observational and genetic analyses was conducted. First, the association between CKD and ICH risk was tested in the Ethnic/Racial Variations of Intracerebral Hemorrhage (ERICH) study, a multicenter case-control study in the US. All participants with available data on CKD from ERICH were included. Second, this analysis was replicated in the UK Biobank (UKB), an ongoing population study in the UK. All participants in the UKB were included in this study. Third, mendelian randomization analyses were implemented in the UKB using 27 CKD-related genetic variants to test for genetic associations. ERICH was conducted from August 1, 2010, to August 1, 2017, and observed participants for 1 year. The UKB enrolled participants between 2006 and 2010 and will continue to observe them for 30 years. Data analysis was performed from November 11, 2019, to May 10, 2022. Exposures: CKD stages 1 to 5. Main Outcomes and Measures: The outcome of interest was ICH, ascertained in ERICH via expert review of neuroimages and in the UKB via a combination of self-reported data and International Statistical Classification of Diseases, Tenth Revision, codes. Results: In the ERICH study, a total of 2914 participants with ICH and 2954 controls who had available data on CKD were evaluated (mean [SD] age, 61.6 [14.0] years; 2433 female participants [41.5%]; 3435 male participants [58.5%]); CKD was found to be independently associated with higher risk of ICH (odds ratio [OR], 1.95; 95% CI, 1.35-2.89; P < .001). This association was not modified by race and ethnicity. Replication in the UKB with 1341 participants with ICH and 501 195 controls (mean [SD] age, 56.5 [8.1] years; 273 402 female participants [54.4%]; 229 134 male participants [45.6%]) confirmed this association (OR, 1.28; 95% CI, 1.01-1.62; P = .04). Mendelian randomization analyses indicated that genetically determined CKD was associated with ICH risk (OR, 1.56; 95% CI, 1.13-2.16; P = .007). Conclusions and Relevance: In this 3-stage study that combined observational and genetic analyses among study participants enrolled in 2 large observational studies with different characteristics and study designs, CKD was consistently associated with higher risk of ICH. Mendelian randomization analyses suggest that this association was causal. Further studies are needed to identify the specific biological pathways that mediate this association.

One-Year Outcome Trajectories and Factors Associated with Functional Recovery Among Survivors of Intracerebral and Intraventricular Hemorrhage With Initial Severe Disability.

Importance: Patients who survive severe intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) typically have poor functional outcome in the short term and understanding of future recovery is limited. Objective: To describe 1-year recovery trajectories among ICH and IVH survivors with initial severe disability and assess the association of hospital events with long-term recovery. Design, Setting, and Participants: This post hoc analysis pooled all individual patient data from the Clot Lysis: Evaluating Accelerated Resolution of Intraventricular Hemorrhage phase 3 trial (CLEAR-III) and the Minimally Invasive Surgery Plus Alteplase for Intracerebral Hemorrhage Evacuation (MISTIE-III) phase 3 trial in multiple centers across the US, Canada, Europe, and Asia. Patients were enrolled from August 1, 2010, to September 30, 2018, with a follow-up duration of 1 year. Of 999 enrolled patients, 724 survived with a day 30 modified Rankin Scale score (mRS) of 4 to 5 after excluding 13 participants with missing day 30 mRS. An additional 9 patients were excluded because of missing 1-year mRS. The final pooled cohort included 715 patients (71.6%) with day 30 mRS 4 to 5. Data were analyzed from July 2019 to January 2022. Exposures: CLEAR-III participants randomized to intraventricular alteplase vs placebo. MISTIE-III participants randomized to stereotactic thrombolysis of hematoma vs standard medical care. Main Outcomes and Measures: Primary outcome was 1-year mRS. Patients were dichotomized into good outcome at 1 year (mRS 0 to 3) vs poor outcome at 1 year (mRS 4 to 6). Multivariable logistic regression models assessed associations between prospectively adjudicated hospital events and 1-year good outcome after adjusting for demographic characteristics, ICH and IVH severity, and trial cohort. Results: Of 715 survivors, 417 (58%) were male, and the overall mean (SD) age was 60.3 (11.7) years. Overall, 174 participants (24.3%) were Black, 491 (68.6%) were White, and 49 (6.9%) were of other races (including Asian, Native American, and Pacific Islander, consolidated owing to small numbers); 98 (13.7%) were of Hispanic ethnicity. By 1 year, 129 participants (18%) had died and 308 (43%) had achieved mRS 0 to 3. In adjusted models for the combined cohort, diabetes (adjusted odds ratio [aOR], 0.50; 95% CI, 0.26-0.96), National Institutes of Health Stroke Scale (aOR, 0.93; 95% CI, 0.90-0.96), severe leukoaraiosis (aOR, 0.30; 95% CI, 0.16-0.54), pineal gland shift (aOR, 0.87; 95% CI, 0.76-0.99]), acute ischemic stroke (aOR, 0.44; 95% CI, 0.21-0.94), gastrostomy (aOR, 0.30; 95% CI, 0.17-0.50), and persistent hydrocephalus by day 30 (aOR, 0.37; 95% CI, 0.14-0.98) were associated with lack of recovery. Resolution of ICH (aOR, 1.82; 95% CI, 1.08-3.04) and IVH (aOR, 2.19; 95% CI, 1.02-4.68) by day 30 were associated with recovery to good outcome. In the CLEAR-III model, cerebral perfusion pressure less than 60 mm Hg (aOR, 0.30; 95% CI, 0.13-0.71), sepsis (aOR, 0.05; 95% CI, 0.00-0.80), and prolonged mechanical ventilation (aOR, 0.96; 95% CI, 0.92-1.00 per day), and in MISTIE-III, need for intracranial pressure monitoring (aOR, 0.35; 95% CI, 0.12-0.98), were additional factors associated with poor outcome. Thirty-day event-based models strongly predicted 1-year outcome (area under the receiver operating characteristic curve [AUC], 0.87; 95% CI, 0.83-0.90), with significantly improved discrimination over models using baseline severity factors alone (AUC, 0.76; 95% CI, 0.71-0.80; P < .001). Conclusions and Relevance: Among survivors of severe ICH and IVH with initial poor functional outcome, more than 40% recovered to good outcome by 1 year. Hospital events were strongly associated with long-term functional recovery and may be potential targets for intervention. Avoiding early pessimistic prognostication and delaying prognostication until after treatment may improve ability to predict future recovery.

Genetically-Proxied Levels of Vitamin D and Risk of Intracerebral Hemorrhage.

Background The evidence linking vitamin D (VitD) levels and spontaneous intracerebral hemorrhage (ICH) remains inconclusive. We tested the hypothesis that lower genetically determined VitD levels are associated with higher risk of ICH. Methods and Results We conducted a 2 sample Mendelian Randomization (MR) study using publicly available summary statistics from published genome-wide association studies of VitD levels (417 580 study participants) and ICH (1545 ICH cases and 1481 matched controls). We used the inverse-variance weighted approach to generate causal estimates and the MR Pleiotropy Residual Sum and Outlier and MR-Egger approaches to assess for horizontal pleiotropy. To account for known differences in their underlying mechanism, we implemented stratified analysis based on the location of the hemorrhage within the brain (lobar or nonlobar). Our primary analysis indicated that each SD decrease in genetically instrumented VitD levels was associated with a 60% increased risk of ICH (odds ratio [OR], 1.60; [95% CI, 1.05-2.43]; P=0.029). We found no evidence of horizontal pleiotropy (MR-Egger intercept and MR Pleiotropy Residual Sum and Outlier global test with P>0.05). Stratified analyses indicated that the association was stronger for nonlobar ICH (OR, 1.87; [95% CI, 1.18-2.97]; P=0.007) compared with lobar ICH (OR, 1.43; [95% CI, 0.86-2.38]; P=0.17). Conclusions Lower levels of genetically proxied VitD levels are associated with higher ICH risk. These results provide evidence for a causal role of VitD metabolism in ICH.

Analysis of Clinical Traits Associated With Cardiovascular Health, Genomic Profiles, and Neuroimaging Markers of Brain Health in Adults Without Stroke or Dementia.

Importance: The American Heart Association (AHA) Life's Simple 7 (LS7) score captures 7 biological and lifestyle factors associated with promoting cardiovascular health. Objectives: To test whether healthier LS7 profiles are associated with significant brain health benefits in persons without stroke or dementia, and to evaluate whether genomic information can recapitulate the observed LS7. Design, Setting, and Participants: This genetic association study was a nested neuroimaging study within the UK Biobank, a large population-based cohort study in the United Kingdom. Between March 2006 and October 2010, the UK Biobank enrolled 502 480 community-dwelling persons aged 40 to 69 years at recruitment. This study focused on a subset of 35 914 participants without stroke or dementia who completed research brain magnetic resonance imaging (MRI) and had available genome-wide data. All analyses were conducted between March 2021 and March 2022. Exposures: The LS7 (blood pressure, low-density lipoprotein cholesterol, hemoglobin A1c, smoking, exercise, diet, and body mass index) profiles were ascertained clinically and genomically. Independent genetic variants known to influence each of the traits included in the LS7 were assessed. The total LS7 score ranges from 0 (worst) to 14 (best) and was categorized as poor (≤4), average (>4 to 9) and optimal (>9). Main Outcomes and Measures: The outcomes of interest were 2 neuroimaging markers of brain health: white matter hyperintensity (WMH) volume and brain volume (BV). Results: The final analytical sample included 35 914 participants (mean [SD] age 64.1 [7.6] years; 18 830 [52.4%] women). For WMH, compared with persons with poor observed LS7 profiles, those with average profiles had 16% (ß = -0.18; SE, 0.03; P < .001) lower mean volume and those with optimal profiles had 39% (ß = -0.39; SE, 0.03; P < .001) lower mean volume. Similar results were obtained using the genomic LS7 for WMH (average LS7 profile: ß = -0.06; SE, 0.014; P < .001; optimal LS7 profile: ß = -0.08; SE, 0.018; P < .001). For BV, compared with persons with poor observed LS7 profiles, those with average LS7 profiles had 0.55% (ß = 0.09; SE, 0.02; P < .001) higher volume, and those with optimal LS7 profiles had 1.9% (ß = 0.14; SE, 0.02; P < .001) higher volume. The genomic LS7 profiles were not associated with BV. Conclusions and Relevance: These findings suggest that healthier LS7 profiles were associated with better profiles of 2 neuroimaging markers of brain health in persons without stroke or dementia, indicating that cardiovascular health optimization was associated with improved brain health in asymptomatic persons. Genomic information appropriately recapitulated 1 of these associations, confirming the feasibility of modeling the LS7 genomically and pointing to an important role of genetic predisposition in the observed association among cardiometabolic and lifestyle factors and brain health.

The Need for Medical Artificial Intelligence That Incorporates Prior Images.

The use of artificial intelligence (AI) has grown dramatically in the past few years in the United States and worldwide, with more than 300 AI-enabled devices approved by the U.S. Food and Drug Administration (FDA). Most of these AI-enabled applications focus on helping radiologists with detection, triage, and prioritization of tasks by using data from a single point, but clinical practice often encompasses a dynamic scenario wherein physicians make decisions on the basis of longitudinal information. Unfortunately, benchmark data sets incorporating clinical and radiologic data from several points are scarce, and, therefore, the machine learning community has not focused on developing methods and architectures suitable for these tasks. Current AI algorithms are not suited to tackle key image interpretation tasks that require comparisons to previous examinations. Focusing on the curation of data sets and algorithm development that allow for comparisons at different points will be required to advance the range of relevant tasks covered by future AI-enabled FDA-cleared devices.

The coronal plane maximum diameter of deep intracerebral hemorrhage predicts functional outcome more accurately than hematoma volume.

BACKGROUND: Among prognostic imaging variables, the hematoma volume on admission computed tomography (CT) has long been considered the strongest predictor of outcome and mortality in intracerebral hemorrhage. AIMS: To examine whether different features of hematoma shape are associated with functional outcome in deep intracerebral hemorrhage. METHODS: We analyzed 790 patients from the ATACH-2 trial, and 14 shape features were quantified. We calculated Spearman's Rho to assess the correlation between shape features and three-month modified Rankin scale (mRS) score, and the area under the receiver operating characteristic curve (AUC) to quantify the association between shape features and poor outcome defined as mRS>2 as well as mRS > 3. RESULTS: Among 14 shape features, the maximum intracerebral hemorrhage diameter in the coronal plane was the strongest predictor of functional outcome, with a maximum coronal diameter >∼3.5 cm indicating higher three-month mRS scores. The maximum coronal diameter versus hematoma volume yielded a Rho of 0.40 versus 0.35 (p = 0.006), an AUC[mRS>2] of 0.71 versus 0.68 (p = 0.004), and an AUC[mRS>3] of 0.71 versus 0.69 (p = 0.029). In multiple regression analysis adjusted for known outcome predictors, the maximum coronal diameter was independently associated with three-month mRS (p < 0.001). CONCLUSIONS: A coronal-plane maximum diameter measurement offers greater prognostic value in deep intracerebral hemorrhage than hematoma volume. This simple shape metric may expedite assessment of admission head CTs, offer a potential biomarker for hematoma size eligibility criteria in clinical trials, and may substitute volume in prognostic intracerebral hemorrhage scoring systems.