Variability in the analysis of a single neuroimaging dataset by many teams.

Data analysis workflows in many scientific domains have become increasingly complex and flexible. Here we assess the effect of this flexibility on the results of functional magnetic resonance imaging by asking 70 independent teams to analyse the same dataset, testing the same 9 ex-ante hypotheses1. The flexibility of analytical approaches is exemplified by the fact that no two teams chose identical workflows to analyse the data. This flexibility resulted in sizeable variation in the results of hypothesis tests, even for teams whose statistical maps were highly correlated at intermediate stages of the analysis pipeline. Variation in reported results was related to several aspects of analysis methodology. Notably, a meta-analytical approach that aggregated information across teams yielded a significant consensus in activated regions. Furthermore, prediction markets of researchers in the field revealed an overestimation of the likelihood of significant findings, even by researchers with direct knowledge of the dataset2-5. Our findings show that analytical flexibility can have substantial effects on scientific conclusions, and identify factors that may be related to variability in the analysis of functional magnetic resonance imaging. The results emphasize the importance of validating and sharing complex analysis workflows, and demonstrate the need for performing and reporting multiple analyses of the same data. Potential approaches that could be used to mitigate issues related to analytical variability are discussed.

Predicting Outcomes Following Endovascular Abdominal Aortic Aneurysm Repair Using Machine Learning.

OBJECTIVE: To develop machine learning (ML) models that predict outcomes following endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA). BACKGROUND: EVAR carries non-negligible perioperative risks; however, there are no widely used outcome prediction tools. METHODS: The National Surgical Quality Improvement Program targeted database was used to identify patients who underwent EVAR for infrarenal AAA between 2011 and 2021. Input features included 36 preoperative variables. The primary outcome was 30-day major adverse cardiovascular event (composite of myocardial infarction, stroke, or death). Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 ML models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Model robustness was evaluated with calibration plot and Brier score. Subgroup analysis was performed to assess model performance based on age, sex, race, ethnicity, and prior AAA repair. RESULTS: Overall, 16,282 patients were included. The primary outcome of 30-day major adverse cardiovascular event occurred in 390 (2.4%) patients. Our best-performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve (95% CI) of 0.95 (0.94-0.96) compared with logistic regression [0.72 [0.70-0.74)]. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.06. Model performance remained robust on all subgroup analyses. CONCLUSIONS: Our newer ML models accurately predict 30-day outcomes following EVAR using preoperative data and perform better than logistic regression. Our automated algorithms can guide risk mitigation strategies for patients being considered for EVAR.

Using Machine Learning (XGBoost) to Predict Outcomes After Infrainguinal Bypass for Peripheral Artery Disease.

OBJECTIVE: To develop machine learning (ML) algorithms that predict outcomes after infrainguinal bypass. BACKGROUND: Infrainguinal bypass for peripheral artery disease carries significant surgical risks; however, outcome prediction tools remain limited. METHODS: The Vascular Quality Initiative database was used to identify patients who underwent infrainguinal bypass for peripheral artery disease between 2003 and 2023. We identified 97 potential predictor variables from the index hospitalization [68 preoperative (demographic/clinical), 13 intraoperative (procedural), and 16 postoperative (in-hospital course/complications)]. The primary outcome was 1-year major adverse limb event (composite of surgical revision, thrombectomy/thrombolysis, or major amputation) or death. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained 6 ML models using preoperative features. The primary model evaluation metric was the area under the receiver operating characteristic curve (AUROC). The top-performing algorithm was further trained using intraoperative and postoperative features. Model robustness was evaluated using calibration plots and Brier scores. RESULTS: Overall, 59,784 patients underwent infrainguinal bypass, and 15,942 (26.7%) developed 1-year major adverse limb event/death. The best preoperative prediction model was XGBoost, achieving an AUROC (95% CI) of 0.94 (0.93-0.95). In comparison, logistic regression had an AUROC (95% CI) of 0.61 (0.59-0.63). Our XGBoost model maintained excellent performance at the intraoperative and postoperative stages, with AUROCs (95% CI's) of 0.94 (0.93-0.95) and 0.96 (0.95-0.97), respectively. Calibration plots showed good agreement between predicted and observed event probabilities with Brier scores of 0.08 (preoperative), 0.07 (intraoperative), and 0.05 (postoperative). CONCLUSIONS: ML models can accurately predict outcomes after infrainguinal bypass, outperforming logistic regression.

Using machine learning to predict outcomes following suprainguinal bypass.

OBJECTIVE: Suprainguinal bypass for peripheral artery disease (PAD) carries important surgical risks; however, outcome prediction tools remain limited. We developed machine learning (ML) algorithms that predict outcomes following suprainguinal bypass. METHODS: The Vascular Quality Initiative database was used to identify patients who underwent suprainguinal bypass for PAD between 2003 and 2023. We identified 100 potential predictor variables from the index hospitalization (68 preoperative [demographic/clinical], 13 intraoperative [procedural], and 19 postoperative [in-hospital course/complications]). The primary outcomes were major adverse limb events (MALE; composite of untreated loss of patency, thrombectomy/thrombolysis, surgical revision, or major amputation) or death at 1 year following suprainguinal bypass. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained six ML models using preoperative features (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). The best performing algorithm was further trained using intra- and postoperative data. Model robustness was evaluated using calibration plots and Brier scores. Performance was assessed on subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, symptom status, procedure type, prior intervention for PAD, concurrent interventions, and urgency. RESULTS: Overall, 16,832 patients underwent suprainguinal bypass, and 3136 (18.6%) developed 1-year MALE or death. Patients with 1-year MALE or death were older (mean age, 64.9 vs 63.5 years; P < .001) with more comorbidities, had poorer functional status (65.7% vs 80.9% independent at baseline; P < .001), and were more likely to have chronic limb-threatening ischemia (67.4% vs 47.6%; P < .001) than those without an outcome. Despite being at higher cardiovascular risk, they were less likely to receive acetylsalicylic acid or statins preoperatively and at discharge. Our best performing prediction model at the preoperative stage was XGBoost, achieving an AUROC of 0.92 (95% confidence interval [CI], 0.91-0.93). In comparison, logistic regression had an AUROC of 0.67 (95% CI, 0.65-0.69). Our XGBoost model maintained excellent performance at the intra- and postoperative stages, with AUROCs of 0.93 (95% CI, 0.92-0.94) and 0.98 (95% CI, 0.97-0.99), respectively. Calibration plots showed good agreement between predicted and observed event probabilities with Brier scores of 0.12 (preoperative), 0.11 (intraoperative), and 0.10 (postoperative). Of the top 10 predictors, nine were preoperative features including chronic limb-threatening ischemia, previous procedures, comorbidities, and functional status. Model performance remained robust on all subgroup analyses. CONCLUSIONS: We developed ML models that accurately predict outcomes following suprainguinal bypass, performing better than logistic regression. Our algorithms have potential for important utility in guiding perioperative risk mitigation strategies to prevent adverse outcomes following suprainguinal bypass.

Link among apolipoprotein E E4, gait, and cognition in neurodegenerative diseases: ONDRI study.

INTRODUCTION: Apolipoprotein E E4 allele (APOE E4) and slow gait are independently associated with cognitive impairment and dementia. However, it is unknown whether their coexistence is associated with poorer cognitive performance and its underlying mechanism in neurodegenerative diseases. METHODS: Gait speed, APOE E4, cognition, and neuroimaging were assessed in 480 older adults with neurodegeneration. Participants were grouped by APOE E4 presence and slow gait. Mediation analyses were conducted to determine if brain structures could explain the link between these factors and cognitive performance. RESULTS: APOE E4 carriers with slow gait had the lowest global cognitive performance and smaller gray matter volumes compared to non-APOE E4 carriers with normal gait. Coexistence of APOE E4 and slow gait best predicted global and domain-specific poorer cognitive performances, mediated by smaller gray matter volume. DISCUSSION: Gait slowness in APOE E4 carriers with neurodegenerative diseases may indicate extensive gray matter changes associated with poor cognition. HIGHLIGHTS: APOE E4 and slow gait are risk factors for cognitive decline in neurodegenerative diseases. Slow gait and smaller gray matter volumes are associated, independently of APOE E4. Worse cognition in APOE E4 carriers with slow gait is explained by smaller GM volume. Gait slowness in APOE E4 carriers indicates poorer cognition-related brain changes.

Predicting outcomes following open revascularization for aortoiliac occlusive disease using machine learning.

OBJECTIVE: Open surgical treatment options for aortoiliac occlusive disease carry significant perioperative risks; however, outcome prediction tools remain limited. Using machine learning (ML), we developed automated algorithms that predict 30-day outcomes following open aortoiliac revascularization. METHODS: The National Surgical Quality Improvement Program (NSQIP) targeted vascular database was used to identify patients who underwent open aortoiliac revascularization for atherosclerotic disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day major adverse limb event (MALE; composite of untreated loss of patency, major reintervention, or major amputation) or death. The 30-day secondary outcomes were individual components of the primary outcome, major adverse cardiovascular event (MACE; composite of myocardial infarction, stroke, or death), individual components of MACE, wound complication, bleeding, other morbidity, non-home discharge, and unplanned readmission. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained six ML models using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score. Variable importance scores were calculated to determine the top 10 predictive features. Performance was assessed on subgroups based on age, sex, race, ethnicity, symptom status, procedure type, and urgency. RESULTS: Overall, 9649 patients were included. The primary outcome of 30-day MALE or death occurred in 1021 patients (10.6%). Our best performing prediction model for 30-day MALE or death was XGBoost, achieving an AUROC of 0.95 (95% confidence interval [CI], 0.94-0.96). In comparison, logistic regression had an AUROC of 0.79 (95% CI, 0.77-0.81). For 30-day secondary outcomes, XGBoost achieved AUROCs between 0.87 and 0.97 (untreated loss of patency [0.95], major reintervention [0.88], major amputation [0.96], death [0.97], MACE [0.95], myocardial infarction [0.88], stroke [0.93], wound complication [0.94], bleeding [0.87], other morbidity [0.96], non-home discharge [0.90], and unplanned readmission [0.91]). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.05. The strongest predictive feature in our algorithm was chronic limb-threatening ischemia. Model performance remained robust on all subgroup analyses of specific demographic/clinical populations. CONCLUSIONS: Our ML models accurately predict 30-day outcomes following open aortoiliac revascularization using preoperative data, performing better than logistic regression. They have potential for important utility in guiding risk-mitigation strategies for patients being considered for open aortoiliac revascularization to improve outcomes.

Using machine learning to predict outcomes following carotid endarterectomy.

OBJECTIVE: Prediction of outcomes following carotid endarterectomy (CEA) remains challenging, with a lack of standardized tools to guide perioperative management. We used machine learning (ML) to develop automated algorithms that predict outcomes following CEA. METHODS: The Vascular Quality Initiative (VQI) database was used to identify patients who underwent CEA between 2003 and 2022. We identified 71 potential predictor variables (features) from the index hospitalization (43 preoperative [demographic/clinical], 21 intraoperative [procedural], and 7 postoperative [in-hospital complications]). The primary outcome was stroke or death at 1 year following CEA. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained six ML models using preoperative features (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). After selecting the best performing algorithm, additional models were built using intra- and postoperative data. Model robustness was evaluated using calibration plots and Brier scores. Performance was assessed on subgroups based on age, sex, race, ethnicity, insurance status, symptom status, and urgency of surgery. RESULTS: Overall, 166,369 patients underwent CEA during the study period. In total, 7749 patients (4.7%) had the primary outcome of stroke or death at 1 year. Patients with an outcome were older with more comorbidities, had poorer functional status, and demonstrated higher risk anatomic features. They were also more likely to undergo intraoperative surgical re-exploration and have in-hospital complications. Our best performing prediction model at the preoperative stage was XGBoost, achieving an AUROC of 0.90 (95% confidence interval [CI], 0.89-0.91). In comparison, logistic regression had an AUROC of 0.65 (95% CI, 0.63-0.67), and existing tools in the literature demonstrate AUROCs ranging from 0.58 to 0.74. Our XGBoost models maintained excellent performance at the intra- and postoperative stages, with AUROCs of 0.90 (95% CI, 0.89-0.91) and 0.94 (95% CI, 0.93-0.95), respectively. Calibration plots showed good agreement between predicted and observed event probabilities with Brier scores of 0.15 (preoperative), 0.14 (intraoperative), and 0.11 (postoperative). Of the top 10 predictors, eight were preoperative features, including comorbidities, functional status, and previous procedures. Model performance remained robust on all subgroup analyses. CONCLUSIONS: We developed ML models that accurately predict outcomes following CEA. Our algorithms perform better than logistic regression and existing tools, and therefore, have potential for important utility in guiding perioperative risk mitigation strategies to prevent adverse outcomes.

Using machine learning to predict outcomes following open abdominal aortic aneurysm repair.

OBJECTIVE: Prediction of outcomes following open abdominal aortic aneurysm (AAA) repair remains challenging with a lack of widely used tools to guide perioperative management. We developed machine learning (ML) algorithms that predict outcomes following open AAA repair. METHODS: The Vascular Quality Initiative (VQI) database was used to identify patients who underwent elective open AAA repair between 2003 and 2023. Input features included 52 preoperative demographic/clinical variables. All available preoperative variables from VQI were used to maximize predictive performance. The primary outcome was in-hospital major adverse cardiovascular event (MACE; composite of myocardial infarction, stroke, or death). Secondary outcomes were individual components of the primary outcome, other in-hospital complications, and 1-year mortality and any reintervention. We split our data into training (70%) and test (30%) sets. Using 10-fold cross-validation, six ML models were trained using preoperative features (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score. The top 10 predictive features in our final model were determined based on variable importance scores. Performance was assessed on subgroups based on age, sex, race, ethnicity, rurality, median area deprivation index, proximal clamp site, prior aortic surgery, and concomitant procedures. RESULTS: Overall, 12,027 patients were included. The primary outcome of in-hospital MACE occurred in 630 patients (5.2%). Compared with patients without a primary outcome, those who developed in-hospital MACE were older with more comorbidities, demonstrated poorer functional status, had more complex aneurysms, and were more likely to require concomitant procedures. Our best performing prediction model for in-hospital MACE was XGBoost, achieving an AUROC of 0.93 (95% confidence interval, 0.92-0.94). Comparatively, logistic regression had an AUROC of 0.71 (95% confidence interval, 0.70-0.73). For secondary outcomes, XGBoost achieved AUROCs between 0.84 and 0.94. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.05. These findings highlight the excellent predictive performance of the XGBoost model. The top three predictive features in our algorithm for in-hospital MACE following open AAA repair were: (1) coronary artery disease; (2) American Society of Anesthesiologists classification; and (3) proximal clamp site. Model performance remained robust on all subgroup analyses. CONCLUSIONS: Open AAA repair outcomes can be accurately predicted using preoperative data with our ML models, which perform better than logistic regression. Our automated algorithms can help guide risk-mitigation strategies for patients being considered for open AAA repair to improve outcomes.

Machine learning to predict outcomes following endovascular abdominal aortic aneurysm repair.

BACKGROUND: Endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA) carries important perioperative risks; however, there are no widely used outcome prediction tools. The aim of this study was to apply machine learning (ML) to develop automated algorithms that predict 1-year mortality following EVAR. METHODS: The Vascular Quality Initiative database was used to identify patients who underwent elective EVAR for infrarenal AAA between 2003 and 2023. Input features included 47 preoperative demographic/clinical variables. The primary outcome was 1-year all-cause mortality. Data were split into training (70 per cent) and test (30 per cent) sets. Using 10-fold cross-validation, 6 ML models were trained using preoperative features with logistic regression as the baseline comparator. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score. RESULTS: Some 63 655 patients were included. One-year mortality occurred in 3122 (4.9 per cent) patients. The best performing prediction model for 1-year mortality was XGBoost, achieving an AUROC (95 per cent c.i.) of 0.96 (0.95-0.97). Comparatively, logistic regression had an AUROC (95 per cent c.i.) of 0.69 (0.68-0.71). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.04. The top 3 predictive features in the algorithm were 1) unfit for open AAA repair, 2) functional status, and 3) preoperative dialysis. CONCLUSIONS: In this data set, machine learning was able to predict 1-year mortality following EVAR using preoperative data and outperformed standard logistic regression models.

White matter hyperintensity burden predicts cognitive but not motor decline in Parkinson's disease: results from the Ontario Neurodegenerative Diseases Research Initiative.

BACKGROUND AND PURPOSE: The pathophysiology of Parkinson's disease (PD) negatively affects brain network connectivity, and in the presence of brain white matter hyperintensities (WMHs) cognitive and motor impairments seem to be aggravated. However, the role of WMHs in predicting accelerating symptom worsening remains controversial. The objective was to investigate whether location and segmental brain WMH burden at baseline predict cognitive and motor declines in PD after 2 years. METHODS: Ninety-eight older adults followed longitudinally from Ontario Neurodegenerative Diseases Research Initiative with PD of 3-8 years in duration were included. Percentages of WMH volumes at baseline were calculated by location (deep and periventricular) and by brain region (frontal, temporal, parietal, occipital lobes and basal ganglia + thalamus). Cognitive and motor changes were assessed from baseline to 2-year follow-up. Specifically, global cognition, attention, executive function, memory, visuospatial abilities and language were assessed as were motor symptoms evaluated using the Movement Disorder Society Unified Parkinson's Disease Rating Scale Part III, spatial-temporal gait variables, Freezing of Gait Questionnaire and Activities Specific Balance Confidence Scale. RESULTS: Regression analysis adjusted for potential confounders showed that total and periventricular WMHs at baseline predicted decline in global cognition (p < 0.05). Also, total WMH burden predicted the decline of executive function (p < 0.05). Occipital WMH volumes also predicted decline in global cognition, visuomotor attention and visuospatial memory declines (p < 0.05). WMH volumes at baseline did not predict motor decline. CONCLUSION: White matter hyperintensity burden at baseline predicted cognitive but not motor decline in early to mid-stage PD. The motor decline observed after 2 years in these older adults with PD is probably related to the primary neurodegenerative process than comorbid white matter pathology.

Characteristics of the Ontario Neurodegenerative Disease Research Initiative cohort.

INTRODUCTION: Understanding synergies between neurodegenerative and cerebrovascular pathologies that modify dementia presentation represents an important knowledge gap. METHODS: This multi-site, longitudinal, observational cohort study recruited participants across prevalent neurodegenerative diseases and cerebrovascular disease and assessed participants comprehensively across modalities. We describe univariate and multivariate baseline features of the cohort and summarize recruitment, data collection, and curation processes. RESULTS: We enrolled 520 participants across five neurodegenerative and cerebrovascular diseases. Median age was 69 years, median Montreal Cognitive Assessment score was 25, median independence in activities of daily living was 100% for basic and 93% for instrumental activities. Spousal study partners predominated; participants were often male, White, and more educated. Milder disease stages predominated, yet cohorts reflect clinical presentation. DISCUSSION: Data will be shared with the global scientific community. Within-disease and disease-agnostic approaches are expected to identify markers of severity, progression, and therapy targets. Sampling characteristics also provide guidance for future study design.

Perivascular spaces mediate a relationship between diabetes and other cerebral small vessel disease markers in cerebrovascular and neurodegenerative diseases.

Type 2 diabetes mellitus (T2DM) and hypertension are risk factors for cerebral small vessel disease (SVD); however, few studies have characterised their relationships with MRI-visible perivascular spaces (PVS). MRI was used to quantify deep (d) and periventricular (p) white matter hyperintensities (WMH), lacunes, PVS in the white matter (wmPVS) or basal ganglia (bgPVS), and diffusion metrics in white matter. Patients with T2DM had greater wmPVS volume and there were greater wmPVS volumes in patients with T2DM and hypertension together. Counterfactual moderated mediation models found indirect effects of T2DM on volumes of other SVD and diffusion markers that were mediated by wmPVS: pWMH, dWMH, periventricular lacunes, and deep lacunes, and progression of deep lacunes over 1 year, in patients with hypertension, but not in patients without hypertension. Studying the regulation of cortical perivascular fluid dynamics may reveal mechanisms that mediate the impact of T2DM on cerebral small vessels.

Caregiving concerns and clinical characteristics across neurodegenerative and cerebrovascular disorders in the Ontario neurodegenerative disease research initiative.

OBJECTIVES: Caregiving burdens are a substantial concern in the clinical care of persons with neurodegenerative disorders. In the Ontario Neurodegenerative Disease Research Initiative, we used the Zarit's Burden Interview (ZBI) to examine: (1) the types of burdens captured by the ZBI in a cross-disorder sample of neurodegenerative conditions (2) whether there are categorical or disorder-specific effects on caregiving burdens, and (3) which demographic, clinical, and cognitive measures are related to burden(s) in neurodegenerative disorders? METHODS/DESIGN: N = 504 participants and their study partners (e.g., family, friends) across: Alzheimer's disease/mild cognitive impairment (AD/MCI; n = 120), Parkinson's disease (PD; n = 136), amyotrophic lateral sclerosis (ALS; n = 38), frontotemporal dementia (FTD; n = 53), and cerebrovascular disease (CVD; n = 157). Study partners provided information about themselves, and information about the clinical participants (e.g., activities of daily living (ADL)). We used Correspondence Analysis to identify types of caregiving concerns in the ZBI. We then identified relationships between those concerns and demographic and clinical measures, and a cognitive battery. RESULTS: We found three components in the ZBI. The first was "overall burden" and was (1) strongly related to increased neuropsychiatric symptoms (NPI severity r = 0.586, NPI distress r = 0.587) and decreased independence in ADL (instrumental ADLs r = -0.566, basic ADLs r = -0.43), (2) moderately related to cognition (MoCA r = -0.268), and (3) showed little-to-no differences between disorders. The second and third components together showed four types of caregiving concerns: current care of the person with the neurodegenerative disease, future care of the person with the neurodegenerative disease, personal concerns of study partners, and social concerns of study partners. CONCLUSIONS: Our results suggest that the experience of caregiving in neurodegenerative and cerebrovascular diseases is individualized and is not defined by diagnostic categories. Our findings highlight the importance of targeting ADL and neuropsychiatric symptoms with caregiver-personalized solutions.

Parkinson's Disease, NOTCH3 Genetic Variants, and White Matter Hyperintensities.

BACKGROUND: White matter hyperintensities (WMH) on magnetic resonance imaging may influence clinical presentation in patients with Parkinson's disease (PD), although their significance and pathophysiological origins remain unresolved. Studies examining WMH have identified pathogenic variants in NOTCH3 as an underlying cause of inherited forms of cerebral small vessel disease. METHODS: We examined NOTCH3 variants, WMH volumes, and clinical correlates in 139 PD patients in the Ontario Neurodegenerative Disease Research Initiative cohort. RESULTS: We identified 13 PD patients (~9%) with rare (<1% of general population), nonsynonymous NOTCH3 variants. Bayesian linear modeling demonstrated a doubling of WMH between variant negative and positive patients (3.1 vs. 6.9 mL), with large effect sizes for periventricular WMH (d = 0.8) and lacunes (d = 1.2). Negative correlations were observed between WMH and global cognition (r = -0.2). CONCLUSION: The NOTCH3 rare variants in PD may significantly contribute to increased WMH burden, which in turn may negatively influence cognition. © 2020 International Parkinson and Movement Disorder Society.

Methods for Improving Screening for Vascular Cognitive Impairment Using the Montreal Cognitive Assessment.

BACKGROUND: Vascular cognitive impairment (VCI) post-stroke is frequent but may go undetected, which highlights the need to better screen cognitive functioning following a stroke. AIM: We examined the clinical utility of the Montreal Cognitive Assessment (MoCA) in detecting cognitive impairment against a gold-standard neuropsychological battery. METHODS: We assessed cognitive status with a comprehensive battery of neuropsychological tests in 161 individuals who were at least 3-months post-stroke. We used receiver operating characteristic (ROC) curves to identify two cut points for the MoCA to maximize sensitivity and specificity at a minimum 90% threshold. We examined the utility of the Symbol Digit Modalities Test, a processing speed measure, to determine whether this additional metric would improve classification relative to the MoCA total score alone. RESULTS: Using two cut points, 27% of participants scored ≤ 23 and were classified as high probability of cognitive impairment (sensitivity 92%), and 24% of participants scored ≥ 28 and were classified as low probability of cognitive impairment (specificity 91%). The remaining 48% of participants scored from 24 to 27 and were classified as indeterminate probability of cognitive impairment. The addition of a processing speed measure improved classification for the indeterminate group by correctly identifying 65% of these individuals, for an overall classification accuracy of 79%. CONCLUSIONS: The utility of the MoCA in detecting cognitive impairment post-stroke is improved when using a three-category approach. The addition of a processing speed measure provides a practical and efficient method to increase confidence in the determined outcome while minimally extending the screening routine for VCI.

The utility of multivariate outlier detection techniques for data quality evaluation in large studies: an application within the ONDRI project.

BACKGROUND: Large and complex studies are now routine, and quality assurance and quality control (QC) procedures ensure reliable results and conclusions. Standard procedures may comprise manual verification and double entry, but these labour-intensive methods often leave errors undetected. Outlier detection uses a data-driven approach to identify patterns exhibited by the majority of the data and highlights data points that deviate from these patterns. Univariate methods consider each variable independently, so observations that appear odd only when two or more variables are considered simultaneously remain undetected. We propose a data quality evaluation process that emphasizes the use of multivariate outlier detection for identifying errors, and show that univariate approaches alone are insufficient. Further, we establish an iterative process that uses multiple multivariate approaches, communication between teams, and visualization for other large-scale projects to follow. METHODS: We illustrate this process with preliminary neuropsychology and gait data for the vascular cognitive impairment cohort from the Ontario Neurodegenerative Disease Research Initiative, a multi-cohort observational study that aims to characterize biomarkers within and between five neurodegenerative diseases. Each dataset was evaluated four times: with and without covariate adjustment using two validated multivariate methods - Minimum Covariance Determinant (MCD) and Candès' Robust Principal Component Analysis (RPCA) - and results were assessed in relation to two univariate methods. Outlying participants identified by multiple multivariate analyses were compiled and communicated to the data teams for verification. RESULTS: Of 161 and 148 participants in the neuropsychology and gait data, 44 and 43 were flagged by one or both multivariate methods and errors were identified for 8 and 5 participants, respectively. MCD identified all participants with errors, while RPCA identified 6/8 and 3/5 for the neuropsychology and gait data, respectively. Both outperformed univariate approaches. Adjusting for covariates had a minor effect on the participants identified as outliers, though did affect error detection. CONCLUSIONS: Manual QC procedures are insufficient for large studies as many errors remain undetected. In these data, the MCD outperforms the RPCA for identifying errors, and both are more successful than univariate approaches. Therefore, data-driven multivariate outlier techniques are essential tools for QC as data become more complex.

Semantically defined subdomains of functional neuroimaging literature and their corresponding brain regions.

The functional neuroimaging literature has become increasingly complex and thus difficult to navigate. This complexity arises from the rate at which new studies are published and from the terminology that varies widely from study-to-study and even more so from discipline-to-discipline. One way to investigate and manage this problem is to build a "semantic space" that maps the different vocabulary used in functional neuroimaging literature. Such a semantic space will also help identify the primary research domains of neuroimaging and their most commonly reported brain regions. In this work, we analyzed the multivariate semantic structure of abstracts in Neurosynth and found that there are six primary domains of the functional neuroimaging literature, each with their own preferred reported brain regions. Our analyses also highlight possible semantic sources of reported brain regions within and across domains because some research topics (e.g., memory disorders, substance use disorder) use heterogeneous terminology. Furthermore, we highlight the growth and decline of the primary domains over time. Finally, we note that our techniques and results form the basis of a "recommendation engine" that could help readers better navigate the neuroimaging literature.

Crowdsourced estimation of cognitive decline and resilience in Alzheimer's disease.

Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer's disease. The Alzheimer's disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer's disease based on high dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for prediction of cognitive performance.

Unique aspects of impulsive traits in substance use and overeating: specific contributions of common assessments of impulsivity.

UNLABELLED: Abstract Background: Impulsivity is a complex trait often studied in substance abuse and overeating disorders, but the exact nature of impulsivity traits and their contribution to these disorders are still debated. Thus, understanding how to measure impulsivity is essential for comprehending addictive behaviors. OBJECTIVES: Identify unique impulsivity traits specific to substance use and overeating. METHODS: Impulsive Sensation Seeking (ImpSS) and Barratt's Impulsivity scales (BIS) Scales were analyzed with a non-parametric factor analytic technique (discriminant correspondence analysis) to identify group-specific traits on 297 individuals from five groups: Marijuana (n = 88), Nicotine (n = 82), Overeaters (n = 27), Marijuauna + Nicotine (n = 63), and CONTROLs (n = 37). RESULTS: A significant overall factor structure revealed three components of impulsivity that explained respectively 50.19% (pperm < 0.0005), 24.18% (pperm < 0.0005), and 15.98% (pperm < 0.0005) of the variance. All groups were significantly different from one another. When analyzed together, the BIS and ImpSS produce a multi-factorial structure that identified the impulsivity traits specific to these groups. The group specific traits are (1) CONTROL: low impulse, avoids thrill-seeking behaviors; (2) Marijuana: seeks mild sensation, is focused and attentive; (3) Marijuana + Nicotine: pursues thrill-seeking, lacks focus and attention; (4) Nicotine: lacks focus and planning; (5) Overeating: lacks focus, but plans (short and long term). CONCLUSIONS: Our results reveal impulsivity traits specific to each group. This may provide better criteria to define spectrums and trajectories - instead of categories - of symptoms for substance use and eating disorders. Defining symptomatic spectrums could be an important step forward in diagnostic strategies.

Predicting Outcomes Following Lower Extremity Endovascular Revascularization Using Machine Learning.

BACKGROUND: Lower extremity endovascular revascularization for peripheral artery disease carries nonnegligible perioperative risks; however, outcome prediction tools remain limited. Using machine learning, we developed automated algorithms that predict 30-day outcomes following lower extremity endovascular revascularization. METHODS AND RESULTS: The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity endovascular revascularization (angioplasty, stent, or atherectomy) for peripheral artery disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day postprocedural major adverse limb event (composite of major reintervention, untreated loss of patency, or major amputation) or death. Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Overall, 21 886 patients were included, and 30-day major adverse limb event/death occurred in 1964 (9.0%) individuals. The best performing model for predicting 30-day major adverse limb event/death was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.94). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.70-0.74). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.09. The top 3 predictive features in our algorithm were (1) chronic limb-threatening ischemia, (2) tibial intervention, and (3) congestive heart failure. CONCLUSIONS: Our machine learning models accurately predict 30-day outcomes following lower extremity endovascular revascularization using preoperative data with good discrimination and calibration. Prospective validation is warranted to assess for generalizability and external validity.