Stroke genetics informs drug discovery and risk prediction across ancestries.

Previous genome-wide association studies (GWASs) of stroke - the second leading cause of death worldwide - were conducted predominantly in populations of European ancestry1,2. Here, in cross-ancestry GWAS meta-analyses of 110,182 patients who have had a stroke (five ancestries, 33% non-European) and 1,503,898 control individuals, we identify association signals for stroke and its subtypes at 89 (61 new) independent loci: 60 in primary inverse-variance-weighted analyses and 29 in secondary meta-regression and multitrait analyses. On the basis of internal cross-ancestry validation and an independent follow-up in 89,084 additional cases of stroke (30% non-European) and 1,013,843 control individuals, 87% of the primary stroke risk loci and 60% of the secondary stroke risk loci were replicated (P < 0.05). Effect sizes were highly correlated across ancestries. Cross-ancestry fine-mapping, in silico mutagenesis analysis3, and transcriptome-wide and proteome-wide association analyses revealed putative causal genes (such as SH3PXD2A and FURIN) and variants (such as at GRK5 and NOS3). Using a three-pronged approach4, we provide genetic evidence for putative drug effects, highlighting F11, KLKB1, PROC, GP1BA, LAMC2 and VCAM1 as possible targets, with drugs already under investigation for stroke for F11 and PROC. A polygenic score integrating cross-ancestry and ancestry-specific stroke GWASs with vascular-risk factor GWASs (integrative polygenic scores) strongly predicted ischaemic stroke in populations of European, East Asian and African ancestry5. Stroke genetic risk scores were predictive of ischaemic stroke independent of clinical risk factors in 52,600 clinical-trial participants with cardiometabolic disease. Our results provide insights to inform biology, reveal potential drug targets and derive genetic risk prediction tools across ancestries.

Prevalence and associated factors of cerebral microbleeds in a rural population of the United States.

OBJECTIVE: Cerebral microbleeds (CMBs) can carry an advanced risk for the development and burden of cerebrovascular and cognitive disorders. Large-scale population-based studies are required to identify the at-risk population. METHOD: Ten percent (N = 3,056) of the Geisinger DiscovEHR Initiative Cohort participants who had brain magnetic resonance imaging (MRI) for any indication were randomly selected. Patients with CMBs were compared to an age-, gender-, body mass index-, and hypertension-matched cohort of patients without CMB. The prevalence of comorbidities and use of anticoagulation therapy was investigated in association with CMB presence (binary logistic regression), quantity (ordinal regression), and topography (multinomial regression). RESULTS: Among 3,056 selected participants, 477 (15.6 %) had CMBs in their MRI. Patients with CMBs were older and were more prevalently hypertensive, with ischemic stroke, arrhythmia, dyslipidemia, coronary artery disease, and the use of warfarin. After propensity-score matching, 477 patients with CMBs and 974 without were included for further analyses. Predictors of ≥5 CMBs were ischemic stroke (OR, 1.6; 95 % CI, 1.2 -2.0), peripheral vascular disease (OR, 1.6; 95 % CI, 1.1-2.3), and thrombocytopenia (OR, 1.9; 95 % CI, 1.2-2.9). Ischemic stroke was associated with strictly lobar CMBs more strongly than deep/infra-tentorial CMBs (OR, 2.1; 95 % CI, 1.5-3.1; vs. OR, 1.4; CI, 1.1-1.8). CONCLUSIONS: CMBs were prevalent in our white population. Old age, hypertension, anticoagulant treatment, thrombocytopenia, and a history of vascular diseases including stroke, were associated with CMBs.

Machine Learning-based Cerebral Venous Thrombosis Diagnosis with Clinical Data.

OBJECTIVES: Cerebral Venous Thrombosis (CVT) poses diagnostic challenges due to the variability in disease course and symptoms. The prognosis of CVT relies on early diagnosis. Our study focuses on developing a machine learning-based screening algorithm using clinical data from a large neurology referral center in southern Iran. METHODS: The Iran Cerebral Venous Thrombosis Registry (ICVTR code: 9001013381) provided data on 382 CVT cases from Namazi Hospital. The control group comprised of adult headache patients without CVT as confirmed by neuroimaging and was retrospectively selected from those admitted to the same hospital. We collected 60 clinical and demographic features for model development and validation. Our modeling pipeline involved imputing missing values and evaluating four machine learning algorithms: generalized linear model, random forest, support vector machine, and extreme gradient boosting. RESULTS: A total of 314 CVT cases and 575 controls were included. The highest AUROC was reached when imputation was used to estimate missing values for all the variables, combined with the support vector machine model (AUROC=0.910, Recall=0.73, Precision=0.88). The best recall was achieved also by the support vector machine model when only variables with less than 50% missing rate were included (AUROC=0.887, Recall=0.77, Precision=0.86). The random forest model yielded the best precision by using variables with less than 50% missing rate (AUROC=0.882, Recall=0.61, Precision=0.94). CONCLUSION: The application of machine learning techniques using clinical data showed promising results in accurately diagnosing CVT within our study population. This approach offers a valuable complementary assistive tool or an alternative to resource-intensive imaging methods.

Long-term mortality in ischemic stroke patients with concomitant chronic obstructive pulmonary disease.

BACKGROUND: Long-term mortality in ischemic stroke patients with concomitant COPD has been largely unexplored. This study aimed to compare long-term all-cause mortality in ischemic stroke patients with and without COPD. METHODS: This was a retrospective cohort study of ischemic stroke patients with and without COPD in the Geisinger Neuroscience Ischemic Stroke database to examine all-cause mortality up to 3 years using Kaplan-Meier estimator and Cox proportional hazards model. RESULTS: Of the 6,589 ischemic stroke patients included in this study, 5,525 (83.9%) did not have COPD (group A). Group B (n=1,006) consisted of patients with COPD diagnosis by ICD-9/10-CM codes. COPD patients in Group C (n=233) were diagnosed by spirometry, and in Group D (n=175) by both ICD-9/10-CM codes and spirometry confirmation. The survival probabilities at three years in Group B, C, and D were significantly lower than in Group A. Group B (HR=1.262, 95% CI 1.122-1.42, p<0.001) and group C (HR=1.251, 95% CI 1.01-1.55, p=0.041) had significantly lower hazard of mortality compared to group A. There was no significant difference in survival between COPD subtypes of chronic bronchitis and emphysema. Patients in Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2 stage had an increased mortality hazard compared to the GOLD 1 stage. CONCLUSIONS: While ischemic stroke patients with preexisting COPD have worse long-term survival than those without COPD, the results largely depended on the definition of COPD used. These results suggest that ischemic stroke patients with COPD need more personalized medical care to decrease long-term mortality.

Replication of Top Loci From COL4A1/2 Associated With White Matter Hyperintensity Burden in Patients With Ischemic Stroke.

BACKGROUND AND PURPOSE: The purpose of this study was to replicate the top loci associated with white matter hyperintensity (WMH) phenotypes identified by large genome-wide association studies and the loci identified from the previous candidate gene studies. METHODS: A total of 946 Geisinger MyCode patients with acute ischemic stroke with validated European ancestry and magnetic resonance imaging data were included in this study. Log-transformed WMH volume, as a quantitative trait, was calculated by a fully automated quantification process. The genome-wide association studies was carried out by a linear mixed regression model (GEMMA). A candidate-single nucleotide polymorphism analysis by including known single nucleotide polymorphisms, reported from a meta-analysis and several large GWAS for WMH, was conducted in all cases and binary converted extreme cases. RESULTS: No genome-wide significantly associated variants were identified. In a candidate-single nucleotide polymorphism study, rs9515201 (COL4A2) and rs3744028 (TRIM65), 2 known genetic loci, showed nominal or trend of association with the WMH volume (ß=0.13 and P=0.001 for rs9515201; ß=0.094 and P=0.094 for rs3744028), and replicated in a subset of extreme cases versus controls (odds ratio=1.78, P=7.74×10-4 for rs9515201; odds ratio=1.53, P=0.047 for rs3744028, respectively). MTHFR677 cytosine/thymine (rs1801133) also showed an association with the binary WMH with odds ratio=1.47 for T allele (P=0.019). CONCLUSIONS: Replication of COL4A1/2 associated with WMH reassures that the genetic risk factors for monogenic and polygenic ischemic stroke are shared at gene level.

Cysteine-Altering NOTCH3 Variants Are a Risk Factor for Stroke in the Elderly Population.

BACKGROUND AND PURPOSE: Cysteine altering NOTCH3 variants, which have previously been exclusively associated with the rare hereditary small vessel disease cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy, have a population frequency of 1:300 worldwide. Using a large population database, and taking genotype as a starting point, we aimed to determine whether individuals harboring a NOTCH3 cysteine altering variant have a higher load of small vessel disease markers on brain magnetic resonance imaging than controls, as well as a higher risk of stroke and cognitive impairment. METHODS: A cross-sectional study using integrated clinical, neuroimaging, and whole-exome sequencing data of 92 456 participants from the Geisinger DiscovEHR initiative cohort. The case group consisted of individuals harboring a NOTCH3 cysteine altering variant (n=118). The control group consisted of randomly selected age- and sex-matched individuals who did not have any nonsynonymous variants in NOTCH3 (n=184). Medical records including brain magnetic resonance imagings were evaluated for clinical and neuroimaging findings associated with small vessel disease. Group comparisons were done using Fisher exact test and ordinal logistic regression models. Risk of stroke was assessed using Cox regression. RESULTS: Of the 118 cases, 39.0% were men, mean age 58.1±16.9 years; 12.6% had a history of stroke, compared with 4.9% of controls. The risk of stroke was significantly increased after age 65 years (hazard ratio, 6.0 [95% CI, 1.4-26.3]). Dementia, mild cognitive impairment, migraine with aura and depression were equally prevalent in cases and controls. Twenty-nine cases (25%) and 45 controls (24%) had an available brain magnetic resonance imaging. After age 65 years, cases had a higher white matter lesion burden and more lacunes. A severe small vessel disease phenotype compatible with cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy was rarely seen. CONCLUSIONS: Cysteine altering NOTCH3 variants are an important contributor to the risk of stroke, lacunes, and white matter hyperintensities in the elderly population.

Effects of White Matter Hyperintensities on 90-Day Functional Outcome after Large Vessel and Non-Large Vessel Stroke.

INTRODUCTION: White matter hyperintensity (WMH) burden is a critically important cerebrovascular phenotype related to the diagnosis and prognosis of acute ischemic stroke. The effect of WMH burden on functional outcome in large vessel occlusion (LVO) stroke has only been sparsely assessed, and direct LVO and non-LVO comparisons are currently lacking. MATERIAL AND METHODS: We reviewed acute ischemic stroke patients admitted between 2009 and 2017 at a large healthcare system in the USA. Patients with LVO were identified and clinical characteristics, including 90-day functional outcomes, were assessed. Clinical brain MRIs obtained at the time of the stroke underwent quantification of WMH using a fully automated algorithm. The pipeline incorporated automated brain extraction, intensity normalization, and WMH segmentation. RESULTS: A total of 1,601 acute ischemic strokes with documented 90-day mRS were identified, including 353 (22%) with LVO. Among those strokes, WMH volume was available in 1,285 (80.3%) who had a brain MRI suitable for WMH quantification. Increasing WMH volume from 0 to 4 mL, age, female gender, a number of stroke risk factors, presence of LVO, and higher NIHSS at presentation all decreased the odds for a favorable outcome. Increasing WMH above 4 mL, however, was not associated with decreasing odds of favorable outcome. While WMH volume was associated with functional outcome in non-LVO stroke (p = 0.0009), this association between WMH and functional status was not statistically significant in the complete case multivariable model of LVO stroke (p = 0.0637). CONCLUSION: The burden of WMH has effects on 90-day functional outcome after LVO and non-LVO strokes. Particularly, increases from no measurable WMH to 4 mL of WMH correlate strongly with the outcome. Whether this relationship of increasing WMH to worse outcome is more pronounced in non-LVO than LVO strokes deserves additional investigation.

A predictive analytics model for differentiating between transient ischemic attacks (TIA) and its mimics.

BACKGROUND: Transient ischemic attack (TIA) is a brief episode of neurological dysfunction resulting from cerebral ischemia not associated with permanent cerebral infarction. TIA is associated with high diagnostic errors because of the subjective nature of findings and the lack of clinical and imaging biomarkers. The goal of this study was to design and evaluate a novel multinomial classification model, based on a combination of feature selection mechanisms coupled with logistic regression, to predict the likelihood of TIA, TIA mimics, and minor stroke. METHODS: We conducted our modeling on consecutive patients who were evaluated in our health system with an initial diagnosis of TIA in a 9-month period. We established the final diagnoses after the clinical evaluation by independent verification from two stroke neurologists. We used Recursive Feature Elimination (RFE) and Least Absolute Shrinkage and Selection Operator (LASSO) for prediction modeling. RESULTS: The RFE-based classifier correctly predicts 78% of the overall observations. In particular, the classifier correctly identifies 68% of the cases labeled as "TIA mimic" and 83% of the "TIA" discharge diagnosis. The LASSO classifier had an overall accuracy of 74%. Both the RFE and LASSO-based classifiers tied or outperformed the ABCD2 score and the Diagnosis of TIA (DOT) score. With respect to predicting TIA, the RFE-based classifier has 61.1% accuracy, the LASSO-based classifier has 79.5% accuracy, whereas the DOT score applied to the dataset yields an accuracy of 63.1%. CONCLUSION: The results of this pilot study indicate that a multinomial classification model, based on a combination of feature selection mechanisms coupled with logistic regression, can be used to effectively differentiate between TIA, TIA mimics, and minor stroke.

Dissecting genetic factors affecting phenylephrine infusion rates during anesthesia: a genome-wide association study employing EHR data.

BACKGROUND: The alpha-adrenergic agonist phenylephrine is often used to treat hypotension during anesthesia. In clinical situations, low blood pressure may require prompt intervention by intravenous bolus or infusion. Differences in responsiveness to phenylephrine treatment are commonly observed in clinical practice. Candidate gene studies indicate genetic variants may contribute to this variable response. METHODS: Pharmacological and physiological data were retrospectively extracted from routine clinical anesthetic records. Response to phenylephrine boluses could not be reliably assessed, so infusion rates were used for analysis. Unsupervised k-means clustering was conducted on clean data containing 4130 patients based on phenylephrine infusion rate and blood pressure parameters, to identify potential phenotypic subtypes. Genome-wide association studies (GWAS) were performed against average infusion rates in two cohorts: phase I (n = 1205) and phase II (n = 329). Top genetic variants identified from the meta-analysis were further examined to see if they could differentiate subgroups identified by k-means clustering. RESULTS: Three subgroups of patients with different response to phenylephrine were clustered and characterized: resistant (high infusion rate yet low mean systolic blood pressure (SBP)), intermediate (low infusion rate and low SBP), and sensitive (low infusion rate with high SBP). Differences among clusters were tabulated to assess for possible confounding influences. Comorbidity hierarchical clustering showed the resistant group had a higher prevalence of confounding factors than the intermediate and sensitive groups although overall prevalence is below 6%. Three loci with P < 1 × 10-6 were associated with phenylephrine infusion rate. Only rs11572377 with P = 6.09 × 10-7, a 3'UTR variant of EDN2, encoding a secretory vasoconstricting peptide, could significantly differentiate resistant from sensitive groups (P = 0.015 and 0.018 for phase I and phase II) or resistant from pooled sensitive and intermediate groups (P = 0.047 and 0.018). CONCLUSIONS: Retrospective analysis of electronic anesthetic records data coupled with the genetic data identified genetic variants contributing to variable sensitivity to phenylephrine infusion during anesthesia. Although the identified top gene, EDN2, has robust biological relevance to vasoconstriction by binding to endothelin type A (ETA) receptors on arterial smooth muscle cells, further functional as well as replication studies are necessary to confirm this association.

Novel Screening Tool for Stroke Using Artificial Neural Network.

BACKGROUND AND PURPOSE: The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting. METHODS: Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method. RESULTS: A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0% (95% confidence interval, 71.8-86.3) and 86.2% (95% confidence interval, 78.7-91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92% (95% confidence interval, 88.7-95.3). CONCLUSIONS: Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination.

FABS: An Intuitive Tool for Screening of Stroke Mimics in the Emergency Department.

BACKGROUND AND PURPOSE: A large number of patients with symptoms of acute cerebral ischemia are stroke mimics (SMs). In this study, we sought to develop a scoring system (FABS) for screening and stratifying SM from acute cerebral ischemia and to identify patients who may require magnetic resonance imaging to confirm or refute a diagnosis of stroke in the emergency setting. METHODS: We designed a scoring system: FABS (6 variables with 1 point for each variable present): absence of Facial droop, negative history of Atrial fibrillation, Age <50 years, systolic Blood pressure <150 mm Hg at presentation, history of Seizures, and isolated Sensory symptoms without weakness at presentation. We evaluated consecutive patients with symptoms of acute cerebral ischemia and a negative head computed tomography for any acute finding within 4.5 hours after symptom onset in 2 tertiary care stroke centers for validation of FABS. RESULTS: A total of 784 patients (41% SMs) were evaluated. Receiver operating characteristic curve (C statistic, 0.95; 95% confidence interval [CI], 0.93-0.98) indicated that FABS≥3 could identify patients with SM with 90% sensitivity (95% CI, 86%-93%) and 91% specificity (95% CI, 88%-93%). The negative predictive value and positive predictive value were 93% (95% CI, 90%-95%) and 87% (95% CI, 83%-91%), respectively. CONCLUSIONS: FABS seems to be reliable in stratifying SM from acute cerebral ischemia cases among patients in whom the head computed tomography was negative for any acute findings. It can help clinicians consider advanced imaging for further diagnosis.

Bistability analyses of CD4+ T follicular helper and regulatory cells during Helicobacter pylori infection.

T follicular helper (Tfh) cells are a highly plastic subset of CD4+ T cells specialized in providing B cell help and promoting inflammatory and effector responses during infectious and immune-mediate diseases. Helicobacter pylori is the dominant member of the gastric microbiota and exerts both beneficial and harmful effects on the host. Chronic inflammation in the context of H. pylori has been linked to an upregulation in T helper (Th)1 and Th17 CD4+ T cell phenotypes, controlled in part by the cytokine, interleukin-21. This study investigates the differentiation and regulation of Tfh cells, major producers of IL-21, in the immune response to H. pylori challenge. To better understand the conditions influencing the promotion and inhibition of a chronically elevated Tfh population, we used top-down and bottom-up approaches to develop computational models of Tfh and T follicular regulatory (Tfr) cell differentiation. Stability analysis was used to characterize the presence of two bi-stable steady states in the calibrated Tfh/Tfr models. Stochastic simulation was used to illustrate the ability of the parameter set to dictate two distinct behavioral patterns. Furthermore, sensitivity analysis helped identify the importance of various parameters on the establishment of Tfh and Tfr cell populations. The core network model was expanded into a more comprehensive and predictive model by including cytokine production and signaling pathways. From the expanded network, the interaction between TGFB-Induced Factor Homeobox 1 (Tgif1) and the retinoid X receptor (RXR) was displayed to exert control over the determination of the Tfh response. Model simulations predict that Tgif1 and RXR respectively induce and curtail Tfh responses. This computational hypothesis was validated experimentally by assaying Tgif1, RXR and Tfh in stomachs of mice infected with H. pylori.

Multiscale modeling of mucosal immune responses.

BACKGROUND: Computational techniques are becoming increasingly powerful and modeling tools for biological systems are of greater needs. Biological systems are inherently multiscale, from molecules to tissues and from nano-seconds to a lifespan of several years or decades. ENISI MSM integrates multiple modeling technologies to understand immunological processes from signaling pathways within cells to lesion formation at the tissue level. This paper examines and summarizes the technical details of ENISI, from its initial version to its latest cutting-edge implementation. IMPLEMENTATION: Object-oriented programming approach is adopted to develop a suite of tools based on ENISI. Multiple modeling technologies are integrated to visualize tissues, cells as well as proteins; furthermore, performance matching between the scales is addressed. CONCLUSION: We used ENISI MSM for developing predictive multiscale models of the mucosal immune system during gut inflammation. Our modeling predictions dissect the mechanisms by which effector CD4+ T cell responses contribute to tissue damage in the gut mucosa following immune dysregulation.Computational modeling techniques are playing increasingly important roles in advancing a systems-level mechanistic understanding of biological processes. Computer simulations guide and underpin experimental and clinical efforts. This study presents ENteric Immune Simulator (ENISI), a multiscale modeling tool for modeling the mucosal immune responses. ENISI's modeling environment can simulate in silico experiments from molecular signaling pathways to tissue level events such as tissue lesion formation. ENISI's architecture integrates multiple modeling technologies including ABM (agent-based modeling), ODE (ordinary differential equations), SDE (stochastic modeling equations), and PDE (partial differential equations). This paper focuses on the implementation and developmental challenges of ENISI. A multiscale model of mucosal immune responses during colonic inflammation, including CD4+ T cell differentiation and tissue level cell-cell interactions was developed to illustrate the capabilities, power and scope of ENISI MSM.

Empirical study using network of semantically related associations in bridging the knowledge gap.

BACKGROUND: The data overload has created a new set of challenges in finding meaningful and relevant information with minimal cognitive effort. However designing robust and scalable knowledge discovery systems remains a challenge. Recent innovations in the (biological) literature mining tools have opened new avenues to understand the confluence of various diseases, genes, risk factors as well as biological processes in bridging the gaps between the massive amounts of scientific data and harvesting useful knowledge. METHODS: In this paper, we highlight some of the findings using a text analytics tool, called ARIANA--Adaptive Robust and Integrative Analysis for finding Novel Associations. RESULTS: Empirical study using ARIANA reveals knowledge discovery instances that illustrate the efficacy of such tool. For example, ARIANA can capture the connection between the drug hexamethonium and pulmonary inflammation and fibrosis that caused the tragic death of a healthy volunteer in a 2001 John Hopkins asthma study, even though the abstract of the study was not part of the semantic model. CONCLUSION: An integrated system, such as ARIANA, could assist the human expert in exploratory literature search by bringing forward hidden associations, promoting data reuse and knowledge discovery as well as stimulating interdisciplinary projects by connecting information across the disciplines.

Many Models, Little Adoption-What Accounts for Low Uptake of Machine Learning Models for Atrial Fibrillation Prediction and Detection?

(1) Background: Atrial fibrillation (AF) is a major risk factor for stroke and is often underdiagnosed, despite being present in 13-26% of ischemic stroke patients. Recently, a significant number of machine learning (ML)-based models have been proposed for AF prediction and detection for primary and secondary stroke prevention. However, clinical translation of these technological innovations to close the AF care gap has been scant. Herein, we sought to systematically examine studies, employing ML models to predict incident AF in a population without prior AF or to detect paroxysmal AF in stroke cohorts to identify key reasons for the lack of translation into the clinical workflow. We conclude with a set of recommendations to improve the clinical translatability of ML-based models for AF. (2) Methods: MEDLINE, Embase, Web of Science, Clinicaltrials.gov, and ICTRP databases were searched for relevant articles from the inception of the databases up to September 2022 to identify peer-reviewed articles in English that used ML methods to predict incident AF or detect AF after stroke and reported adequate performance metrics. The search yielded 2815 articles, of which 16 studies using ML models to predict incident AF and three studies focusing on ML models to detect AF post-stroke were included. (3) Conclusions: This study highlights that (1) many models utilized only a limited subset of variables available from patients' health records; (2) only 37% of models were externally validated, and stratified analysis was often lacking; (3) 0% of models and 53% of datasets were explicitly made available, limiting reproducibility and transparency; and (4) data pre-processing did not include bias mitigation and sufficient details, leading to potential selection bias. Low generalizability, high false alarm rate, and lack of interpretability were identified as additional factors to be addressed before ML models can be widely deployed in the clinical care setting. Given these limitations, our recommendations to improve the uptake of ML models for better AF outcomes include improving generalizability, reducing potential systemic biases, and investing in external validation studies whilst developing a transparent modeling pipeline to ensure reproducibility.

Comparative analysis of machine learning versus traditional method for early detection of parental depression symptoms in the NICU.

Introduction: Neonatal intensive care unit (NICU) admission is a stressful experience for parents. NICU parents are twice at risk of depression symptoms compared to the general birthing population. Parental mental health problems have harmful long-term effects on both parents and infants. Timely screening and treatment can reduce these negative consequences. Objective: Our objective is to compare the performance of the traditional logistic regression with other machine learning (ML) models in identifying parents who are more likely to have depression symptoms to prioritize screening of at-risk parents. We used data obtained from parents of infants discharged from the NICU at Children's National Hospital (n = 300) from 2016 to 2017. This dataset includes a comprehensive list of demographic characteristics, depression and stress symptoms, social support, and parent/infant factors. Study design: Our study design optimized eight ML algorithms - Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, XGBoost, Naïve Bayes, K-Nearest Neighbor, and Artificial Neural Network - to identify the main risk factors associated with parental depression. We compared models based on the area under the receiver operating characteristic curve (AUC), positive predicted value (PPV), sensitivity, and F-score. Results: The results showed that all eight models achieved an AUC above 0.8, suggesting that the logistic regression-based model's performance is comparable to other common ML models. Conclusion: Logistic regression is effective in identifying parents at risk of depression for targeted screening with a performance comparable to common ML-based models.

Prevalence and Determinants of Long-Term Post-COVID Conditions in the United States: 2022 Behavioral Risk Factor Surveillance System.

BACKGROUND: A significant proportion of COVID survivors experience lingering and debilitating symptoms following acute COVID-19 infection. According to the national research plan on long COVID, it is a national priority to identify the prevalence of post-COVID conditions and their associated factors. METHOD: We performed a cross-sectional analysis of the Prevention Behavioral Risk Factor Surveillance System (BRFSS) 2022, the largest continuously gathered health survey dataset worldwide by the Centers for Disease Control. After identifying individuals with a positive history of COVID-19, we grouped COVID-19 survivors based on whether they experienced long-term post-COVID conditions. Using survey-specific R packages, we compared the two groups' socio-demographics, comorbidities, and lifestyle-related factors. A logistic regression model was used to identify factors associated with post-COVID conditions. RESULTS: The overall estimated prevalence of long-term post-COVID conditions among COVID survivors was 21.7%. Fatigue (5.7%), dyspnea (4.2%), and anosmia/ageusia (3.8%) were the most frequent symptoms. Based on multivariate logistic regression analysis, female sex, body mass index (BMI)≥25, lack of insurance, history of pulmonary disease, depression, and arthritis, being a former smoker, and sleep duration <7 h/d were associated with higher odds of post-COVID conditions. On the other hand, age >64 y/o, Black race, and annual household income ≥$100k were associated with lower odds of post-COVID conditions. CONCLUSION: Our findings indicate a notable prevalence of post-COVID conditions, particularly among middle-aged women and individuals with comorbidities or adverse lifestyles. This high-risk demographic may require long-term follow-up and support. Further investigations are essential to facilitate the development of specified healthcare and therapeutic strategies for those suffering from post-COVID conditions.

Machine Learning-Based Prediction of Stroke in Emergency Departments.

Background: Stroke misdiagnosis, associated with poor outcomes, is estimated to occur in 9% of all stroke patients. Objectives: We hypothesized that machine learning (ML) could assist in the diagnosis of ischemic stroke in emergency departments (EDs). Design: The study was conducted and reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines. We performed model development and prospective temporal validation, using data from pre- and post-COVID periods; we also performed a case study on a small cohort of previously misdiagnosed stroke patients. Methods: We used structured and unstructured electronic health records (EHRs) of 56,452 patient encounters from 13 hospitals in Pennsylvania, from September 2003 to January 2021. ML pipelines, including natural language processing, were created using pre-event clinical data and provider notes in the EDs. Results: Using pre-event information, our model's area under the receiver operating characteristics curve (AUROC) ranged from 0.88 to 0.92 with a similar range accuracy (0.87-0.90). Using provider notes, we identified five models that reached a balanced performance in terms of AUROC, sensitivity, and specificity. Model AUROC ranged from 0.93 to 0.99. Model sensitivity and specificity reached 0.90 and 0.99, respectively. Four of the top five performing models were based on the post-COVID provider notes; however, no performance difference between models tested on pre- and post-COVID was observed. Conclusion: This study leveraged pre-event and at-encounter level EHR for stroke prediction. The results indicate that available clinical information can be used for building EHR-based stroke prediction models and ED stroke alert systems.

Development and internal validation of machine learning-based models and external validation of existing risk scores for outcome prediction in patients with ischaemic stroke.

Aims: We developed new machine learning (ML) models and externally validated existing statistical models [ischaemic stroke predictive risk score (iScore) and totalled health risks in vascular events (THRIVE) scores] for predicting the composite of recurrent stroke or all-cause mortality at 90 days and at 3 years after hospitalization for first acute ischaemic stroke (AIS). Methods and results: In adults hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models [random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBOOST)] and externally validated the iScore and THRIVE scores for predicting the composite outcomes after AIS hospitalization, using data from 721 patients and 90 potential predictor variables. At 90 days and 3 years, 11 and 34% of patients, respectively, reached the composite outcome. For the 90-day prediction, the area under the receiver operating characteristic curve (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year prediction, the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE. Conclusion: The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for long-term outcome prediction. Our findings warrant comparative analyses of ML and existing statistical method-based risk prediction tools for outcome prediction after AIS in new data sets.