Association of COVID-19 with short- and long-term risk of cardiovascular disease and mortality: a prospective cohort in UK Biobank

Cardiovascular Research, Journal Year: 2023, Volume and Issue: 119(8), P. 1718 - 1727

Published: Jan. 19, 2023

This study aims to evaluate the short- and long-term associations between COVID-19 development of cardiovascular disease (CVD) outcomes mortality in general population.A prospective cohort patients with infection 16 March 2020 30 November was identified from UK Biobank, followed for up 18 months, until 31 August 2021. Based on age (within 5 years) sex, each case randomly matched 10 participants without two cohorts-a contemporary a historical 2018 2018. The characteristics groups were further adjusted propensity score-based marginal mean weighting through stratification. To determine association CVD within 21 days diagnosis (acute phase) after this period (post-acute phase), Cox regression employed. In acute phase, (n = 7584) associated significantly higher short-term risk {hazard ratio (HR): 4.3 [95% confidence interval (CI): 2.6- 6.9]; HR: 5.0 (95% CI: 3.0-8.1)} all-cause [HR: 81.1 58.5-112.4); 67.5 49.9-91.1)] than 75 790) controls 774), respectively. Regarding post-acute 7139) persisted 1.4 1.2-1.8); 1.3 1.1- 1.6)] 4.3-5.8); 4.5 3.9-5.2) compared 71 296) 314), respectively.COVID-19 infection, including long-COVID, is increased risks mortality. Ongoing monitoring signs symptoms developing these complications post till at least year recovery may benefit infected patients, especially those severe disease.

Language: Английский

---

Prognostic models in COVID-19 infection that predict severity: a systematic review

European Journal of Epidemiology, Journal Year: 2023, Volume and Issue: 38(4), P. 355 - 372

Published: Feb. 25, 2023

Abstract Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize critically appraise the available studies that have developed, assessed and/or validated of predicting health outcomes. searched six bibliographic databases identify published articles investigated univariable multivariable adverse outcomes in adult patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) mortality. identified 314 eligible from more than 40 countries, with 152 these presenting mortality, 66 progression severe or critical illness, 35 mortality ICU admission combined, 17 only, while remaining 44 reported prediction for mechanical ventilation (MV) combination multiple The sample size included varied 11 7,704,171 participants, mean age ranging 18 93 years. There were 353 investigated, area under curve (AUC) 0.44 0.99. A great proportion (61.5%, 193 out 314) internal external validation replication. In 312 (99.4%) studies, be at high risk bias due uncertainties challenges surrounding methodological rigor, sampling, handling missing data, failure deal overfitting heterogeneous definitions severity While several been described literature, they are limited generalizability deficiencies addressing fundamental statistical concerns. Future large, multi-centric well-designed prospective needed clarify uncertainties.

Language: Английский

---

Toward artificial intelligence (AI) applications in the determination of COVID-19 infection severity: considering AI as a disease control strategy in future pandemics

Iranian Journal of Blood and Cancer, Journal Year: 2023, Volume and Issue: 15(3), P. 93 - 111

Published: Aug. 1, 2023

Toward artificial intelligence (AI) applications in the determination of COVID-19 infection severity: considering AI as a disease control strategy future pandemics

Language: Английский

---

Variables associated with cognitive function: an exposome-wide and mendelian randomization analysis

Alzheimer s Research & Therapy, Journal Year: 2025, Volume and Issue: 17(1)

Published: Jan. 7, 2025

Evidence indicates that cognitive function is influenced by potential environmental factors. We aimed to determine the variables influencing function. Our study included 164,463 non-demented adults (89,644 [54.51%] female; mean [SD] age, 56.69 [8.14] years) from UK Biobank who completed four assessments at baseline. 364 were finally extracted for analysis through a rigorous screening process. performed univariate analyses identify significantly associated with each in two equal-sized split discovery and replication datasets. Subsequently, identified further assessed multivariable model. Additionally, model, we explored associations longitudinal decline. Moreover, one- two- sample Mendelian randomization (MR) conducted confirm genetic associations. Finally, quality of pooled evidence between was evaluated. 252 (69%) exhibited significant least one dataset. Of these, 231 (92%) successfully replicated. our 41 function, spanning categories such as education, socioeconomic status, lifestyle factors, body measurements, mental health, medical conditions, early life household characteristics. Among these variables, 12 more than domain, all subgroup analyses. And LASSO, rigde, principal component indicated robustness primary results. among Furthermore, 22 supported one-sample MR analysis, 5 confirmed two-sample analysis. 10 rated high. Based on adopting favorable 38% 34% decreased risks dementia Alzheimer's disease (AD). Overall, constructed an database which could contribute prevention impairment dementia.

Language: Английский

---

Predictors of developing severe COVID-19 among hospitalized patients: a retrospective study

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 11

Published: Jan. 14, 2025

COVID-19 poses a significant threat to global public health. As the severity of SARS-CoV-2 infection varies among individuals, elucidating risk factors for severe is important predicting and preventing illness progression, as well lowering case fatality rates. This work aimed explore developing enhance quality care provided patients prevent complications. A retrospective study was conducted in Saudi Arabia's eastern province, including all aged 18 years or older who were hospitalized at Prince Saud Bin Jalawi Hospital July 2020. Comparative tests both univariate multivariate logistic regression analyses performed identify poor outcomes. Based on comparative statistical with statistically significantly associated age had higher respiratory rate, longer hospital stay, prevalence diabetes than non-severe cases. They also exhibited association high levels potassium, urea, creatinine, lactate dehydrogenase (LDH), D-dimer, aspartate aminotransferase (AST). The analysis shows that having diabetes, acute chest X-ray scores, old age, prolong hospitalization, potassium dehydrogenase, using insulin, heparin, corticosteroids, favipiravir azithromycin COVID-19. However, after adjustments analysis, sole predictor serum LDH (p = 0.002; OR 1.005; 95% CI 1.002-1.009). In addition, odds being prescribed 0.001; 13.725; 3.620-52.043). Regarding outcomes, median stay duration death, intensive unit admission (ICU), mechanical ventilation. On other hand, azithromycin, beta-agonists, reduced mortality, ICU admission, need sheds light numerous parameters may be utilized construct prediction model evaluating no protective included this model.

Language: Английский

---

A machine learning model on Real World Data for predicting progression to Acute Respiratory Distress Syndrome (ARDS) among COVID-19 patients

PLoS ONE, Journal Year: 2022, Volume and Issue: 17(7), P. e0271227 - e0271227

Published: July 28, 2022

Introduction Identifying COVID-19 patients that are most likely to progress a severe infection is crucial for optimizing care management and increasing the likelihood of survival. This study presents machine learning model predicts cases COVID-19, defined as presence Acute Respiratory Distress Syndrome (ARDS) highlights different risk factors play significant role in disease progression. Methods A cohort composed 289,351 diagnosed with April 2020 was created using US administrative claims data from Oct 2015 Jul 2020. For each patient, information about 817 diagnoses, were collected medical history ahead infection. The primary outcome ARDS 4 months following randomly split into training set used development, test evaluation validation real-world performance estimation. Results We analyzed three classifiers predict ARDS. Among algorithms considered, Gradient Boosting Decision Tree had highest an AUC 0.695 (95% CI, 0.679–0.709) AUPRC 0.0730 0.0676 – 0.0823), showing 40% increase against baseline classifier. panel five clinicians also compare predictive ability clinical experts. comparison indicated our on par or outperforms predictions made by clinicians, both terms precision recall. Conclusion uses patient perform its have been extensively linked severity specialized literature. contributing diagnosis can be easily retrieved early screening infected patients. Overall, proposed could promising tool deploy healthcare setting facilitate optimize

Language: Английский

---

An Integrative Explainable Artificial Intelligence Approach to Analyze Fine-Scale Land-Cover and Land-Use Factors Associated with Spatial Distributions of Place of Residence of Reported Dengue Cases

Tropical Medicine and Infectious Disease, Journal Year: 2023, Volume and Issue: 8(4), P. 238 - 238

Published: April 20, 2023

Dengue fever is a prevalent mosquito-borne disease that burdens communities in subtropical and tropical regions. transmission ecologically complex; several environmental conditions are critical for the spatial temporal distribution of dengue. Interannual variability dengue well-studied; however, effects land cover use yet to be investigated. Therefore, we applied an explainable artificial intelligence (AI) approach integrate EXtreme Gradient Boosting Shapley Additive Explanation (SHAP) methods evaluate patterns residences reported cases based on various fine-scale land-cover land-use types, Shannon's diversity index, household density Kaohsiung City, Taiwan, between 2014 2015. We found proportions general roads residential areas play essential roles case with nonlinear patterns. Agriculture-related features were negatively associated incidence. Additionally, index showed U-shaped relationship infection, SHAP dependence plots different relationships types Finally, landscape-based prediction maps generated from best-fit model highlighted high-risk zones within metropolitan region. The AI delineated precise associations diverse characteristics. This information beneficial resource allocation control strategy modification.

Language: Английский

---

Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients

Clinical & Experimental Immunology, Journal Year: 2024, Volume and Issue: 216(3), P. 293 - 306

Published: Feb. 28, 2024

Sepsis is characterized by a dysfunctional host response to infection culminating in life-threatening organ failure that requires complex patient management and rapid intervention. Timely diagnosis of the underlying cause sepsis crucial, identifying those at risk complications death imperative for triaging treatment resource allocation. Here, we explored potential explainable machine learning models predict mortality causative pathogen patients. By using modelling pipeline employing multiple feature selection algorithms, demonstrate feasibility integrative patterns from clinical parameters, plasma biomarkers, extensive phenotyping blood immune cells. While no single variable had sufficient predictive power, combined five more features showed macro area under curve (AUC) 0.85 90-day after diagnosis, AUC 0.86 discriminate between Gram-positive Gram-negative bacterial infections. Parameters associated with cellular contributed most mortality, notably, proportion T cells among PBMCs, together expression CXCR3 CD4+ CD25 mucosal-associated invariant (MAIT) Frequencies Vδ2+ γδ profound impact on prediction infections, alongside other T-cell-related variables total neutrophil count. Overall, our findings highlight added value measuring activation conventional unconventional patients combination immunological, biochemical, parameters.

Language: Английский

---

Clinical prognosis evaluation of COVID-19 patients: An interpretable hybrid machine learning approach

Current Research in Translational Medicine, Journal Year: 2021, Volume and Issue: 70(1), P. 103319 - 103319

Published: Oct. 30, 2021

Language: Английский

---

Importance of sex and gender factors for COVID-19 infection and hospitalisation: a sex-stratified analysis using machine learning in UK Biobank data

BMJ Open, Journal Year: 2022, Volume and Issue: 12(5), P. e050450 - e050450

Published: May 1, 2022

Objective To examine sex and gender roles in COVID-19 test positivity hospitalisation sex-stratified predictive models using machine learning. Design Cross-sectional study. Setting UK Biobank prospective cohort. Participants tested between 16 March 2020 18 May were analysed. Main outcome measures The endpoints of the study hospitalisation. Forty-two individuals’ demographics, psychosocial factors comorbidities used as likely determinants outcomes. Gradient boosting was for building prediction models. Results Of 4510 individuals (51.2% female, mean age=68.5±8.9 years), 29.4% positive. Males more to be positive than females (31.6% vs 27.3%, p=0.001). In females, living deprived areas, lower income, increased low-density lipoprotein (LDL) high-density (HDL) ratio, working night shifts with a greater number family members associated higher likelihood test. While males, body mass index LDL HDL ratio Older age adverse cardiometabolic characteristics most prominent variables test-positive patients both overall Conclusion High-risk jobs, crowded arrangements areas infection while high-risk influential males. Gender-related have impact on females; hence, they should considered identifying priority groups vaccination campaigns.

Language: Английский

---