A machine learning-based predictive model for the in-hospital mortality of critically ill patients with atrial fibrillation DOI Creative Commons

Yanting Luo,

Ruimin Dong,

Jinlai Liu

et al.

International Journal of Medical Informatics, Journal Year: 2024, Volume and Issue: 191, P. 105585 - 105585

Published: Aug. 1, 2024

Atrial fibrillation (AF) is common among intensive care unit (ICU) patients and significantly raises the in-hospital mortality rate. Existing scoring systems or models have limited predictive capabilities for AF in ICU. Our study developed validated machine learning to predict risk of ICU with AF. Medical Information Mart Intensive Care (MIMIC)-IV dataset eICU Collaborative Research Database (eICU-CRD) were analyzed. Among ten classifiers compared, adaptive boosting (AdaBoost) showed better performance predicting all-cause patients. A compact model 15 features was validated. Both all variable exhibited excellent area under receiver operating characteristic curves (AUCs) 1(95%confidence interval [CI]: 1.0–1.0) training set. In MIMIC-IV testing set, AUCs 0.978 (95% CI: 0.973–0.982) 0.977 0.972–0.982), respectively. external validation 0.825 0.815–0.834) 0.807 0.796–0.817), An AdaBoost-based subjected internal validation, highlighting its strong capacity assessing

Language: Английский

Association between the systemic immunity-inflammation index and stroke: a population-based study from NHANES (2015–2020) DOI Creative Commons

Rui Shi,

Ye Tian, Jinzhou Tian

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 2, 2025

Background The systemic immunity-inflammation index(SII) is a new indicator of composite inflammatory response. Inflammatory response an important pathological process in stroke. Therefore, this study sought to investigate the association between SII and Methods We collected data on participants with stroke from 2015–2020 cycle National Health Nutrition Examination Survey (NHANES) for cross-sectional investigation. Multivariate linear regression models were used test Fitted smoothing curves threshold effect analysis applied describe nonlinear relationship. Results A total 13,287 included our study, including 611 (4.598%) In multivariate analysis, we found significant positive stroke, odds ratio (OR) [95% CI] associating prevalence was [1.02 (1.01, 1.04)] (P < 0.01). subgroup interaction experiments, that relationship not significantly correlated among different population settings such as age, gender, race, education level, smoking status, high blood pressure, diabetes coronary heart disease trend > 0.05). Moreover, inflection point 740 (1,000 cells /µl) by using two-segment model. Conclusions This implies increased levels are linked To confirm findings, more large-scale prospective investigations needed.

Language: Английский

Citations

3

Elevated Platelet‐to‐Lymphocyte Ratio as a Predictor of All‐Cause and Cardiovascular Mortality in Hypertensive Individuals DOI Creative Commons
Rui Xu, Ling Chen,

Changshun Yan

et al.

Journal of Clinical Hypertension, Journal Year: 2025, Volume and Issue: 27(1)

Published: Jan. 1, 2025

The platelet-to-lymphocyte ratio (PLR) has been proposed as a promising inflammatory biomarker, with potential implications for cardiovascular prognosis. However, its association mortality outcomes in hypertensive individuals is not fully elucidated. This investigation sought to clarify the linkage between PLR and both overall individuals. Data from 15 483 adults NHANES (2005-2018) were analyzed. Mortality data, including all-cause deaths, sourced National Death Index (NDI) up December 31, 2019. risk was depicted using restricted cubic spline (RCS) models. Cox proportional hazards regression models assessed independent of risk, adjustments incrementally applied: Model 1 without adjustments; 2 adjusted age sex; 3 further age, gender, race, marital status, diabetes, alcohol intake, smoking body mass index (BMI), history disease (CVD), high-density lipoprotein cholesterol (HDL), low-density (LDL), total (TC), triglyceride (TG), creatinine (CR). Over median follow-up 79 months, there 2820 deaths 758 deaths. multivariate analysis showed that those highest quartile had significantly elevated risks (Model 1: HR = 1.28, 95% CI 1.16-1.42, p < 0.001; 2: 1.14, 1.03-1.26, 0.014; 3: 1.16, 1.05-1.29, 0.004)and 1.59, 1.30-1.94, 1.38, 1.13-1.68, 1.47, 1.20-1.80, 0.001). study reveals U-shaped relationship mortality, alongside linear mortality. A threshold 118.83 identified indicative an adverse prognosis Elevated independently predicts heightened among patients.

Language: Английский

Citations

1

The Prognostic Role of the Neutrophil-to-Lymphocytes Ratio in the Most Frequent Cardiovascular Diseases: An Update DOI Creative Commons
Evelina Maria Gosav, Daniela Maria Tănase, Oana Nicoleta Buliga-Finiș

et al.

Life, Journal Year: 2024, Volume and Issue: 14(8), P. 985 - 985

Published: Aug. 7, 2024

Given the continuous changes in world, with an increasing trend of unhealthy lifestyles, metabolic comorbidities, and increased susceptibility to cardiovascular diseases (CVDs), researchers change their attention improve not only therapeutic platform but also current CVD predictive prognostic tools disease outcomes. As is characterized by inflammatory paradigm involving, some degree, innate adaptative immune systems, neutrophil-to-lymphocyte ratio (NLR) emerged as a potential low-cost, rapidly available, reliable marker, substantial recent evidence showing its utility clinical practice. Thus, this literature review, we will present up-to-date discussion role NLR most frequent CVDs, such acute chronic coronary disease, atherosclerotic heart failure, cardiac valvopathies, arrhythmias predilection atrial fibrillation.

Language: Английский

Citations

8

Evaluation of Absolute Neutrophil, Lymphocyte and Platelet Count and Their Ratios as Predictors of Thrombotic Risk in Patients with Prefibrotic and Overt Myelofibrosis DOI Creative Commons
Marko Lucijanić, Ivan Krečak,

Ena Sorić

et al.

Life, Journal Year: 2024, Volume and Issue: 14(4), P. 523 - 523

Published: April 17, 2024

Aim: To investigate the prognostic contribution of absolute neutrophil (ANC), lymphocyte (ALC), platelet count and their ratios, neutrophil–lymphocyte ratio (NLR) platelet–lymphocyte (PLR), to thrombotic risk in patients with prefibrotic overt fibrotic myelofibrosis (MF). Methods: We retrospectively analyzed a cohort 256 (85 patients) MF (171 treated six Croatian hematological centers. Results: Prefibrotic compared presented significantly higher ALC, PLR, experienced longer time thrombosis (TTT). Among patients, ANC > 8.33 × 109/L (HR 13.08, p = 0.036), ALC 2.58 20.63, 0.049) 752 10.5, 0.043) remained independently associated shorter TTT. 8.8 4.49, 0.004), ≤ 1.43 4.15, 0.003), 385 4.68, 0.004) chronic kidney disease 9.07, < 0.001) Conclusions: Prognostic properties ANC, are mutually independent exceed those NLR PLR regarding stratification. associate opposite directions patients.

Language: Английский

Citations

4

Systemic immune inflammation index with all-cause and cause-specific mortality: a meta-analysis DOI
Wei Li,

Xiaoning Wang,

Houze Diao

et al.

Inflammation Research, Journal Year: 2024, Volume and Issue: 73(12), P. 2199 - 2216

Published: Oct. 14, 2024

Language: Английский

Citations

4

Left atrial appendage velocity, association with inflammatory indices in non-valvular atrial fibrillation patients DOI

Hamideh Khesali,

Amir Ghaffari Jolfayi, Amirali Soheili

et al.

Future Cardiology, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 9

Published: Jan. 28, 2025

Decreased left atrial appendage emptying velocity (LAAV) is a marker for thrombus formation. This study evaluates the association between LAAV and inflammatory indices in non-valvular fibrillation (AF) patients. The population was 1428 patients with AF, 875 of whom enrolled. Based on LAAV, were divided into three groups 262 <25 cm/s, 360 25 to 55 253 >55 cm/s assess compare terms indices, including platelet-to-lymphocyte ratio, neutrophil-to-lymphocyte systemic immune inflammation index, neutrophil - platelet ratio white blood cell-to-platelet (WPR). There no statistical difference level groups, none them related (p > .05) except WPR weak negative correlation = 0.01, r -0.10). Patients lower found have higher age 0.001), decreased ventricular ejection fraction 0.001) greater volume index 0.001). did not show any AF WPR.

Language: Английский

Citations

0

The association between the systemic immune-inflammation index and in-hospital mortality among acute ischemic stroke with atrial fibrillation patients undergoing intravenous thrombolysis DOI Creative Commons

Kadiyan Aierken,

Liang Ma, Yu Zhu

et al.

Frontiers in Cardiovascular Medicine, Journal Year: 2025, Volume and Issue: 12

Published: April 7, 2025

This study aimed to explore the relationship between systemic immune-inflammatory index (SII) and probability of in-hospital mortality among acute ischemic stroke (AIS) with atrial fibrillation (AF) patients undergoing intravenous thrombolysis. single-center, retrospective observational included individuals AIS AF who received The SII is determined by taking product platelet neutrophil counts, followed dividing this result lymphocyte count. In-hospital was defined as a Modified Rankin Scale (mRS) score 6 point. investigation applied logistic regression models, along subgroup, sensitivity, receiver operating characteristic (ROC) curve analyses assessments, mortality. 541 were in study, 50 (9.24%) whom died during their hospital stay. Multifactorial using fully adjusted demonstrated that independently associated risk death. Patients elevated levels experienced significantly increased mortality, which found be 2.557 (95% CI: 1.154-5.665, P = 0.021) times greater compared those lower levels. Through multivariate analyses, notable correlation death hospitalization observed across various subgroups, including aged ≤75 >75years, women, persistent AF, receiving thrombolytic therapy, diabetic nondiabetic patients, BMI ≥24 kg/m2, an admission National Institutes Health Stroke ≤20 (P < 0.05). Two sensitivity confirmed robustness association from multiple perspectives ROC analysis SII, baseline model, combined model all showed strong predictive power for Notably, outperformed alone In addition, value higher than neutrophil-to-lymphocyte ratio (NLR) platelet-to-lymphocyte (PLR). A significant has been individual thrombolysis SII.

Language: Английский

Citations

0

The relationship of pan-immune-inflammation value (PIV) and HALP score with prognosis in patients with atrial fibrillation DOI Creative Commons
Azmi Eyiol

Medicine, Journal Year: 2024, Volume and Issue: 103(36), P. e39643 - e39643

Published: Sept. 6, 2024

Because earlier studies have proven a link between hemoglobin, albumin, lymphocyte, and platelet (HALP) pan-immune-inflammation value (PIV) scores inflammation, we examined if these 2 markers had predictive in patients with atrial fibrillation (AF). In the intensive care unit, 444 without AF were retrospectively analyzed. Patients compared regard to their HALP PIV scores. High low categories of established based on cutoff values. Furthermore, using receiver operating characteristic analysis, mortality efficacy was assessed 230 AF. significantly higher score than those AF; however, found be lower ( P < .05 for all groups). The analysis revealed that exhibited sensitivity 66.7% specificity 75.3% at 2.037 (AUC: 0.753, .001). 1062.7, but both 55.7% 55.8%, respectively 0.571, .05). mechanical ventilation requirement in-hospital rate high (PIV > 1062.7) (HALP ≤ 2.037) groups. There is significant association upon admission critically ill Although serves as powerful prognostic factor patients, lacks capability predict mortality.

Language: Английский

Citations

2

A machine learning-based predictive model for the in-hospital mortality of critically ill patients with atrial fibrillation DOI Creative Commons

Yanting Luo,

Ruimin Dong,

Jinlai Liu

et al.

International Journal of Medical Informatics, Journal Year: 2024, Volume and Issue: 191, P. 105585 - 105585

Published: Aug. 1, 2024

Atrial fibrillation (AF) is common among intensive care unit (ICU) patients and significantly raises the in-hospital mortality rate. Existing scoring systems or models have limited predictive capabilities for AF in ICU. Our study developed validated machine learning to predict risk of ICU with AF. Medical Information Mart Intensive Care (MIMIC)-IV dataset eICU Collaborative Research Database (eICU-CRD) were analyzed. Among ten classifiers compared, adaptive boosting (AdaBoost) showed better performance predicting all-cause patients. A compact model 15 features was validated. Both all variable exhibited excellent area under receiver operating characteristic curves (AUCs) 1(95%confidence interval [CI]: 1.0–1.0) training set. In MIMIC-IV testing set, AUCs 0.978 (95% CI: 0.973–0.982) 0.977 0.972–0.982), respectively. external validation 0.825 0.815–0.834) 0.807 0.796–0.817), An AdaBoost-based subjected internal validation, highlighting its strong capacity assessing

Language: Английский

Citations

1