Predicting Cardiovascular Disease and All-Cause Mortality Using the Lymphocyte-to-Monocyte Ratio: Insights from Explainable Machine Learning Models

International Journal of Cardiology Cardiovascular Risk and Prevention, Journal Year: 2025, Volume and Issue: unknown, P. 200372 - 200372

Published: Jan. 1, 2025

Language: Английский

---

Survival Prediction in Brain Metastasis Patients Treated with Stereotactic Radiosurgery: A Hybrid Machine Learning Approach

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 266 - 266

Published: March 1, 2025

Objectives: Accurate survival prediction for brain metastasis patients undergoing stereotactic radiotherapy (SRT) is crucial personalized treatment planning and improving patient outcomes. This study aimed to develop a machine learning model estimate times, providing clinicians with reliable tool making informed decisions based on individual characteristics. The goal was compare the performance of multiple algorithms identify most effective clinical use. Methods: We applied hybrid approach predict in treated SRT, utilizing real-world data. Four algorithms—XGBoost, CatBoost, Random Forest, Gradient Boosting—were compared within meta-model framework accurate prediction. Model evaluated using metrics such as MSE, MAE, MAPE, C index. Results: XGBoost outperformed all other algorithms, achieving an MSE 0.14%, MAE 0.10%, MAPE 0.093%, high C-index 100%. CatBoost showed reasonable performance, while Boosting had higher error rates (MSE 6.99%, 21.04%, 19.29%). Forest performed weakest, highest (14.39%), (30.23%), (33.58%). Conclusion: Inputting relevant variables into enables obtain highly predictions metastasis. enhances decision by more precise understanding expected XGBoost-based exceptional accuracy predicting after offering valuable support making. Integrating practice can improve personalize care these patients.

Language: Английский

---

The association between nutritional-inflammatory status and chronic kidney disease prognosis: a population-based study

Renal Failure, Journal Year: 2025, Volume and Issue: 47(1)

Published: March 14, 2025

Background Chronic kidney disease (CKD) prognosis is closely tied to the interplay between nutrition and inflammation. However, comprehensive nutritional-inflammatory indices for prognostic evaluation are rare in CKD. This study explored association of advanced lung cancer inflammation index (ALI) with estimated glomerular filtration rate (eGFR) all-cause mortality CKD patients.

Language: Английский

---

Association of neutrophil to lymphocyte ratio with all-cause and cardiovascular mortality among individuals with kidney stone disease: result from NHANES, 2007-2018

Frontiers in Endocrinology, Journal Year: 2025, Volume and Issue: 16

Published: March 14, 2025

The objective of this study is to investigate the relationship between neutrophil-to-lymphocyte ratio (NLR) and all-cause as well cause-specific mortality among patients with kidney stones, evaluate capability NLR a predictor mortality. This included 2,995 stones from NHANES database during period 2007 2018, subsequently linked data National Death Index. was analyzed using Cox proportional hazards model Kaplan-Meier survival curves. Additionally, restricted cubic spline (RCS) curves were employed explore dose-response mortality, while time-dependent ROC utilized assess predictive for Finally, mediating effect estimated glomerular filtration rate (eGFR) on also analyzed. ultimately median follow-up 74 months. A total 395 deaths recorded, which 87 attributed cardiovascular diseases. An cut-off 3.62 identified significantly associated outcomes 'maxstat' package principle maximum rank statistics. plot indicates non-linear both After adjusting relevant covariates, regression analysis demonstrated that, in comparison lower group, higher group exhibited 1.05-fold (HR 2.05, 95% CI 1.51-2.78, P < 0.001) increased risk 1.99-fold 2.99, 1.89-4.72, Furthermore, eGFR significant found that exhibiting high have U.S. population. Therefore, monitoring may be important prognosis stones.

Language: Английский

---

Association between blood inflammatory status and the survival of tuberculosis: a five-year cohort study

Frontiers in Immunology, Journal Year: 2025, Volume and Issue: 16

Published: March 21, 2025

Background Blood inflammatory status is closely associated with tuberculosis (TB) progression. Emerging indices from different leukocyte subtypes have become a prognostic hotspot for various diseases, yet their application in TB prognosis remains limited. This study aims to assess the impact of on patients’ and its potential as indicator optimize assessment therapeutic strategies. Methods included 4027 patients admitted tuberculosis-designated hospital Shenzhen January 2017 December 2022. Patients were classified into three statuses (Q1-Q3) based each index’s level. We conducted Cox regression restricted cubic splines (RCS) analyses evaluate association between unfavorable outcome, subgroup understand heterogeneous associations among subpopulations, receiver operating characteristic (ROC) performance treatment outcomes. Results During 48991.79 person-months follow-up involving patients, 225 outcomes occurred. Multivariable indicated that Q3 levels CAR, CLR, dNLR, NLR, SII, SIRI increased risk outcome by 45%-99% (HR: 1.45-1.99, all P &lt;0.050), whereas ENR reduced 29% 0.71, =0.040) compared Q1. RCS curves revealed linear positive SIRI, negative (all nonlinear&gt;0.050), nonlinear MLR, PNI nonlinear&lt;0.050). Subgroup identified across age, sex, BMI, comorbidities, drug resistance interaction&lt;0.050), attenuated effects SII aged 30-60 years, male, BMI≥24.0 kg/m², smokers, retreatment cases, those tumor. ROC analysis demonstrated stable predictive performances (AUC: 0.785–0.804 at 6-month, 0.781–0.793 9-month, 0.762–0.773 12-month), combination significantly optimized basic model (9-month AUC: 0.811 vs 0.780, =0.024; 12-month 0.794 0.758, =0.013). Conclusion Pretreatment blood effectively predicts patients. Our findings hold significant clinical value patient management warrant prospective evaluation future studies.

Language: Английский

---

Chronic Inflammation and Hearing Loss: Key Biomarkers and Subgroup Differences by Gender and BMI in a National Cohort

Immunity Inflammation and Disease, Journal Year: 2025, Volume and Issue: 13(4)

Published: April 1, 2025

ABSTRACT Background Hearing loss (HL) significantly impacts quality of life and economic status worldwide. Chronic inflammation is suggested to influence hearing, yet the connection with inflammation‐related indexes in general population not well understood. Methods This cross‐sectional study analyzed data from 7231 adults six cycles (2005–2012 2015–2018) National Health Nutrition Examination Survey (NHANES). It examined correlation between systemic immune‐inflammatory biomarkers (NLR, SII, PLR, LMR) auditory threshold shifts/HL using multivariable logistic regression models. Smooth curve fitting visualized association, log‐likelihood ratio tests determined existence thresholds biomarker effects, supplemented by subgroup analyses. Results After adjustments, significant associations were found for low‐frequency HL ln‐transformed NLR (OR = 1.29, 95% CI: 1.06–1.56, p 0.0116), ln‐SII 1.31, 1.08–1.59, 0.0065), ln‐LMR 0.74, 0.60–0.91, 0.00043). For high‐frequency HL, similar patterns observed 1.25, 1.05–1.48, 0.0105) 0.76, 0.64–0.90, 0.007); however, association ln‐NLR did reach statistical significance 1.18, 1.00–1.40, 0.0562). SII positively correlated while LMR showed a negative correlation. No was noted PLR. Dose–response relationships observed, particularly all categorized frequencies HL. Subgroup analyses indicated that are risk factors healthy BMI males, being more protective elderly, diabetics. Conclusions Systemic indexes, especially predictive both high‐ highlighting role inflammatory homeostasis hearing health. may offer specific subgroups. These findings suggest potential targets treatment regulating inflammation, warranting further investigation into their clinical application.

Language: Английский

---

Association between aging phenotypes and chronic kidney disease: evidence from the NHANES and Mendelian randomization

International Urology and Nephrology, Journal Year: 2025, Volume and Issue: unknown

Published: April 9, 2025

Language: Английский

---

Inflammatory Indices in First Trimester as Predictors of Gestational Diabetes Mellitus and Adverse Pregnancy Outcomes

American Journal of Reproductive Immunology, Journal Year: 2025, Volume and Issue: 93(4)

Published: April 1, 2025

ABSTRACT Objectives To explore the association between systemic inflammatory markers (systemic inflammation response index [SIRI], immune [SII], interleukin [IL]‐33, and soluble tumorigenicity 2 [sST2]) gestational diabetes mellitus (GDM), as well adverse pregnancy outcomes (APOs), to assess impact of glycemic control on these relationships. Methods A total 777 participants were included, comprising 476 women with GDM 301 without. Clinical characteristics, markers, analyzed. Logistic regression was employed risk APOs associated elevated indices control. Diagnostic performance evaluated using receiver operating characteristic (ROC) curves. Results Women exhibited significantly higher levels SII, SIRI, IL‐33, sST2. Multivariate logistic demonstrated that sST2 independent predictors GDM. Moreover, highest tertiles IL‐33 strongly APO risk. ROC analysis revealed SII had predictive value for (AUC 0.763), while greatest accuracy 0.669). Effective reduced marker (SII, aOR 3.9; 3.7; 2.4) a decreased large‐for‐gestational‐age (LGA) infants in Conclusions Elevated are significant APOs, being most robust predictor APOs. Glycemic reduces may improve

Language: Английский

---

Chronic kidney Disease overall survival prediction model based on frailty index score: construction and validation using NHANES data

Renal Failure, Journal Year: 2025, Volume and Issue: 47(1)

Published: April 21, 2025

Frailty predicts poor outcomes in chronic kidney disease (CKD) patients. This study compared frailty's predictive power with other factors and aimed to develop a model for predicting overall survival (OS) CKD The included 3,714 participants from the National Health Nutrition Examination Survey 2005-2018. death data were updated December 31, 2019. Lasso-Cox regression identified significant predictors among 42 factors, resulting prognostic nomogram using 11 key variables. Subsequent evaluation of involved C-index, Areas Under Time-dependent Receiver Operating Characteristic Curves (AUC) calibration curves. Over median follow-up 5.92 years, 1,234 deaths occurred. final OS patients age, ethnicity, smoking status, estimated pulse wave velocity, body fat percentage, blood uric acid concentration, urea nitrogen albumin neutrophil-to-lymphocyte ratio, urine albumin-to-creatinine ratio level, frailty index (FI) score. FI score was strongest predictor an HR 76.54 (95% CI: 42.93, 136.46, p < 0.0001). In training set, AUC values 80.11% 1-year, 79.90% 3-year, 79.53% 5-year, 81.34% 10-year follow-ups. internal validation 78.66%, 77.78%, 77.56%, 79.54%, respectively. nomogram's corrected C-index 0.76 0.75 - 0.78), curves showed satisfactory accuracy. is OS. developed based on promising tool

Language: Английский

---

Interaction of nutritional and inflammatory levels on all-cause mortality among individuals with rheumatoid arthritis: a prospective cohort study

Clinical Rheumatology, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Language: Английский

---