Predictor Of Mortality In Patients Research Articles

What is the best predictor of mortality in patients with type 2 diabetes and chronic kidney disease: mean, variability of HbA1c or HbA1c-Hemoglobin ratio?

AimLimitations in the measurement of glycated hemoglobin (HbA1c) in patients with type 2 diabetes (T2D) and chronic kidney disease (CKD) result in uncertainty about the best predictor of mortality among these patients. Our study aimed to determine the association between the mean and average real variability (ARV) of HbA1c, as well as HbA1c-hemoglobin (HH) ratio with mortality among patients with T2D and CKD.Materials and methodsWe identified 16,868 T2D patients with stage 3 or above CKD from outpatient visits during 2003–2018. We ascertained all-cause and cardiovascular mortality through linkage to Taiwan’s National Death Registry. Mortality rates were estimated using the Poisson distribution, and we conducted Cox proportional hazards regressions to assess relative risks of mortality corresponding to the mean HbA1c, ARV of HbA1c and HH ratio.ResultsCompared to patients with a mean HbA1c of 7.0–7.9%, a mean HbA1c < 7.0% was persistently associated with highest risk of all-cause but not cardiovascular mortality after adjusting for confounders. On the contrary, patients with HbA1c-ARV in the second to fourth quartiles and HH ratios in the higher quartiles showed increased risk of all-cause and cardiovascular mortality compared to those in the first quartiles.ConclusionsHbA1c-ARV was more effective than mean HbA1c or HH ratio in predicting mortality in T2D patients with CKD. Apart from optimal glucose control, multidisciplinary care focusing on glycemic variability is essential for reducing mortality in these patients.

IL-33/sST2 signaling pathway in pulmonary thromboembolism: A clinical observational study

BackgroundPulmonary thromboembolism (PTE) is a cardiovascular emergency that can result in mortality. In the interleukin-33 (IL-33) /soluble suppression of tumorigenicity 2 (sST2) signaling pathway, increased sST2 is a cardiovascular risk factor. This study aimed to investigate the effectiveness of biomarkers in the IL-33/sST2 signaling pathway in determining PTE diagnosis, clinical severity, and mortality. MethodThis study was conducted as a single-center, prospective, observational study. Patients admitted to the emergency department and diagnosed with PTE constituted the patient group (n = 112), and healthy volunteers with similar sociodemographic characteristics constituted the control group (n = 62). Biomarkers in the IL-33/sST2 signaling pathway were evaluated for diagnosis, clinical severity, and prognosis. ResultsIL-33 was lower in the patient group than in the control group (275.89 versus 403.35 pg/mL), while sST2 levels were higher in the patient group than in the control group (53.16 versus 11.78 ng/mL) (p < 0.001 and p = 0.001; respectively). The AUC of IL-33 to diagnose PTE was 0.656 (95 % CI: 0.580–0.726). The optimal IL-33 cut-off point to diagnose PTE was ≤304.11 pg/mL (56.2 % sensitivity, 79 % specificity). The AUC of sST2 to diagnose PTE was 0.818 (95 % CI: 0.752–0.872). The optimal sST2 cut-off point to diagnose PTE was >14.48 ng/mL (83 % sensitivity, 71 % specificity).IL-33 levels were lower in patients with mortality (169.85 versus 332.04 pg/mL) compared to patients without mortality, whereas sST2 levels were higher in patients with mortality (118.32 versus 28.07 ng/mL) compared to patients without mortality (p > 0.001 for both). The AUC of IL-33 to predict the mortality of PTE was 0.801 (95 % CI: 0.715–0.870). The optimal IL-33 cut-off point to predict the mortality of PTE was ≤212.05 pg/mL (75 % sensitivity, 79.5 % specificity). The AUC of sST2 to predict the mortality of PTE was 0.824 (95 % CI: 0.740–0.889). The optimal sST2 cut-off point to predict the mortality of PTE was >81 ng/mL (95.8 % sensitivity, 78.4 % specificity). ConclusionIn the IL-33/ST2 signaling pathway, decreased IL-33 and increased sST2 are valuable biomarkers for diagnosis and prediction of mortality in patients with PTE.

Predictors of Mortality Following Mitral Valve Replacement: A SystematicReview

Introduction: Valvular heart diseases are some of the most common causes of cardiovascular morbidity and mortality worldwide. The mitral valve is estimated to be the cause of 15% of deaths in heart valve disease. Mitral valve dysfunction can be treated with a variety of operative options, one of whichis mitral valve replacement. Although it is less desirable than repair, in some situations, it is the only viable option. Thus, we conducted this systematic review to help guide future risk assessment for mitral valve replacement patients and help in the construction of pre-operative risk assessment tools. Methods: This is a systematic review of original articles discussing the topic of predictors of mortality for patients undergoing mitral valve replacement surgery. A systematic search was conducted via independent researchers across a number of databases, starting with PubMed databases utilizing its MeSH database, followed by a complementary search through Google Scholar. Results: In total, 27 original articles were included in a collective cohort of 145005 patients. Older age was the most commonly cited variable as a mortality predictor, followed by decreased left ventricular ejection fraction. EuroSCORE is a well-known scoring system that predicts in-hospital mortality following major cardiac surgeries. It was found that it overestimated mortality greatly, while another study found that the revised EuroSCORE II system was a better predictor of mortality. Overall, we note that both versions usually overestimate mortality. Conclusion: There seems to be an overall agreement over several factors, including older age, decreased ejection fraction, and the expertise of the surgeon and the institution on being clear predictors of postoperative mortality. There is also an obvious need for new tools to better predict mortality rates preoperatively, as the currently used scores often result in greatly inaccurate predictions

Prognostic value of plasma big endothelin-1 in patients with light chain cardiac amyloidosis

BackgroundLight chain cardiac amyloidosis (AL-CA) is associated with a high incidence of mortality. Big endothelin-1 (ET-1), the precursor of endothelial-vasoconstrictive ET-1, is closely related to the concentration of bioactive ET-1....

Thigh muscle by CT images as a predictor of mortality in patients with newly diagnosed colorectal cancer

This study aimed to evaluate the prognostic value of thigh muscle assessed by CT images to predict overall mortality in patients with colorectal cancer (CRC). This was a multicenter cohort study including adults (≥ 18 years old) newly diagnosed with CRC, who performed a diagnostic computed tomography (CT) exam including thigh regions. CT images were analyzed to evaluate skeletal muscle (SM in cm2), skeletal muscle index (SMI in cm2/m2), and skeletal muscle density (SMD in HU). Muscle abnormalities (low SM, SMI, and SMD) were defined as the values below the median by sex. Kaplan–Meyer curves and hazard ratios (HRs) for low SM, SMI and SMD were evaluated for overall mortality, stratified by sex. A total of 257 patients were included in the final analysis. Patients’ mean age was 62.6 ± 12.1 years, and 50.2% (n = 129) were females. In males, low thigh SMI was associated with shorter survival (log-rank P = .02). Furthermore, this low thigh SMI (cm2/m2) was independently associated with higher mortality rates (HR adjusted 2.08, 95% CI 1.03–4.18). Our additional findings demonstrated that low SMD was independently associated with overall mortality among early-stage patients (I–III) (HR adjusted 2.78, 95% CI 1.26–6.15).

Machine learning for the prediction of 1-year mortality in patients with sepsis-associated acute kidney injury

IntroductionSepsis-associated acute kidney injury (SA-AKI) is strongly associated with poor prognosis. We aimed to build a machine learning (ML)-based clinical model to predict 1-year mortality in patients with SA-AKI.MethodsSix ML algorithms were included to perform model fitting. Feature selection was based on the feature importance evaluated by the SHapley Additive exPlanations (SHAP) values. Area under the receiver operating characteristic curve (AUROC) was used to evaluate the discriminatory ability of the prediction model. Calibration curve and Brier score were employed to assess the calibrated ability. Our ML-based prediction models were validated both internally and externally.ResultsA total of 12,750 patients with SA-AKI and 55 features were included to build the prediction models. We identified the top 10 predictors including age, ICU stay and GCS score based on the feature importance. Among the six ML algorithms, the CatBoost showed the best prediction performance with an AUROC of 0.813 and Brier score of 0.119. In the external validation set, the predictive value remained favorable (AUROC = 0.784).ConclusionIn this study, we developed and validated a ML-based prediction model based on 10 commonly used clinical features which could accurately and early identify the individuals at high-risk of long-term mortality in patients with SA-AKI.

Utilizing APACHE IV and GRACE Scores as Predictors of Mortality Compared with SAPS-3 Scores for Acute Coronary Syndrome Patients in the Cardiac Vascular Care Unit

Background: Acute coronary syndromes (ACS) frequent cause of hospitalization in the cardiovascular care unit. Positive predictive data are being developed and shown to be effective for patients with ACS; the Global Registry of Acute Coronary Events, or GRACE, has shown the most accurate outcomes. In contrast, prognostic scores derived from diverse cohorts of critically ill patients are predominantly employed by intensive care clinicians. Prominent examples of such scores include APACHE IV and SAPS 3. The objective of this research endeavor was to assess and contrast the efficacy of these three scores across an unselected sample of ACS cases.. Objective: The Cardiovascular Care Unit of RSUD Dr. Saiful Anwar Malang treats Acute Coronary Syndrome patients. This study compares SAPS 3, GRACE, and APACHE IV score parameters through calibration and discrimination tests to predict patient mortality. Material and Methods: The study included all ACS patients admitted from August 2021 to November 2023. Hospital mortality prediction was assessed using score calibration and discrimination. Result: There were 843 patients in total included. SAPS 3 could not be calibrated appropriately, whereas APACHE IV and GRACE could. Across all scores, discrimination was exceptional (area under the curve values of 0.811 for APACHE IV, 0.740 for GRACE, and 0.732 for SAPS 3). Conclusion: GRACE and APACHE IV were calibrated thoroughly in this cohort of intensive care unit-admitted ACS patients; however, SAPS 3 lacked such calibration. All three scores exhibited exceptional discrimination. GRACE and APACHE IV may be utilized to predict the risk of mortality in patients with ACS. Keyword: Acute Physiology and Chronic Health Evaluation Score, Global Registry of Acute Coronary Events, Intensive Cardiovascular Care Unit, Simplified Acute Physiology Score 3.

Prevalence and prognostic role of thoracic lymphadenopathy inCovid-19.

The prevalent coronavirus disease 2019 (COVID-19) pandemic has spread throughout the world and is considered a serious threat to global health. The prognostic role of thoracic lymphadenopathy in COVID-19 is unclear. The aimof the present meta-analysis was to analyze the prognostic role of thoracic lymphadenopathy for the prediction of 30-day mortality in patients with COVID-19. The MEDLINE library, Cochrane, and SCOPUS databases were screened for associations between CT-defined features and mortality in COVID-19 patients up to June 2021. In total, 21 studies were included in the present analysis. The quality of the included studies was assessed by the Newcastle-Ottawa Scale. The meta-analysis was performed using RevMan 5.3. Heterogeneity was calculated by means of the inconsistency index I2. DerSimonian and Laird random-effect models with inverse variance weights were performed without any further correction. The included studies comprised 4621 patients. The prevalence of thoracic lymphadenopathy varied between 1 % and 73.4 %. The pooled prevalence was 16.7 %, 95 % CI = (15.6 %; 17.8 %). The hospital mortality was higher in patients with thoracic lymphadenopathy (34.7 %) than in patients without (20.0 %). The pooled odds ratio for the influence of thoracic lymphadenopathy on mortality was 2.13 (95 % CI = [1.80-2.52], p < 0.001). The prevalence of thoracic lymphadenopathy in COVID-19 is 16.7 %. The presence of thoracic lymphadenopathy is associated with an approximately twofold increase in the risk for hospital mortality in COVID-19. · The prevalence of lymphadenopathy in COVID-19 is 16.7 %.. · Patients with lymphadenopathy in COVID-19 have a higher risk of mortality during hospitalization.. · Lymphadenopathy nearly doubles mortality and plays an important prognostic role.. · Bucher AM, Sieren M, Meinel F et al. Prevalence and prognostic role of thoracic lymphadenopathy in Covid-19. Fortschr Röntgenstr 2024; DOI: 10.1055/a-2293-8132.

Blood lipid profiles as a prognostic biomarker in idiopathic pulmonary fibrosis

BackgroundDysregulation of lipid metabolism is implicated in the pathogenesis of idiopathic pulmonary fibrosis (IPF). However, the association between the blood lipid profiles and the prognosis of IPF is not well defined. We aimed to identify the impacts of lipid profiles on prognosis in patients with IPF.MethodsClinical data of 371 patients with IPF (145 and 226 in the derivation and validation cohorts, respectively), including serum lipid profiles (total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, apolipoprotein A-I [Apo A-I], and apolipoprotein B), were retrospectively collected. The association with mortality was analyzed using the Cox proportional hazard model.ResultsIn the derivation cohort, the mean age was 67.5 years, 86.2% were men, and 30.3% died during the follow-up (median: 18.0 months). Non-survivors showed lower lung function and greater gender-age-physiology scores than survivors. Among the serum lipid profiles, the levels of triglyceride and Apo A-I were significantly lower in non-survivors than in survivors. In the multivariate Cox analysis, low Apo A-I levels (< 140 mg/dL) were independently associated with the risk of mortality (hazard ratio 3.910, 95% confidence interval 1.170-13.069; P = 0.027), when adjusted for smoking history, body mass index, GAP score, and antifibrotic agent use. In both derivation and validation cohorts, patients with low Apo A-I levels (< 140 mg/dL) had worse survival (median survival: [derivation] 34.0 months vs. not reached, P = 0.003; [validation] 40.0 vs. 53.0 months, P = 0.027) than those with high Apo A-I levels in the Kaplan–Meier survival analysis.ConclusionsOur results indicate that low serum Apo A-1 levels are an independent predictor of mortality in patients with IPF, suggesting the utility of serum Apo A-I as a prognostic biomarker in IPF.

Importance of hospital and clinical factors for early mortality in Takotsubo syndrome: Insights from the Swedish Coronary Angiography and Angioplasty Registry

BackgroundTakotsubo syndrome (TTS) is an acute heart failure syndrome with symptoms similar to acute myocardial infarction. TTS is often triggered by acute emotional or physical stress and is a significant cause of morbidity and mortality. Predictors of mortality in patients with TS are not well understood, and there is a need to identify high-risk patients and tailor treatment accordingly. This study aimed to assess the importance of various clinical factors in predicting 30-day mortality in TTS patients using a machine learning algorithm.MethodsWe analyzed data from the nationwide Swedish Coronary Angiography and Angioplasty Registry (SCAAR) for all patients with TTS in Sweden between 2015 and 2022. Gradient boosting was used to assess the relative importance of variables in predicting 30-day mortality in TTS patients.ResultsOf 3,180 patients hospitalized with TTS, 76.0% were women. The median age was 71.0 years (interquartile range 62–77). The crude all-cause mortality rate was 3.2% at 30 days. Machine learning algorithms by gradient boosting identified treating hospitals as the most important predictor of 30-day mortality. This factor was followed in significance by the clinical indication for angiography, creatinine level, Killip class, and age. Other less important factors included weight, height, and certain medical conditions such as hyperlipidemia and smoking status.ConclusionsUsing machine learning with gradient boosting, we analyzed all Swedish patients diagnosed with TTS over seven years and found that the treating hospital was the most significant predictor of 30-day mortality.

Machine learning-based prediction of 1-year all-cause mortality in patients undergoing CRT implantation: validation of the SEMMELWEIS-CRT score in the European CRT Survey I dataset.

We aimed to externally validate the SEMMELWEIS-CRT score for predicting 1-year all-cause mortality in the European Cardiac Resynchronization Therapy (CRT) Survey I dataset-a large multi-centre cohort of patients undergoing CRT implantation. The SEMMELWEIS-CRT score is a machine learning-based tool trained for predicting all-cause mortality in patients undergoing CRT implantation. This tool demonstrated impressive performance during internal validation but has not yet been validated externally. To this end, we applied it to the data of 1367 patients from the European CRT Survey I dataset. The SEMMELWEIS-CRT predicted 1-year mortality with an area under the receiver operating characteristic curve (AUC) of 0.729 (0.682-0.776), which concurred with the performance measured during internal validation [AUC: 0.768 (0.674-0.861), P = 0.466]. Moreover, the SEMMELWEIS-CRT score outperformed multiple conventional statistics-based risk scores, and we demonstrated that a higher predicted probability is not only associated with a higher risk of death [odds ratio (OR): 1.081 (1.061-1.101), P < 0.001] but also with an increased risk of hospitalizations for any cause [OR: 1.013 (1.002-1.025), P = 0.020] or for heart failure [OR: 1.033 (1.015-1.052), P < 0.001], a less than 5% improvement in left ventricular ejection fraction [OR: 1.033 (1.021-1.047), P < 0.001], and lack of improvement in New York Heart Association functional class compared with baseline [OR: 1.018 (1.006-1.029), P = 0.003]. In the European CRT Survey I dataset, the SEMMELWEIS-CRT score predicted 1-year all-cause mortality with good discriminatory power, which confirms the generalizability and demonstrates the potential clinical utility of this machine learning-based risk stratification tool.

Development and validation of an interpretable machine learning for mortality prediction in patients with sepsis.

Sepsis is a leading cause of death. However, there is a lack of useful model to predict outcome in sepsis. Herein, the aim of this study was to develop an explainable machine learning (ML) model for predicting 28-day mortality in patients with sepsis based on Sepsis 3.0 criteria. We obtained the data from the Medical Information Mart for Intensive Care (MIMIC)-III database (version 1.4). The overall data was randomly assigned to the training and testing sets at a ratio of 3:1. Following the application of LASSO regression analysis to identify the modeling variables, we proceeded to develop models using Extreme Gradient Boost (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) techniques with 5-fold cross-validation. The optimal model was selected based on its area under the curve (AUC). Finally, the Shapley additive explanations (SHAP) method was used to interpret the optimal model. A total of 5,834 septic adults were enrolled, the median age was 66 years (IQR, 54-78 years) and 2,342 (40.1%) were women. After feature selection, 14 variables were included for developing model in the training set. The XGBoost model (AUC: 0.806) showed superior performance with AUC, compared with RF (AUC: 0.794), LR (AUC: 0.782) and SVM model (AUC: 0.687). SHAP summary analysis for XGBoost model showed that urine output on day 1, age, blood urea nitrogen and body mass index were the top four contributors. SHAP dependence analysis demonstrated insightful nonlinear interactive associations between factors and outcome. SHAP force analysis provided three samples for model prediction. In conclusion, our study successfully demonstrated the efficacy of ML models in predicting 28-day mortality in sepsis patients, while highlighting the potential of the SHAP method to enhance model transparency and aid in clinical decision-making.

Accurate prediction of all-cause mortality in patients with metabolic dysfunction-associated steatotic liver disease using electronic health records

Introduction and ObjectivesDespite the huge clinical burden of MASLD, validated tools for early risk stratification are lacking, and heterogeneous disease expression and a highly variable rate of progression to clinical outcomes result in prognostic uncertainty. We aimed to investigate longitudinal electronic health record-based outcome prediction in MASLD using a state-of-the-art machine learning model. Patients and Methodsn = 940 patients with histologically-defined MASLD were used to develop a deep-learning model for all-cause mortality prediction. Patient timelines, spanning 12 years, were fully-annotated with demographic/clinical characteristics, ICD-9 and -10 codes, blood test results, prescribing data, and secondary care activity. A Transformer neural network (TNN) was trained to output concomitant probabilities of 12-, 24-, and 36-month all-cause mortality. In-sample performance was assessed using 5-fold cross-validation. Out-of-sample performance was assessed in an independent set of n = 528 MASLD patients. ResultsIn-sample model performance achieved AUROC curve 0.74–0.90 (95 % CI: 0.72–0.94), sensitivity 64 %-82 %, specificity 75 %–92 % and Positive Predictive Value (PPV) 94 %-98 %. Out-of-sample model validation had AUROC 0.70–0.86 (95 % CI: 0.67–0.90), sensitivity 69 %–70 %, specificity 96 %–97 % and PPV 75 %–77 %. Key predictive factors, identified using coefficients of determination, were age, presence of type 2 diabetes, and history of hospital admissions with length of stay >14 days. ConclusionsA TNN, applied to routinely-collected longitudinal electronic health records, achieved good performance in prediction of 12-, 24-, and 36-month all-cause mortality in patients with MASLD. Extrapolation of our technique to population-level data will enable scalable and accurate risk stratification to identify people most likely to benefit from anticipatory health care and personalized interventions.

Predicting the Prognosis of Acute Pulmonary Embolism Using Computed Tomography Pulmonary Angiography Measurable Parameters in Comparison to Pulmonary Embolism Severity Index (PESI)

Abstract Background Pulmonary embolism is a leading cause of cardiovascular death and with CTPA being the gold standard in its diagnosis, it is feasible with radiologic parameters to stratify and early identify patients at risk of death. Aim of the Work To detect the prognostic value of radiologic parameters of CT pulmonary angiography (CTPA) in comparison to pulmonary embolism severity index (PESI). Patients and Methods This was a prospective study done at Ain Shams University Hospitals and included 84 patients diagnosed with acute pulmonary embolism and referred to the radio-diagnosis department for CT pulmonary angiography examination. Results 3.6% of patients died within 24 hours and 44% died within 30 days of diagnosis of PE. All patients who died within 30 days had abnormal CTPA findings especially RV/LV ratio, PT diameter, septal bowing and contrast reflux in the IVC which revealed significant relationship between them and 30-day-mortality. Meanwhile PESI showed contradictory results and was less reliable than the radiologic parameters. Conclusion The CTPA radiological parameters appeared valuable for the prediction of 30-day mortality in patients with acute PE, and was superior to the PESI.

Predictors of In-Hospital Mortality in Type A Acute Aortic Syndrome: Data From the RENADA-RO Registry

This study aimed to analyse the baseline characteristics of patients admitted with acute type A aortic syndrome (ATAAS) and to identify the potential predictors of in-hospital mortality in surgically managed patients. Data regarding demographics, clinical presentation, laboratory work-up, and management of 501 patients with ATAAS enrolled in the National Registry of Aortic Dissections-Romania registry from January 2011 to December 2022 were evaluated. The primary endpoint was in-hospital all-cause mortality. Multivariate logistic regression was conducted to identify independent predictors of mortality in patients with acute Type A aortic dissection (ATAAD) who underwent surgery. The mean age was 60±11 years and 65% were male. Computed tomography was the first-line diagnostic tool (79%), followed by transoesophageal echocardiography (21%). Cardiac surgery was performed in 88% of the patients. The overall mortality in the entire cohort was 37.9%, while surgically managed ATAAD patients had an in-hospital mortality rate of 29%. In multivariate logistic regression, creatinine value (OR 6.76), ST depression on ECG (OR 6.3), preoperative malperfusion (OR 5.77), cardiogenic shock (OR 5.77), abdominal pain (OR 4.27), age ≥70 years (OR 3.76), and syncope (OR 3.43) were independently associated with in-hospital mortality in surgically managed ATAAD patients. Risk stratification based on the variables collected at admission may help to identify ATAAS patients with high risk of death following cardiac surgery.

Neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio as predictors of mortality in acute pulmonary embolism: A systematic review and meta-analysis.

The purpose of this review was to examine the association between neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) and mortality rates in patients with acute pulmonary embolism (PE). PubMed Central, Scopus, Web of Science, and Embase were searched for studies reporting the association between NLR and PLR with mortality up to March 17th 2023. Adjusted ratios were sourced from studies and combined to generate pooled outcomes as odds ratio (OR) in a random-effects model. Risk of bias was assessed using the Newcastle Ottawa Scale. Fifteen studies were included. Meta-analysis showed that NLR was a significant predictor of mortality in patients with PE (OR: 1.42 95% CI: 1.26, 1.61 I2=92%). Results were unchanged on sensitivity analysis and subgroup analysis based on study location, method of diagnosis, sample size, overall mortality rates, cut-offs, and follow-up. Pooled analysis failed to demonstrate PLR as a predictor of mortality in patients with PE (OR: 1.00 95% CI: 1.00, 1.01 I2=57%). Results were unchanged on sensitivity analysis and subgroup analysis based on study location, diagnosis of PE, overall mortality rates, and cut-off. Current evidence from retrospective studies shows that NLR can independently predict mortality in acute PE. Data on PLR was limited and failed to indicate an independent role in the prognosis of PE patients. Registration No. PROSPERO (CRD42023407573).

Biochemical Signals of Survival: A Study on Mortality Markers in Coronary Bypass Surgery Patients.

Coronary bypass surgery remains a cornerstone treatment for advanced coronary artery disease. Identifying reliable predictors of postoperative mortality can significantly enhance patient care and outcomes. This study investigates the prognostic value of preoperative and postoperative amylase levels, creatinine, alanine aminotransferase, and aspartate aminotransferase as mortality markers in coronary bypass surgery patients. We conducted a retrospective analysis of 343 patients who underwent coronary bypass surgery. We compared the preoperative and postoperative biochemical markers (amylase, creatinine, alanine aminotransferase, and aspartate aminotransferase) of patients who died within the first week post-surgery (n = 52) and those who survived (n = 291). Statistical analyses included chi-square tests for categorical variables, t-tests for continuous variables, and receiver operating characteristic analysis for predicting mortality. No significant difference was observed in the distribution of blood groups between deceased and surviving patients. However, significant differences were noted in gender distribution and mean ages, with higher mortality observed in older and male patients. Preoperative creatinine levels were significantly higher in patients who died compared to survivors. Postoperatively, deceased patients exhibited significantly higher levels of amylase, creatinine, alanine aminotransferase, and aspartate aminotransferase. Receiver operating characteristic analysis revealed that postoperative amylase, creatinine, alanine aminotransferase, and aspartate aminotransferase values were good predictors of mortality, with amylase being the most significant predictor. This study highlights the importance of biochemical markers, particularly amylase, as predictors of mortality in patients undergoing coronary bypass surgery. The findings suggest that monitoring and managing amylase, creatinine, alanine aminotransferase, and aspartate aminotransferase levels pre- and post-surgery could improve patient outcomes. This study lays the groundwork for further research into the mechanistic links between these biochemical markers and patient survival, potentially leading to improved prognostic tools and therapeutic strategies.

Serum uric acid as a predictor of mortality in patients with stroke: results from National Health and Nutrition Examination Survey 2007-2016.

This research endeavors to explore the relationship between serum uric acid (SUA) concentration and all-cause mortality in stroke patients. We undertook a cross-sectional analysis utilizing data derived from the National Health and Nutrition Examination Survey (NHANES) spanning 2007 to 2016. The concentrations of SUA served as the independent variable, while the dependent variable was defined as all-cause mortality in stroke patients. The quartile method was utilized to classify uric acid levels into four distinct categories. Subsequently, three models were developed, and Cox proportional hazards regression was used to assess the effect of varying uric acid concentrations on the risk of all-cause mortality among stroke patients. The study included a total of 10,805 participants, of whom 395 were stroke patients. Among all populations, the group with elevated levels of uric acid (Q4) exhibited a significant association with the overall mortality risk among stroke patients in all three models (model 1 p < 0.001, model 2 p < 0.001, model 3 p < 0.001). In the male population, there was no significant correlation observed between uric acid levels and the overall mortality risk among stroke patients in model 3 (Q2 p = 0.8, Q3 p = 0.2, Q4 p = 0.2). However, within the female population, individuals with high uric acid levels (Q4) demonstrated a noteworthy association with the overall mortality risk among stroke patients across all three models (model 1 p < 0.001, model 2 p < 0.001, model 3 p < 0.001). This cross-sectional investigation reveals a significant correlation between SUA levels and all-cause mortality in stroke patients, with a noticeable trend observed among females. Consequently, SUA may serve as a promising biomarker for assessing the prognosis of individuals affected by stroke.

Personalized prediction of mortality in patients with acute ischemic stroke using explainable artificial intelligence

BackgroundResearch into the acute kidney disease (AKD) after acute ischemic stroke (AIS) is rare, and how clinical features influence its prognosis remain unknown. We aim to employ interpretable machine learning (ML) models to study AIS and clarify its decision-making process in identifying the risk of mortality.MethodsWe conducted a retrospective cohort study involving AIS patients from January 2020 to June 2021. Patient data were randomly divided into training and test sets. Eight ML algorithms were employed to construct predictive models for mortality. The performance of the best model was evaluated using various metrics. Furthermore, we created an artificial intelligence (AI)-driven web application that leveraged the top ten most crucial features for mortality prediction.ResultsThe study cohort consisted of 1633 AIS patients, among whom 257 (15.74%) developed subacute AKD, 173 (10.59%) experienced AKI recovery, and 65 (3.98%) met criteria for both AKI and AKD. The mortality rate stood at 4.84%. The LightGBM model displayed superior performance, boasting an AUROC of 0.96 for mortality prediction. The top five features linked to mortality were ACEI/ARE, renal function trajectories, neutrophil count, diuretics, and serum creatinine. Moreover, we designed a web application using the LightGBM model to estimate mortality risk.ConclusionsComplete renal function trajectories, including AKI and AKD, are vital for fitting mortality in AIS patients. An interpretable ML model effectively clarified its decision-making process for identifying AIS patients at risk of mortality. The AI-driven web application has the potential to contribute to the development of personalized early mortality prevention.

Machine learning for the prediction of in-hospital mortality in patients with spontaneous intracerebral hemorrhage in intensive care unit

This study aimed to develop a machine learning (ML)-based tool for early and accurate prediction of in-hospital mortality risk in patients with spontaneous intracerebral hemorrhage (sICH) in the intensive care unit (ICU). We did a retrospective study in our study and identified cases of sICH from the MIMIC IV (n = 1486) and Zhejiang Hospital databases (n = 110). The model was constructed using features selected through LASSO regression. Among five well-known models, the selection of the best model was based on the area under the curve (AUC) in the validation cohort. We further analyzed calibration and decision curves to assess prediction results and visualized the impact of each variable on the model through SHapley Additive exPlanations. To facilitate accessibility, we also created a visual online calculation page for the model. The XGBoost exhibited high accuracy in both internal validation (AUC = 0.907) and external validation (AUC = 0.787) sets. Calibration curve and decision curve analyses showed that the model had no significant bias as well as being useful for supporting clinical decisions. XGBoost is an effective algorithm for predicting in-hospital mortality in patients with sICH, indicating its potential significance in the development of early warning systems.