Predictor Of 1-year Mortality Research Articles

Abstract 13800: Comparison of Predictive Value of Risk Scores for Mortality in Asian Patients With Heart Failure With Preserved Ejection Fraction

Background: Several risk scores have been developed to predict mortality and morbidity in heart failure (HF), including heart failure with preserved ejection fraction (HFpEF). However, these scores have primarily been derived from data obtained from Western patients. Research Questions: It remains unclear whether these risk factors are applicable to Asian patients, whose pathophysiology of HFpEF may exhibit ethnic differences compared to Western populations. Aims: To compare the predictive value of widely used risk scores for mortality in Japanese patients with HFpEF. Methods: We assessed the predictive value of three commonly utilized risk scores: MAGGIC, BCN-BioHF, and 3C-HF risk scores, which are applicable to patients with HFpEF. A total of 1,095 patients registered in the PURSUIT-HFpEF, a multicenter registry comprising individuals hospitalized with decompensated HFpEF, were enrolled (mean age 81±9 years, 54.8% female). The MAGGIC risk score and the predicted 1-year mortality rate by the web-based BCN-BioHF and 3C-HF risk calculators were obtained for all patients. Patients were followed for a median duration of 428 days (interquartile range: 208-794 days) to observe all-cause mortality. The predictive value of the risk scores was compared using the area under the curve (AUC) of time-dependent ROC curves for 1-year mortality. Results: Complete risk scores and predicted 1-year mortality rates were available for 1,082 (98.8%) patients. The AUC for 1-year mortality prediction was 0.73 (95% CI 0.68, 0.78) for the MAGGIC score, 0.65 (0.59, 0.71) for BCN-BioHF, and 0.71 (0.64, 0.76) for 3C-HF. The MAGGIC score exhibited a significantly higher AUC than BCN-BioHF (p=0.003), while no significant differences were observed between the MAGGIC score and 3C-HF, or between BCN-BioHF and 3C-HF. Conclusion: This study demonstrates that the MAGGIC, BCN-BioHF, and 3C-HF risk scores provide good predictive value for 1-year mortality in Japanese patients with HFpEF. The superior performance of the MAGGIC score suggests that considering the ethnic differences in HFpEF pathophysiology is crucial for accurate risk prediction in Asian populations.

Shear wave elastography-based deep learning model for prognosis of patients with acutely decompensated cirrhosis.

This study aimed to develop and validate a deep learning model based on two-dimensional (2D) shear wave elastography (SWE) for predicting prognosis in patients with acutely decompensated cirrhosis. We prospectively enrolled 288 acutely decompensated cirrhosis patients with a minimum 1-year follow-up, divided into a training cohort (202 patients, 1010 2D SWE images) and a test cohort (86 patients, 430 2D SWE images). Using transfer learning by Resnet-50 to analyze 2D SWE images, a SWE-based deep learning signature (DLswe) was developed for 1-year mortality prediction. A combined nomogram was established by incorporating deep learning SWE information and laboratory data through a multivariate Cox regression analysis. The performance of the nomogram was evaluated with respect to predictive discrimination, calibration, and clinical usefulness in the training and test cohorts. The C-index for DLswe was 0.748 (95% CI 0.666-0.829) and 0.744 (95% CI 0.623-0.864) in the training and test cohorts, respectively. The combined nomogram significantly improved the C-index, accuracy, sensitivity, and specificity of DLswe to 0.823 (95% CI 0.763-0.883), 86%, 75%, and 89% in the training cohort, and 0.808 (95% CI 0.707-0.909), 83%, 74%, and 85% in the test cohort (both p < 0.05). Calibration curves demonstrated good calibration of the combined nomogram. Decision curve analysis indicated that the nomogram was clinically valuable. The 2D SWE-based deep learning model holds promise as a noninvasive tool to capture valuable prognostic information, thereby improving outcome prediction in patients with acutely decompensated cirrhosis.

Risk stratification model integrating nutritional and inflammatory factors for predicting 1-year mortality after valvular heart surgery: a retrospective cohort study.

Existing risk-scoring systems for cardiac surgery include only standard preoperative factors, without considering nutritional and inflammatory status or intraoperative factors. The objective of this study was to develop a comprehensive prediction model for mortality incorporating nutritional, inflammatory, and perioperative factors in patients undergoing valvular heart surgery. In this retrospective review of 2,046 patients who underwent valvular heart surgery, Cox and LASSO regression analyses were performed to identify independent prognostic factors of 1-year postoperative mortality among various perioperative factors known to affect prognosis, including objective nutritional and inflammatory indices. A novel nomogram model incorporating selected prognostic factors was developed, and its discrimination ability was evaluated using the C-index. The model was validated in internal and external cohorts. The 1-year mortality rate after valvular heart surgery was 5.1% (105 of 2,046 patients) and was significantly associated with several preoperative objective inflammatory and nutritional indices. Cox and LASSO analyses identified the following five independent prognostic factors for mortality: monocyte-to-lymphocyte ratio (an objective inflammatory index), EuroSCORE II, Controlling Nutritional Status score, cardiopulmonary bypass time, and number of erythrocyte units transfused intraoperatively. Our nomogram model incorporating these five factors had a C-index of 0.834 (95% CI 0.791-0.877), which was higher than that of EuroSCORE II alone (0.744, 95% CI 0.697-0.791) (P<0.001). The nomogram achieved good discrimination ability, with C-indices of 0.836 (95% CI 0.790-0.878) and 0.727 (95% CI 0.651-0.803) in the internal and external validation cohorts, respectively, and showed well-fitted calibration curves. A nomogram model incorporating five inflammatory, nutritional, and perioperative factors, as well as EuroSCORE II, was a better predictor of 1-year mortality after valvular heart surgery than EuroSCORE II alone, with good discrimination and calibration power for predicting mortality in both internal and external validation cohorts.

Machine learning-based mortality prediction in hip fracture patients using biomarkers.

The purpose of this retrospective study was to assess whether mortality following a hip fracture can be predicted by a machine learning model trained on basic blood and lab test data as well as basic demographic data. Additionally, the purpose was to identify the key variables most associated with 1-, 5-, and 10-year mortality and investigate their clinical significance. Input data included 3751 hip fracture patient records sourced from the Medical Information Mart for Intensive Care IV database, which provided records from in-hospital database systems at the Beth Israel Deaconess Medical Center. The 1-year mortality rate for all patients studied was 21% and for those aged 80+ was 29%. We assessed 10 different machine learning classification models, finding LightGBM to have the strongest 1-year mortality prediction performance, with accuracy of 81%, AUC of 0.79, sensitivity of 0.34, and specificity of 0.98 on the test set. The strongest-weighted features of the 1-year model included age, glucose, red blood cell distribution width, mean corpuscular hemoglobin concentration, white blood cells, urea nitrogen, prothrombin time, platelet count, calcium levels, and partial thromboplastin time. Most of these were also in the top 10 features of the LightGBM 5- and 10-year prediction models trained. Testing for these high-ranking biomarkers in new hip fracture patients can aid clinicians in assessing the likelihood of poor outcomes for hip fracture patients, and additional research can use these biomarkers to develop a mortality risk score.

Mortality Prediction in Patients With or Without Heart Failure Using a Machine Learning Model

BackgroundMost risk prediction models are confined to specific medical conditions, thus limiting their application to general medical populations. ObjectivesThe MARKER-HF (Machine learning Assessment of RisK and EaRly mortality in Heart Failure) risk model was developed in heart failure (HF) patients. We assessed the ability of MARKER-HF to predict 1-year mortality in a large community-based hospital registry database including patients with and without HF. MethodsThis study included 41,749 consecutive patients who underwent echocardiography in a tertiary referral hospital (4,640 patients with and 37,109 without HF). Patients without HF were further subdivided into those with (n = 22,946) and without cardiovascular disease (n = 14,163) and also into cohorts based on recent acute coronary syndrome or history of atrial fibrillation, chronic obstructive pulmonary disease, chronic kidney disease, diabetes mellitus, hypertension, or malignancy. ResultsThe median age of the 41,749 patients was 65 years, and 56.2% were male. The receiver operated area under the curves for MARKER-HF prediction of 1-year mortality of patients with HF was 0.729 (95% CI: 0.706-0.752) and for patients without HF was 0.770 (95% CI: 0.760-0.780). MARKER-HF prediction of mortality was consistent across subgroups with and without cardiovascular disease and in patients diagnosed with acute coronary syndrome, atrial fibrillation, chronic obstructive pulmonary disease, chronic kidney disease, diabetes mellitus, or hypertension. Patients with malignancy demonstrated higher mortality at a given MARKER-HF score than did patients in the other groups. ConclusionsMARKER-HF predicts mortality for patients with HF as well as for patients suffering from a variety of diseases.

Predictors of 5-Year Mortality in Patients Managed With a Magnetically Levitated Left Ventricular Assist Device

BackgroundIn advanced heart failure patients implanted with a fully magnetically levitated HeartMate 3 (HM3, Abbott) left ventricular assist device (LVAD), it is unknown how preimplant factors and postimplant index hospitalization events influence 5-year mortality in those able to be discharged. ObjectivesThe goal was to identify risk predictors of mortality through 5 years among HM3 LVAD recipients conditional on discharge from index hospitalization in the MOMENTUM 3 pivotal trial. MethodsThis analysis evaluated 485 of 515 (94%) patients discharged after implantation of the HM3 LVAD. Preimplant (baseline), implant surgery, and index hospitalization characteristics were analyzed individually, and as multivariable predictors for mortality risk through 5 years. ResultsCumulative 5-year mortality in the cohort (median age: 62 years, 80% male, 65% White, 61% destination therapy due to transplant ineligibility) was 38%. Two preimplant characteristics (elevated blood urea nitrogen and prior coronary artery bypass graft or valve procedure) and 3 postimplant characteristics (hemocompatibility-related adverse events, ventricular arrhythmias, and estimated glomerular filtration rate <60 mL/min/1.73 m2 at discharge) were predictors of 5-year mortality. In 171 of 485 patients (35.3%) without any risk predictors, 5-year mortality was reduced to 22.6% (95% CI: 15.4%-32.7%). Even among those with 1 or more predictors, mortality was <50% at 5 years (45.7% [95% CI: 39.0%-52.8%]). ConclusionsLong-term survival in successfully discharged HM3 LVAD recipients is largely influenced by clinical events experienced during the index surgical hospitalization in tandem with baseline factors, with mortality of <50% at 5 years. In patients without identified predictors of risk, long-term 5-year mortality is low and rivals that achieved with heart transplantation, even though most were implanted with destination therapy intent. (MOMENTUM 3 IDE Clinical Study Protocol, NCT02224755; MOMENTUM 3 Pivotal Cohort Extended Follow-up PAS, NCT03982979)

Systemic inflammation and biological aging in the Health and Retirement Study

Chronic, low-level systemic inflammation associated with aging, or inflammaging, is a risk factor for several chronic diseases and mortality. Using data from the Health and Retirement Study, we generated a continuous latent variable for systemic inflammation from seven measured indicators of inflammation and examined associations with another biomarker of biological aging, DNA methylation age acceleration measured by epigenetic clocks, and 4-year mortality (N = 3,113). We found that greater systemic inflammation was positively associated with DNA methylation age acceleration for 10 of the 13 epigenetic clocks, after adjustment for sociodemographics and chronic disease risk factors. The latent variable for systemic inflammation was associated with 4-year mortality independent of DNA methylation age acceleration and was a better predictor of 4-year mortality than any of the epigenetic clocks examined, as well as mortality risk factors, including obesity and multimorbidity. Inflammaging and DNA methylation age acceleration may represent different biological processes contributing to mortality risk. Leveraging multiple measured inflammation markers to capture inflammaging is important for biology of aging research.

Novel pneumonia score based on a machine learning model for predicting mortality in pneumonia patients on admission to the intensive care unit

BackgroundScores for predicting the long-term mortality of severe pneumonia are lacking. The purpose of this study is to use machine learning methods to develop new pneumonia scores to predict the 1-year mortality and hospital mortality of pneumonia patients on admission to the intensive care unit (ICU). MethodsThe study population was screened from the MIMIC-IV and eICU databases. The main outcomes evaluated were 1-year mortality and hospital mortality in the MIMIC-IV database and hospital mortality in the eICU database. From the full data set, we separated patients diagnosed with community-acquired pneumonia (CAP) and ventilator-associated pneumonia (VAP) for subgroup analysis. We used common shallow machine learning algorithms, including logistic regression, decision tree, random forest, multilayer perceptron and XGBoost. ResultsThe full data set of the MIMIC-IV database contained 4697 patients, while that of the eICU database contained 13760 patients. We defined a new pneumonia score, the "Integrated CCI-APS", using a multivariate logistic regression model including six variables: metastatic solid tumor, Charlson Comorbidity Index, readmission, congestive heart failure, age, and Acute Physiology Score III. The area under the curve (AUC) and accuracy of the integrated CCI-APS were assessed in three data sets (full, CAP, and VAP) using both the test set derived from the MIMIC-IV database and the external validation set derived from the eICU database. The AUC value ranges in predicting 1-year and hospital mortality were 0.784–0.797 and 0.691–0.780, respectively, and the corresponding accuracy ranges were 0.723–0.725 and 0.641–0.718, respectively. ConclusionsThe main contribution of this study was a benchmark for using machine learning models to build pneumonia scores. Based on the idea of integrated learning, we propose a new integrated CCI-APS score for severe pneumonia. In the prediction of 1-year mortality and hospital mortality, our new pneumonia score outperformed the existing score.

Interstitial Brachytherapy for Hepatocellular Carcinoma: Analysis of Prognostic Factors for Overall Survival and Progression-Free Survival and Application of a Risk Stratification Model

Introduction: Interstitial brachytherapy (iBT) is an effective treatment for hepatocellular carcinoma (HCC). Identification of prognostic factors is pivotal for patient selection and treatment efficacy. This study aimed to assess the impact of low skeletal muscle mass (LSMM) on overall survival (OS) and progression-free survival (PFS) of iBT in patients with HCC. Methods: For this single-center study, we retrospectively identified 77 patients with HCC who underwent iBT between 2011 and 2018. Follow-up visits were recorded until 2020. The psoas muscle area, psoas muscle index, psoas muscle density (MD), and the skeletal muscle gauge were assessed on the L3 level on pre-treatment cross-sectional CT scans. Results: Median OS was 37 months. 42 patients (54.5%) had LSMM. An AFP level of >400 ng/ml (hazard ratio [HR] 5.705, 95% confidence interval [CI]: 2.228–14.606, p = 0.001), BCLC stage (HR 3.230, 95% CI: 0.972–10.735, p = 0.026), and LSMM (HR 3.365, 95% CI: 1.490–7.596, p = 0.002) showed a relevant association with OS. Weighted hazard ratios were used to form a predictive risk stratification model with three groups: patients with low risk (median OS 62 months), intermediate risk (median OS 31 months), and high risk (median OS 9 months). The model showed a good prediction of 1-year mortality, with an AUC of 0.71. Higher MD was associated with better PFS (HR 0.920, 95% CI: 0.881–0.962, p < 0.001). Conclusion: In patients undergoing iBT for HCC, LSMM is associated with worse OS. A risk stratification model based on LSMM, AFP >400 ng/mL, and BCLC stage successfully predicted patient mortality. The model may support and enhance patient selection.

Temporary trends of cardiac device related infective endocarditis in a tertiary referral center between 2006 and 2022

Abstract Funding Acknowledgements Type of funding sources: None. Background Infective endocarditis (IE) is a rare, but life-threatening complication of cardiac device implantation. Despite recent preventive strategies and advances in antimicrobial and surgical treatment, morbidity and mortality rates are still high. Aims The objective of our study was to assess the epidemiological characteristics, temporal trends and mortality rates of cardiac device related IE (CDRIE) in our high-volume, tertiary referral center. Methods retrospective data collection was performed between January 1, 2006 and March 31, 2022. Median follow-up was 3.8 yrs (IQR: 0.6 – 9.2 yrs). Patients admitted between 2006 and 2013 (group 1) and between 2014 and 2022 (group 2) were compared to assess temporal trends. Thirty-day, 6-month and 1-year mortality rates were estimated. Results During the observed 17 years 82 patients were admitted with CDRIE (61 males [74%]), mean age: 57.3 ±18 yrs; 6 VVI, 7 VDD, 17 VVI-ICD, 24 DDD, 10 DDD-ICD and 18 CRT devices [4 CRT-P, 14 CRT-D]); median time since first implantation was 3.8 yrs [IQR: 1.1 – 6.6 yrs]). Staphylococci were the most prevalent infective agents (62%), S. aureus (SA) infection was found in 37 cases (out of whom 13 were MRSA [16%]), coagulase negative Staphylococcus in 14 cases (17%), Enterococcus faecalis in 9 cases (11%), streptococci in 4 cases (5%), blood culture was negative in 13 cases (15%), and in 5 cases other pathogens were the underlying microorganism. Patients in Group 1 (n=42) did not differ from patients in Group 2 (n=40) in terms of age, male gender or ejection fraction. Patients in Group 2 had higher CRP level at admission (42,9 [IQR:34-55] mmol/l vs 90 [IQR:25-60] mmol/l, p=0.02). ICD lead (29% vs 67%, p&amp;lt;0.001) and E. faecalis infection (2% vs 20%, p=0.03) and percutan extraction (55% vs 75%, p=0.05) were more prevalent in Group 2. The 30-day and 6-month mortality rates were worse in Group 2 than in Group 1 (2% vs 17.5% p=0.03; and 16% vs 35% p=0.04 resp.) while the 1-year mortality did not differ (24% vs 40%). The all-cause mortality was 10% at 30 days, 26% at 6 month and 32% at 1 year. Univariate regression showed that age (HR: 1.03 [1.01-1.07] p&amp;lt;0.05), ejection fraction (HR: 0.96 [0.93-0.98] p&amp;lt;0.005), ICD lead (HR: 4.89 [1.82-14.40] p&amp;lt;0.005) and the time since first implantation (HR: 0.88 [0.77-0.98] p&amp;lt;0.05) were the predictors of 1-year mortality. However, in Cox multiple regression model only age (HR: 1.05 [1.004-1.1] p&amp;lt;0.05) and ICD lead (HR: 1.16 [1.16-17.38] p&amp;lt;0.05) remains independent predictors of outcome at 1 year. Conclusions In the past 17 years the most prevalent underlying microorganism were staphylococcal species, although Enterococcus faecalis infection increased over time. Patients with CDRIE had poor prognosis, every third patient died at 1 year after diagnosis. The short-term prognosis is even worse in the past few years than before, which may be a negative consequence of limited accessibility of healthcare due to COVID 19 pandemic.

Predictors of 1-Year Mortality from a Subacute Geriatric Ward in Singapore

Predictors of 1-Year Mortality from a Subacute Geriatric Ward in Singapore

Validation of a Novel Clinical Dyspnea Scale - A Retrospective Pilot Study.

Objective: to examine the validity of a novel dyspnea scale, Edmonton Dyspnea Inventory in idiopathic pulmonary fibrosis (IPF). Methods: Edmonton Dyspnea Inventory (EDI), is a clinical instrument to measure dyspnea severity with activities of daily living, exercise and rest using a numeric rating scale (0 -10). Consecutive IPF patients (2012-2018) with baseline MRC and EDI were included. To validate EDI, psychometric analysis was conducted. Correlations between EDI, MRC and lung function were examined. Group-based trajectory modeling was used to group patients based on dyspnea severity. Net Reclassification Improvement (NRI) was calculated to assess the improvement in 1-year mortality prediction by adding trajectory groups to MRC grade. Results: 100 consecutive IPF patients were identified; mean age 73 years (SD = 9) and 65% males; 73% were in MRC grades ≥3. Item analysis showed all 8 EDI components have excellent discrimination power with ability to differentiate patients with varying dyspnea severity. EDI has good internal consistency (Cronbach α = .92). Exploratory factor analysis showed a one-factor solution with loadings from .66 to .89 suggesting 8 EDI components measured essentially one dimension of dyspnea. All EDI components were correlated with MRC and some with lung function. Modeling data identified three EDI dyspnea severity groups with differing mortality (P = .009). The addition of EDI dyspnea severity groups to the MRC score improved 1-year mortality prediction (NRI = .66; 95% CI, .18-1.14). Conclusions: EDI is a valid dyspnea instrument, correlated with MRC and lung function. It can categorize IPF patients into 3 dyspnea severity groups associated with increased mortality. Key Message: We describe the development of a novel scale, Edmonton Dyspnea Inventory, that facilitates measurement of dyspnea severity in the context of daily activities in patients with IPF. The results indicate that the new instrument is valid and correlated to MRC. It identifies 3 categories of severity not recognized by MRC with impact on mortality. Knowledge of dyspnea severity can help triage patients and assign appropriate therapies.

The Utility of Glasgow Prognostic Score as an Indicator of Mortality After Transcatheter Aortic Valve Implantation

Aim&#x0D; The Glasgow Prognostic Score (GPS) is a scoring system obtained by using inflammatory (C-reactive protein) and nutritional (albumin) parameters together, and it has been shown to have prognostic value in various cardiac pathologies in previous studies. In this study, we aimed to investigate the usability of the Glasgow Prognostic Score (GPS) in predicting 1-year mortality in patients who underwent transcatheter aortic valve implantation (TAVI).&#x0D; Method&#x0D; Patients who underwent TAVI with the diagnosis of severe, symptomatic aortic stenosis in our hospital between 2013 and 2017 were included in this single center study retrospectively. Demographic, clinical and laboratory data were obtained by reviewing patient files. GPS value was calculated by using C-reactive protein and albumin values which was obtained on admission to. Two groups were formed as survivors and non-survivors according to 1-year mortality data. &#x0D; Results&#x0D; A total of 170 patients were included in this retrospective study and 59 patients constituted the non-survivors group. History of chronic obstructive pulmonary disease and cerebrovascular disease were higher in non-survivors’ group. High STS-TAVR, Euro SCORE II and GPS levels were also higher in non-survivors group. High GPS value calculated with pre-procedural data was determined as a predictor of 1-year mortality.&#x0D; Conclusion&#x0D; The Glasgow Prognostic Score allows the evaluation of inflammation and nutritional status together, is a practical method that can be obtained from routine laboratory parameters. It can be used as a predictor of mortality in patients undergoing TAVI. It can guide clinicians in taking preventive measures to reduce mortality before the procedure.

Prognostic relevance of mitral and tricuspid regurgitation after transcatheter aortic valve implantation: Impact of follow-up time point for decision-making.

In patients with aortic stenosis treated by transcatheter aortic valve implantation (TAVI), mitral and tricuspid regurgitation (MR and TR) at baseline and after TAVI are likely to be of prognostic relevance, and questions such as whether and when treatment further improves prognosis in these patients arise. Against that background, the purpose of this study was to analyze a variety of clinical characteristics including MR and TR with respect to their potential value as predictors of 2-year mortality after TAVI. A cohort of 445 typical TAVI patients was available for the study and clinical characteristics were evaluated baseline, 6 to 8 weeks as well as 6 months after TAVI. In 39% of the patients relevant (moderate or severe) MR and in 32% of the patients relevant (moderate or severe) TR could be detected at baseline. The rates were 27% for MR (p = 0.001, compared to baseline) and 35% for TR (p = n.s., compared to baseline) at the 6- to 8-week follow-up. After 6 months, relevant MR was observable in 28% (p = 0.036, compared to baseline) and relevant TR in 34% (p = n.s., compared to baseline) of the patients. As predictors of 2-year mortality, a multivariate analysis identified the following parameters for the different time points: sex, age, AS entity, atrial fibrillation, renal function, relevant TR, systolic pulmonary artery pressure (PAPsys), and 6-min walk distance at baseline; clinical frailty scale and PAPsys 6-8 weeks after TAVI and BNP and relevant MR 6 months after TAVI. There was a significantly worse 2-year survival in patients with relevant TR at baseline (68.4% vs. 82.6%, p < 0.001; whole population, n = 445) and in patients with relevant MR at 6 months (87.9% vs. 95.2%, p = 0.042; landmark analysis: n = 235). This real-life study demonstrated the prognostic relevance of repeated evaluation of MR and TR before and after TAVI. Choosing the right time point for treatment is a remaining clinical challenge, which should be further addressed in randomized trials.

Association between Fibrinogen-to-Albumin Ratio and Prognosis in Patients Admitted to an Intensive Care Unit.

The objective of this study was to investigate the usefulness of fibrinogen-to-albumin ratio (FAR) as a prognostic marker in patients admitted to an intensive care unit (ICU) compared with Sequential Organ Failure Assessment (SOFA) score, a widely used prognostic scoring system. An inverse probability weighting (IPW) was used to control for selection bias and confounding factors. After IPW adjustment, the high FAR group showed significantly higher risk of 1-year compared with low FAR group (36.4% vs. 12.4%, adjust hazard ratio = 1.72; 95% confidence interval (CI): 1.59-1.86; p < 0.001). In the receiver-operating characteristic curve analysis associated with the prediction of 1-year mortality, there was no significant difference between the area under the curve of FAR on ICU admission (C-statistic: 0.684, 95% CI: 0.673-0.694) and that of SOFA score on ICU admission (C-statistic: 0.679, 95% CI: 0.669-0.688) (p = 0.532). In this study, FAR and SOFA score at ICU admission were associated with 1-year mortality in patients admitted to an ICU. Especially, FAR was easier to obtain in critically ill patients than SOFA score. Therefore, FAR is feasible and might help predict long-term mortality in these patients.

Five-Year Survival and Complications of Thoracic Endovascular Aortic Repair (TEVAR): A Single Tertiary Center Registry for All-Comers Patients

IntroductionStudies on the mid and long-term outcomes of thoracic endovascular aortic repair (TEVAR) are scarce. This study aimed to investigate the long-term outcomes of TEVAR for all-comers patients with various types of thoracic aortic pathologies, predominantly thoracic aortic dissections and thoracic aortic aneurysms. MethodsBetween January 2005 and December 2015, 123 consecutive patients with thoracic aortic pathologies underwent TEVAR. The patients were divided into groups based on aortic pathologies (dissections or aneurysms) and the type of procedure (hybrid TEVAR or non-hybrid TEVAR). Mortality, complications, and reintervention rates were compared between these four groups. The Kaplan–Meier curve and the Cox regression analysis were employed to estimate survivals and factors associated with 5-year mortality. ResultsOne hundred twenty-three consecutive patients with various aortic pathologies undergoing TEVAR were evaluated. Hypertension (79.7 %) and smoking (39 %) were the most common comorbidities in the study population. The patients were followed up for a mean duration of 58.1 ± 7.1 months to evaluate the postprocedural surveillance. Most complications occurred in the dissection and hybrid groups; however, these differences were nonsignificant. The overall 5-year surveillance and reintervention rates were 65 % and 12.1 %, respectively. A significant difference existed in 5-year survival between the patients with aneurysmal and aortic dissection pathologies based on the log-rank test (P = 0.01). On the other hand, no significant differences were observed in 5-year survival between the patients who underwent hybrid and non-hybrid TEVAR. The Cox regression analysis confirmed that chronic kidney disease, previous coronary artery bypass grafting, age >65 years, platelet counts <150∗ 103/μL, aneurysmal aortic pathology, and ejection fraction ≤ 50 % were predictors of 5-year mortality. ConclusionsThe long-term outcomes of TEVAR for various aortic pathologies disclosed that this procedure was well-tolerated in a group of patients with high comorbid conditions. The five-year survival rate of TEVAR for thoracic aortic dissections was more favorable than that for thoracic aortic aneurysms, but there were no significant differences between hybrid and non-hybrid procedures regarding the mortality rate.

External validation of the SORG machine learning algorithms for predicting 90-day and 1-year survival of patients with lung cancer-derived spine metastases: a recent bi-center cohort from China

BACKGROUND CONTEXTThe survival prediction of lung cancer-derived spinal metastases is often underestimated by several scores. The SORG machine learning (ML) algorithm is considered a promising tool to predict the risk of 90-day and 1-year mortality in patients with spinal metastases, but not been externally validated for lung cancer. PURPOSEThis study aimed to externally validate the SORG ML algorithms on lung cancer-derived spinal metastases patients from two large-volume, tertiary medical centers between 2018 and 2021. STUDY DESIGN/SETTINGRetrospective, cohort study. PATIENT SAMPLEPatients aged 18 years or older at two tertiary medical centers in China are treated surgically for spinal metastasis. OUTCOME MEASURESMortality within 90 days of surgery, mortality within 1 year of surgery. METHODSThe baseline characteristics were compared between the development cohort and our validation cohort. Discrimination (receiver operating curve), calibration (calibration plot, intercept, and slope), the overall performance (Brier score), and decision curve analysis was used to assess the overall performance of the SORG ML algorithms. RESULTSThis study included 150 patients with lung cancer-derived spinal metastases from two medical centers in China. Ninety-day and 1-year mortality rates were 12.9% (19/147) and 51.3% (60/117), respectively. Lung Cancer with targeted therapies had the lowest Hazard Ratio (HR=0.490), showing an optimal protecting factor. The AUC of the SORG ML algorithm for 90-day mortality prediction in lung cancer-derived spinal metastases is 0.714. While the AUC for 1-year mortality prediction is 0.832 (95CI%, 0.758–0.906). The algorithm for 1-year mortality was well-calibrated with an intercept of 0.13 and a calibration slope of 1.00. However, the 90-day mortality prediction was underestimated with an intercept of 0.60 and a slope of 0.37. The SORG ML algorithms for 1-year mortality showed a greater net benefit than the “treats all or no patients” strategies. CONCLUSIONSIn the latest cohort of lung cancer-derived spinal metastases in China, the SORG algorithms for predicting 1-year mortality performed well on external validation. However, 90-day mortality was underestimated. The algorithm should be further validated by single primary tumor-derived metastasis treated with the latest comprehensive treatment in diverse populations.

Machine learning for prediction of all-cause mortality after transcatheter aortic valve implantation.

Prediction of adverse events in mid-term follow-up after transcatheter aortic valve implantation (TAVI) is challenging. We sought to develop and validate a machine learning model for prediction of 1-year all-cause mortality in patients who underwent TAVI and were discharged following the index procedure. The model was developed on data of patients who underwent TAVI at a high-volume centre between January 2013 and March 2019. Machine learning by extreme gradient boosting was trained and tested with repeated 10-fold hold-out testing using 34 pre- and 25 peri-procedural clinical variables. External validation was performed on unseen data from two other independent high-volume TAVI centres. Six hundred four patients (43% men, 81±5 years old, EuroSCORE II 4.8 [3.0-6.3]%) in the derivation and 823 patients (46% men, 82±5 years old, EuroSCORE II 4.7 [2.9-6.0]%) in the validation cohort underwent TAVI and were discharged home following the index procedure. Over the 12 months of follow-up, 68 (11%) and 95 (12%) subjects died in the derivation and validation cohorts, respectively. In external validation, the machine learning model had an area under the receiver-operator curve of 0.82 (0.78-0.87) for prediction of 1-year all-cause mortality following hospital discharge after TAVI, which was superior to pre- and peri-procedural clinical variables including age 0.52 (0.46-0.59) and the EuroSCORE II 0.57 (0.51-0.64), P<0.001 for a difference. Machine learning based on readily available clinical data allows accurate prediction of 1-year all-cause mortality following a successful TAVI.

Utility of carotid ultrasound on prediction of 1-year mortality in emergency department patients with neurological deficits: A 10-year population-based cohort study.

This study aimed to investigate the association between the carotid ultrasound results and 1-yr mortality of patients with neurological deficits in the emergency department (ED). This study included patients with neurological symptoms who presented to the ED between January 1, 2009 and December 31, 2018, and underwent sonographic imaging of the bilateral carotid bulb, common carotid artery (CCA), internal carotid artery (ICA), and external carotid arteries. A stenosis degree of >50% was defined as significant carotid stenosis. Carotid plaque score (CPS) was calculated by adding the score of stenosis severity of all segments. The association between carotid ultrasound results and 1-yr mortality was investigated using the Cox regression model. The analysis included 7,961 patients (median age: 69 yr; men: 58.7%). Among them, 247 (3.1%) passed away from cardiovascular (CV)-related causes, and 746 (9.4%) died within a year. The mortality group presented with more significant carotid stenosis of the carotid bulb, CCA, or ICA and had a higher median CPS. A higher CPS was associated with a greater 1-yr all-cause mortality (adjusted hazard ratio [aHR] = 1.08; 95% confidence interval [CI] = 1.03-1.13; p = 0.001; log-rank p < 0.001) and CV-related mortality (aHR = 1.13; 95% CI = 1.04-1.22; p = 0.002, log-rank p < 0.001). Significant stenosis of either carotid artery segment did not result in a higher risk of 1-yr mortality. We comprehensively investigated the utility of carotid ultrasound parameters on predicting mortality in this 10-yr population-based cohort, which included over 7,000 patients with acute neurological deficits presented to the ED. The result showed that CPS could be used as risk stratification tools for 1-yr all-cause and CV mortality.

Identification of Prognostic Factors for Recurrence and Mortality in Patients With Acute Pulmonary Embolism.

This study aimed to explore prognostic factors for 1-year recurrence and mortality in patients with acute pulmonary embolism (APE). APE patients who attended the Emergency Department of Fujian Provincial Hospital from January 2016 to June 2020 were recruited. Univariate and multivariate logistic regression analyses were carried out to determine the prognostic factors for 1-year recurrence and mortality. A total of 458 APE patients were included, of whom 81 (17.69%) had recurrence, and 97 (21.18%) died. Multivariate logistic regression analyses revealed that smoke (OR: 1.949; 95% CI: 1.094-3.470; P = 0.023), abnormal platelet distribution width (OR: 3.013; 95% CI: 1.574-5.767; P = 0.001), and interrupted maintenance therapy (OR: 18.280; 95% CI: 9.777-34.179; P < 0.001) were significantly associated with an increased risk of 1-year recurrence in APE patients. Age ≥65 years (OR: 3.492; 95% CI: 1.876-6.500; P < 0.001), history of malignancy (OR: 7.190; 95% CI: 3.804-13.587; P < 0.001), history of long-term immobilization (OR: 6.244; 95% CI: 3.472-11.228; P < 0.001), mechanical ventilation (OR: 5.971; 95% CI: 3.154-11.304; P < 0.001), and interrupted maintenance therapy (OR: 2.414; 95% CI: 1.315-4.432; P = 0.004) were independent prognostic factors for 1-year mortality. The AUC of 1-year mortality and recurrence prediction models were 0.852 (95% CI: 0.805-0.898) and 0.868 (95%CI: 0.832-0.905). In patients with APE, history of smoking, abnormal PDW, and interrupted maintenance therapy were significantly associated with the risk of 1-year recurrence, while age ≥65 years, history of malignancy, history of long-term immobilization, mechanical ventilation, and interrupted maintenance therapy were independent prognostic factors for 1-year mortality.