Predictor Of 1-year Mortality Research Articles

Comparison of five scores to predict mortality in malignant pleural effusion.

Malignant pleural effusion (MPE) is a complication of malignancy. Treatment of MPE is based on predicted outcome. The aim of this study was to compare the performance characteristics of LENT, PROMISE, RECLS, AL and pNLR scores for prediction of mortality in lung cancer patients who have MPE. Patients who were diagnosed with MPE that was associated with underlying lung cancer between January 2010 and December 2019 were included and analyzed retrospectively in a single center. Outcomes considered were 30-day, 6 months, and 1-year mortality. A total of 180 patients were examined. For 30-day mortality, the areas under the ROC curves (AUC) (95% CI) were: LENT 0.83 (0.76-0.87), RECLS 0.71 (0.63-0.77), and PROMISE 0.70 (0.17-0.38). For 6-month and 1-year mortality the order of these AUCs was similar. Cox regression showed that none of the scores were significantly associated with 30-day mortality, but LENT and RECLS were significantly associated with 6-month and 1-year mortality. Comparison of - 2log likelihood ratios showed that LENT score was more, strongly associated with 6-month mortality than PROMISE (p = 0.001) or RECLS (p = 0.02). LENT score was also more strongly associated with 1-year mortality than PROMISE (p = 0.001) but there was no difference between LENT and RECLS score (p = 0.64). We observed that the LENT score was more predictive than the other scores in mortality in patients who have lung cancer and MPE. The LENT and RECLS scores have similar performance characteristics for prediction of 1-year mortality in these patients.

Enhanced machine learning models for predicting one-year mortality in individuals suffering from type A aortic dissection

ObjectiveThe study objective was to develop and validate an interpretable machine learning model to predict 1-year mortality in patients with type A aortic dissection, improving risk classification and aiding clinical decision-making. MethodsWe enrolled 289 patients with type A aortic dissection, dividing them into a training cohort (202 patients) and a validation cohort (87 patients). The Least Absolute Shrinkage and Selection Operator method with 10-fold cross-validation identified 8 key factors related to 1-year mortality. The Treebag model's performance was assessed using accuracy, F1-Score, Brier score, area under the curve, and area under the precision-recall curve with calibration and clinical utility evaluated through decision curves. Shapley Additive Explanations analysis determined the most influential predictors. ResultsThe Treebag model outperformed others, achieving a Brier score of 0.128 and an area under the curve of 0.91. Key risk factors included older age and elevated white blood cell count, whereas higher systolic blood pressure, lymphocyte, carbon dioxide combining power, eosinophil, β-receptor blocker use, and surgical intervention were protective. A web-based application, TAAD One-Year Prognostic Risk Assessment Web, was developed for clinical use (available at https://taad-1year-mortality-predictor.streamlit.app/). This platform allows for the prediction of 1-year mortality in patients with type A aortic dissection based on the identified predictive factors, facilitating clinical decision-making and patient management. ConclusionsThe Treebag machine learning model effectively predicts 1-year mortality in patients with type A aortic dissection, stratifying risk profiles. Key factors for enhancing survival include surgical intervention, β-blocker administration, and management of systolic blood pressure, lymphocyte, carbon dioxide combining power, eosinophil, and white blood cell levels, offering a valuable tool for improving patient outcomes.

Predictors of 2-year mortality in geriatric patients hospitalized with COVID-19 in Türkiye: a retrospective cohort study.

Aim: To reveal factors affecting 2-year mortality in geriatric patients hospitalized with COVID-19.Methods: Demographic characteristics, clinical and laboratory data, thorax computed tomography (CT) images, second-year survival status, and causes of death were analyzed.Results: The 2-year post-discharge mortality rate of 605 patients was 21.9%. Mean age of patients in the deceased group was 76.8±8.1years, which was shorter than the life expectancy at birth in Türkiye. Older age (≥85), delirium, some co-morbidities, and atypical thorax CT involvement were associated with a significant increase in 2-year mortality (p<0.05).Conclusion: This is the first study to evaluate factors associated with 2-year mortality in older COVID-19 patients. Identifying risk factors for long-term mortality in geriatric COVID-19 patients is important.

Association between red blood cell distribution width-platelet ratio (RPR) and mortality in patients with heart failure from the MIMIC IV database: A retrospective cohort study

The association between the red blood cell distribution width-platelet ratio (RPR) and mortality in heart failure patients remains unclear. We aimed to investigate the potential non-linear relationship between RPR and 1-year mortality risk. A retrospective cohort study was conducted involving 6982 participants from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Multivariable Cox regression and restricted cubic spline analyses were performed to evaluate the association between RPR and 1-year mortality, adjusting for potential confounders. We observed 1091 patients died in hospital and 2535 patients died during 1 year follow-up period. The prevalence or incidence of mortality did not show statistically significant differences among RPR groups in the overall study population. However, a positive association between RPR and the risk of mortality was noted after adjusting for multiple variables (HR = 1.38, 95 % CI = 1.06–1.81, P = 0.018). Analysis using restricted cubic splines indicated a U-shaped relationship between RPR levels and the risk of mortality (P nonlinearity <0.05), with the point of lowest risk at 0.104. Compared to this level, lower RPR (<0.104) was associated with increased mortality (HR = 0.046, 95 % CI: 0.004–0.546), as was higher RPR (>0.104) (HR = 2.656, 95 % CI: 1.692–4.170).This U-shaped association was consistent across subgroup analyses (all interaction P values > 0.05). RPR exhibits a U-shaped association with 1-year mortality in heart failure patients, suggesting both low and high RPR levels are linked to increased risk. RPR may serve as a relevant biomarker for risk stratification in this population. We incorporated RPR into the SOFA (AUC 0.731) and SAPS II (AUC 0.746) models, which significantly improved their predictive ability for in-hospital mortality. For 1-year mortality prediction, RPR + SAPS II (AUC 0.683) showed significantly improved accuracy, while RPR + SOFA (AUC 0.626) did not improve significantly.

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.

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.

Validation of the Charlson Comorbidity Index for the prediction of 30-day and 1-year mortality among patients who underwent hip fracture surgery

IntroductionThe aim of our study was to validate the original Charlson Comorbidity Index (1987) (CCI) and adjusted CCI (2011) as a prediction model for 30-day and 1-year mortality after hip fracture surgery. The secondary aim of this study was to verify each variable of the CCI as a factor associated with 30-day and 1-year mortality.MethodsA prospective database of two-level II trauma teaching hospitals in the Netherlands was used. The original CCI from 1987 and the adjusted CCI were calculated based on medical history. To validate the original CCI and the adjusted CCI, the CCI was plotted against the observed 30-day and 1-year mortality, and the area under the curve (AUC) was calculated.ResultsA total of 3523 patients were included in this cohort study. The mean of the original CCI in this cohort was 5.1 (SD ± 2.0) and 4.6 (SD ± 1.9) for the adjusted CCI. The AUCs of the prediction models were 0.674 and 0.696 for 30-day mortality for the original and adjusted CCIs, respectively. The AUCs for 1-year mortality were 0.705 and 0.717 for the original and adjusted CCIs, respectively.ConclusionsA higher original and adjusted CCI is associated with a higher mortality rate. The AUC was relatively low for 30-day and 1-year mortality for both the original and adjusted CCIs compared to other prediction models for hip fracture patients in our cohort. The CCI is not recommended for the prediction of 30-day and 1-year mortality in hip fracture patients.

Left and right ventricular function measured by strain analysis predicts one-year mortality in ventricular tachycardia ablation patients with structural heart disease

Abstract Introduction Radiofrequency catheter ablation has become increasingly important in the management of scar-related ventricular tachycardia (VT). Wide range of clinical and procedural predictors of VT recurrence and mortality are described by previous studies. However, currently known echocardiographic predictors are mainly limited to conventional echo parameters. Speckle tracking echocardiography (STE) is a novel and promising method to evaluate systolic and diastolic function. STE derived parameters, such as global longitudinal strain (GLS), are proven predictors of mortality and arrhythmic events in heart diseases. Aims The aim of the present study was to assess whether STE derived parameters could be considered predictors of VT recurrence and mortality after catheter ablation of ventricular tachycardia in patients with structural heart disease. Methods We measured pre-ablation strain and strain rate parameters with speckle tracking. Left ventricular four-chamber longitudinal strain (LV4CLS), early diastolic strain rate (e’-sr), right ventricular free wall longitudinal strain (RVFWLS) and right ventricular four-chamber longitudinal strain (RV4CLS) were assessed in 73 cases. Patients were followed up for one year. Endpoints were VT recurrence, which was defined as either ICD recording of a sustained VT episode requiring therapy or an episode of sustained VT recorded on 12-lead ECG or CIED, and all-cause mortality. Results Univariate analysis using the Cox proportional hazard model revealed that only lower LVEF (HR: 0.52 [0.31-0.88], p=0.02) was associated with higher VT recurrence in the first year among the echocardiographic parameters. High LVEDD (HR: 3.9 [1.31-11.65], p=0.02), low TAPSE (HR: 0.52 [0.28-0.98], p=0.04), low LV4CLS (HR: 0.4 [0.19-0.83], p=0.01) and low RV4CLS (HR: 0.31 [0.13-0.72], p&amp;lt;0.01) were the predictors of 1-year mortality. Conclusion Strain parameters, especially right ventricular four-chamber longitudinal strain may supplement conventional echocardiographic parameters in the prediction of one-year mortality after catheter ablation in patients with structural heart disease. Further prospective clinical studies are necessary to verify the significance of strain parameters.

#1751 Validation of the ReDO Death Score in a Portuguese cohort

Abstract Background and Aims Mortality within the first year after dialysis start is estimated to be 20-30%, and it is mostly due to cardiovascular disease. Prognostic assessment after starting hemodialysis is challenging. Clark et al. developed the Recovery and Death Outcome risk score, which accurately predicted the likelihood of renal recovery to dialysis independence and of death within 1 year after discharge from in-hospital dialysis initiation. These models can be used at discharge or soon after patients start outpatient dialysis. We aimed to validate the Death Outcome risk score to predict one-year mortality after dialysis start in our population. Method .Retrospective analysis of hospitalized patients who initiated hemodialysis in a tertiary care hospital (Unidade Local de Saúde Santa Maria), from January 1st of 2016 to December 31st of 2019, and were discharged to outpatient dialysis. The risk of death within one year of discharge was calculated according to the ReDO score. We evaluated all-cause mortality within one year of hospital discharge. We classified patients into death outcome risk groups (labeled D1 to D4) according to the ReDO predictive score. Cox regression method was used to determine if the risk score was predictive of mortality within the first year after discharge. The discriminatory ability for the ReDO score to predict mortality was determined using the receiver operating characteristic (ROC) curve. Results 369 patients were included, with a mean age of 71.1 ± 14.3 years. The majority were male (59.9%, n = 221) and 87% were Caucasian (n = 321). The median Charlson score was 7 ± 3. The mortality rate within one year after discharge was 22.2% (n = 82). The one-year survival was significantly lower in patients with the highest probability of death (D4 = 61.3% vs. D3 = 67.6% vs. D2 = 81.3% vs. D4 = 97.3%, p &amp;lt; 0.001). The ReDO Death score accurately predicted the one-year risk of mortality, with an area under the ROC curve of 0.741, [95% CI (0.687–0.794), p &amp;lt; 0.001] (Fig. 1). The optimal REDO Death risk cut-off was &amp;gt;30%, with a hazard ratio of 6.57 [95% CI (3.48–12.2), p &amp;lt; 0.001] for one year risk of death, with a sensitivity of 78.0% and specificity of 60.6%. Conclusion We validated the ReDO score for 1-year mortality prediction after starting hemodialysis during hospitalization in a Portuguese population. This score can be used as a tool to inform goals of care discussion at the time of transition to out-of-hospital care, involving the in-hospital nephrology care team, the patient, and, if applicable, the future care team, as it can enlighten clinical decisions and, in some cases, lead to better end-of-life planning.

Machine learning prediction of one-year mortality after percutaneous coronary intervention in acute coronary syndrome patients

BackgroundMachine learning (ML) models have the potential to accurately predict outcomes and offer novel insights into inter-variable correlations. In this study, we aimed to design ML models for the prediction of 1-year mortality after percutaneous coronary intervention (PCI) in patients with acute coronary syndrome. MethodsThis study was performed on 13,682 patients at Tehran Heart Center from 2015 to 2021. Patients were split into 70:30 for testing and training. Four ML models were designed: a traditional Logistic Regression (LR) model, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Ada Boost models. The importance of features was calculated using the RF feature selector and SHAP based on the XGBoost model. The Area Under the Receiver Operating Characteristic Curve (AUC-ROC) for the prediction on the testing dataset was the main measure of the model's performance. ResultsFrom a total of 9,073 patients with >1-year follow-up, 340 participants died. Higher age and higher rates of comorbidities were observed in these patients. Body mass index and lipid profile demonstrated a U-shaped correlation with the outcome. Among the models, RF had the best discrimination (AUC 0.866), while the highest sensitivity (80.9%) and specificity (88.3%) were for LR and XGBoost models, respectively. All models had AUCs of >0.8. ConclusionML models can predict 1-year mortality after PCI with high performance. A classic LR statistical approach showed comparable results with other ML models. The individual-level assessment of inter-variable correlations provided new insights into the non-linear contribution of risk factors to post-PCI mortality.

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction.

Background and Objectives: Patients presenting with ST Elevation Myocardial Infarction (STEMI) due to occlusive coronary arteries remain at a higher risk of excess morbidity and mortality despite being treated with primary percutaneous coronary intervention (PPCI). Identifying high-risk patients is prudent so that close monitoring and timely interventions can improve outcomes. Materials and Methods: A cohort of 605 STEMI patients [64.2 ± 13.2 years, 432 (71.41%) males] treated with PPCI were recruited. Their arterial pressure (AP) wave recorded throughout the PPCI procedure was analyzed to extract features to predict 1-year mortality. After denoising and extracting features, we developed two distinct feature selection strategies. The first strategy uses linear discriminant analysis (LDA), and the second employs principal component analysis (PCA), with each method selecting the top five features. Then, three machine learning algorithms were employed: LDA, K-nearest neighbor (KNN), and support vector machine (SVM). Results: The performance of these algorithms, measured by the area under the curve (AUC), ranged from 0.73 to 0.77, with accuracy, specificity, and sensitivity ranging between 68% and 73%. Moreover, we extended the analysis by incorporating demographics, risk factors, and catheterization information. This significantly improved the overall accuracy and specificity to more than 76% while maintaining the same level of sensitivity. This resulted in an AUC greater than 0.80 for most models. Conclusions: Machine learning algorithms analyzing hemodynamic traces in STEMI patients identify high-risk patients at risk of mortality.

Prediction of 30-day, 90-day, and 1-year mortality after colorectal cancer surgery using a data-driven approach

PurposeTo develop prediction models for short-term mortality risk assessment following colorectal cancer surgery.MethodsData was harmonized from four Danish observational health databases into the Observational Medical Outcomes Partnership Common Data Model. With a data-driven approach using the Least Absolute Shrinkage and Selection Operator logistic regression on preoperative data, we developed 30-day, 90-day, and 1-year mortality prediction models. We assessed discriminative performance using the area under the receiver operating characteristic and precision-recall curve and calibration using calibration slope, intercept, and calibration-in-the-large. We additionally assessed model performance in subgroups of curative, palliative, elective, and emergency surgery.ResultsA total of 57,521 patients were included in the study population, 51.1% male and with a median age of 72 years. The model showed good discrimination with an area under the receiver operating characteristic curve of 0.88, 0.878, and 0.861 for 30-day, 90-day, and 1-year mortality, respectively, and a calibration-in-the-large of 1.01, 0.99, and 0.99. The overall incidence of mortality were 4.48% for 30-day mortality, 6.64% for 90-day mortality, and 12.8% for 1-year mortality, respectively. Subgroup analysis showed no improvement of discrimination or calibration when separating the cohort into cohorts of elective surgery, emergency surgery, curative surgery, and palliative surgery.ConclusionWe were able to train prediction models for the risk of short-term mortality on a data set of four combined national health databases with good discrimination and calibration. We found that one cohort including all operated patients resulted in better performing models than cohorts based on several subgroups.

Surgical site infection after trochanteric and subtrochanteric fractures: a single centre retrospective analysis

Surgical site infection (SSI) following osteosynthesis of trochanteric or subtrochanteric fractures is a rare but serious complication with incidence rate ranging from 1 to 3%. SSIs are associated with higher mortality and increased length of hospital stay resulting in higher healthcare costs and loss of life quality. In this retrospective analysis all patients with SSI following osteosynthesis of trochanteric or subtrochanteric fractures at the Department of Trauma Surgery were identified. We included all surgical procedures performed from 1992 to 2018, using data from electronic health records and SSI-Trauma-Registry. The aim was to describe epidemiological data, as well as to identify parameters correlating with the occurrence of SSI and mortality. Of 2753 patients, 53 (1.9%) developed SSI. Longer operative time was demonstrated among patients with SSI (P = 0.008). Mortality during the first postoperative year was significantly higher in the SSI group (32.1% vs. 19.1%; P = 0.018), with detection of methicillin-sensitive (MSSA) and methicillin-resistant Staphylococcus aureus (MRSA; HR 4.13, CI 95% 1.24–13.80; P = 0.021) or Enterococcus spp. (HR 5.58, CI 95% 1.67–18.65; P = 0.005) being independent risk factors. Male sex (HR 2.25, 95% CI 1.86–2.73; P < 0.001) and higher mean age (HR 1.05, 95% CI 1.04–1.06; P < 0.001) were found to be predictors for 1-year mortality in non-infected patients. SSI rate was low with 1.9% and longer duration of surgery was associated with infection. Patients with SSI had a higher 1-year mortality, with detection of MSSA, MRSA and enterococci significantly increasing the risk of dying. Male sex and higher age were risk factors for one-year mortality in patients without SSI.

Quantitative chest computed tomography predicts mortality in systemic sclerosis: A longitudinal study.

Quantitative chest computed tomography (qCT) methods are new tools that objectively measure parenchymal abnormalities and vascular features on CT images in patients with interstitial lung disease (ILD). We aimed to investigate whether the qCT measures are predictors of 5-year mortality in patients with systemic sclerosis (SSc). Patients diagnosed with SSc were retrospectively selected from 2011 to 2022. Patients should have had volumetric high-resolution CTs (HRCTs) and pulmonary function tests (PFTs) performed at baseline and at 24 months of follow-up. The following parameters were evaluated in HRCTs using Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER): ground glass opacities, reticular pattern, honeycombing, and pulmonary vascular volume. Factors associated with death were evaluated by Kaplan‒Meier survival curves and multivariate analysis models. Semiquantitative analysis of the HRCTs images was also performed. Seventy-one patients were included (mean age, 54.2 years). Eleven patients (15.49%) died during the follow-up, and all patients had ILD. As shown by Kaplan‒Meier curves, survival was worse among patients with an ILD extent (ground glass opacities + reticular pattern + honeycombing) ≥ 6.32%, a reticular pattern ≥ 1.41% and a forced vital capacity (FVC) < 70% at baseline. The independent predictors of mortality by multivariate analysis were a higher reticular pattern (Exp 2.70, 95%CI 1.26-5.82) on qCT at baseline, younger age (Exp 0.906, 95%CI 0.826-0.995), and absolute FVC decline ≥ 5% at follow-up (Exp 15.01, 95%CI 1.90-118.5), but not baseline FVC. Patients with extensive disease (>20% extension) by semiquantitative analysis according to Goh's staging system had higher disease extension on qCT at baseline and follow-up. This study showed that the reticular pattern assessed by baseline qCT may be a useful tool in the clinical practice for assessing lung damage and predicting mortality in SSc.

Improving 1-Year Mortality Prediction After Pediatric Heart Transplantation Using Hypothetical Donor-Recipient Matches

Improving 1-Year Mortality Prediction After Pediatric Heart Transplantation Using Hypothetical Donor-Recipient Matches

Prehospital Targeting of 1-Year Mortality in Acute Chest Pain by Cardiac Biomarkers.

The identification and appropriate management of patients at risk of suffering from acute chest pain (ACP) in prehospital care are not straightforward. This task could benefit, as occurs in emergency departments (EDs), from cardiac enzyme assessment. The aim of the present work was to derive and validate a scoring system based on troponin T (cTnT), N-terminal pro B-type natriuretic peptide (NT-proBNP), and D-dimer to predict 1-year mortality in patients with ACP. This was a prospective, multicenter, ambulance-based cohort study of adult patients with a prehospital ACP diagnosis who were evacuated by ambulance to the ED between October 2019 and July 2021. The primary outcome was 365-day cumulative mortality. A total of 496 patients fulfilled the inclusion criteria. The mortality rate was 12.1% (60 patients). The scores derived from cTnT, NT-proBNP, and D-dimer presented an AUC of 0.802 (95% CI: 0718-0.886) for 365-day mortality. This AUC was superior to that of each individual cardiac enzyme. Our study provides promising evidence for the predictive value of a risk score based on cTnT, NT-proBNP, and D-dimer for the prediction of 1-year mortality in patients with ACP. The implementation of this score has the potential to benefit emergency medical service care and facilitate the on-scene decision-making process.

Predictors of 1-year mortality after gastrectomy for gastric cancer.

One-year mortality is important for referrals to specialist palliative care or advance care planning (ACP). This helps optimize comfort for those who cannot be cured or have a lower life expectancy. Few studies have investigated the risk factors for 1-year mortality after gastrectomy for gastric cancer (GC). A total of 1415 patients with gastric cancer (stages I-IV) who underwent gastrectomy between 2005 and 2020 were included. The patients were randomly assigned to the investigation group (n=850) and validation group (n=565) in a 3:2 ratio. In the investigation group, significant independent prognostic factors for predicting 1-year survival were identified. A scoring system for predicting 1-year mortality was developed which was validated in the validation group. Multivariate analysis revealed that the following seven variables were significant independent factors for 1-year survival: age ≧78, preoperative comorbidity, total gastrectomy, postoperative complication (Clavien-Dindo classification CD≧3a), stage III and IV, and R2 resection. While developing a 1-year mortality score (OMS), an age ≧78 was scored 2, preoperative comorbidity, total gastrectomy, and postoperative complication (CD≧3a) were scored 1, and stage III, IV, and R2-resection were scored 2, 3, and 3, respectively. OMS 3 had a sensitivity of 91% and a specificity of 66% for predicting death within 1year. In the validation group, OMS 5 had a sensitivity of 55% and a specificity of 93% for predicting death within 1year. OMS may provide important information and help surgeons select the timing of ACP in patients with GC.

Acute muscle wasting rate assessment and long-term mortality in critically ill trauma.

To evaluate the relationship between acute muscle wasting rate and long-term mortality in critically ill trauma. A single-center, retrospective study was conducted in critically ill trauma. Patients with Computed Tomography scans including the L3 vertebra within 24 hours and at 1 week after trauma were recruited. Acute muscle wasting rate was defined as the mean percent variation per day of skeletal muscle index in the first week after trauma. Multivariate logistic regression analysis and receiver operating characteristic curve analysis were performed to determine whether acute muscle wasting rate could help predict hospital malnutrition and 1-year mortality. Skeletal muscle index was 49.3±10.7 cm2/m2 at baseline and decreased to 45.1±9.6 cm2/m2 (p<0.001) at 1 week and 39.8±10.8cm2/m2 (p<0.001) at 1 month after trauma. A sustained decrease of skeletal muscle index was observed from baseline up to 6 months (33.7±8.4cm2/m2, p<0.001) post trauma, and lasted for 1 year (37.7±5.6cm2/m2, p=0.004). Logistic regression analysis showed that acute muscle wasting rate was an independent risk factor for hospital malnutrition and 1-year mortality. Every 1% absolute increase of acute muscle wasting rate was associated with 1.82-fold higher odds of 1-year mortality in critically ill trauma. The area under curve of acute muscle wasting rate was 0.813 for hospital malnutrition prediction and 0.715 for 1-year mortality prediction. Acute muscle wasting rate was independently associated with higher 1-year mortality and hospital malnutrition in critically ill trauma.

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.