Mortality Risk Stratification Research Articles

Malperfusion Syndrome in Patients Undergoing Repair for Acute Type A Aortic Dissection: Presentation, Mortality and Utility of the Penn Classification

The current study aims to report the presentation of the malperfusion syndrome in patients with acute Type A aortic dissection admitted to surgery and its impact on mortality. Data were retrieved from the multicenter European Registry of Type A Aortic Dissection (ERTAAD). The Penn classification was utilized to categorize malperfusion syndromes. A machine learning algorithm was applied to assess the multivariate interaction's importance regarding in-hospital mortality. A total of 3,902 consecutive patients underwent repair for Acute Type A Aortic Dissection. Local malperfusion syndrome occurred in 1,584 (40.58%) patients. Multi-organ involvement occurred in 582 patients (36.74%) whereas 1,002 patients (63.26%) had single-organ malperfusion. The prevalence was the highest for cerebral (21.27%) followed by peripheral (13.94%), myocardial (9.7%), renal (9.33%), mesenteric (4.15%), and spinal malperfusion (2.10%). Multi-organ involvement predominantly occurred in organs perfused by the downstream aorta. Malperfusion significantly increased mortality risk (p < 0.001, OR 1.95 ± 0.29). The Boruta machine learning algorithm identified the Penn classification as significantly associated with in-hospital mortality (p< 0.0001, variable importance = 7.91), however, 8 other variables yielded higher prediction importance. According to the Penn classification mortality rates were for Penn A = 12.38%, Penn B = 20.71% Penn C = 28.90%, and Penn BC = 31.84% respectively. Nearly half of the examined cohort presented with signs of malperfusion syndrome predominantly due to local involvement. More than one-third of patients with local malperfusion syndrome had a multivessel involvement. Furthermore, different levels of Penn classification can be used only as a first tool for preliminary stratification of early mortality risk.

Coronary Artery Calcium for Risk Stratification of Heart Failure Mortality: The Coronary Artery Calcium Consortium.

There is increasing interest in predicting heart failure (HF), a major cause of morbidity and mortality with a significant financial burden. The role of coronary artery calcium (CAC), an accessible and inexpensive test, in predicting long-term HF mortality amongst asymptomatic adults remains unknown. We aim to determine if CAC burden is associated with HF-related mortality in the CAC Consortium. The study included 66,636 primary prevention patients from the CAC Consortium. Multivariable competing risks regression was used to assess the association between CAC and HF-related mortality adjusting for demographics and traditional risk factors. The mean age was 54.4 years, 67% male, 89% white, and 55% had CAC >0. 260 HF-related mortality events were observed during a median follow up of 12.5 years, 75.3% occurred among those with a baseline CAC score >100. Compared with CAC = 0, there was a stepwise higher risk (P < 0.005) of HF mortality for CAC 1-100 (subdistribution hazard ratio [SHR]: 2.27; 95% CI: 1.3-3.99), 100-400 (SHR: 3.68; 95% CI 2.1-6.43), and >400 (SHR: 7.05; 95% CI 4.05-12.29). This increasing risk of HF mortality across higher CAC scores persisted across age groups, sex, and in the intermediate and high-risk groups as calculated by the pooled cohort (PCE) and PREVENT equations. Higher CAC is associated with increasing incidence of long-term HF-related mortality in the primary prevention population, particularly intermediate and high-risk patients. Early preventive approaches in patients with high CAC must focus on preventing heart failure and ASCVD with lifestyle changes and medications.

Preoperative nutritional scores to predict mortality after liver transplantation: a retrospective cohort study.

Malnutrition is a well-known risk factor for mortality and morbidity. We investigated whether preoperative malnutrition, diagnosed using an objective nutritional index, was associated with postoperative mortality in patients undergoing liver transplantation (LT). This retrospective cohort observational study assessed the preoperative nutritional status of 440 patients who underwent LT, using the Nutritional Risk Index (NRI), Prognostic Nutritional Index (PNI), and Controlling Nutritional Status (CONUT) score. We evaluated the association between preoperative malnutrition and 3-year postoperative mortality using the Kaplan-Meier curve and log-rank test. In addition, we identified prognostic factors for mortality using Cox proportional hazard analysis. Malnutrition was identified in 72.7% (n = 320), 66.1% (n = 291), and 97.3% (n = 428) of patients as assessed by the NRI, PNI, and CONUT score, respectively. The Kaplan- Meier survival curve demonstrated that mortality increased with the presence and severity of malnutrition risk, as assessed by the NRI and PNI, respectively; however, NRI was the only index identified as an independent risk factor for mortality, along with preoperative renal replacement therapy, platelet count, and C-reactive protein. After adjustment, lower NRI was associated with a higher risk of mortality (hazard ratio 0.97, 95% confidence interval 0.95- 0.99, P = 0.009). The malnutrition group (NRI ≤ 100) had a significantly greater incidence of postoperative acute kidney injury than that of the normal group. Preoperative NRI is an independent risk factor for mortality after LT, and therefore it would be a helpful tool for mortality risk stratification in patients undergoing LT.

Screening for stage B heart failure in Type 2 diabetes: natriuretic peptide screening alone misses echocardiographic abnormalities

Abstract Background Heart failure (HF) often manifests as the first cardiac event in individuals with type 2 diabetes mellitus (T2DM). International guidelines recommend natriuretic peptide (NP) screening for stage B/ pre-HF in asymptomatic individuals with T2DM, with echocardiography reserved for those with elevated NPs ("NP-gated" echo approach). Whether this strategy misses individuals with echocardiographic abnormalities despite normal NPs is not fully understood. Purpose To assess the proportion of individuals with T2DM who will be classified as Stage B HF based on biomarker and echocardiography, using independent and combined screening approaches. Methods We utilised the Performance of NT-proBNP In risk Stratification for Cardiovascular Events and mortality in patients with diabetes [PISCES] study (n=765, mean age 62±9 years, 62% men), which enrolled patients with T2DM with no HF. All patients underwent laboratory-based N-terminal pro-B-type NP (NT-proBNP) testing and a point-of-care artificial intelligence echocardiography (Us2.ai). Abnormal echocardiography was defined as left ventricular ejection fraction &amp;lt;50%, left ventricular mass index ≥115(male) or ≥95g/m2(female), left atrial volume index&amp;gt;34 in sinus rhythm or &amp;gt;40mL/m2 in atrial fibrillation, relative wall thickness (RWT) &amp;gt;0.42, E/e' &amp;gt;9, peak tricuspid regurgitation velocity &amp;gt;2.8m/s, pulmonary arterial systolic pressure &amp;gt;35mmHg. Patients with T2DM were classified into either (1) Stage B(biomarker) with elevated NT-proBNP (≥125pg/mL) and normal echocardiography, or (2) Stage B(echo) with abnormal echocardiography and normal NT-proBNP, or (3) Stage B(biomarker+echo) with elevated NT-proBNP and abnormal echocardiography or (4) no abnormalities. Results Among asymptomatic patients with T2DM, the highest proportion of individuals were in Stage B(echo) (43%), followed by those with no abnormalities (37%), Stage B(biomarker+echo) (15%) and Stage B(biomarker) (5%). Patients with Stage B(echo) (vs. no abnormalities) were older (62.5 vs 59.8 years), had a higher prevalence of hypertension (78.4 vs. 72.4%), higher systolic blood pressure (135 vs. 128 mmHg), higher RWT and higher E/e’ (p&amp;lt;0.001 for all). Individuals in Stage B(biomarker+echo) (versus no abnormalities) were older, had a longer duration of T2DM, higher prevalence of hypertension, atrial fibrillation, prior CVD, highest NT-proBNP levels, lowest eGFR levels, and more echocardiography abnormalities (higher RWT and E/e’). Patients identified as Stage B(biomarker) (versus no abnormalities) had a longer duration of T2DM, higher NT-proBNP levels, higher prevalence of comorbidities and comparable echocardiographic measures. Conclusion Among asymptomatic patients with T2DM, a significant proportion have subclinical cardiac abnormalities despite a lack of diagnostic NP elevation. Instead of NP-gated echocardiography, an integrated approach using both NT-proBNP and AI echocardiography may improve the early detection of Stage B HF.

Integrating VAI-Assisted Quantified CXRs and Multimodal Data to Assess the Risk of Mortality.

To address the unmet need for a widely available examination for mortality prediction, this study developed a foundation visual artificial intelligence (VAI) to enhance mortality risk stratification using chest X-rays (CXRs). The VAI employed deep learning to extract CXR features and a Cox proportional hazard model to generate a hazard score ("CXR-risk"). We retrospectively collected CXRs from patients visited outpatient department and physical examination center. Subsequently, we reviewed mortality and morbidity outcomes from electronic medical records. The dataset consisted of 41,945, 10,492, 31,707, and 4441 patients in the training, validation, internal test, and external test sets, respectively. During the median follow-up of 3.2 (IQR, 1.2-6.1) years of both internal and external test sets, the "CXR-risk" demonstrated C-indexes of 0.859 (95% confidence interval (CI), 0.851-0.867) and 0.870 (95% CI, 0.844-0.896), respectively. Patients with high "CXR-risk," above 85th percentile, had a significantly higher risk of mortality than those with low risk, below 50th percentile. The addition of clinical and laboratory data and radiographic report further improved the predictive accuracy, resulting in C-indexes of 0.888 and 0.900. The VAI can provide accurate predictions of mortality and morbidity outcomes using just a single CXR, and it can complement other risk prediction indicators to assist physicians in assessing patient risk more effectively.

Inflammation scores based on C-reactive protein and albumin predict mortality in hospitalized older patients independent of the admission diagnosis

Systemic inflammation significantly increases the risk of short- and long-term mortality in geriatric hospitalized patients. To predict mortality in older patients with various age-related diseases and infections, including COVID-19, inflammatory biomarkers such as the C-reactive protein (CRP) to albumin ratio (CAR), and related scores and indexes, i.e. Glasgow Prognostic Score (GPS), modified GPS (mGPS), and high sensitivity (hs)-mGPS, have been increasingly utilized. Despite their easy affordability and widespread availability, these biomarkers are predominantly assessed for clinical purposes rather than predictive applications, leading to their underutilization in hospitalized older patients. In this study, we investigated the association of CAR, GPS, mGPS, and hs-mGPS with short-term mortality in 3,206 geriatric hospitalized patients admitted for acute conditions, irrespective of admission diagnosis. We observed that unit increases of CAR, and the highest classes of GPS, mGPS, and hs-mGPS were significantly associated with a two- to threefold increased risk of death, even adjusting the risk for different confounding variables. Interestingly, a hs-mGPS of 2 showed the highest effect size. Furthermore, gender analysis indicated a stronger association between all CRP-albumin based parameters and mortality in men, underscoring the gender-specific relevance of inflammation-based circulating parameters in mortality prediction. In conclusion, scores based on serum CRP and albumin levels offer additional guidance for the stratification of in-hospital mortality risk in older patients by providing additional information on the degree of systemic inflammation.

A-017 Clinical Performance Evaluation of the Atellica IM High-Sensitivity Troponin I Assay to Aid in Risk Stratification for All-Cause Mortality and Major Adverse Cardiac Events

Abstract Background Cardiac troponin I (cTnI) is the only troponin isoform present in the myocardium, where it binds to actin and inhibits actin and myosin interaction. Upon myocardial injury, cTnI is released into circulation and serial measurements can be used to aid in the diagnosis of acute myocardial infarction (AMI). In addition, in patients presenting with signs and symptoms of acute coronary syndrome (ACS), elevated cTnI levels provide useful prognostic information relative to short and long-term risk of all-cause mortality (ACM) and major adverse cardiac events (MACE). The objective of this study was to evaluate the clinical performance of the Atellica® IM TNIH assay to aid in risk stratification for ACM/MACE*. Methods Patients from 29 emergency departments (ED) across the United States presenting with signs and symptoms suggestive of ACS were followed for 30-, 90-, and 365-day progression to ACM/MACE (consisting of myocardial infarction, urgent revascularization, cardiac death, or heart failure hospitalization). At each timepoint, the risk (cumulative incidence) and hazard ratios were calculated for populations with baseline cTnI levels ≤ or &amp;gt; the 99th percentile value. Kaplan-Meier curves were generated to display the absolute risk (cumulative incidence) of ACM/MACE outcomes. Analyses were performed for all enrolled patients (entire population) and separately for the entire population excluding those with an adjudicated AMI at presentation. Analyses were performed separately for both serum and plasma (lithium heparin) sample types. Results For the Entire Population cohort, the binary baseline TNIH result (TNIH &amp;gt; overall 99th percentile or ≤ overall 99th percentile) was significantly associated with 30-, 90-, and 365-day cumulative ACM/MACE (p-value&amp;lt;0.0125) for both plasma and serum samples. For plasma samples, risk difference increased from 6.27% at day 30 to 19.62% at day 365. For serum samples, risk difference increased from 6.24% at day 30 to 18.71% at day 365. Cox proportional hazard regression analysis compared the TNIH 99th percentile groups in their hazard of experiencing an ACM/MACE event in the 30-, 90-, and 365-days post ED presentation. For plasma samples, the hazard of ACM/MACE for subjects with cTnI values above the TNIH 99th percentile was relatively constant at each follow-up interval as more than double the rate of subjects below the 99th percentile; hazard ratios ranged between 2.81 (p-value&amp;lt;0.0001) and 3.49-fold (p-value&amp;lt;0.0001) for the three follow up visits. For serum samples, the hazard ratios were between 2.69 (p-value&amp;lt;0.0001) and 3.28-fold (p-value&amp;lt;0.0001) for the three follow up visits. Similar results were obtained for the Entire Population Excluding Subjects with Adjudicated AMI During Initial Presentation cohort. Conclusions The Atellica IM TNIH assay can be used in the detection of myocardial injury and can aid in risk stratification for 30-, 90-, and 365-day all-cause mortality (ACM) and major adverse cardiac events (MACE) in patients presenting with signs and symptoms suggestive of acute coronary syndrome (ACS). *This prognostic claim is not available in the United States.

Weight-adjusted waist index is positively and linearly associated with all-cause and cardiovascular mortality in metabolic dysfunction-associated steatotic liver disease: findings from NHANES 1999-2018.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most common chronic liver disease. Body mass index (BMI) is the most used obesity index but has important limitations. The weight-adjusted waist index (WWI) is a novel obesity metric and accurately reflects body composition. We explored the association of WWI with all-cause and cardiovascular disease (CVD) mortality in MASLD. Adult participants with MASLD were included from NHANES 1999-2018. WWI was calculated by dividing the waist circumference (WC) by the square root of body weight. MASLD was diagnosed by the presence of hepatic steatosis and at least one cardiometabolic risk factor in the absence of other causes of steatosis. A fatty liver index ≥60 suggested the presence of hepatic steatosis. Mortality data was obtained by prospectively linking to the National Death Index. Multivariate Cox proportional hazards regression analyses were used to explore these associations and multiple adjustment models were constructed including crude, partial, and fully adjusted models. After adjusting for all covariates including BMI, WWI remained positively and linearly associated with all-cause and CVD mortality in MASLD (hazard ratios [HR] 1.247 and 1.218, respectively). Higher WWI was associated with a significantly increased risk of mortality (both p for trend <0.05). There was an "obesity paradox" between BMI and all-cause mortality in MASLD, with significantly lower all-cause mortality in those with overweight/obesity compared to normal BMI (HR 0.625 and 0.596, respectively, p for trend = 0.024), and no association between BMI and CVD mortality. Interaction analyses indicated that these associations were influenced by several demographic variables and disease status. Time-dependent receiver operating characteristic curves indicated that the predictive value of WWI for mortality in MASLD was higher than that of BMI, WC, and waist-to-height ratio across all follow-up durations. WWI was positively and linearly associated with all-cause and CVD mortality in MASLD, whereas BMI did not accurately reflect mortality risk. WWI provided the optimal predictive value for mortality compared to traditional obesity indicators. These findings emphasize the potential use of WWI as a novel obesity indicator for mortality risk assessment, stratification, and prevention in MASLD.

Application of a deep-learning marker for morbidity and mortality prediction derived from retinal photographs: a cohort development and validation study

Biological ageing markers are useful to risk stratify morbidity and mortality more precisely than chronological age. In this study, we aimed to develop a novel deep-learning-based biological ageing marker (referred to as RetiPhenoAge hereafter) using retinal images and PhenoAge, a composite biomarker of phenotypic age. We used retinal photographs from the UK Biobank dataset to train a deep-learning algorithm to predict the composite score of PhenoAge. We used a deep convolutional neural network architecture with multiple layers to develop our deep-learning-based biological ageing marker, as RetiPhenoAge, with the aim of identifying patterns and features in the retina associated with variations of blood biomarkers related to renal, immune, liver functions, inflammation, and energy metabolism, and chronological age. We determined the performance of this biological ageing marker for the prediction of morbidity (cardiovascular disease and cancer events) and mortality (all-cause, cardiovascular disease, and cancer) in three independent cohorts (UK Biobank, the Singapore Epidemiology of Eye Diseases [SEED], and the Age-Related Eye Disease Study [AREDS] from the USA). We also compared the performance of RetiPhenoAge with two other known ageing biomarkers (hand grip strength and adjusted leukocyte telomere length) and one lifestyle factor (physical activity) for risk stratification of mortality and morbidity. We explored the underlying biology of RetiPhenoAge by assessing its associations with different systemic characteristics (eg, diabetes or hypertension) and blood metabolite levels. We also did a genome-wide association study to identify genetic variants associated with RetiPhenoAge, followed by expression quantitative trait loci mapping, a gene-based analysis, and a gene-set analysis. Cox proportional hazards models were used to estimate the hazard ratios (HRs) and corresponding 95% CIs for the associations between RetiPhenoAge and the different morbidity and mortality outcomes. Retinal photographs for 34 061UK Biobank participants were used to train the model, and data for 9429participants from the SEED cohort and for 3986participants from the AREDS cohort were included in the study. RetiPhenoAge was associated with all-cause mortality (HR 1·92 [95% CI 1·42-2·61]), cardiovascular disease mortality (1·97 [1·02-3·82]), cancer mortality (2·07 [1·29-3·33]), and cardiovascular disease events (1·70[1·17-2·47]), independent of PhenoAge and other possible confounders. Similar findings were found in the two independent cohorts (HR 1·67 [1·21-2·31] for cardiovascular disease mortality in SEED and 2·07 [1·10-3·92] in AREDS). RetiPhenoAge had stronger associations with mortality and morbidity than did hand grip strength, telomere length, and physical activity. We identified two genetic variants that were significantly associated with RetiPhenoAge (single nucleotide polymorphisms rs3791224 and rs8001273), and were linked to expression quantitative trait locis in various tissues, including the heart, kidneys, and the brain. Our new deep-learning-derived biological ageing marker is a robust predictor of mortality and morbidity outcomes and could be used as a novel non-invasive method to measure ageing. Singapore National Medical Research Council and Agency for Science, Technology and Research, Singapore.

Association between red blood cell distribution width and 30-day mortality in critically ill septic patients: a propensity score-matched study

BackgroundSepsis is the leading cause of death worldwide, and a number of biomarkers have been developed for early mortality risk stratification. Red blood cell distribution width (RDW) is a routinely available hematological data and has been found to be associated with mortality in a number of diseases; therefore, we aim to address the association between RDW and mortality in critically ill patients with sepsis.MethodsWe analyzed data of critically ill adult patients with sepsis on the TriNetX platform, excluding those with hematologic malignancies, thalassemia, and iron deficiency anemia. Propensity score-matching (PSM) (1:1) was used to mitigate confounding effects, and hazard ratio (HR) with 95% confidence (CI) was calculated to determine the association between RDW and 30-day mortality. We further conducted sensitivity analyses through using distinct cut-points of RDW and severities of sepsis.ResultsA total of 256,387 critically ill septic patients were included in the analysis, and 40.0% of them had RDW equal to or higher than 16%. After PSM, we found that high RDW was associated with an increased 30-day mortality rate (HR: 1.887, 95% CI 1.847–1.928). The associations were consistent using distinct cut-points of RDW, with the strength of association using cut-points of 12%, 14%, 16%, 18% and 20% were 2.098, 2.204, 1.887, 1.809 and 1.932, respectively. Furthermore, we found consistent associations among critically ill septic patients with distinct severities, with the association among those with shock, receiving mechanical ventilation, bacteremia and requirement of hemodialysis being 1.731, 1.735, 2.380 and 1.979, respectively.ConclusionWe found that RDW was associated with 30-day mortality in critically ill septic patients, underscoring the potential as a prognostic marker in sepsis. More studies are needed to explore the underlying mechanisms.

CtDNA-based molecular residual disease and survival in resectable colorectal cancer.

The interim analysis of the CIRCULATE-Japan GALAXY observational study demonstrated the association of circulating tumor DNA (ctDNA)-based molecular residual disease (MRD) detection with recurrence risk and benefit from adjuvant chemotherapy (ACT) in resectable colorectal cancer (CRC). This updated analysis with a 23-month median follow-up, including 2,240 patients with stage II-III colon cancer or stage IV CRC, reinforces the prognostic value of ctDNA positivity during the MRD window with significantly inferior disease-free survival (DFS; hazard ratio (HR): 11.99, P < 0.0001) and overall survival (OS; HR: 9.68, P < 0.0001). In patients who experienced recurrence, ctDNA positivity correlated with shorter OS (HR: 2.71, P < 0.0001). The significantly shorter DFS in MRD-positive patients was consistent across actionable biomarker subsets. Sustained ctDNA clearance in response to ACT was an indicator of favorable DFS and OS compared to transient clearance (24-month DFS: 89.0% versus 3.3%; 24-month OS: 100.0% versus 82.3%). True spontaneous clearance rate with no clinical recurrence was 1.9% (2/105). Overall, our findings provide evidence for the utility of ctDNA monitoring for post-resection recurrence and mortality risk stratification that could be used for guiding adjuvant therapy.

Cardiac ultrasomics for acute myocardial infarction risk stratification and prediction of all-cause mortality: a feasibility study

BackgroundCurrent risk stratification tools for acute myocardial infarction (AMI) have limitations, particularly in predicting mortality. This study utilizes cardiac ultrasound radiomics (i.e., ultrasomics) to risk stratify AMI patients when predicting all-cause mortality.ResultsThe study included 197 patients: (a) retrospective internal cohort (n = 155) of non-ST-elevation myocardial infarction (n = 63) and ST-elevation myocardial infarction (n = 92) patients, and (b) external cohort from the multicenter Door-To-Unload in ST-segment–elevation myocardial infarction [DTU-STEMI] Pilot Trial (n = 42). Echocardiography images of apical 2, 3, and 4-chamber were processed through an automated deep-learning pipeline to extract ultrasomic features. Unsupervised machine learning (topological data analysis) generated AMI clusters followed by a supervised classifier to generate individual predicted probabilities. Validation included assessing the incremental value of predicted probabilities over the Global Registry of Acute Coronary Events (GRACE) risk score 2.0 to predict 1-year all-cause mortality in the internal cohort and infarct size in the external cohort. Three phenogroups were identified: Cluster A (high-risk), Cluster B (intermediate-risk), and Cluster C (low-risk). Cluster A patients had decreased LV ejection fraction (P < 0.01) and global longitudinal strain (P = 0.03) and increased mortality at 1-year (log rank P = 0.05). Ultrasomics features alone (C-Index: 0.74 vs. 0.70, P = 0.04) and combined with global longitudinal strain (C-Index: 0.81 vs. 0.70, P < 0.01) increased prediction of mortality beyond the GRACE 2.0 score. In the DTU-STEMI clinical trial, Cluster A was associated with larger infarct size (> 10% LV mass, P < 0.01), compared to remaining clusters.ConclusionsUltrasomics-based phenogroup clustering, augmented by TDA and supervised machine learning, provides a novel approach for AMI risk stratification.

Comparison of Global Registry of Acute Coronary Events and Rapid Emergency Medicine Scores in In-Hospital Mortality of Patients Admitted to the Emergency Service and Diagnosed with Non-ST-Segment Elevation Myocardial Infarction.

Although there are many scoring systems for acute coronary syndromes, there is no suitable score for early risk stratification during initial medical contact with non-ST-elevation myocardial infarction (NSTEMI) patients. The present study compared the Rapid Emergency Medicine Score (REMS), an easy-to-use scoring system in emergency departments, with the Global Registry of Acute Coronary Events (GRACE) score used for in-hospital mortality risk stratification of NSTEMI patients. The results were: (i) the REMS score outperformed the GRACE score in predicting the in-hospital mortality; (ii) in estimating in-hospital mortality, the sensitivity of the GRACE score was 88%, the specificity was 65%, while the sensitivity of the REMS score was 100% and the specificity was 76%; (iii) the AUC (Area Under Curve) value of the REMS score (AUC 0.89) was superior to the GRACE score (AUC 0.79) in the data obtained from Receiver operating characteristic (ROC) descriptive analysis, but not statistically significant (P > .05). We suggest that the REMS score can be used to predict in-hospital mortality in patients with NSTEMI.

Deep learning to predict long-term mortality from plain chest X-ray in patients referred for suspected coronary artery disease.

The hypothesis that a deep learning (DL) model can produce long-term prognostic information from chest X-ray (CXR) has already been confirmed within cancer screening programs. We summarize our experience with DL prediction of long-term mortality, from plain CXR, in patients referred for angina and coronary angiography. Data of patients referred to an Italian academic hospital were analyzed retrospectively. We designed a deep convolutional neural network (DCNN) that, from CXR, could predict long-term mortality. External validation was performed on patients referred to a Dutch academic hospital. A total of 6,031 were used for model training (71%; n=4,259) and fine-tuning/validation (10%; n=602). Internal validation was performed with the remaining patients (19%; n=1,170). Patients' stratification followed the DL-CXR risk score quartiles division. Median follow-up was 6.1 years [interquartile range (IQR), 3.3-8.7 years]. We observed an increment in estimated mortality with the increase of DL-CXR risk score (low-risk 5%, moderate 17%, high 29%, very high 46%; P<0.001). The DL-CXR risk score predicted median follow-up outcome with an area under the curve (AUC) of 0.793 [95% confidence interval (CI): 0.759-0.827, sensitivity 78%, specificity 68%]. Prediction was better than that achieved using coronary angiography findings (AUC: 0.569, 95% CI: 0.52-0.61, P<0.001) and age (AUC: 0.735, 95% CI: 0.69-0.77, P<0.004). At Cox regression, the DL-CXR risk score predicted follow-up mortality (P<0.005, hazard ratio: 3.30, 95% CI: 2.35-4.64). External validation confirmed the DL-CXR risk score performance (AUC: 0.71, 95% CI: 0.49-0.92; sensitivity 0.838; specificity 0.338). In patients referred for coronary angiogram because of angina, the DL-CXR risk score could be used to stratify mortality risk and predict long-term outcome better than age and coronary artery disease status.

Geriatric Trauma Outcome Score as a Mortality Predictor in Isolated Moderate to Severe Traumatic Brain Injury: A Single-Center Retrospective Study.

Traumatic brain injury (TBI) is a major cause of mortality and disability worldwide, with severe cases significantly increasing the risk of complications and long-term mortality. The Geriatric Trauma Outcome Score (GTOS), based on age, injury severity, and transfusion need, has been validated for predicting mortality in older trauma patients, but its utility in predicting mortality for TBI patients remains unexplored. This retrospective study included 5543 adult trauma patients with isolated moderate to severe TBI, defined by head Abbreviated Injury Scale (AIS) scores of ≥ 3, from 1998 to 2021. GTOS was calculated with the following formula: age + (Injury Severity Score × 2.5) + 22 (if transfused within 24 h). The area under the receiver operating characteristic curve (AUROC) assessed GTOS's ability to predict mortality. The optimal GTOS cutoff value was determined using Youden's index. Mortality rates were compared between high- and low-GTOS groups, separated by the optimal GTOS cutoff value, including a propensity score-matched analysis adjusting for baseline characteristics. Among 5543 patients, mortality was 8.3% (462 deaths). Higher mortality is correlated with male sex, older age, higher GTOS, and comorbidities like hypertension, coronary artery disease, and end-stage renal disease. The optimal GTOS cut-off for mortality prediction was 121.5 (AUC = 0.813). Even when the study population was matched by propensity score, patients with GTOS ≥121.5 had much higher odds of death (odds ratio 2.64, 95% confidence interval 1.93-3.61, p < 0.001) and longer hospital stays (mean 16.7 vs. 12.2 days, p < 0.001) than those with GTOS < 121.5. These findings support the idea that GTOS is a useful tool for risk stratification of in-hospital mortality in isolated moderate to severe TBI patients. However, we encourage further research to refine GTOS for better applicability in TBI patients.

Mortality Risk Stratification Utilizing Artificial Intelligence Electrocardiogram for Hyperkalemia in Cardiac Intensive Care Unit Patients

BackgroundHyperkalemia has been associated with increased mortality in cardiac intensive care unit (CICU) patients. An artificial intelligence (AI) enhanced electrocardiogram (ECG) can predict hyperkalemia, and other AI-ECG algorithms have demonstrated mortality risk-stratification in CICU patients. ObjectivesThe authors hypothesized that the AI-ECG hyperkalemia algorithm could stratify mortality risk beyond laboratory serum potassium measurement alone. MethodsWe included 11,234 unique Mayo Clinic CICU patients admitted from 2007 to 2018 with a 12-lead ECG and blood potassium (K) level obtained at admission with K ≥5 mEq/L defining hyperkalemia. ECGs underwent AI evaluation for the probability of hyperkalemia (probability >0.5 defined as positive). Hospital mortality was analyzed using logistic regression, and survival to 1 year was estimated using Kaplan-Meier and Cox analysis. ResultsIn the final cohort (n = 11,234), the mean age was 69.6 ± 10.5 years, 37.8% were females, and 92.4% were White. Chronic kidney disease was present in 20.2%. The mean laboratory potassium value for the cohort was 4.2 ± 0.3 mEq/L. The AI-ECG predicted hyperkalemia in 33.9% (n = 3,810) of CICU patients and 12.9% (n = 1,451) of patients had laboratory-confirmed hyperkalemia (K ≥5 mEq/L). In-hospital mortality increased in false-positive, false-negative, and true-positive patients, respectively (P < 0.001), and each of these patient groups had successively lower survival out to 1 year. ConclusionsAI-ECG-based prediction of hyperkalemia, even with a normal laboratory potassium value, was associated with higher in-hospital mortality and lower 1-year survival in CICU patients. This study demonstrated that AI-ECG probability of hyperkalemia may enable rapid individualized risk stratification in critically ill patients beyond laboratory value alone.

Age, sex, and multi-morbidity stratified mortality risk estimates for adults with cerebral palsy to inform clinical decision making

BackgroundWhile research has provided key insights into mortality rates and risks for individuals with cerebral palsy (CP), clinically useable mortality risk estimates remain unreported for adults with CP, especially by key patient-level factors. ObjectiveThe objective of this study was to generate clinically useable mortality risk estimates among adults with CP to inform clinical decision making. MethodsThis retrospective cohort study, using a fee-for-service Medicare database, identified adults ≥18-years-old with CP from 01/01/2008-12/31/2010 and followed through 12/31/2019 for death. Mortality risk at 1-, 3-, 5-, and 9-year intervals were selected based on common clinical length of time to reasonably benefit from preventive care. Sex-stratified analyses assessed risk estimates by narrow age group (18-25/26-34/35-44/45-54/55-64/65-74/≥75 years old) and multi-morbidity group (Whitney Comorbidity Index score 0-2/3/4-6/≥7). ResultsOf 24,767 adults with CP, n=12,962 were men (mean [SD] age=48.3 [15.0] years) and n=11,805 were women (age=49.7 [15.8] years). Loss to follow-up was rare. 1-year risk was similar between men and women (3.4% vs. 3.3%), but increased slightly more for men than women through 9-years (30.1% vs. 28.0%). As expected, the mortality risk increased with older age and higher WCI scores. The probability of death (and survival) is presented per age and multi-morbidity group for men and women with CP. ConclusionsMortality risk estimates were reported at clinically relevant intervals by age, sex, and multi-morbidity status. This information can be used to weigh harm-to-benefit ratios of screening and treatment strategies based on mortality expectancy estimates.

Acute kidney injury and cardiogenic shock severity for mortality risk stratification in patients supported with VA ECMO.

To assess the stage of acute kidney injury (AKI), as an index of organ perfusion, combined with shock severity, measured by the Society for Cardiovascular Angiography and Interventions (SCAI) shock stage classification, to stratify the risk of mortality in patients diagnosed with cardiogenic shock (CS) and supported with venoarterial extracorporeal membrane oxygenation (VA ECMO). From January 2018 to December 2020, consecutive adult patients diagnosed with CS and received VA ECMO were retrospectively evaluated. The highest AKI stage within 48h after ECMO initiation was assessed using the Kidney Disease: Improving Global Outcomes criteria. We included 216 patients with a mean age of 58.8years and 31.0% were females. 88.4% of patients received ECMO for postcardiotomy, while 11.6% for medical CS. The total in-hospital mortality was 53.2%. AKI occurred in 182 (84.3%) patients receiving ECMO for CS. AKI stage 0, 1, 2, and 3 were present in 15.7%, 17.6%, 18.1%, and 48.6% of patients with in-hospital mortality of 26.5%, 26.3%, 61.5%, and 68.6%, respectively (P<0.001). The AKI stage (P<0.001), SCAI shock stage before ECMO (P=0.008), and NYHA ≥ Class III on admission (P=0.044) were independent predictors of in-hospital mortality. The area under the receiver operating characteristic curve of 0.754 (95% confidence interval: 0.690 to 0.811) for AKI stage combined with SCAI shock stage was better than those for AKI stage (0.676), SCAI shock stage (0.657), serum lactate level (0.682), SOFA score (0.644), SVAE score (0.582), and VIS score (0.530) prior to ECMO. In this single-center CS population who received VA ECMO for circulatory support, predominantly postcardiotomy cases, AKI occurred in 84.3% of the patients. AKI stage, as an index of organ perfusion combined with shock severity measured by the SCAI shock classification, demonstrates a good correlation with in-hospital mortality.

Braden score predicts 30-day mortality risk in patients with ischaemic stroke in the ICU: A retrospective analysis based on the MIMIC-IV database.

Ischaemic stroke remains a significant global health challenge, associated with high mortality rates. While the Braden Scale is traditionally employed to assess pressure ulcer risk, its potential to predict mortality among the intensive care unit (ICU) patients with ischaemic stroke has not been thoroughly investigated. This study evaluates the predictive value of the Braden Scale for 30-day mortality among patients with ischaemic stroke admitted to ICU. We conducted a retrospective analysis of 4710 adult patients with ischaemic stroke from the Medical Information Mart for Intensive Care (MIMIC)-IV database. The association between the Braden Scale scores and 30-day mortality was assessed using receiver operating characteristic (ROC) curve analysis, Cox regression models and Kaplan-Meier survival estimates. Patients with Braden Scale scores ≤ 15.5 showed significantly higher 30-day mortality rates (p-value < 0.001; hazard ratio (HR): 2.08, 95% confidence interval (CI): 1.71-2.53). The area under the ROC curve (AUC) was 0.71, demonstrating good predictive performance. Multivariate analysis confirmed the Braden Scale as an independent predictor of mortality, after adjusting for age, gender and comorbidities. The Braden Scale effectively identifies high-risk ischaemic stroke patients in ICU settings, endorsing its integration into routine assessments to facilitate early intervention strategies. Integrating the Braden Scale into routine ICU evaluations can enhance mortality risk stratification and improve patient care tailoring.

Prognostic value of CT body composition analysis for 1-year mortality after transcatheter aortic valve replacement.

To investigate the value of body composition indices derived from pre-procedural computed tomography (CT) in predicting 1-year mortality among patients who underwent transcatheter aortic valve replacement (TAVR). We assessed consecutive patients who underwent TAVR between June 2016 and December 2021 at a single academic medical center. Skeletal muscle and subcutaneous fat area at the T4, T12, and L3 levels on pre-procedural CT were measured. The association between body composition and 1-year mortality was evaluated using Cox proportional hazard regression analysis. Finally, 408 patients were included (185 men and 223 women; mean age, 81.7 ± 5.1 years; range, 62-98 years). Post-procedural death occurred in 13.2% of patients. The muscle-height index and fat-height index at the L3 level were more strongly correlated with those at the T12 level (r = 0.765, p < 0.001 and r = 0.932, p < 0.001, respectively) than with those at the T4 level (r = 0.535, p < 0.001 and r = 0.895, p < 0.001, respectively). The cumulative 1-year mortality rate was highest for patients with both sarcopenia and adipopenia (26%), followed by those with adipopenia only(17%), those with sarcopenia only (12%), and those with neither sarcopenia nor adipopenia (8%, p = 0.002). Multivariable analysis revealed that body composition at the T12 level was an independent risk factor for 1-year mortality (hazard ratio: 4.09, 95% confidence interval: 2.01-8.35) in patients with both sarcopenia and adipopenia (p < 0.001). Sarcopenia or adipopenia assessed with CT at the thoracic level may be valuable for stratifying 1-year all-cause mortality in patients who undergo TAVR. Skeletal muscle and subcutaneous fat mass indices at the level of T12, measured on pre-procedural CT, have value for risk stratification of 1-year all-cause mortality in patients who undergo transcatheter aortic valve replacement. Sarcopenia and adipopenia are associated with the prognosis of patients undergoing transcatheter aortic valve replacement. Body composition at the T12 level was an independent risk factor for 1-year all-cause mortality. Sarcopenia or adipopenia assessed at T12 with pre-procedural CT is valuable for risk stratification.