Mortality Risk Calculator Research Articles

Development and Internal-external Validation of a Post-operative Mortality Risk Calculator for Pediatric Surgical Patients in Low- and Middle- Income Countries Using Machine Learning

BackgroundThe purpose of this study was to develop and validate a mortality risk algorithm for pediatric surgery patients treated at KidsOR sites in 14 low- and middle-income countries. MethodsA SuperLearner machine learning algorithm was trained to predict post-operative mortality by hospital discharge using the retrospectively and prospectively collected KidsOR database including patients treated at 20 KidsOR sites from June 2018 to June 2023. Algorithm performance was evaluated by internal-external cross-validated AUC and calibration. FindingsOf 23,905 eligible patients, 21,703 with discharge status recorded were included in the analysis, representing a post-operative mortality rate of 3.1% (671 mortality events). The candidate algorithm with the best cross-validated performance was an extreme gradient boosting model. The cross-validated AUC was 0.945 (95% CI 0.936 to 0.954) and cross-validated calibration slope and intercept were 1.01 (95% CI 0.96 to 1.06) and 0.05 (95% CI -0.10 to 0.21). For Super Learner models trained on all but one site and evaluated in the holdout site for sites with at least 25 mortality events, overall external validation AUC was 0.864 (95% CI 0.846 to 0.882) with calibration slope and intercept of 1.03 (95% CI 0.97 to 1.09) and 1.18 (95% CI 0.98 to 1.39). InterpretationThe KidsOR post-operative mortality risk algorithm had outstanding cross-validated discrimination and strong cross-validated calibration. Across all external validation sites, discrimination of Super Learner models trained on the remaining sites was excellent, though re-calibration may be necessary prior to use at new sites. This model has the potential to inform clinical practice and guide resource allocation at KidsOR sites world-wide. Type of Study and Level of EvidenceObservational Study, Level III.

Predicting Risk of Post-Operative Morbidity and Mortality following Gynaecological Oncology Surgery (PROMEGO): A Global Gynaecological Oncology Surgical Outcomes Collaborative Led Study.

The medical complexity of surgical patients is increasing, and surgical risk calculators are crucial in providing high-value, patient-centered surgical care. However, pre-existing models are not validated to accurately predict risk for major gynecological oncology surgeries, and many are not generalizable to low- and middle-income country settings (LMICs). The international GO SOAR database dataset was used to develop a novel predictive surgical risk calculator for post-operative morbidity and mortality following gynecological surgery. Fifteen candidate features readily available pre-operatively across both high-income countries (HICs) and LMICs were selected. Predictive modeling analyses using machine learning methods and linear regression were performed. The area-under-the-receiver-operating characteristic curve (AUROC) was calculated to assess overall discriminatory performance. Neural networks (AUROC 0.94) significantly outperformed other models (p < 0.001) for evaluating the accuracy of prediction across three groups, i.e., minor morbidity (Clavien-Dindo I-II), major morbidity (Clavien-Dindo III-V), and no morbidity. Logistic-regression modeling outperformed the clinically established SORT model in predicting mortality (AUROC 0.66 versus 0.61, p < 0.001). The GO SOAR surgical risk prediction model is the first that is validated for use in patients undergoing gynecological surgery. Accurate surgical risk predictions are vital within the context of major cytoreduction surgery, where surgery and its associated complications can diminish quality-of-life and affect long-term cancer survival. A model that requires readily available pre-operative data, irrespective of resource setting, is crucial to reducing global surgical disparities.

Predicting Mortality Prior to Interhospital Hospital for "Unseen" General Surgery Patients: Development, Validation and Feasibility Trial of a Mortality Risk Calculator.

Develop and validate a mortality risk calculator that could be utilized at the time of transfer, leveraging routinely collected variables that could be obtained by trained non-clinical transfer personnel. There are no objective tools to predict mortality at the time of inter-hospital transfer for Emergency General Surgery (EGS) patients that are "unseen" by the accepting system. Patients transferred to general or colorectal surgery services from January 2016 through August 2022 were retrospectively identified and randomly divided into training and validation cohorts (3:1 ratio). The primary outcome was admission-related mortality, defined as death during the index admission or within 30 days post-discharge. Multiple predictive models were developed and validated. Among 4,664 transferred patients, 280 (6.0%) experienced mortality. Predictive models were generated utilizing 19 routinely collected variables; the penalized regression model was selected over other models due to excellent performance using only 12 variables. The model performance on the validating set resulted in an area under the receiver operating characteristic curve, sensitivity, specificity, and balanced accuracy of 0.851, 0.90, 0.67, and 0.79, respectively. After bias correction, Brier score was 0.04, indicating a strong association between the assigned risk and the observed frequency of mortality. A risk calculator using twelve variables has excellent predictive ability for mortality at the time of interhospital transfer among "unseen" EGS patients. Quantifying a patient's mortality risk at the time of transfer could improve patient triage, bed and resource allocation, and standardize care.

The Association of Post-Lung Transplant Pulmonary Embolism With the Development of Chronic Lung Allograft Dysfunction.

Pulmonary embolism (PE) is a rare yet serious postoperative complication for lung transplant recipients (LTRs). The association between timing and severity of PE and the development of chronic allograft lung dysfunction (CLAD) has not been described. A single-center, retrospective cohort analysis of first LTRs included bilateral or single lung transplants and excluded multiorgan transplants and retransplants. PEs were confirmed by computed tomography angiography or ventilation/perfusion (VQ) scans. Infarctions were confirmed on computed tomography angiography by a trained physician. The PE severity was defined by the Pulmonary Embolism Severity Index (PESI) score, a 30-d post-PE mortality risk calculator, and stratified by low I and II (0-85), intermediate III and IV (85-125), and high V (>125). PE and PESI were analyzed in the outcomes of overall survival, graft failure, and chronic lung allograft dysfunction (CLAD). We identified 57 of 928 patients (6.14%) who had at least 1 PE in the LTR cohort with a median follow-up of 1623 d. In the subset with PE, the median PESI score was 85 (75.8-96.5). Most of the PESI scores (32/56 available) were in the low-risk category. In the CLAD analysis, there were 49 LTRs who had a PE and 16 LTRs (33%) had infarction. When treating PE as time-dependent and adjusting for covariates, PE was significantly associated with death (hazard ratio [HR] 1.8; 95% confidence interval [CI], 1.3-2.5), as well as increased risk of graft failure, defined as retransplant, CLAD, or death (HR 1.8; 95% CI, 1.3-2.5), and CLAD (HR 1.7; 95% CI, 1.2-2.4). Infarction was not associated with CLAD or death. The PESI risk category was not a significant predictor of death or CLAD. PE is associated with decreased survival and increased hazard of developing CLAD. PESI score was not a reliable predictor of CLAD or death in this lung transplant cohort.

Feasibility of implementing an intervention to reduce burden of adjuvant therapy for older women with low-risk breast cancer.

445 Background: In patients ≥70 with early stage (pT1, c/p N0), hormone-receptor positive/ HER2 negative breast cancer, there is an opportunity to reduce adjuvant treatment burden through short-course radiotherapy (RT) approaches and/or endocrine therapy (ET) monotherapy. However, practices may vary in approach to treatment, necessitating differences in approach to interventions designed to tailor decision-making. Methods: Site needs assessment and semi-structured stakeholder interviews at 6 Minority Underserved NCORP sites was conducted, including 3 radiation oncologists (RO), 2 medical oncologists (MO), 1 research coordinator, and 2 breast surgeons (BS). Participant responses were manually recorded and used to construct structural and workflow maps for the possible patient care pathways across the 6 sites. Baseline information on ET and RT use was collected. A planned multi-level intervention that includes patient questionnaires (including a mortality risk calculator) to inform tailored decision-making, and education on guideline-concordant, lower burden options was introduced and dominant themes for barriers and facilitators of the intervention were abstracted. Results: Patients followed multiple pathways and received care at more than one site. The 6 sites span urban, suburban, and rural areas with variable presence of provider types (RO, MO, BS), research support, and RT technology. At baseline, patient reported data, geriatric assessments, mortality risk calculators, and decision aid tools were not routinely used. About 85% of eligible patients receive both ET and moderately hypofractionated whole breast RT; the only commonly used form of partial breast RT is intra-operative. Themes were physician acceptability of the intervention, multidisciplinary care, and physician willingness to offer lower burden treatment options. Physician acceptability subthemes included high baseline guideline knowledge, interest in mortality risk calculator use, need for support to interpret and incorporate patient questionnaire data, and variable physician research engagement. Multidisciplinary care facilitators were multi-campus tumor boards and strong research support staff; barriers were variable insurance across providers and surgeon-driven care plan expectations. Lower burden care subthemes included support for ET for almost all patients; barriers to RT omission were concern about ET non-adherence and to short-course RT were lack of data and toxicity concerns in patients with larger body habitus/resultant RT dose inhomogeneity. Conclusions: Results demonstrated multiple barriers and facilitators of interventions targeting lower burden treatment options for low-risk early-stage breast cancer and identified physician education about interpretation/use of patient-reported data and mortality risk assessments as key to successful study design.

A Real-Time Automated Machine Learning Algorithm for Predicting Mortality in Trauma Patients: Survey Says it's Ready for Prime-Time.

Though artificial intelligence ("AI") has been increasingly applied to patient care, many of these predictive models are retrospective and not readily available for real-time decision-making. This survey-based study aims to evaluate implementation of a new, validated mortality risk calculator (Parkland Trauma Index of Mortality, "PTIM") embedded in our electronic healthrecord ("EHR") that calculates hourly predictions of mortality with high sensitivity and specificity. This is a prospective, survey-based study performed at a level 1 trauma center. An anonymous survey was sent to surgical providers and regarding PTIM implementation. The PTIM score evaluates 23 variables including Glasgow Coma Score (GCS), vital signs, and laboratory data. Of the 40 completed surveys, 35 reported using PTIM in decision-making. Prior to reviewing PTIM, providers identified perceived top 3 predictors of mortality, including GCS (22/38, 58%), age (18/35, 47%), and maximum heart rate (17/35, 45%). Most providers reported the PTIM assisted their treatment decisions (27/35, 77%) and timing of operative intervention (23/35, 66%). Many providers agreed that PTIM integrated into rounds and patient assessment (22/36, 61%) and that it improved efficiency in assessing patients' potential mortality (21/36, 58%). Artificial intelligence algorithms are mostly retrospective and lag in real-time prediction of mortality. To our knowledge, this is the first real-time, automated algorithm predicting mortality in trauma patients. In this small survey-based study, we found PTIM assists in decision-making, timing of intervention, and improves accuracy in assessing mortality. Next steps include evaluating the short- and long-term impact on patient outcomes.

An artificial intelligence approach for prognosis of COVID-19 course in hospitalized patients

Aim. To create algorithm and risk calculator for predicting the lethal outcome in patients with COVID-19.Materials and methods. Based on machine learning approach mortality risk calculator was developed in Almazov National Medical Research Centre using data of the hospitalised patients with an established diagnosis of COVID-19 (n=4071).Results. This mathematical model, which includes 11 significant features, has been proposed for estimation of fatal outcomes in the Clinical Infectious Hospital named after S.P. Botkin. Some key features were not assessed in most hospitals according to accepted standards of care for COVID-19. So systematic analysis of factors affecting the course of disease in patients (n=2876) were conducted and «urea» and «total protein» were replaced with «sex» and «BMI». Modified algorithm demonstrated high sensitivity and specificity. Conclusion. This calculator is able to predict hospitalisation outcome with high accuracy in patients infected with different strains of SARS-CoV-2. This decision support system may be used for risk stratification and following correct patients routing.

A Point-Based Risk Calculator for Mortality After Hepatectomy.

Preoperative risk stratification for hepatectomy patients can aid clinical decision making. The objective of this retrospective cohort study was to determine postoperative mortality risk factors and develop a score-based risk calculator using a limited number of preoperative predictors to estimate mortality risk in patients undergoing hepatectomy. Data were collected from patients that underwent hepatectomy from the National Surgical Quality Improvement Program dataset from 2014 to 2020. Baseline characteristics were compared between survival and 30-day mortality cohorts using the χ 2 test. Next, the data were split into a training set to build the model and a test set to validate the model. A multivariable logistic regression model modeling 30-day postoperative mortality was trained on the training set using all available features. Next, a risk calculator using preoperative features was developed for 30-day mortality. The results of this model were converted into a score-based risk calculator. A point-based risk calculator was developed that predicted 30-day postoperative mortality in patients who underwent hepatectomy surgery. The final dataset included 38,561 patients who underwent hepatectomy. The data were then split into a training set from 2014 to 2018 (n = 26,397) and test set from 2019 to 2020 (n = 12,164). Nine independent variables associated with postoperative mortality were identified and included age, diabetes, sex, sodium, albumin, bilirubin, serum glutamic-oxaloacetic transaminase (SGOT), international normalized ratio, and American Society of Anesthesiologists classification score. Each of these features were then assigned points for a risk calculator based on their odds ratio. A univariate logistic regression model using total points as independent variables were trained on the training set and then validated on the test set. The area under the receiver operating characteristics curve on the test set was 0.719 (95% confidence interval, 0.681-0.757). Development of risk calculators may potentially allow surgical and anesthesia providers to provide a more transparent plan to support patients planned for hepatectomy.

Evaluation of a 30-day-mortality risk calculator for patients undergoing surgical fixation of fragility hip fractures

IntroductionHip fractures often occur in medically complex patients and can be associated with high perioperative mortality. Mortality risk assessment tools that are specific to hip fracture patients have not been extensively studied. The objective of this study is to evaluate a recently published 30-day mortality risk calculator (Hip Fracture Estimator of Mortality Amsterdam [HEMA]) in a group of patients treated at a university health system. Materials & Methods625 patients treated surgically for hip fractures between 2015 and 2020 at our institution were retrospectively reviewed. Patients younger than age 65, periprosthetic fractures, revision procedures, and fractures treated non-operatively were excluded. Univariate and multivariate analyses were used to determine significant relationships between variables and 30-day mortality after surgery. Additional patient-specific risk factors not included in the original risk calculator were also evaluated. ResultsThe observed 30-day mortality was 5.6%. HEMA score was significantly associated with 30-mortality, though our cohort had significantly lower mortality rates in high-risk patients than expected based on the HEMA tool. In analyzing patient characteristics not included in HEMA score, history of dementia and elevated troponin were significantly associated with 30-day mortality. DiscussionThe HEMA score reliably stratifies risk for 30-day mortality after hip fracture, though overestimates mortality in high-risk patients treated at a tertiary care center with a multidisciplinary team. The HEMA score may be enhanced by considering additional variables, including troponin level and history of dementia. Level of EvidenceIV

Analysis of risk factors for severe COVID-19

Global aging has accompanied the worldwide increase in average life expectancy over the past century. The coronavirus disease (COVID-19) pandemic has increased morbidity among all groups of the population, but it poses a particular threat to people of older age groups. Multiple concomitant pathologies form an unfavorable background for the course of COVID-19. It was found that the level of in-hospital mortality in the care of older age groups was high, including in countries with high-income levels and expenditures on health care. We have identified predictors of the severe course of COVID-19. In our opinion, such predictors should be considered when identifying risk groups and applying anticipatory strategies to them, in particular, timely hospitalization, the administration of antiviral therapy, and treatment of concomitant pathology (chronic kidney disease, hypertension, diabetes mellitus, etc.). The question of testing elderly patients for the presence of SARS-CoV-2 is especially relevant when weakness increases, the state of consciousness worsens, and/or dyspnea appears or worsens. Postponement of hospitalization can negatively affect the results of treatment. Thus, interleukin-6, C-reactive protein, the absolute level of lymphocytes, albumin, and ferritin can be used when evaluating the criteria for hospitalization in this group of patients. Interleukin-6 and C-reactive protein are positively associated with body mass index. The excess of adipose tissue is considered an independent predictor of severe COVID-19 and, unlike age, can be modified. We suggested that a hospital mortality risk calculator based on the personalized lethality risk index on admission should be used in practice. Adequate therapy of concomitant pathology is also important in the prevention of COVID-19 complications. Protection of susceptible groups at high risk of severe COVID-19 has strategic importance in preventing high mortality rates in population regardless of age.

Novel Risk Score Calculator for Perioperative Mortality after EVAR with Incorporation of Anatomical Factors

Hostile proximal aortic neck anatomy has been associated with increased risk of perioperative mortality after endovascular aneurysm repair (EVAR). However, all available mortality risk prediction models after EVAR lack neck anatomic associations. The aim of this study is to develop a preoperative prediction model for perioperative mortality after EVAR incorporating important anatomic factors. Data were obtained from the Vascular Quality Initiative database on all patients who underwent elective EVAR between January 2015 and December 2018. Stepwise multivariable logistic regression analysis was implemented to identify independent predictors and develop a risk calculator for perioperative mortality after EVAR. Internal validation was done using bootstrap of 1000 reps. A total of 25,133 patients were included, of whom 1.1% (N=271) died within 30 days or before discharge. Significant preoperative predictors of perioperative mortality were age (odds ratio [OR], 1.053; 95% CI, 1.050-1.056; P<.001), female sex (OR, 1.46; 95% CI, 1.38-1.54; P<.001), chronic kidney disease (OR, 1.65; 95% CI, 1.57-1.73; P<.001), chronic obstructive pulmonary disease (OR, 1.86; 95% CI, 1.77-1.94; P<.001), congestive heart failure (OR, 2.02; 95% CI, 1.91-2.13, P<.001), aneurysm diameter ≥ 6.5cm (OR, 2.35; 95% CI, 2.24-2.47, P<.001), proximal neck length< 10mm (OR, 1.96; 95% CI, 1.81-2.12; P<.001), proximal neck diameter ≥30mm (OR, 1.41; 95% CI, 1.32-1.5; P<.001), infrarenal neck angulation ≥60° (OR, 1.27; 95% CI, 1.18-1.26; P<.001) and suprarenal neck angulation ≥60° (OR, 1.26; 95% CI, 1.16-1.37; P<.001). Significant protective factors included aspirin use (OR, 0.89; 95% CI, 0.85-0.93; P<.001) and statin intake (OR, 0.77; 95% CI, 0.73-0.81; P<.001), These predictors were incorporated to build an interactive risk calculator of perioperative mortality after EVAR (C-statistic=0.749) CONCLUSION: This study provides a prediction model for mortality following EVAR that incorporates aortic neck features. The risk calculator can be used to weigh risk/benefit ratio when counseling patients preoperatively. Prospective use of this risk calculator may show its benefit in long-term prediction of adverse outcomes.

Implementation of an Automated, Real-Time Machine Learning Algorithm Predicting Mortality in Trauma Patients: Survey Says Ready for Prime Time

INTRODUCTION: Although artificial intelligence has been increasingly applied to patient care, many of these predictive models are retrospective and not readily available for real-time decision making. This survey-based study aims to evaluate implementation of a new, validated mortality risk calculator (MRC) embedded in our electronic medical record that calculates hourly predictions of mortality with high sensitivity and specificity. METHODS: This is a prospective, survey-based study at a Level I trauma center. An anonymous survey was sent to ICU providers about MRC implementation. The MRC score evaluates 23 variables including Glasgow Coma Score, vital signs, and laboratory data. RESULTS: Of the 36 completed surveys, 31 reported using MRC in decision-making. Before reviewing the MRC, providers proposed the top 3 predictors of mortality, including Glasgow Coma Score (22/33, 67%), age (16/33, 48%), and maximum heart rate (17/33, 51%). The actual MRC score also ranked Glasgow Coma Score (20/20, 100%), age (18/20, 90%), and maximum heart rate (14/20, 70%) as the top 3 predictors of mortality. Most providers reported MRC assisted their treatment decisions (26/33, 79%), timing of operative intervention (23/33, 70%), and ability to assess the patient’s stability for nonurgent intervention with a high MRC (greater than 50; 19/22, 86%). CONCLUSION: Artificial intelligence algorithms are mostly retrospective and lag in real-time prediction of mortality. To our knowledge, this is the first real-time, automated algorithm predicting mortality in trauma patients. This MRC assists in decision-making, timing of intervention, and improves accuracy in assessing mortality. Next steps include evaluating the short- and long-term effect on patient outcomes.

Real-time mortality risk calculator following pancreatoduodenectomy: quantifying the impact of perioperative events.

Estimation of mortality risk traditionally has only included preoperative factors. We sought to develop "real-time" mortality risk-calculator for patients who undergo pancreatoduodenectomy (PD) based on preoperative factors, as well as events that occurred during the course of patient's surgery and hospitalization. Patients who underwent PD from 2014 to 2018 were identified in the ACS-NSQIP dataset. Training and validation cohorts were created. Pre-, intra-, and post-operative models to predict 30-day mortality were developed based on perioperative variables selected by stepwise cox regression analyses; model performance was assessed using AUC. Among 17,683 patients who underwent PD, 1.6% died within 30-days. Patient factors and events associated with 30-day mortality were incorporated into a risk calculator (https://ktsahara.shinyapps.io/Real-timePD/). The accuracy of the risk-calculator increased relative to hospital time-course in both the training (AUC, pre-:0.696, intra-:0.724, post-operative:0.871) and validation (AUC, pre-:0.681, intra-:0.702, post-operative:0.850) cohorts. One in 3 patients had a concordant calculated risk of mortality using pre-versus postoperative variables to inform the risk model (kappa=0.474). Risk of mortality fluctuated over the hospital course following PD and preoperative risk assessment was often discordant with risk assessed at other periods. The proposed "real-time" calculator may help better stratify patients with increased risk of 30-day mortality.

Prognosis patients with COVID-19 using deep learning

BackgroundThe coronavirus (COVID-19) is a novel pandemic and recently we do not have enough knowledge about the virus behaviour and key performance indicators (KPIs) to assess the mortality risk forecast. However, using a lot of complex and expensive biomarkers could be impossible for many low budget hospitals. Timely identification of the risk of mortality of COVID-19 patients (RMCPs) is essential to improve hospitals' management systems and resource allocation standards.MethodsFor the mortality risk prediction, this research work proposes a COVID-19 mortality risk calculator based on a deep learning (DL) model and based on a dataset provided by the HM Hospitals Madrid, Spain. A pre-processing strategy for unbalanced classes and feature selection is proposed. To evaluate the proposed methods, an over-sampling Synthetic Minority TEchnique (SMOTE) and data imputation approaches are introduced which is based on the K-nearest neighbour.ResultsA total of 1,503 seriously ill COVID-19 patients having a median age of 70 years old are comprised in the research work, with 927 (61.7%) males and 576 (38.3%) females. A total of 48 features are considered to evaluate the proposed method, and the following results are achieved. It includes the following values i.e., area under the curve (AUC) 0.93, F2 score 0.93, recall 1.00, accuracy, 0.95, precision 0.91, specificity 0.9279 and maximum probability of correct decision (MPCD) 0.93.ConclusionThe results show that the proposed method is significantly best for the mortality risk prediction of patients with COVID-19 infection. The MPCD score shows that the proposed DL outperforms on every dataset when evaluating even with an over-sampling technique. The benefits of the data imputation algorithm for unavailable biomarker data are also evaluated. Based on the results, the proposed scheme could be an appropriate tool for critically ill Covid-19 patients to assess the risk of mortality and prognosis.

Real-Time Mortality Risk Calculator Following Pancreatoduodenectomy: Quantifying the Impact of Perioperative Events

Background: Estimation of mortality risk traditionally has only included preoperative factors. We sought to develop a “real-time” mortality risk-calculator for patients who undergo pancreatoduodenectomy (PD) based on preoperative factors, as well as events that occurred during the course of a patient’s surgery and hospitalization.

EP.FRI.552 Evaluating short term and long term outcome for patients undergoing emergency laparotomy in comparison to NELA mortality risk calculator

Abstract Aim NELA is a project that was introduced in the UK since 2013, aiming to improve quality of care for patients undergoing emergency laparotomy. NELA mortality risk calculator”was launched in 2017, which estimates the risk of death within 30 days of emergency laparotomy. Our aim is to determine the short-term (30-day) and long-term (12 months) outcome in patients undergoing emergency laparotomy surgery and compare this with the estimated scores that were documented in the NELA website. Methods This is retrospective study involving patients who underwent emergency laparotomy surgery in the year of 2019. The primary outcome is to determine short-term (30-day) mortality. Results A total of 135 patients were included. The overall 30-day mortality was 8.8% (12/135). 55.77% (78/135) had NELA mortality score of &amp;lt; 5%. Only 1 out of these (1.28%) died within 30 days. (4/78,5.12%) died in 6 to 12 months period of this group. 9 patients (11.53%) had NELA score &amp;gt; 30%, of which 6 (66.66%) died within 30 days and 1 died within 6 months. 26.96% (48/135) had NELA scores 55 to 30%, 5 of them (10.41%) died within 30 days while 7 (14.58%) died within 6-12 months. Patients with NELA scores more than 5% who survived the operation had higher chance of 30-day complications (25.58%, 11/43), when compared to those with scores less than 5% (11.68%, 9/77). Conclusion NELA mortality score has high accuracy especially if it was &amp;gt;30%. In addition, high NELA scores are associated with increased risk of post operative complications.

Risk calculator predicts 30-day mortality after thoracic endovascular aortic repair for intact descending thoracic aortic aneurysms in the Vascular Quality Initiative

ObjectiveThoracic endovascular aortic repair (TEVAR) for descending thoracic aortic aneurysm (DTAA) is associated with high perioperative survival, although mortality is a possible outcome. However, no risk score has been developed to predict mortality after TEVAR for intact DTAA to aid in risk discussion and preoperative patient selection. Our objective was to use a multi-institutional database to develop a 30-day mortality risk calculator for TEVAR after DTAA repair. MethodsThe Vascular Quality Initiative database was queried for patients treated with TEVAR for intact DTAA between August 2014 and August 2020. Univariable and multivariable analyses aided in developing a 30-day mortality risk score. Internal validation was done with K-fold cross-validation and calibration curve analysis. ResultsOf 2141 patients included in the analysis, 90 (4.2%) died within 30 days after the procedure. Clinically relevant variables identified to be independently associated with 30-day mortality and therefore used to derive the predictive model included age 75 years or greater (odds ratio [OR], 2.27; 95% confidence interval [CI], 1.50-3.44; P < .001), coronary artery disease (OR, 1.60; 95% CI, 1.03-2.47; P = .036), American Society of Anesthesiologists class IV/V (OR, 2.39; 95% CI, 1.39-4.10; P = .002), urgent vs elective procedure (OR, 3.47; 95% CI, 1.90-6.33; P < .001), emergent vs elective procedure (OR, 5.27; 95% CI, 2.36-11.75; P < .001), prior carotid revascularization (OR, 3.24; 95% CI, 1.64-6.39; P = .001), and proximal landing zone <3 (OR, 2.51; 95% CI, 1.65-3.81; P < .001). The model showed an area under the receiver operating characteristic curve of 0.75. Internal validation demonstrated a bias-corrected area under the receiver operating characteristic curve of 0.73 (95% CI, 0.66-0.79) and a calibration slope of 1.00 with a corresponding intercept of 0.00. ConclusionsThis study provides a novel clinically relevant risk prediction model to estimate 30-day mortality risk after TEVAR for DTAA. The TEVAR Mortality Risk Calculator provides useful prognostic information to guide patient selection and facilitate preoperative discussions and shared decision making. An easily accessible online version of the TEVAR Mortality Risk Score is available to facilitate ease of use.

A Risk Calculator Predicting Thirty-day Mortality After Thoracic Endovascular Aortic Repair

Thoracic endovascular aortic repair (TEVAR) for descending thoracic aortic aneurysm (DTAA) is associated with high perioperative survival. However, no risk score has been developed to guide discussions with patients prior to surgery. We developed a 30-day mortality risk calculator for TEVAR after DTAA repair.

Creation of mortality risk calculator using a I-123 mIBG-based machine learning model: differential prediction of arrhythmic death and heart-failure death

Abstract Funding Acknowledgements Type of funding sources: None. Background Although I-123 meta-iodobenzylguanidine (mIBG) has been applied to patients with chronic heart failure (CHF), a diagnostic tool for differential prediction of fatal arrhythmic events (ArE) and heart-failure death (HFD) has been pursued. Purpose The aim of this study was to create a calculator of mortality risk for differentiating mode of cardiac death using a machine learning (ML) method, and to test the accuracy in a new cohort of patients with CHF. Methods A total of 529 patients with CHF was used as the training database for ML. The ArE group consisted of patients with arrhythmic death, sudden cardiac death and appropriate therapy by implantable cardioverter defibrillator. A heart-to-mediastinum ratio (H/M) standardized to the medium-energy collimator condition was calculated with a planar anterior mIBG scintigram. The best classifier models for predicting HFD and ArE were determined by four-fold cross validation. Input variables included age, sex, New York Heart Association (NYHA) functional class, left ventricular ejection fraction, ischemic etiology, mIBG H/M and washout rate, and b-type natriuretic peptide (BNP) or NT Pro BNP, estimated glomerular filtration rate, hemoglobin, and complications such as diabetes and hypertension. After creating the ML-based model, the constructed classifier functions for ArE, HFD, and survival were exported for subsequent use. A new cohort of patients (n = 312, age 67 ± 13 years, 2015 or later) was used to test the ML-based model. Results The training database included 141 events (27%) with ArE (7%) and HFD (20%). Receiver-operating characteristic analysis by four-fold validation showed area under the curve value of 0.90 for HFD and 0.73 for ArE. Among various ML methods, the logistic regression method demonstrated the most stable calculation of the probability of ArE followed by random forest and gradient boosted tree methods. Therefore, the logistic-regression method was used for calculating both HFD and ArE probabilities. In the test cohort, patients with a high HFD probability &amp;gt;8% resulted in 6.3-fold higher HFD than those with low probability (≤ 8%). Patients with high ArE probability &amp;gt;8% showed 2.5-fold higher ArE than those with low probability (≤ 8%). Conclusion The ML-based mortality risk calculator could be used for stratifying patients at high and low risks, which might be useful for estimating appropriate treatment strategy.

Absolute mortality risk assessment of COVID-19 patients: the Khorshid COVID Cohort (KCC) study

BackgroundAlready at hospital admission, clinicians require simple tools to identify hospitalized COVID-19 patients at high risk of mortality. Such tools can significantly improve resource allocation and patient management within hospitals. From the statistical point of view, extended time-to-event models are required to account for competing risks (discharge from hospital) and censoring so that active cases can also contribute to the analysis.MethodsWe used the hospital-based open Khorshid COVID Cohort (KCC) study with 630 COVID-19 patients from Isfahan, Iran. Competing risk methods are used to develop a death risk chart based on the following variables, which can simply be measured at hospital admission: sex, age, hypertension, oxygen saturation, and Charlson Comorbidity Index. The area under the receiver operator curve was used to assess accuracy concerning discrimination between patients discharged alive and dead.ResultsCause-specific hazard regression models show that these baseline variables are associated with both death, and discharge hazards. The risk chart reflects the combined results of the two cause-specific hazard regression models. The proposed risk assessment method had a very good accuracy (AUC = 0.872 [CI 95%: 0.835–0.910]).ConclusionsThis study aims to improve and validate a personalized mortality risk calculator based on hospitalized COVID-19 patients. The risk assessment of patient mortality provides physicians with additional guidance for making tough decisions.