The NIV Outcomes (NIVO) Score: prediction of in-hospital mortality in exacerbations of COPD requiring assisted ventilation

IntroductionAcute exacerbations of COPD (AECOPD) complicated by acute (acidaemic) hypercapnic respiratory failure (AHRF) requiring ventilation are common. When applied appropriately, ventilation substantially reduces mortality. Despite this, there is evidence of poor practice and prognostic pessimism. A clinical prediction tool could improve decision making regarding ventilation, but none is routinely used.MethodsConsecutive patients admitted with AECOPD and AHRF treated with assisted ventilation (principally non-invasive ventilation) were identified in two hospitals serving differing populations. Known and potential prognostic indices were identified a priori. A prediction tool for in-hospital death was derived using multivariable regression analysis. Prospective, external validation was performed in a temporally separate, geographically diverse 10-centre study. The trial methodology adhered to TRIPOD recommendations.ResultsDerivation cohort, n=489, in-hospital mortality 25.4%; validation cohort, n=733, in-hospital mortality 20.1%. Using 6 simple categorised variables; extended Medical Research Council Dyspnoea score (eMRCD)1–4/5a/5b, time from admission to acidaemia >12 h, pH<7.25, presence of atrial fibrillation, Glasgow coma scale ≤14 and chest radiograph consolidation a simple scoring system with strong prediction of in-hospital mortality is achieved. The resultant NIVO score had area under the receiver operated curve of 0.79 and offers good calibration and discrimination across stratified risk groups in its validation cohort.DiscussionThe NIVO score outperformed pre-specified comparator scores. It is validated in a generalisable cohort and works despite the heterogeneity inherent to both this patient group and this intervention. Potential applications include informing discussions with patients and their families, aiding treatment escalation decisions, challenging pessimism, and comparing risk-adjusted outcomes across centres.

Download Full-text

External validation of a risk assessment model for venous thromboembolism in the hospitalised acutely-ill medical patient (VTE-VALOURR)

Thrombosis and Haemostasis ◽

10.1160/th14-03-0239 ◽

2014 ◽

Vol 112 (10) ◽

pp. 692-699 ◽

Cited By ~ 40

Author(s):

Charles Mahan ◽

Yang Liu ◽

A. Graham Turpie ◽

Jennifer Vu ◽

Nancy Heddle ◽

...

Keyword(s):

Risk Assessment ◽

Validation Cohort ◽

External Validation ◽

Medical Patient ◽

Risk Groups ◽

Assessment Model ◽

Medical Patients ◽

Control Cohort ◽

Derivation Cohort ◽

Risk Assessment Models

SummaryVenous thromboembolic (VTE) risk assessment remains an important issue in hospitalised, acutely-ill medical patients, and several VTE risk assessment models (RAM) have been proposed. The purpose of this large retrospective cohort study was to externally validate the IMPROVE RAM using a large database of three acute care hospitals. We studied 41,486 hospitalisations (28,744 unique patients) with 1,240 VTE hospitalisations (1,135 unique patients) in the VTE cohort and 40,246 VTE-free hospitalisations (27,609 unique patients) in the control cohort. After chart review, 139 unique VTE patients were identified and 278 randomly-selected matched patients in the control cohort. Seven independent VTE risk factors as part of the RAM in the derivation cohort were identified. In the validation cohort, the incidence of VTE was 0.20%; 95% confidence interval (CI) 0.18–0.22, 1.04%; 95%CI 0.88–1.25, and 4.15%; 95%CI 2.79–8.12 in the low, moderate, and high VTE risk groups, respectively, which compared to rates of 0.45%, 1.3%, and 4.74% in the three risk categories of the derivation cohort. For the derivation and validation cohorts, the total percentage of patients in low, moderate and high VTE risk occurred in 68.6% vs 63.3%, 24.8% vs 31.1%, and 6.5% vs 5.5%, respectively. Overall, the area under the receiver-operator characteristics curve for the validation cohort was 0.7731. In conclusion, the IMPROVE RAM can accurately identify medical patients at low, moderate, and high VTE risk. This will tailor future thromboprophylactic strategies in this population as well as identify particularly high VTE risk patients in whom multimodal or more intensive prophylaxis may be beneficial.

Download Full-text

Development of a machine learning model for predicting pediatric mortality in the early stages of intensive care unit admission

Scientific Reports ◽

10.1038/s41598-020-80474-z ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Bongjin Lee ◽

Kyunghoon Kim ◽

Hyejin Hwang ◽

You Sun Kim ◽

Eun Hee Chung ◽

...

Keyword(s):

Machine Learning ◽

Intensive Care Unit ◽

Intensive Care ◽

Validation Cohort ◽

External Validation ◽

Learning Model ◽

Derivation Cohort ◽

Icu Admission ◽

Early Stages ◽

Machine Learning Model

AbstractThe aim of this study was to develop a predictive model of pediatric mortality in the early stages of intensive care unit (ICU) admission using machine learning. Patients less than 18 years old who were admitted to ICUs at four tertiary referral hospitals were enrolled. Three hospitals were designated as the derivation cohort for machine learning model development and internal validation, and the other hospital was designated as the validation cohort for external validation. We developed a random forest (RF) model that predicts pediatric mortality within 72 h of ICU admission, evaluated its performance, and compared it with the Pediatric Index of Mortality 3 (PIM 3). The area under the receiver operating characteristic curve (AUROC) of RF model was 0.942 (95% confidence interval [CI] = 0.912–0.972) in the derivation cohort and 0.906 (95% CI = 0.900–0.912) in the validation cohort. In contrast, the AUROC of PIM 3 was 0.892 (95% CI = 0.878–0.906) in the derivation cohort and 0.845 (95% CI = 0.817–0.873) in the validation cohort. The RF model in our study showed improved predictive performance in terms of both internal and external validation and was superior even when compared to PIM 3.

Download Full-text

Risk stratification model for in-hospital death in patients undergoing percutaneous coronary intervention: a nationwide retrospective cohort study in Japan

BMJ Open ◽

10.1136/bmjopen-2018-026683 ◽

2019 ◽

Vol 9 (5) ◽

pp. e026683 ◽

Cited By ~ 7

Author(s):

Taku Inohara ◽

Shun Kohsaka ◽

Kyohei Yamaji ◽

Hideki Ishii ◽

Tetsuya Amano ◽

...

Keyword(s):

Percutaneous Coronary Intervention ◽

Cohort Study ◽

Risk Stratification ◽

Hospital Mortality ◽

Retrospective Cohort ◽

Validation Cohort ◽

Coronary Intervention ◽

Hospital Death ◽

Risk Models ◽

Percutaneous Coronary

ObjectivesTo provide an accurate adjustment for mortality in a benchmark, developing a risk prediction model from its own dataset is mandatory. We aimed to develop and validate a risk model predicting in-hospital mortality in a broad spectrum of Japanese patients after percutaneous coronary intervention (PCI).DesignA retrospective cohort study was conducted.SettingThe Japanese-PCI (J-PCI) registry includes a nationally representative retrospective sample of patients who underwent PCI and covers approximately 88% of all PCIs in Japan.ParticipantsOverall, 669 181 patients who underwent PCI between January 2014 and December 2016 in 1018 institutes.Main outcome measuresIn-hospital death.ResultsThe study population (n=669 181; mean (SD) age, 70.1(11.0) years; women, 24.0%) was divided into two groups: 50% of the sample was used for model derivation (n=334 591), while the remaining 50% was used for model validation (n=334 590). Using the derivation cohort, both ‘full’ and ‘preprocedure’ risk models were developed using logistic regression analysis. Using the validation cohort, the developed risk models were internally validated. The in-hospital mortality rate was 0.7%. The preprocedure model included age, sex, clinical presentation, previous PCI, previous coronary artery bypass grafting, hypertension, dyslipidaemia, smoking, renal dysfunction, dialysis, peripheral vascular disease, previous heart failure and cardiogenic shock. Angiographic information, such as the number of diseased vessel and location of the target lesion, was also included in the full model. Both models performed well in the entire validation cohort (C-indexes: 0.929 and 0.926 for full and preprocedure models, respectively) and among prespecified subgroups with good calibration, although both models underestimated the risk of mortality in high-risk patients with the elective procedure.ConclusionsThese simple models from a nationwide J-PCI registry, which is easily applicable in clinical practice and readily available directly at the patients’ presentation, are valid tools for preprocedural risk stratification of patients undergoing PCI in contemporary Japanese practice.

Download Full-text

Prediction model of bleeding after endoscopic submucosal dissection for early gastric cancer: BEST-J score

Gut ◽

10.1136/gutjnl-2019-319926 ◽

2020 ◽

pp. gutjnl-2019-319926 ◽

Cited By ~ 1

Author(s):

Waku Hatta ◽

Yosuke Tsuji ◽

Toshiyuki Yoshio ◽

Naomi Kakushima ◽

Shu Hoteya ◽

...

Keyword(s):

Gastric Cancer ◽

High Risk ◽

Early Gastric Cancer ◽

Prediction Model ◽

Endoscopic Submucosal Dissection ◽

Clinical Decision Making ◽

Validation Cohort ◽

External Validation ◽

Derivation Cohort ◽

Submucosal Dissection

ObjectiveBleeding after endoscopic submucosal dissection (ESD) for early gastric cancer (EGC) is a frequent adverse event after ESD. We aimed to develop and externally validate a clinically useful prediction model (BEST-J score: Bleeding after ESD Trend from Japan) for bleeding after ESD for EGC.DesignThis retrospective study enrolled patients who underwent ESD for EGC. Patients in the derivation cohort (n=8291) were recruited from 25 institutions, and patients in the external validation cohort (n=2029) were recruited from eight institutions in other areas. In the derivation cohort, weighted points were assigned to predictors of bleeding determined in the multivariate logistic regression analysis and a prediction model was established. External validation of the model was conducted to analyse discrimination and calibration.ResultsA prediction model comprised 10 variables (warfarin, direct oral anticoagulant, chronic kidney disease with haemodialysis, P2Y12 receptor antagonist, aspirin, cilostazol, tumour size >30 mm, lower-third in tumour location, presence of multiple tumours and interruption of each kind of antithrombotic agents). The rates of bleeding after ESD at low-risk (0 to 1 points), intermediate-risk (2 points), high-risk (3 to 4 points) and very high-risk (≥5 points) were 2.8%, 6.1%, 11.4% and 29.7%, respectively. In the external validation cohort, the model showed moderately good discrimination, with a c-statistic of 0.70 (95% CI, 0.64 to 0.76), and good calibration (calibration-in-the-large, 0.05; calibration slope, 1.01).ConclusionsIn this nationwide multicentre study, we derived and externally validated a prediction model for bleeding after ESD. This model may be a good clinical decision-making support tool for ESD in patients with EGC.

Download Full-text

Development of a New Risk Stratification System for Patients with Newly Diagnosed Multiple Myeloma Using R-ISS and 18F-FDG PET/CT

Blood ◽

10.1182/blood-2021-152008 ◽

2021 ◽

Vol 138 (Supplement 1) ◽

pp. 3757-3757

Author(s):

Hee Jeong Cho ◽

Juhyung Kim ◽

Jung Min Lee ◽

Dong Won Baek ◽

Sung-Hoon Jung ◽

...

Keyword(s):

Validation Cohort ◽

External Validation ◽

Stage Iv ◽

Risk Groups ◽

Stage Ii ◽

Stage Iii ◽

Pet Ct ◽

Stratification System ◽

Fdg Pet Ct ◽

Risk Stratification System

Abstract Background A high number of focal lesions (FL) detected using PET/CT at diagnosis were found to be associated with adverse prognosis along with Revised International Staging System (R-ISS). In present study, we combined R-ISS with FL using PET/CT to design a reliable and easily applicable risk stratification system in patients with newly diagnosed MM (NDMM). Methods In training cohort, the data of 380 patients with NDMM who underwent 18F-fluorodeoxyglucose (18F-FDG) PET/CT upon diagnosis from 10 hospitals of the Korean Multiple Myeloma Working Party were retrospectively analyzed. All patients were classified by R-ISS and were treated by frontline therapy with proteasome inhibitors (PI) and/or immunomodulatory drugs (IMiD). The K-adaptive partitioning algorithm was adopted to develop the new risk groups with homogeneous survival. Sixty-seven patients in external validation cohort were additionally collected to confirm reproducibility of the new risk groups. Results In the training cohort, 199 patients (52.4%) showed FL > 3 using PET/CT at diagnosis. R-ISS stages I, II, and III were 78 patients (20.5%), 230 (60.5%), and 72 (18.9%), respectively. The combined R-ISS with PET/CT newly allocated NDMM patients into four groups: R-ISS/PET stage I (n=30; R-ISS I with FL≤3), stage II (n=149; R-ISS I with FL>3 and R-ISS II with FL≤3), stage III (n=166; R-ISS II with FL>3 and R-ISS III with FL≤3), and stage IV (n=35; R-ISS III with FL>3). The new R-ISS/PET showed significantly pronounced survival differences according to stages. Two-year overall survival (OS) rates were 96.6%, 89.5%, 75.0%, and 57.9% (p < 0.001), and 2-year progression-free survival (PFS) rates were 86.9%, 65.1%, 41.9%, and 15.2% (p < 0.001) in stages I, II, III, and IV, respectively. The prognostic role of the R-ISS/PET for survival outcomes was also confirmed in different subgroups classified by transplant eligibility and by types of treatments. In the external validation cohort, the new R-ISS/PET was successfully implemented. Two-year OS rates for were 100%, 89.9%, 82.6%, and 42.0% for R-ISS/PET I, II, III, and IV, respectively (p = 0.001). PFS rates at 2 years for each R-ISS/PET were 100%, 74.5%, 57.9%, and 25.6%, respectively (p = 0.004). In the multivariate Cox analysis for survival outcome, R-ISS/PET was a significant factor and could predict long-term outcomes with regard to OS: stage II vs. I (HR 2.50, p = 0.215), (ii) stage III vs. I (HR 5.11, p = 0.025), and (iii) stage IV vs. I (HR 10.3, p = 0.003) and PFS: (i) stage II vs. I (HR 2.21, p = 0.005), (ii) stage III vs. I (HR 4.57, p < 0.001), and (iii) stage IV vs. I (HR 9.48, p < 0.001). Conclusion The new R-ISS/PET had a remarkable prognostic power for estimating the survival outcomes of patients with NDMM. This system helps discriminate patients with a good prognosis from those with a poor prognosis more precisely. Thus, R-ISS/PET is applicable for identifying heterogeneous manifestation of clinical MM. Figure 1 Figure 1. Disclosures No relevant conflicts of interest to declare.

Download Full-text

Machine learning identifies clinical parameters to predict mortality in patients undergoing transcatheter mitral valve repair

European Heart Journal ◽

10.1093/eurheartj/ehab724.2221 ◽

2021 ◽

Vol 42 (Supplement_1) ◽

Author(s):

E Zweck ◽

M Spieker ◽

P Horn ◽

C Iliadis ◽

C Metze ◽

...

Keyword(s):

Machine Learning ◽

Clinical Trials ◽

Mitral Valve ◽

Risk Stratification ◽

Mitral Valve Repair ◽

Validation Cohort ◽

External Validation ◽

Valve Repair ◽

Derivation Cohort ◽

Transcatheter Mitral Valve Repair

Abstract Background Transcatheter Mitral Valve Repair (TMVR) with MitraClip is an important treatment option for patients with severe mitral regurgitation. The lack of appropriate, validated and specific means to risk stratify TMVR patients complicates the evaluation of prognostic benefits of TMVR in clinical trials and practice. Purpose We aimed to develop an optimized risk stratification model for TMVR patients using machine learning (ML). Methods We included a total of 1009 TMVR patients from three large university hospitals, of which one (n=317) served as an external validation cohort. The primary endpoint was all-cause 1-year mortality, which was known in 95% of patients. Model performance was assessed using receiver operating characteristics. In the derivation cohort, different ML algorithms, including random forest, logistic regression, support vectors machines, k nearest neighbors, multilayer perceptron, and extreme gradient boosting (XGBoost) were tested using 5-fold cross-validation in the derivation cohort. The final model (Transcatheter MITral Valve Repair MortALIty PredicTion SYstem; MITRALITY) was tested in the validation cohort with respect to existing clinical scores. Results XGBoost was selected as the final algorithm for the MITRALITY Score, using only six baseline clinical features for prediction (in order of predictive importance): blood urea nitrogen, hemoglobin, N-terminal prohormone of brain natriuretic peptide (NT-proBNP), mean arterial pressure, body mass index, and creatinine. In the external validation cohort, the MITRALITY Score's area under the curve (AUC) was 0.783, outperforming existing scores which yielded AUCs of 0.721 and 0.657 at best. 1-year mortality in the MITRALITY Score quartiles across the total cohort was 0.8%, 1.3%, 10.5%, and 54.6%, respectively. Odds of mortality in MITRALITY Score quartile 4 as compared to quartile 1 were 143.02 [34.75; 588.57]. Survival analyses showed that the differences in outcomes between the MITRALITY Score quartiles remained even over a timeframe of 3 years post intervention (log rank: p<0.005). With each increase by 1% in the MITRALITY score, the respective proportional hazard ratio for 3-year survival was 1.06 [1.05, 1.07] (Cox regression, p<0.05). Conclusion The MITRALITY Score is a novel, internally and externally validated ML-based tool for risk stratification of patients prior to TMVR. These findings may potentially allow for more precise design of future clinical trials, may enable novel treatment strategies tailored to populations of specific risk and thereby serve future daily clinical practice. FUNDunding Acknowledgement Type of funding sources: None. Summary Figure

Download Full-text

Development and external validation of a prognostic tool for COVID-19 critical disease

PLoS ONE ◽

10.1371/journal.pone.0242953 ◽

2020 ◽

Vol 15 (12) ◽

pp. e0242953

Author(s):

Daniel S. Chow ◽

Justin Glavis-Bloom ◽

Jennifer E. Soun ◽

Brent Weinberg ◽

Theresa Berens Loveless ◽

...

Keyword(s):

Critical Care ◽

Prognostic Model ◽

Validation Cohort ◽

External Validation ◽

Vital Signs ◽

Clinical Tool ◽

Derivation Cohort ◽

Laboratory Values ◽

Increased Risk ◽

Care Capacity

Background The rapid spread of coronavirus disease 2019 (COVID-19) revealed significant constraints in critical care capacity. In anticipation of subsequent waves, reliable prediction of disease severity is essential for critical care capacity management and may enable earlier targeted interventions to improve patient outcomes. The purpose of this study is to develop and externally validate a prognostic model/clinical tool for predicting COVID-19 critical disease at presentation to medical care. Methods This is a retrospective study of a prognostic model for the prediction of COVID-19 critical disease where critical disease was defined as ICU admission, ventilation, and/or death. The derivation cohort was used to develop a multivariable logistic regression model. Covariates included patient comorbidities, presenting vital signs, and laboratory values. Model performance was assessed on the validation cohort by concordance statistics. The model was developed with consecutive patients with COVID-19 who presented to University of California Irvine Medical Center in Orange County, California. External validation was performed with a random sample of patients with COVID-19 at Emory Healthcare in Atlanta, Georgia. Results Of a total 3208 patients tested in the derivation cohort, 9% (299/3028) were positive for COVID-19. Clinical data including past medical history and presenting laboratory values were available for 29% (87/299) of patients (median age, 48 years [range, 21–88 years]; 64% [36/55] male). The most common comorbidities included obesity (37%, 31/87), hypertension (37%, 32/87), and diabetes (24%, 24/87). Critical disease was present in 24% (21/87). After backward stepwise selection, the following factors were associated with greatest increased risk of critical disease: number of comorbidities, body mass index, respiratory rate, white blood cell count, % lymphocytes, serum creatinine, lactate dehydrogenase, high sensitivity troponin I, ferritin, procalcitonin, and C-reactive protein. Of a total of 40 patients in the validation cohort (median age, 60 years [range, 27–88 years]; 55% [22/40] male), critical disease was present in 65% (26/40). Model discrimination in the validation cohort was high (concordance statistic: 0.94, 95% confidence interval 0.87–1.01). A web-based tool was developed to enable clinicians to input patient data and view likelihood of critical disease. Conclusions and relevance We present a model which accurately predicted COVID-19 critical disease risk using comorbidities and presenting vital signs and laboratory values, on derivation and validation cohorts from two different institutions. If further validated on additional cohorts of patients, this model/clinical tool may provide useful prognostication of critical care needs.

Download Full-text

DERIVATION AND VALIDATION OF A CLINICAL SCORE TO PREDICT DEATH AMONG NON-PALLIATIVE COVID-19 PATIENTS PRESENTING TO EMERGENCY DEPARTMENTS: THE CCEDRRN COVID MORTALITY SCORE

10.1101/2021.07.28.21261283 ◽

2021 ◽

Author(s):

Corinne M Hohl ◽

Rhonda J Rosychuk ◽

Patrick M Archambault ◽

Fiona O'Sullivan ◽

Murdoch Leeies ◽

...

Keyword(s):

Hospital Mortality ◽

Validation Cohort ◽

Area Under The Curve ◽

Clinical Score ◽

Severe Liver ◽

Derivation Cohort ◽

Response Network ◽

Sex Type ◽

Patient Arrival ◽

Severe Liver Disease

Background: Predicting mortality from coronavirus disease 2019 (COVID-19) using information available when patients present to the Emergency Department (ED) can inform goals-of-care decisions and assist with ethical allocation of critical care resources. Methods: We conducted an observational study to develop and validate a clinical score to predict ED and in-hospital mortality among consecutive non-palliative COVID-19 patients. We recruited from 44 hospitals participating in the Canadian COVID-19 ED Rapid Response Network (CCEDRRN) between March 1, 2020 and January 31, 2021. We randomly assigned hospitals to derivation or validation, and pre-specified clinical variables as candidate predictors. We used logistic regression to develop the score in a derivation cohort, and examined its performance in predicting ED and in-hospital mortality in a validation cohort. Results: Of 8,761 eligible patients, 618 (7·01%) died. The score included age, sex, type of residence, arrival mode, chest pain, severe liver disease, respiratory rate, and level of respiratory support. The area under the curve was 0·92 (95% confidence intervals [CI] 0·91—0·93) in derivation and 0·92 (95%CI 0·89—0·93) in validation. The score had excellent calibration. Above a score of 15, the observed mortality was 81·0% (81/100) with a specificity of 98·8% (95%CI 99·5—99·9%). Interpretation: The CCEDRRN COVID Mortality Score is a simple score that accurately predicts mortality with variables that are available on patient arrival without the need for diagnostic tests.

Download Full-text

Development and validation of risk stratification trees for incident slow gait speed in persons at high risk for knee osteoarthritis

Annals of the Rheumatic Diseases ◽

10.1136/annrheumdis-2019-215353 ◽

2019 ◽

Vol 78 (10) ◽

pp. 1412-1419 ◽

Cited By ~ 1

Author(s):

Leena Sharma ◽

Kent Kwoh ◽

Jungwha (Julia) Lee ◽

Jane Cauley ◽

Rebecca Jackson ◽

...

Keyword(s):

High Risk ◽

Risk Stratification ◽

Knee Osteoarthritis ◽

Gait Speed ◽

Validation Cohort ◽

Risk Group ◽

Risk Groups ◽

Classification And Regression Tree ◽

Predictive Values ◽

Derivation Cohort

ObjectivesDisability prevention strategies are more achievable before osteoarthritis disease drives impairment. It is critical to identify high-risk groups, for strategy implementation and trial eligibility. An established measure, gait speed is associated with disability and mortality. We sought to develop and validate risk stratification trees for incident slow gait in persons at high risk for knee osteoarthritis, feasible in community and clinical settings.MethodsOsteoarthritis Initiative (derivation cohort) and Multicenter Osteoarthritis Study (validation cohort) participants at high risk for knee osteoarthritis were included. Outcome was incident slow gait over up to 10-year follow-up. Derivation cohort classification and regression tree analysis identified predictors from easily assessed variables and developed risk stratification models, then applied to the validation cohort. Logistic regression compared risk group predictive values; area under the receiver operating characteristic curves (AUCs) summarised discrimination ability.Results1870 (derivation) and 1279 (validation) persons were included. The most parsimonious tree identified three risk groups, from stratification based on age and WOMAC Function. A 7-risk-group tree also included education, strenuous sport/recreational activity, obesity and depressive symptoms; outcome occurred in 11%, varying 0%–29 % (derivation) and 2%–23 % (validation) depending on risk group. AUCs were comparable in the two cohorts (7-risk-group tree, 0.75, 95% CI 0.72 to 0.78 (derivation); 0.72, 95% CI 0.68 to 0.76 (validation)).ConclusionsIn persons at high risk for knee osteoarthritis, easily acquired data can be used to identify those at high risk of incident functional impairment. Outcome risk varied greatly depending on tree-based risk group membership. These trees can inform individual awareness of risk for impaired function and define eligibility for prevention trials.

Download Full-text

P3429A novel prediction model for mortality after cardiac surgery using institutional case volume

European Heart Journal ◽

10.1093/eurheartj/ehz745.0303 ◽

2019 ◽

Vol 40 (Supplement_1) ◽

Author(s):

S Lee ◽

J B Park ◽

Y J Cho ◽

H G Ryu ◽

E J Jang

Keyword(s):

Cardiac Surgery ◽

Hospital Mortality ◽

Risk Prediction ◽

Prediction Models ◽

Validation Cohort ◽

Mortality Data ◽

P Value ◽

Case Volume ◽

Risk Prediction Models ◽

Derivation Cohort

Abstract Purpose A number of risk prediction models have been developed to identify short term mortality after cardiovascular surgery. Most models include patient characteristics, laboratory data, and type of surgery, but no consideration for the amount of surgical experience. With numerous reports on the impact of case volume on patient outcome after high risk procedures, we attempted to develop a risk prediction models for in-hospital and 1-year mortality that takes institutional case volume into account. Methods We identified adult patients who underwent cardiac surgery from January 2008 to December 2017 from the National Health Insurance Service (NHIS) database by searching for patients with procedure codes of coronary artery bypass grafting, valve surgery, and surgery on thoracic aorta during the hospitalization. Study subjects were randomly assigned to either the derivation cohort or the validation cohort. In-hospital mortality and 1-year mortality data were collected using the NHIS database. Risk prediction models were developed from the derivation cohort using Cox proportional hazards regression. The prediction performances of models were evaluated in the validation cohort. Results The models developed in this study demonstrated fair discrimination for derivation cohort (N=22,004, c-statistics, 0.75 for in-hospital mortality; 0.73 for 1-year mortality) and acceptable calibration in the validation cohort. (N=22,003, Hosmer-Lemeshow χ2-test, P=0.08 and 0.16, respectively). Case volume was the key factor of mortality prediction models after cardiac surgery. (50≤ x <100 case per year. 100≤ x <200 case per year, ≥200 case per year are correlated with OR 3.29, 2.49, 1.85 in in-hospital mortality, 2.76, 1.99, 1.69 in 1-year mortality respectively, P value <0.001.) Annual case volume as risk factor Variables In-hospital mortality 1-year mortality OR (95% CI) p-value OR (95% CI) p-value Annual case-volume (reference: ≥200) – – 100–200 1.69 (1.48, 1.93) <0.001 1.85 (1.58, 2.18) <0.001 50–100 1.99 (1.75, 2.25) <0.001 2.49 (2.15, 2.89) <0.001 <50 2.76 (2.44, 3.11) <0.001 3.29 (2.85, 3.79) <0.001 OR: Odds ratio; CI: confidence interval; Ref: Reference. Discrimination and calibration Conclusion We developed and validated new risk prediction models for in-hospital and 1-year mortality after cardiac surgery using the NHIS database. These models may provide useful guides to predict mortality risks of patients with basic information and without laboratory findings.

Download Full-text