Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit

被引:9
作者
Yamga, Eric [1 ]
Mantena, Sreekar [2 ]
Rosen, Darin [3 ]
Bucholz, Emily M. [4 ,5 ]
Yeh, Robert W. [2 ,6 ]
Celi, Leo A. [2 ,7 ,8 ]
Ustun, Berk [9 ]
Butala, Neel M. [4 ,10 ]
机构
[1] Ctr Hosp Univ Montreal CHUM, Dept Med, Montreal, PQ, Canada
[2] Harvard Med Sch, Boston, MA USA
[3] Johns Hopkins Sch Med, Baltimore, MD USA
[4] Univ Colorado, Sch Med, Aurora, CO USA
[5] Childrens Hosp Colorado, Heart Inst, Aurora, CO USA
[6] Beth Israel Deaconess Med Ctr, Div Cardiol, Richard A & Susan F Smith Ctr Outcomes Res Cardio, Boston, MA USA
[7] MIT Inst Med Engn & Sci, Lab Computat Physiol, Cambridge, MA USA
[8] Harvard TH Chan Sch Publ Hlth, Dept Biostat, Boston, MA USA
[9] Univ Calif San Diego, Haliciiogglu Data Sci Inst, San Diego, CA USA
[10] Rocky Mt Reg VA Med Ctr, Aurora, CO USA
来源
JOURNAL OF THE AMERICAN HEART ASSOCIATION | 2023年 / 12卷 / 13期
基金
美国国家科学基金会;
关键词
cardiogenic shock; CICU; machine learning; mortality; risk score; SCAI shock; ACUTE MYOCARDIAL-INFARCTION; PERCUTANEOUS CORONARY INTERVENTION; IN-HOSPITAL MORTALITY; SCIENTIFIC STATEMENT; 30-DAY MORTALITY; SUPPORT; STRATIFICATION; CALIBRATION; REGISTRY;
D O I
10.1161/JAHA.122.029232
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
BackgroundMortality prediction in critically ill patients with cardiogenic shock can guide triage and selection of potentially high-risk treatment options. Methods and ResultsWe developed and externally validated a checklist risk score to predict in-hospital mortality among adults admitted to the cardiac intensive care unit with Society for Cardiovascular Angiography & Interventions Shock Stage C or greater cardiogenic shock using 2 real-world data sets and Risk-Calibrated Super-sparse Linear Integer Modeling (RiskSLIM). We compared this model to those developed using conventional penalized logistic regression and published cardiogenic shock and intensive care unit mortality prediction models. There were 8815 patients in our training cohort (in-hospital mortality 13.4%) and 2237 patients in our validation cohort (in-hospital mortality 22.8%), and there were 39 candidate predictor variables. The final risk score (termed BOS,MA(2)) included maximum blood urea nitrogen & GE;25 mg/dL, minimum oxygen saturation <88%, minimum systolic blood pressure <80 mm Hg, use of mechanical ventilation, age & GE;60 years, and maximum anion gap & GE;14 mmol/L, based on values recorded during the first 24 hours of intensive care unit stay. Predicted in-hospital mortality ranged from 0.5% for a score of 0 to 70.2% for a score of 6. The area under the receiver operating curve was 0.83 (0.82-0.84) in training and 0.76 (0.73-0.78) in validation, and the expected calibration error was 0.9% in training and 2.6% in validation. ConclusionsDeveloped using a novel machine learning method and the largest cardiogenic shock cohorts among published models, BOS,MA(2) is a simple, clinically interpretable risk score that has improved performance compared with existing cardiogenic-shock risk scores and better calibration than general intensive care unit risk scores.
引用
收藏
页数:24
相关论文
共 43 条
[1]  
Alpaydin E., 2020, INTRO MACHINE LEARNI
[2]   Using the Standardized Difference to Compare the Prevalence of a Binary Variable Between Two Groups in Observational Research [J].
Austin, Peter C. .
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2009, 38 (06) :1228-1234
[3]   SCAI clinical expert consensus statement on the classification of cardiogenic shock This document was endorsed by the American College of Cardiology (ACC), the American Heart Association (AHA), the Society of Critical Care Medicine (SCCM), and the Society of Thoracic Surgeons (STS) in April 2019 [J].
Baran, David A. ;
Grines, Cindy L. ;
Bailey, Steven ;
Burkhoff, Daniel ;
Hall, Shelley A. ;
Henry, Timothy D. ;
Hollenberg, Steven M. ;
Kapur, Navin K. ;
O'Neill, William ;
Ornato, Joseph P. ;
Stelling, Kelly ;
Thiele, Holger ;
van Diepen, Sean ;
Naidu, Srihari S. .
CATHETERIZATION AND CARDIOVASCULAR INTERVENTIONS, 2019, 94 (01) :29-37
[4]   Epidemiology of Shock in Contemporary Cardiac Intensive Care Units Data From the Critical Care Cardiology Trials Network Registry [J].
Berg, David D. ;
Bohula, Erin A. ;
van Diepen, Sean ;
Katz, Jason N. ;
Alviar, Carlos L. ;
Baird-Zars, Vivian M. ;
Barnett, Christopher F. ;
Barsness, Gregory W. ;
Burke, James A. ;
Cremer, Paul C. ;
Cruz, Jennifer ;
Daniels, Lori B. ;
DeFilippis, Andrew P. ;
Haleem, Affan ;
Hollenberg, Steven M. ;
Horowitz, James M. ;
Keller, Norma ;
Kontos, Michael C. ;
Lawler, Patrick R. ;
Menon, Venu ;
Metkus, Thomas S. ;
Ng, Jason ;
Orgel, Ryan ;
Overgaard, Christopher B. ;
Park, Jeong-Gun ;
Phreaner, Nicholas ;
Roswell, Robert O. ;
Schulman, Steven P. ;
Snell, R. Jeffrey ;
Solomon, Michael A. ;
Ternus, Bradley ;
Tymchak, Wayne ;
Vikram, Fnu ;
Morrow, David A. .
CIRCULATION-CARDIOVASCULAR QUALITY AND OUTCOMES, 2019, 12 (03)
[5]   The Critical Importance of Risk Score Calibration Time for Transformative Approach to Risk Score Validation?* [J].
Blaha, Michael J. .
JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2016, 67 (18) :2131-2134
[6]   A simple risk chart for initial risk assessment of 30-day mortality in patients with cardiogenic shock from ST-elevation myocardial infarction [J].
Cheng, Jin M. ;
Helming, Anne Mijn ;
van Vark, Laura C. ;
Kardys, Isabella ;
Den Uil, Corstiaan A. ;
Jewbali, Lucia S. D. ;
van Geuns, Robert-Jan ;
Zijlstra, Felix ;
van Domburg, Ron T. ;
Boersma, Eric ;
Akkerhuis, K. Martijn .
EUROPEAN HEART JOURNAL-ACUTE CARDIOVASCULAR CARE, 2016, 5 (02) :101-107
[7]   Selecting patients with atrial fibrillation for anticoagulation - Stroke risk stratification in patients taking aspirin [J].
Gage, BF ;
van Walraven, C ;
Pearce, L ;
Hart, RG ;
Koudstaal, PJ ;
Petersen, P .
CIRCULATION, 2004, 110 (16) :2287-2292
[8]   Early Risk Stratification of Patients With Cardiogenic Shock Complicating Acute Myocardial Infarction Who Undergo Percutaneous Coronary Intervention [J].
Garcia-Alvarez, Ana ;
Arzamendi, Dabit ;
Loma-Osorio, Pablo ;
Kiamco, Ricardo ;
Masotti, Monica ;
Sionis, Alessandro ;
Betriu, Amadeo ;
Brugada, Josep ;
Bosch, Xavier .
AMERICAN JOURNAL OF CARDIOLOGY, 2009, 103 (08) :1073-1077
[9]   Predictors of hospital mortality in the global registry of acute coronary events [J].
Granger, CB ;
Goldberg, RJ ;
Dabbous, O ;
Pieper, KS ;
Eagle, KA ;
Cannon, CP ;
Van de Werf, F ;
Avezum, A ;
Goodman, SG ;
Flather, MD ;
Fox, KAA .
ARCHIVES OF INTERNAL MEDICINE, 2003, 163 (19) :2345-2353
[10]   Clinical picture and risk prediction of short-term mortality in cardiogenic shock [J].
Harjola, Veli-Pekka ;
Lassus, Johan ;
Sionis, Alessandro ;
Kober, Lars ;
Tarvasmaki, Tuukka ;
Spinar, Jindrich ;
Parissis, John ;
Banaszewski, Marek ;
Silva-Cardoso, Jose ;
Carubelli, Valentina ;
Di Somma, Salvatore ;
Tolppanen, Heli ;
Zeymer, Uwe ;
Thiele, Holger ;
Nieminen, Markku S. ;
Mebazaa, Alexandre .
EUROPEAN JOURNAL OF HEART FAILURE, 2015, 17 (05) :501-509