Vida Abedi1, Venkatesh Avula2, Seyed-Mostafa Razavi3, Shreya Bavishi4, Durgesh Chaudhary5, Shima Shahjouei6, Ming Wang7, Christoph J Griessenauer8, Jiang Li9, Ramin Zand10. 1. Department of Molecular and Functional Genomics, Geisinger, Danville, PA, United States; Biocomplexity Institute, Virginia Tech, Blacksburg, VA, United States. Electronic address: vidaabedi@gmail.com. 2. Department of Molecular and Functional Genomics, Geisinger, Danville, PA, United States. Electronic address: vavula1@geisinger.edu. 3. Heart and Rhythm Clinic, San Jose, CA, United States. Electronic address: razavi.mos@gmail.com. 4. AMC MET Medical College, Gujarat University, Ahmedabad, India. Electronic address: bavishi.shreya@gmail.com. 5. Geisinger Neuroscience Institute, Geisinger, Danville, PA, United States. Electronic address: dpchaudhary@geisinger.edu. 6. Geisinger Neuroscience Institute, Geisinger, Danville, PA, United States. Electronic address: sshahjouei@geisinger.edu. 7. Department of Public Health Sciences, Penn State Cancer Institute, PA, United States. Electronic address: mwang@phs.psu.edu. 8. Geisinger Neuroscience Institute, Geisinger, Danville, PA, United States; Research Institute of Neurointervention, Paracelsus Medical University, Salzburg, Austria. Electronic address: christoph.griessenauer@gmail.com. 9. Department of Molecular and Functional Genomics, Geisinger, Danville, PA, United States. Electronic address: jli@geisinger.edu. 10. Geisinger Neuroscience Institute, Geisinger, Danville, PA, United States. Electronic address: ramin.zand@gmail.com.
Abstract
OBJECTIVE: Despite improvements in treatment, stroke remains a leading cause of mortality and long-term disability. In this study, we leveraged administrative data to build predictive models of short- and long-term post-stroke all-cause-mortality. METHODS: The study was conducted and reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guideline. We used patient-level data from electronic health records, three algorithms, and six prediction windows to develop models for post-stroke mortality. RESULTS: We included 7144 patients from which 5347 had survived their ischemic stroke after two years. The proportion of mortality was between 8%(605/7144) within 1-month, to 25%(1797/7144) for the 2-years window. The three most common comorbidities were hypertension, dyslipidemia, and diabetes. The best Area Under the ROC curve(AUROC) was reached with the Random Forest model at 0.82 for the 1-month prediction window. The negative predictive value (NPV) was highest for the shorter prediction windows - 0.91 for the 1-month - and the best positive predictive value (PPV) was reached for the 6-months prediction window at 0.92. Age, hemoglobin levels, and body mass index were the top associated factors. Laboratory variables had higher importance when compared to past medical history and comorbidities. Hypercoagulation state, smoking, and end-stage renal disease were more strongly associated with long-term mortality. CONCLUSION: All the selected algorithms could be trained to predict the short and long-term mortality after stroke. The factors associated with mortality differed depending on the prediction window. Our classifier highlighted the importance of controlling risk factors, as indicated by laboratory measures.
OBJECTIVE: Despite improvements in treatment, stroke remains a leading cause of mortality and long-term disability. In this study, we leveraged administrative data to build predictive models of short- and long-term post-stroke all-cause-mortality. METHODS: The study was conducted and reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guideline. We used patient-level data from electronic health records, three algorithms, and six prediction windows to develop models for post-stroke mortality. RESULTS: We included 7144 patients from which 5347 had survived their ischemic stroke after two years. The proportion of mortality was between 8%(605/7144) within 1-month, to 25%(1797/7144) for the 2-years window. The three most common comorbidities were hypertension, dyslipidemia, and diabetes. The best Area Under the ROC curve(AUROC) was reached with the Random Forest model at 0.82 for the 1-month prediction window. The negative predictive value (NPV) was highest for the shorter prediction windows - 0.91 for the 1-month - and the best positive predictive value (PPV) was reached for the 6-months prediction window at 0.92. Age, hemoglobin levels, and body mass index were the top associated factors. Laboratory variables had higher importance when compared to past medical history and comorbidities. Hypercoagulation state, smoking, and end-stage renal disease were more strongly associated with long-term mortality. CONCLUSION: All the selected algorithms could be trained to predict the short and long-term mortality after stroke. The factors associated with mortality differed depending on the prediction window. Our classifier highlighted the importance of controlling risk factors, as indicated by laboratory measures.
Authors: Dariush Mozaffarian; Emelia J Benjamin; Alan S Go; Donna K Arnett; Michael J Blaha; Mary Cushman; Sandeep R Das; Sarah de Ferranti; Jean-Pierre Després; Heather J Fullerton; Virginia J Howard; Mark D Huffman; Carmen R Isasi; Monik C Jiménez; Suzanne E Judd; Brett M Kissela; Judith H Lichtman; Lynda D Lisabeth; Simin Liu; Rachel H Mackey; David J Magid; Darren K McGuire; Emile R Mohler; Claudia S Moy; Paul Muntner; Michael E Mussolino; Khurram Nasir; Robert W Neumar; Graham Nichol; Latha Palaniappan; Dilip K Pandey; Mathew J Reeves; Carlos J Rodriguez; Wayne Rosamond; Paul D Sorlie; Joel Stein; Amytis Towfighi; Tanya N Turan; Salim S Virani; Daniel Woo; Robert W Yeh; Melanie B Turner Journal: Circulation Date: 2015-12-16 Impact factor: 29.690
Authors: Raphae S Barlas; Katie Honney; Yoon K Loke; Stephen J McCall; Joao H Bettencourt-Silva; Allan B Clark; Kristian M Bowles; Anthony K Metcalf; Mamas A Mamas; John F Potter; Phyo K Myint Journal: J Am Heart Assoc Date: 2016-08-17 Impact factor: 5.501
Authors: Lee Hwangbo; Yoon Jung Kang; Hoon Kwon; Jae Il Lee; Han-Jin Cho; Jun-Kyeung Ko; Sang Min Sung; Tae Hong Lee Journal: Sci Rep Date: 2022-10-17 Impact factor: 4.996