1
|
Waddell KJ, Myers LJ, Perkins AJ, Sico JJ, Sexson A, Burrone L, Taylor S, Koo B, Daggy JK, Bravata DM. Development and validation of a model predicting mild stroke severity on admission using electronic health record data. J Stroke Cerebrovasc Dis 2023; 32:107255. [PMID: 37473533 DOI: 10.1016/j.jstrokecerebrovasdis.2023.107255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2022] [Revised: 07/10/2023] [Accepted: 07/13/2023] [Indexed: 07/22/2023] Open
Abstract
OBJECTIVE Initial stroke severity is a potent modifier of stroke outcomes but this information is difficult to obtain from electronic health record (EHR) data. This limits the ability to risk-adjust for evaluations of stroke care and outcomes at a population level. The purpose of this analysis was to develop and validate a predictive model of initial stroke severity using EHR data elements. METHODS This observational cohort included individuals admitted to a US Department of Veterans Affairs hospital with an ischemic stroke. We extracted 65 independent predictors from the EHR. The primary analysis modeled mild (NIHSS score 0-3) versus moderate/severe stroke (NIHSS score ≥4) using multiple logistic regression. Model validation included: (1) splitting the cohort into derivation (65%) and validation (35%) samples and (2) evaluating how the predicted stroke severity performed in regard to 30-day mortality risk stratification. RESULTS The sample comprised 15,346 individuals with ischemic stroke (n = 10,000 derivation; n = 5,346 validation). The final model included 15 variables and correctly classified 70.4% derivation sample patients and 69.4% validation sample patients. The areas under the curve (AUC) were 0.76 (derivation) and 0.76 (validation). In the validation sample, the model performed similarly to the observed NIHSS in terms of the association with 30-day mortality (AUC: 0.72 observed NIHSS, 0.70 predicted NIHSS). CONCLUSIONS EHR data can be used to construct a surrogate measure of initial stroke severity. Further research is needed to better differentiate moderate and severe strokes, enhance stroke severity classification, and how to incorporate these measures in evaluations of stroke care and outcomes.
Collapse
Affiliation(s)
- Kimberly J Waddell
- VA Center for Health Equity Research and Promotion (CHERP), Crescenz VA Medical Center; Philadelphia, PA, USA; Department of Physical Medicine and Rehabilitation, Perelman School of Medicine, University of Pennsylvania; Philadelphia, PA, USA; Leonard Davis Institute for Health Economics, University of Pennsylvania; Philadelphia, PA, USA.
| | - Laura J Myers
- VA HSR&D Center for Health Information and Communication (CHIC), Richard L. Roudebush VA Medical Center; Indianapolis, IN, USA; Department of Medicine, Indiana University School of Medicine; Indianapolis, IN, USA; Department of Veterans Affairs (VA) Health Services Research and Development (HSR&D) Expanding Expertise Through E-health Network Development (EXTEND) Quality Enhancement Research Initiative (QUERI), Indianapolis, IN, USA; Regenstrief Institute; Indianapolis, IN, USA
| | - Anthony J Perkins
- VA HSR&D Center for Health Information and Communication (CHIC), Richard L. Roudebush VA Medical Center; Indianapolis, IN, USA; Department of Veterans Affairs (VA) Health Services Research and Development (HSR&D) Expanding Expertise Through E-health Network Development (EXTEND) Quality Enhancement Research Initiative (QUERI), Indianapolis, IN, USA; Department of Biostatistics and Health Data Science, Indiana University School of Medicine & Fairbanks School of Public Health, Indianapolis, IN, USA
| | - Jason J Sico
- Neurology Service, VA Connecticut Healthcare System; West Haven, CT, USA; Departments of Neurology and Internal Medicine, Yale School of Medicine; New Haven, CT, USA; Pain Research, Informatics, and Multi-morbidities, and Education (PRIME) Center, VA Connecticut Healthcare System; West Haven, CT, USA
| | - Ali Sexson
- VA HSR&D Center for Health Information and Communication (CHIC), Richard L. Roudebush VA Medical Center; Indianapolis, IN, USA
| | - Laura Burrone
- Pain Research, Informatics, and Multi-morbidities, and Education (PRIME) Center, VA Connecticut Healthcare System; West Haven, CT, USA
| | - Stanley Taylor
- VA HSR&D Center for Health Information and Communication (CHIC), Richard L. Roudebush VA Medical Center; Indianapolis, IN, USA; Department of Veterans Affairs (VA) Health Services Research and Development (HSR&D) Expanding Expertise Through E-health Network Development (EXTEND) Quality Enhancement Research Initiative (QUERI), Indianapolis, IN, USA
| | - Brian Koo
- Neurology Service, VA Connecticut Healthcare System; West Haven, CT, USA; Departments of Neurology and Internal Medicine, Yale School of Medicine; New Haven, CT, USA; Pain Research, Informatics, and Multi-morbidities, and Education (PRIME) Center, VA Connecticut Healthcare System; West Haven, CT, USA
| | - Joanne K Daggy
- VA HSR&D Center for Health Information and Communication (CHIC), Richard L. Roudebush VA Medical Center; Indianapolis, IN, USA; Department of Veterans Affairs (VA) Health Services Research and Development (HSR&D) Expanding Expertise Through E-health Network Development (EXTEND) Quality Enhancement Research Initiative (QUERI), Indianapolis, IN, USA; Department of Biostatistics and Health Data Science, Indiana University School of Medicine & Fairbanks School of Public Health, Indianapolis, IN, USA
| | - Dawn M Bravata
- VA HSR&D Center for Health Information and Communication (CHIC), Richard L. Roudebush VA Medical Center; Indianapolis, IN, USA; Department of Medicine, Indiana University School of Medicine; Indianapolis, IN, USA; Department of Veterans Affairs (VA) Health Services Research and Development (HSR&D) Expanding Expertise Through E-health Network Development (EXTEND) Quality Enhancement Research Initiative (QUERI), Indianapolis, IN, USA; Department of Neurology, Indiana University School of Medicine; Indianapolis, IN, USA; Regenstrief Institute; Indianapolis, IN, USA
| |
Collapse
|
2
|
Adenova G, Kausova G, Tazhiyeva A. Improving multidisciplinary hospital care for acute cerebral circulation disorders in Kazakhstan. Heliyon 2023; 9:e18435. [PMID: 37593645 PMCID: PMC10427984 DOI: 10.1016/j.heliyon.2023.e18435] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Revised: 07/14/2023] [Accepted: 07/17/2023] [Indexed: 08/19/2023] Open
Abstract
Background According to the World Stroke Organization, there was a significant increase in stroke cases, stroke deaths, and the DALY rate in low- and middle-income countries in 2022. The number of stroke cases rose by 70.0%, stroke deaths reached 86.0%, and the DALY rate reached 89.0%. Among cerebrovascular diseases, ischemic stroke accounts for 62.0% of all strokes, with more than 7.6 million cases reported annually.Kazakhstan, with a population of 19,832,737, is the largest country in Central Asia in terms of territory. In Kazakhstan, the incidence of cerebrovascular disease has risen from 258.4 cases per 100,000 population in 2015 to 433.7 cases per 100,000 population in 2020. Official statistics indicate that the average inpatient mortality rate from stroke in the country is 16.2%, and the average time for patients to be delivered to the hospital after an ambulance call is 40 min (83.2%).Our study findings reveal that in the regions of Kazakhstan, the main contributors to the high morbidity and mortality rates in stroke are a shortage of doctors, inadequate primary healthcare, insufficient follow-up and treatment, and delayed hospitalization. Consequently, this study has helped fill knowledge gaps regarding the epidemiological situation in these regions and underscores the need for training doctors in managing high-risk patients, establishing multidisciplinary home visit teams, and establishing "Stroke Schools" to enhance public awareness of early stroke signs and the fundamentals of a healthy lifestyle. Future research endeavors should consider these study results as valuable contributions towards addressing the existing problems. Aim To study the prevalence and mortality of acute cerebral circulation impairment in the population within multidisciplinary hospitals in the cities of Nur-Sultan and Almaty, Republic of Kazakhstan, for the period of 2018-2020.This retrospective study was conducted in two stages. In the first stage, an analysis of morbidity, prevalence, and mortality was conducted for the population of Nur-Sultan and Almaty cities, as well as for the overall population of Kazakhstan. This analysis was based on data from the "Electronic Register of Discharged Patients" (IS ERDB) and the annual collection "Health of the Population of the Republic of Kazakhstan and the Activities of Health Organizations in 2015-2020". In the second stage, we examined the care provided to patients with acute impaired cerebral circulation in a multidisciplinary hospital in these two cities. The analysis was based on data regarding the sex and age composition of treated patients in hospitals across the Republic of Kazakhstan, categorized according to the ICD-10 code "Acute Impaired Cerebral Circulation" (I60-I64). We investigated the methods of patients' delivery to medical organizations, types of hospitalization, and outcomes of treated patients. The sample of patients was selected using data from the "Electronic Register of Dispensary Patients" of the Ministry of Health of the Republic of Kazakhstan, along with the statistical collection "Health of the Population of the Republic of Kazakhstan and the Activities of Healthcare Organizations". Between January 1, 2018, and December 31, 2020, a total of 5965 patients were diagnosed with a cerebrovascular event and admitted to a general hospital in Nur-Sultan city, while 13,498 patients were diagnosed and admitted in Almaty city.
Collapse
Affiliation(s)
| | - Galina Kausova
- Kazakhstan Medical University “KSPH”, Almaty, Kazakhstan
| | - Aigul Tazhiyeva
- Asfendiyarov Kazakh National Medical University, Almaty, Kazakhstan
| |
Collapse
|