1
|
Kostev K, Wu T, Wang Y, Chaudhuri K, Reeve R, Tanislav C. Predicting the Risk of Ischemic Stroke in Patients Treated with Novel Oral Anticoagulants: A Machine Learning Approach. Neuroepidemiology 2021; 55:387-392. [PMID: 34350851 DOI: 10.1159/000517512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Accepted: 05/29/2021] [Indexed: 11/19/2022] Open
Abstract
INTRODUCTION The aim of this cohort study was to estimate the predictors of ischemic stroke in patients treated with non-vitamin K antagonist oral anticoagulants (NOACs) in a large database containing data from general practitioners in Germany using machine learning methods. METHODS This retrospective cohort study included 39,652 patients with a diagnosis of atrial fibrillation (AF) and an initial prescription of NOAC in 1,278 general practices in Germany between January 2011 and December 2018. Of 39,652 patients, 2,310 (5.8%) receive the first stroke or TIA diagnosis during the follow-up time (average follow-up time 2.5 [SD: 1.8] years). Sub-Population Optimization and Modeling Solutions (SOMS) tool was used to identify subgroups at a higher risk of stroke compared to the overall population receiving NOAC based on 37 different variables. RESULTS Using SOMS, a total of 9 variables were considered important for the stroke prediction. Age had 59.1% of prediction importance, following by ischemic heart diseases (10.6%), urinary tract infections (4.6%), dementia (3.5%), and male sex (3.5%). Further variables with less importance were dizziness (2.2%), dorsalgia (1.5%), shoulder lesions (1.1%), and diabetes mellitus (1.1%). DISCUSSION/CONCLUSIONS The stroke risk in AF patients treated with NOAC could be predicted based on comorbidities like ischemic heart diseases, urinary tract infections, and dementia additionally to age and male sex. Knowing and addressing these factors may help reduce the risk of stroke in this patient population.
Collapse
Affiliation(s)
| | - Tong Wu
- Advanced Analytics, IQVIA, Plymouth Meeting, Pennsylvania, USA
| | - Yue Wang
- Advanced Analytics, IQVIA, Plymouth Meeting, Pennsylvania, USA
| | - Kal Chaudhuri
- Global Consulting, IQVIA, Plymouth Meeting, Pennsylvania, USA
| | - Russel Reeve
- Biostatistics & Decision Sciences, IQVIA, Durham, North Carolina, USA
| | - Christian Tanislav
- Department of Geriatrics and Neurology, Diakonie Hospital Jung Stilling Siegen, Siegen, Germany
| |
Collapse
|
2
|
Jacob L, Kostev K. Urinary and fecal incontinence in stroke survivors followed in general practice: A retrospective cohort study. Ann Phys Rehabil Med 2020; 63:488-494. [PMID: 31981836 DOI: 10.1016/j.rehab.2019.12.007] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2019] [Revised: 12/03/2019] [Accepted: 12/08/2019] [Indexed: 11/24/2022]
Abstract
BACKGROUND Investigating the short- and long-term health outcomes after stroke is a public health priority. OBJECTIVES We aimed to analyse the incidence of urinary and fecal incontinence within 10 years of stroke in individuals followed in general practice in Germany. METHODS Individuals who had received an initial stroke diagnosis at one of 1262 general practices in Germany between January 2006 and December 2015 were included (index date). Individuals without stroke were matched (1:1) to those with stroke based on propensity scores by using a "greedy" algorithm and logistic regression with sex, age, index year, and 17 comorbidities diagnosed in the 12 months before the index date. The main outcome of the study was the incidence of urinary and fecal incontinence within 10 years of stroke. RESULTS This study analysed data for 16,181 individuals with stroke and 16,181 without stroke. Within 10 years of the index date, 22% and 11% of men with and without stroke received a diagnosis of urinary incontinence (log-rank P<0.001); the prevalence of urinary incontinence was 34% in female stroke survivors and 17% in females with no history of stroke (log-rank P<0.001). The respective proportions of fecal incontinence were 5% and 2% for men (log-rank P<0.001) and 6% and 3% for women (log-rank P<0.001). Overall, stroke was positively associated with both urinary incontinence (men: hazard ratio [HR] 2.34, 95% confidence interval [CI] 2.10-2.61; women: HR 2.36, 95% CI 2.14-2.61) and fecal incontinence (men: HR 2.43, 95% CI 1.88-3.13; women: HR 2.60, 95% CI 1.98-3.41). CONCLUSION This study, using data from Germany, suggests that general practitioners should regularly screen for urinary and fecal incontinence in the decade following stroke.
Collapse
Affiliation(s)
- Louis Jacob
- Faculty of Medicine, University of Versailles Saint-Quentin-en-Yvelines, Montigny-le-Bretonneux, France; Research and Development Unit, Parc Sanitari Sant Joan de Déu, CIBERSAM, Dr. Antoni Pujadas, 42, Sant Boi de Llobregat, 08830 Barcelona, Spain
| | - Karel Kostev
- Epidemiology, IQVIA, Main Airport Centre, Unterschweinstiege 2-14 60549 Frankfurt am Main, Germany.
| |
Collapse
|
3
|
Jacob L, Kostev K. Cancer risk in stroke survivors followed for up to 10 years in general practices in Germany. J Cancer Res Clin Oncol 2019; 145:1013-1020. [PMID: 30739168 DOI: 10.1007/s00432-019-02855-w] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2018] [Accepted: 02/01/2019] [Indexed: 01/01/2023]
Abstract
AIMS The goal of this study was to analyze cancer risk in stroke survivors followed for up to 10 years in general practices in Germany. METHODS The current study sample included patients who received an initial stroke diagnosis in one of 1262 general practices in Germany between 2006 and 2015 (index date). Patients without stroke were matched (1:1) to patients with stroke by age, gender, index year, and 16 comorbidities diagnosed in the 12 months prior to the index date using a propensity score method. The main outcome of the study was the risk of cancer as a function of stroke within 10 years of the index date. RESULTS The stroke and non-stroke groups included 9579 men and 9089 women. After 10 years of follow-up, 29.3% of men with stroke and 23.8% of those without stroke developed any of the included types of cancer (log-rank p value < 0.001). During the same time, the prevalence of cancer was 25.0% in women with stroke and 20.5% in women without stroke (log-rank p value < 0.001). There was a positive association between stroke and any cancer in men (hazard ratio [HR] = 1.18, 95% confidence interval [CI] 1.09-1.28) and in women (HR = 1.22, 95% CI 1.12-1.34). This association was significant for cancers of respiratory and intrathoracic organs in men and women and for cancers of digestive organs in men. CONCLUSIONS This study, including more than 37,000 patients from Germany, found that stroke was associated with an increased cancer risk.
Collapse
Affiliation(s)
- Louis Jacob
- Faculty of Medicine, University of Versailles Saint-Quentin-en-Yvelines, Montigny-le-Bretonneux, France
| | - Karel Kostev
- Epidemiology, IQVIA, Unterschweinstiege 2-14, 60549, Frankfurt am Main, Germany.
| |
Collapse
|
4
|
Duan D, Li H, Xu J, Wong L, Xu G, Kong F, Li S, Gong Q, Zhang X, Zhao J, Zhang L, Xu G, Xing W, Han L. Does Body Mass Index and Height Influence the Incident Risk of Ischemic Stroke in Newly Diagnosed Type 2 Diabetes Subjects? J Diabetes Res 2019; 2019:2591709. [PMID: 30805371 PMCID: PMC6362488 DOI: 10.1155/2019/2591709] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/28/2018] [Revised: 09/02/2018] [Accepted: 09/16/2018] [Indexed: 12/13/2022] Open
Abstract
OBJECTIVE To estimate the incident risk of ischemic stroke (IS) in newly diagnosed type 2 diabetes (T2D) subjects according to different body mass index (BMI) and height categories. METHODS A total of 25,130 newly diagnosed T2D subjects were included in this study. All T2D subjects were enrolled consecutively from the Chronic Disease Surveillance System (CDSS) of Ningbo. Standardized incidence ratio (SIR) and its 95% confidence interval (95% CI) stratified by BMI categories and height quartiles were used to estimate the incident risk of IS in T2D subjects. RESULTS In total, 22,795 subjects completed the follow-up. Among them, 1268 newly diagnosed IS cases were identified, with 149,675 person-years. The SIRs of normal BMI (18.5-24.0 kg/m2), overweight (24.0-28.0 kg/m2), and obese (≥28.0 kg/m2) in overall subjects were 2.56 (95% CI 1.90-3.13), 2.13 (95% CI 1.90-3.13), and 1.87 (95% CI 1.29-2.43), respectively (P trend < 0.01), comparing to the general population of Ningbo. For each 1 kg/m2 increment in BMI, the SIR was 0.948 (95% CI 0.903-0.999). For height quartiles, the SIRs of male subjects in quartile 1 (<160 cm), quartile 2 (161-165 cm), quartile 3 (165-170 cm), and quartile 4 (≥171 cm) were 2.27 (95% CI 1.99-2.56), 2.01 (95% CI 1.67-2.45), 1.37 (95% CI 1.05-1.68), and 0.91 (95% CI 0.40-1.32), respectively (P trend < 0.01). While for female subjects, the SIRs in quartile 1 (<155 cm), quartile 2 (156-160 cm), quartile 3 (161-165 cm), and quartile 4 (≥166 cm) were 3.57 (95% CI 3.11-3.49), 2.96 (95% CI 2.61-3.31), 1.94 (95% CI 1.51-2.36), and 1.71 (95% CI 0.95-2.47), respectively (P trend < 0.01). CONCLUSION Compared to the general population of Ningbo, T2D subjects had a higher incident risk of IS. Furthermore, the IS incident risk was not only higher in newly diagnosed T2D subjects with normal BMI but also lower in taller newly diagnosed T2D subjects.
Collapse
Affiliation(s)
- Donghui Duan
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
- Institute of Non-Communicable Disease Control and Prevention, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, China
| | - Hui Li
- Institute of Non-Communicable Disease Control and Prevention, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, China
| | - Jiaying Xu
- Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, USA
| | - Liping Wong
- Department of Social Preventive Medicine, Faculty of Medicine, University of Malaya, 50603 Kuala Lumpur, Malaysia
| | - Guodong Xu
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| | - Fanqian Kong
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| | - Sixuan Li
- Institute of Non-Communicable Disease Control and Prevention, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, China
| | - Qinghai Gong
- Institute of Non-Communicable Disease Control and Prevention, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, China
| | - Xiaohong Zhang
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| | - Jinshun Zhao
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| | - Lina Zhang
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| | - Guozhang Xu
- Institute of Non-Communicable Disease Control and Prevention, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, China
| | - Wenhua Xing
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| | - Liyuan Han
- Department of Preventive Medicine, Zhejiang Provincial Key Laboratory of Pathophysiology, School of Medicine, Ningbo University, Ningbo, China
| |
Collapse
|