1
|
Fitzhugh N, Rasmussen LR, Simoni AH, Valentin JB. Misuse of multinomial logistic regression in stroke related health research: A systematic review of methodology. Eur J Neurosci 2023; 58:3116-3131. [PMID: 37442794 DOI: 10.1111/ejn.16084] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2022] [Revised: 06/13/2023] [Accepted: 06/17/2023] [Indexed: 07/15/2023]
Abstract
Multinomial logistic regression (MLR) is often used to model the association between a nominal outcome variable and one or more covariates. The results of MLR are interpreted as relative risk ratios (RRR) and warrant a more coherent interpretation than ordinary logistic regression. Some authors compare the results of MLR to ordinal logistic regression (OLR), irrespective of the fact that these estimate different quantities. We aim to investigate the time trends in the use and misuse of MLR in studies including stroke patients, specifically the extent to which (1) the results are denoted as anything other than RRR, (2) comparisons are made of results with results of OLR and (3) results have been interpreted coherently. Secondarily, we examine the use of model validation techniques in studies with predictive aims. We searched EMBASE and PubMed for articles using MLR on populations of stroke patients. Identified studies were screened, and information pertaining to our aims was extracted. A total of 285 articles were identified through a systematic literature search, and 68 of these were included in the review. Of these, 60 articles (88%) did not denote exponentiated coefficients of MLR as relative risk ratios but rather some other measure. Additionally, 63 articles (93%) interpreted the results of MLR in a non-coherent manner. Two articles attempted to compare MLR results with those of OLR. Nine studies attempted to use MLR for predictive means, and three used relevant validation techniques. From these findings, it is clear that the interpretation of MLR is often suboptimal.
Collapse
Affiliation(s)
- Nicholas Fitzhugh
- Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Gistrup, Denmark
- Danish Health Technology Council (Behandlingsrådet), Aalborg, Denmark
| | - Line Ryberg Rasmussen
- Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Gistrup, Denmark
| | - Amalie Helme Simoni
- Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Gistrup, Denmark
| | - Jan Brink Valentin
- Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Gistrup, Denmark
| |
Collapse
|
2
|
Liu Y, Liu X, Jia J, Guo J, Li G, Zhao X. Uric Acid and Clinical Outcomes in Young Patients with Ischemic Stroke. Neuropsychiatr Dis Treat 2022; 18:2219-2228. [PMID: 36199274 PMCID: PMC9529006 DOI: 10.2147/ndt.s373493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/11/2022] [Accepted: 09/14/2022] [Indexed: 11/23/2022] Open
Abstract
BACKGROUND AND PURPOSE There is limited available evidence for the relationship between uric acid (UA) levels and ischemic stroke in young adults. We aimed to explore the association between UA levels and acute ischemic stroke (AIS) in young patients. MATERIALS AND METHODS This was a prospective and observational study. We recruited young patients aged 18-45 years with AIS at our tertiary hospital. Patients were categorized into four groups according to quartiles of UA levels. The primary outcome was functional outcome at 3 months. The secondary outcomes included stroke severity, in-hospital complications, and functional outcome at discharge. Modified Rankin Scale (mRS) scores were used to assess functional outcome as poor (mRS=2-6) or favorable(mRS=0-1). RESULTS A total of 636 patients were enrolled in the current analysis. The four groups were defined as follows: Q1≤289.8 µmol/L, 289.8 µmol/ L<Q2≤349.0 µmol/L, 349.0 µmol/L<Q3≤421 µmol/L, and Q4>421 µmol/L. Multiple logistic regression analysis showed that UA levels were not significantly predictive of functional outcome either at discharge or at 3 months after AIS. However, compared to Q1, higher UA levels were significantly negatively associated with the rate of moderate-severe stroke (NIHSS≥5) at admission (p for trend =0.016). Furthermore, a reduction in the risk for in-hospital pneumonia was significantly associated with higher UA levels compared to Q1 (P for trend < 0.0001). CONCLUSION Serum UA was a protective factor for stroke severity and in-hospital pneumonia after AIS in young patients. However, we were unable to identify the predictive significance of UA for functional outcome either at discharge or at 3 months after AIS.
Collapse
Affiliation(s)
- Yanfang Liu
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People's Republic of China.,China National Clinical Research Center for Neurological Diseases, Beijing, People's Republic of China.,Research Unit of Artificial Intelligence in Cerebrovascular Disease, Chinese Academy of Medical Sciences, Beijing, People's Republic of China
| | - Xinmin Liu
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People's Republic of China.,China National Clinical Research Center for Neurological Diseases, Beijing, People's Republic of China
| | - Jiaokun Jia
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People's Republic of China.,China National Clinical Research Center for Neurological Diseases, Beijing, People's Republic of China.,Research Unit of Artificial Intelligence in Cerebrovascular Disease, Chinese Academy of Medical Sciences, Beijing, People's Republic of China
| | - Jiahuan Guo
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People's Republic of China.,China National Clinical Research Center for Neurological Diseases, Beijing, People's Republic of China
| | - Guangshuo Li
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People's Republic of China.,China National Clinical Research Center for Neurological Diseases, Beijing, People's Republic of China
| | - Xingquan Zhao
- Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, People's Republic of China.,China National Clinical Research Center for Neurological Diseases, Beijing, People's Republic of China.,Research Unit of Artificial Intelligence in Cerebrovascular Disease, Chinese Academy of Medical Sciences, Beijing, People's Republic of China.,Beijing Institute of Brain Disorders, Collaborative Innovation Center for Brain Disorders, Capital Medical University, Beijing, People's Republic of China
| |
Collapse
|
3
|
Ren Y, Qiu ZH, Wu WH, Dong XG, Han S, Zhang FL, Kong FL, Li FE. Hypertriglyceridemic waist phenotype: Association with initial neurological severity and etiologic subtypes in patients with acute ischemic stroke. Front Endocrinol (Lausanne) 2022; 13:1024398. [PMID: 36531467 PMCID: PMC9751905 DOI: 10.3389/fendo.2022.1024398] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/21/2022] [Accepted: 11/03/2022] [Indexed: 12/02/2022] Open
Abstract
OBJECTIVE To explore the relationship of hypertriglyceridemic waist phenotype (HTWP) with initial neurological severity and etiologic subtypes in patients with acute ischemic stroke. METHODS The data for this study were collected from hospitalized patients within 72 h of acute ischemic stroke onset at the Department of Neurology of the Affiliated Hospital of Beihua University from 1 July 2020 to 30 June 2022. The initial neurological severity was assessed by the National Institute of Health Stroke Scale (NIHSS) on the day of admission: NIHSS <6 was defined as mild stroke, and NIHSS ≥6 as moderate to severe stroke. HTWP was defined by fasting serum triglycerides ≥1.7 mmol/L and waist circumference ≥90 cm in men and ≥80 cm in women. Differentiation of etiologic subtypes was based on the method reported in the Trial of Org 10 172 in Acute Stroke Treatment. Multivariate logistic regression analysis was used to analyze the association of HTWP with initial neurological severity and etiologic subtypes. RESULTS The study included 431 patients. Compared with the normal waist-normal blood triglyceride group, patients with HTWP had reduced risks of moderate to severe stroke [odds ratio (OR): 0.384, 95% confidence interval (CI): 0.170-0.869; P = 0.022]. In addition, the risk of small-artery occlusion stroke was 2.318 times higher in the HTWP group than in the normal triglyceride-normal waist (NWNT) group (OR: 2.318, 95% CI: 1.244-4.319; P = 0.008). CONCLUSION Initial neurological severity was less severe in patients with HTWP, and HTWP was associated with an increased risk of small-artery occlusion stroke.
Collapse
Affiliation(s)
- Yuan Ren
- Department of Postgraduate, School of Clinical Medicine, Beihua University, Jilin, China
- Department of Neurology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Zi-Han Qiu
- Department of Postgraduate, School of Clinical Medicine, Beihua University, Jilin, China
| | - Wei-Hua Wu
- Department of Neurology, the Affiliated Hospital of Beihua University, Jilin, China
| | - Xiao-Guang Dong
- Department of Neurology, the Affiliated Hospital of Beihua University, Jilin, China
| | - Shuang Han
- Department of Postgraduate, School of Clinical Medicine, Beihua University, Jilin, China
| | - Fu-Liang Zhang
- Department of Neurology, The First Hospital of Jilin University, Changchun, China
| | - Fan-Li Kong
- Department of Neurology, The First Hospital of Jilin University, Changchun, China
- *Correspondence: Fan-Li Kong, ; Feng-E Li,
| | - Feng-E Li
- Department of Neurology, the Affiliated Hospital of Beihua University, Jilin, China
- *Correspondence: Fan-Li Kong, ; Feng-E Li,
| |
Collapse
|
4
|
Xiang W, Chen X, Ye W, Li J, Zhang X, Xie D. Prognostic Nutritional Index for Predicting 3-Month Outcomes in Ischemic Stroke Patients Undergoing Thrombolysis. Front Neurol 2020; 11:599. [PMID: 32670192 PMCID: PMC7333017 DOI: 10.3389/fneur.2020.00599] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2020] [Accepted: 05/22/2020] [Indexed: 02/04/2023] Open
Abstract
Objective: Malnutrition has been reported to be related to adverse prognosis in acute ischemic stroke (AIS) patients. Unfortunately, traditional nutritional assessment tools usually increase the workload of neurologists, which makes them unfeasible in the daily clinic work. We aimed to elucidate the association between the prognostic nutritional index (PNI), an easily obtainable baseline nutritional marker, and 3-month outcomes in AIS patients receiving intravenous thrombolysis (IVT). Research methods and procedures: The present study retrospectively included 405 patients. PNI was calculated as 5*lymphocyte count (109 /L) + serum albumin concentration (g/L), and the good prognosis was defined as modified Rankin Scale score of 0–3. The relationship between PNI and clinical parameters was evaluated. The multiple logistic regression model was performed to find out independent predictors of the 3-month outcomes. Results: We found that the patients in the low PNI group had a higher frequency of anemia (12.9 vs. 2.3%, P < 0.001) and a higher level of the Controlling nutritional status (CONUT) score (P < 0.001). The relationship between PNI and nutrition-related factors, such as body mass index (r = 0.208, P = 0.001), age (r = −0.329, P < 0.001), total cholesterol (r = 0.268, P < 0.001) and hemoglobin concentration (r = 0.328, P < 0.001), was significant. Low PNI value (adjusted odds ratio: 2.250, confidence interval: 1.192–4.249, p = 0.012) stayed as an independent predictor for the poor outcome at three months, after adjustment for potential confounders. Conclusions: The PNI was independently associated with 3-month outcomes in AIS patients undergoing IVT. As an easily obtainable nutritional marker, PNI may be a useful nutritional assessment tool in the clinic work.
Collapse
Affiliation(s)
- Weiwei Xiang
- Department of Neurology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Xiyi Chen
- Department of Cardiovascular and Thoracic Surgery, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Weiyi Ye
- Department of Neurology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Jia Li
- Department of Neurology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Xu Zhang
- Department of Neurology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Dewei Xie
- Department of Neurology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| |
Collapse
|