1
|
Cui Y, Xiang L, Zhao P, Chen J, Cheng L, Liao L, Yan M, Zhang X. Machine learning decision support model for discharge planning in stroke patients. J Clin Nurs 2024. [PMID: 38358023 DOI: 10.1111/jocn.16999] [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: 09/14/2023] [Revised: 12/28/2023] [Accepted: 01/07/2024] [Indexed: 02/16/2024]
Abstract
BACKGROUND/AIM Efficient discharge for stroke patients is crucial but challenging. The study aimed to develop early predictive models to explore which patient characteristics and variables significantly influence the discharge planning of patients, based on the data available within 24 h of admission. DESIGN Prospective observational study. METHODS A prospective cohort was conducted at a university hospital with 523 patients hospitalised for stroke. We built and trained six different machine learning (ML) models, followed by testing and tuning those models to find the best-suited predictor for discharge disposition, dichotomized into home and non-home. To evaluate the accuracy, reliability and interpretability of the best-performing models, we identified and analysed the features that had the greatest impact on the predictions. RESULTS In total, 523 patients met the inclusion criteria, with a mean age of 61 years. Of the patients with stroke, 30.01% had non-home discharge. Our model predicting non-home discharge achieved an area under the receiver operating characteristic curve of 0.95 and a precision of 0.776. After threshold was moved, the model had a recall of 0.809. Top 10 variables by importance were National Institutes of Health Stroke Scale (NIHSS) score, family income, Barthel index (BI) score, FRAIL score, fall risk, pressure injury risk, feeding method, depression, age and dysphagia. CONCLUSION The ML model identified higher NIHSS, BI, and FRAIL, family income, higher fall risk, pressure injury risk, older age, tube feeding, depression and dysphagia as the top 10 strongest risk predictors in identifying patients who required non-home discharge to higher levels of care. Modern ML techniques can support timely and appropriate clinical decision-making. RELEVANCE TO CLINICAL PRACTICE This study illustrates the characteristics and risk factors of non-home discharge in patients with stroke, potentially contributing to the improvement of the discharge process. REPORTING METHOD STROBE guidelines.
Collapse
Affiliation(s)
- Yanli Cui
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- School of Nursing, Southern Medical University, Guangzhou, China
| | - Lijun Xiang
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Peng Zhao
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- School of Nursing, Southern Medical University, Guangzhou, China
| | - Jian Chen
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- School of Nursing, Southern Medical University, Guangzhou, China
| | - Lei Cheng
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- School of Nursing, Southern Medical University, Guangzhou, China
| | - Lin Liao
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- School of Nursing, Southern Medical University, Guangzhou, China
| | - Mingyu Yan
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
- School of Nursing, Southern Medical University, Guangzhou, China
| | - Xiaomei Zhang
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
| |
Collapse
|
2
|
Cai H, Zhang H, Liang J, Liu Z, Huang G. Genetic liability to frailty in relation to functional outcome after ischemic stroke. Int J Stroke 2024; 19:50-57. [PMID: 37542426 DOI: 10.1177/17474930231194676] [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] [Indexed: 08/07/2023]
Abstract
BACKGROUND Frailty appears to be associated with unfavorable prognosis after stroke in observational studies, but the causality remains largely unknown. AIMS The aim of this study is to investigate the potential causal effect of frailty on functional outcome at 3 months after ischemic stroke using the Mendelian randomization (MR) framework. METHODS Genetic instruments for frailty index were identified in a genome-wide association study meta-analysis including 175,226 individuals of European descent. Corresponding genetic association estimates for functional outcome after ischemic stroke at 90 days were taken from the Genetic of Ischemic Stroke Functional Outcome (GISCOME) network of 6021 patients. We performed inverse-variance weighted MR as the main analyses, followed by several alternate methods and sensitivity analyses. RESULTS In univariable MR, we found evidence that genetically predicted higher frailty index (odds ratio (OR) = 5.12; 95% confidence interval (CI) = 1.31-20.09; p = 0.019) was associated with worse functional outcome (modified Rankin Scale score ⩾3) after ischemic stroke. In further multivariable MR adjusting for potential confounding traits including body mass index, C-reactive protein, inflammatory bowel disease, and smoking initiation, the overall patterns between genetic liability to frailty and poor functional outcome status remained. Sensitivity analyses with complementary methods and with model unadjusted for baseline stroke severity (OR = 4.19; 95% CI = 1.26-13.90; p = 0.019) yielded broadly concordant results. CONCLUSIONS The present MR study suggested a possible causal effect of frailty on poor functional outcome after ischemic stroke. Frailty might represent a potential target for intervention to improve recovery after ischemic stroke.
Collapse
Affiliation(s)
- Huan Cai
- Department of Rehabilitation Medicine, Zhongshan City People's Hospital, Zhongshan, China
| | - Hao Zhang
- Department of Neurology, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Jialin Liang
- Department of Endocrinology and Metabolism, Zhongshan City People's Hospital, Zhongshan, China
| | - Zhonghua Liu
- Department of Rehabilitation Medicine, Zhongshan City People's Hospital, Zhongshan, China
| | - Guozhi Huang
- Department of Rehabilitation Medicine, Zhujiang Hospital, Southern Medical University, Guangzhou, China
- School of Rehabilitation Medicine, Southern Medical University, Guangzhou, China
| |
Collapse
|
3
|
Mennema Å, Vliet Vlieland TPM, Achterberg WP, Oosterveer DM. Functioning and recovery during stroke rehabilitation: a comparison between pre-stroke frail and non-frail patients. Eur Geriatr Med 2023; 14:1343-1351. [PMID: 37935943 PMCID: PMC10754730 DOI: 10.1007/s41999-023-00885-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Accepted: 10/11/2023] [Indexed: 11/09/2023]
Abstract
PURPOSE Pre-stroke frailty in older adults is associated with adverse outcomes after stroke in community-based and hospital-based populations. The aim of our study was to investigate the prevalence of pre-stroke frailty among older stroke survivors receiving medical specialistic rehabilitation and its association with outcomes and recovery. METHODS Pre-stroke frailty was measured by the Groningen Frailty Indicator (GFI, score ≥ 4 indicates frailty) in patients ≥ 65 years receiving stroke medical specialistic rehabilitation. Baseline, follow-up and change (i.e. recovery) scores of the Barthel index (BI), Stroke Impact Scale (SIS) 'mobility', 'communication', and 'memory and thinking', Hospital Anxiety and Depression Scale (HADS) and the EuroQoL-5 dimensions (EQ-5D) were compared between frail and non-frail patients with a multivariable regression model adjusting for confounders. RESULTS Of 322 included patients (34.2% females, median age 70 years), 43 (13.4%) patients reported pre-stroke frailty. There were no differences in BI or in destination of discharge between pre-stroke frail and non-frail stroke survivors receiving inpatient rehabilitation. However, pre-stroke frailty was associated with worse follow-up scores for all other measures. Recovery in pre-stroke frail patients was less favorable compared to non-frail patients for SIS mobility, HADS subscales and EQ-5D index and visual analogue scale. CONCLUSION Pre-stroke frailty was present in a minority of older stroke survivors receiving medical specialistic rehabilitation. BI and destination of discharge did not differ. Nevertheless, pre-stroke frailty was associated with worse functioning at follow-up for most measures of health status and with smaller improvements in mobility, mood and quality of life.
Collapse
Affiliation(s)
- Åsa Mennema
- Basalt, Wassenaarseweg 501, 2333 AL, Leiden, The Hague, The Netherlands.
- Department of Orthopaedics, Rehabilitation and Physical Therapy, Leiden University Medical Center, Leiden, The Netherlands.
| | - Thea P M Vliet Vlieland
- Basalt, Wassenaarseweg 501, 2333 AL, Leiden, The Hague, The Netherlands
- Department of Orthopaedics, Rehabilitation and Physical Therapy, Leiden University Medical Center, Leiden, The Netherlands
| | - Wilco P Achterberg
- Department of Primary Care and Public Health, Leiden University Medical Center, Leiden, The Netherlands
| | - Daniëlla M Oosterveer
- Basalt, Wassenaarseweg 501, 2333 AL, Leiden, The Hague, The Netherlands
- Department of Orthopaedics, Rehabilitation and Physical Therapy, Leiden University Medical Center, Leiden, The Netherlands
- Department of Rehabilitation, Alrijne Hospital, Leiden, The Netherlands
| |
Collapse
|
4
|
Kanda M, Sato T, Yoshida Y, Kuwabara H, Kobayashi Y, Inoue T. Effect of admission in the stroke care unit versus intensive care unit on in-hospital mortality in patients with acute ischemic stroke. BMC Neurol 2023; 23:402. [PMID: 37957571 PMCID: PMC10641943 DOI: 10.1186/s12883-023-03454-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 11/06/2023] [Indexed: 11/15/2023] Open
Abstract
BACKGROUND/OBJECTIVE Few reports have directly compared the outcomes of patients with acute ischemic stroke (AIS) who are managed in a stroke care unit (SCU) with those who are managed in an intensive care units (ICU). This large database study in Japan aimed to compare in-hospital mortality between patients with AIS admitted into SCU and those admitted into ICU. METHODS Patients with AIS who were admitted between April 1, 2014, and March 31, 2019, were selected from the administrative database and divided into the SCU and ICU groups. We calculated the propensity score to match groups for which the admission unit assignment was independent of confounding factors, including the modified Rankin scale (mRS) score. The primary outcome was in-hospital mortality, and secondary outcomes were the mRS score at discharge, length of stay (LOS), and total hospitalization cost. RESULTS Overall, 8,683 patients were included, and 960 pairs were matched. After matching, the in-hospital mortality rates of the SCU and ICU groups were not significantly different (5.9% vs. 7.9%, P = 0.106). LOS was significantly shorter (SCU = 20.9 vs. ICU = 26.2 days, P < 0.001) and expenses were significantly lower in the SCU group than in the ICU group (SCU = 1,686,588 vs. ICU = 1,998,260 yen, P < 0.001). mRS scores (score of 1-3 or 4-6) at discharge were not significantly different after matching. Stratified analysis showed that the in-hospital mortality rate was lower in the ICU group than in the SCU group among patients who underwent thrombectomy. CONCLUSIONS In-hospital mortality was not significantly different between the ICU and SCU groups, with significantly lower costs and shorter LOS in the SCU group than in the ICU group.
Collapse
Affiliation(s)
- Masato Kanda
- Department of Cardiovascular Medicine, Chiba University Graduate School of Medicine, Chiba, Japan
- Healthcare Management Research Center, Chiba University Hospital, Chiba, Japan
| | - Takanori Sato
- Department of Cardiovascular Medicine, Chiba University Graduate School of Medicine, Chiba, Japan
| | - Yoichi Yoshida
- Department of Neurological Surgery, Chiba University Graduate School of Medicine, Chiba, Japan
| | - Hiroyo Kuwabara
- Healthcare Management Research Center, Chiba University Hospital, Chiba, Japan
| | - Yoshio Kobayashi
- Department of Cardiovascular Medicine, Chiba University Graduate School of Medicine, Chiba, Japan
| | - Takahiro Inoue
- Healthcare Management Research Center, Chiba University Hospital, Chiba, Japan.
| |
Collapse
|
5
|
Keiser M, Buterakos R, Stutzky H, Moran L, Hewelt D. Evaluating the FRAIL Questionnaire as a Trigger for Palliative Care Consultation After Acute Stroke. J Hosp Palliat Nurs 2023; 25:124-128. [PMID: 36989192 DOI: 10.1097/njh.0000000000000940] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/30/2023]
Abstract
The American Heart Association and the American Stroke Association jointly released guidelines stating that all patients with a new diagnosis of stroke should receive palliative care consultation starting in the acute phase of care. The purpose of this project was to increase palliative care consultation rates for patients after an acute stroke by using a frailty score to trigger a palliative care consult. Provider education on palliative care and a 5-question fatigue, resistance, ambulation, illnesses, and loss of weight (FRAIL) questionnaire was delivered by a presentation, handouts, and a follow-up email using previously developed content. Patients included adults admitted to the neuroscience critical care unit of a Midwestern comprehensive stroke center with an admission diagnosis of acute stroke (n = 120). The charge nurse completed the FRAIL questionnaire as a screening tool to trigger a palliative care consult. A survey was also distributed to providers (n = 54) to understand their knowledge, thoughts, and feelings toward palliative care. There was an increase in patients who received palliative care consultation from 14.9% to 21.7% after implementation of the FRAIL questionnaire. Also, providers felt better able to provide symptom management to patients after acute stroke. Further research is necessary to determine if the FRAIL survey is an adequate trigger for palliative care consultation.
Collapse
|
6
|
Pereira M, Batista R, Marreiros A, Nzwalo H. Neutrophil-to-leukocyte ratio and admission glycemia as predictors of short-term death in very old elderlies with lobar intracerebral hemorrhage. Brain Circ 2023; 9:94-98. [PMID: 37576580 PMCID: PMC10419730 DOI: 10.4103/bc.bc_5_23] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 04/04/2023] [Accepted: 04/10/2023] [Indexed: 08/15/2023] Open
Abstract
BACKGROUND The incidence of spontaneous intracerebral hemorrhage (SICH) is highest in very old elderlies (≥75 years). The increasing use of antithrombotic drugs is shifting the epidemiology of SICH towards predominance of lobar subtype, suggesting an incremented propensity of bleeding associated with underlying cerebral amyloid angiopathy. With population aging and antithrombotic use, a parallel raise of proportion of lobar SICH is occurring. Improvement of prognostication in this specific age group and SICH type is needed. Routine blood biomarkers can contribute to prediction of short-term mortality after SICH. OBJECTIVE Our aim was to investigate the contribution of routine blood biomarkers for short-term mortality (30-days) in elderly patients with lobar SICH. METHODS Retrospective analysis of consecutive 130 patients with ≥ 75 years and lobar SICH. The outcome was 30-day mortality. Logistic regression analysis was used to investigate whether admission routine biomarkers can be used as predictors. RESULTS The case fatality was 40.8%. Admission glycaemia level, neutrophil to lymphocyte ratio and mean platelet volume were significantly different between groups (p = 0.001, p = 0.024, p = 0.038, respectively). There was no significant difference in all other routine biomarkers. On multivariate analysis, admission higher mean BG level (odds ratio [OR]: 1.010, 95% confidence interval [CI]: 1.001-1.019, p = 0.026) and neutrophil to lymphocyte ratio (OR: 1.070, 95% CI: 1.008-1.136, p = 0.027) emerged as predictors. CONCLUSION In very old patients with lobar SICH, higher BG level and neutrophil to lymphocyte ratio are associated with increased risk of short-term death.
Collapse
Affiliation(s)
- Marta Pereira
- Medical Education Unit, Faculty of Medicine and Biomedical Sciences, Algarve University, Faro, Portugal
- Algarve Biomedical Center Research Institute, Algarve University Hospital Center, Faro, Portugal
| | - Rafael Batista
- Medical Education Unit, Faculty of Medicine and Biomedical Sciences, Algarve University, Faro, Portugal
- Algarve Biomedical Center Research Institute, Algarve University Hospital Center, Faro, Portugal
| | - Ana Marreiros
- Medical Education Unit, Faculty of Medicine and Biomedical Sciences, Algarve University, Faro, Portugal
- Algarve Biomedical Center Research Institute, Algarve University Hospital Center, Faro, Portugal
| | - Hipolito Nzwalo
- Medical Education Unit, Faculty of Medicine and Biomedical Sciences, Algarve University, Faro, Portugal
- Algarve Biomedical Center Research Institute, Algarve University Hospital Center, Faro, Portugal
- Stroke Unit, Algarve University Hospital Center, Faro, Portugal
| |
Collapse
|
7
|
Huang R, Pan F, Kong C, Lu S. Morphology of paraspinal muscles in frail and non-frail older adults evaluated through FRAIL scale. BMC Musculoskelet Disord 2023; 24:35. [PMID: 36650481 PMCID: PMC9843921 DOI: 10.1186/s12891-023-06144-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Accepted: 01/06/2023] [Indexed: 01/18/2023] Open
Abstract
BACKGROUND Frailty is a condition characterized by the progressive deterioration of physiological functioning, which is closely related to adverse events. Multiple previous investigations applied frailty scales for spine research, and the purpose of this study is to investigate the differences in the morphology of the paraspinal muscles in frail and non-frail older adults evaluated through FRAIL scale. METHODS The sample of this retrospectively cross-sectional study consisted of individuals who were ≥ 60 years of age and with lumbar degenerative disease. We divided patients into two groups (0-2 = non-Frail, 3-5 = Frail) according to the FRAIL scale. The cross-sectional area (CSA) and percentage of the fatty infiltration (FI%) of the paraspinal muscles were compared between the two groups. RESULTS The fCSA (functional cross-sectional area) of the non-Frail group (32.78 [28.52, 38.28]) (cm2) was significantly greater than that of the Frail group (28.50 [24.11, 34.77]) (p < 0.001). The ES FI% (erector spinae fatty infiltration rate) (24.83 ± 6.61 vs. 29.60 ± 7.92, p < 0.001) and MF FI% (multifidus fatty infiltration rate) (31.68 ± 5.63 vs. 41.12 ± 7.04, p < 0.001) of the non-Frail group were significantly lower than that of Frail group. CONCLUSIONS The paraspinal muscles of elderly Frail patients screened by the FRAIL scale are worse than those of the non-Frail patients, and the ability of the FRAIL scale to distinguish paraspinal muscle morphology has important clinical significance.
Collapse
Affiliation(s)
- Rufeng Huang
- grid.413259.80000 0004 0632 3337Department of Orthopedics, Xuanwu Hospital, Capital Medical University, Beijing, China ,National Clinical Research Center for Geriatric Diseases, Beijing, China
| | - Fumin Pan
- grid.413259.80000 0004 0632 3337Department of Orthopedics, Xuanwu Hospital, Capital Medical University, Beijing, China ,National Clinical Research Center for Geriatric Diseases, Beijing, China
| | - Chao Kong
- grid.413259.80000 0004 0632 3337Department of Orthopedics, Xuanwu Hospital, Capital Medical University, Beijing, China ,National Clinical Research Center for Geriatric Diseases, Beijing, China
| | - Shibao Lu
- grid.413259.80000 0004 0632 3337Department of Orthopedics, Xuanwu Hospital, Capital Medical University, Beijing, China ,National Clinical Research Center for Geriatric Diseases, Beijing, China
| |
Collapse
|
8
|
Song X, Chen X, Bai J, Zhang J. Association between pre-stroke sarcopenia risk and stroke-associated infection in older people with acute ischemic stroke. Front Med (Lausanne) 2023; 10:1090829. [PMID: 36910490 PMCID: PMC9995446 DOI: 10.3389/fmed.2023.1090829] [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: 12/05/2022] [Accepted: 01/27/2023] [Indexed: 02/25/2023] Open
Abstract
Background Stroke-associated infection (SAI) is a common complication after a stroke. The incidence of infection was higher in people with sarcopenia than in the general population. However, the relationship between pre-stroke sarcopenia risk and SAI in older patients has not been confirmed. This study aimed to investigate the association between pre-stroke sarcopenia risk and SAI in older patients with acute ischemic stroke (AIS). Methods This retrospective study was conducted by the Peking University People's Hospital. We evaluated the pre-stroke sarcopenia risk by applying the SARC-F questionnaire. Multivariate logistic regression was applied to explore the association between pre-stroke sarcopenia risk and SAI. Results A total of 1,002 elder patients with AIS (592 men; 72.9 ± 8.6 years) were enrolled in our study. Pre-stroke sarcopenia risk was found in 29.1% of the cohort. The proportion of patients with pre-stroke sarcopenia risk was larger in the SAI group than in the non-SAI group (43.2 vs. 25.3%, p < 0.001). In multivariate logistic analysis, pre-stroke sarcopenia risk was shown to be independently associated with SAI (OR = 1.454, 95% CI: 1.008-2.097, p = 0.045) after adjusting for potential factors. This association remained consistent across the subgroups based on age, sex, body mass index, smoking status, drinking status, diabetes, hypertension, and dyslipidemia. Conclusion Pre-stroke sarcopenia risk was independently associated with SAI in older patients with AIS. Our findings highlight the significance of pre-stroke sarcopenia identification in the prevention and management of SAI in this population.
Collapse
Affiliation(s)
- Xiaodong Song
- Department of Neurology, Peking University People's Hospital, Beijing, China
| | - Xufeng Chen
- Department of Neurology, Beijing Jishuitan Hospital, Beijing, China
| | - Jie Bai
- Department of Infectious Diseases, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jun Zhang
- Department of Neurology, Peking University People's Hospital, Beijing, China
| |
Collapse
|