Dataset Information

Predicting short and long-term mortality after acute ischemic stroke using EHR.

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.

SUBMITTER: Abedi V

PROVIDER: S-EPMC8480306 | biostudies-literature | 2021 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting short and long-term mortality after acute ischemic stroke using EHR.

Abedi Vida V Avula Venkatesh V Razavi Seyed-Mostafa SM Bavishi Shreya S Chaudhary Durgesh D Shahjouei Shima S Wang Ming M Griessenauer Christoph J CJ Li Jiang J Zand Ramin R

Journal of the neurological sciences 20210629

<h4>Objective</h4>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.<h4>Methods</h4>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, t ...[more]

PMID: 34218182

Similar Datasets

Project description:BackgroundIschemic stroke is one of the leading causes of mortality and disability. The neuroimaging methods are the gold standard for diagnostics. Biomarkers of cerebral ischemia are considered to be potentially helpful in the determination of the etiology and prognosis of patients with ischemic stroke.AimThis study aimed to investigate the usefulness of serum S100B protein levels as a short- and long-term prognostic factor in patients with ischemic stroke.Study design and methodsThe study group comprised 65 patients with ischemic stroke. S100B protein levels were measured by immunoenzymatic assay. Short-term functional outcome was determined by the NIHSS score on day 1 and the difference in the NIHSS scores between day 1 and day 9 (delta NIHSS). Long-term outcome was assessed by the modified Rankin Scale (MRS) at 3 months after the stroke. At the end of the study, patients were divided into groups based on the NIHSS score on day 9 (0-8 "good" and >8 "poor"), the delta NIHSS ("no improvement" ≤0 and >0 "improvement"), and the MRS ("good" 0-2 and >2 "poor"). Differences in S100B levels between groups were analyzed with the ROC curve to establish the optimal cut-off point for S100B. The odds ratio was calculated to determine the strength of association. Correlations between S100B levels at three time points and these variables were evaluated.ResultsWe revealed a statistically significant correlation between S100B levels at each measurement point (<24 h, 24-48 H, 48-72 h) and the NIHSS score on day 9 (R Spearman 0.534, 0.631, and 0.517, respectively) and the MRS score after 3 months (R Spearman 0.620, 0.657, and 0.617, respectively). No statistically significant correlation was found between S100B levels and the delta NIHSS. Analysis of the ROC curve confirmed a high sensitivity and specificity for S100B. The calculated AUC for the NIHSS on day 9 were 90.2%, 95.0%, and 82.2%, respectively, and for the MRS, 83.5%, 83.4%, and 84.0%, respectively. After determining the S100B cut-off, the odds ratio for beneficial effect (NIHSS ≤ 8 at day 9 or MRS 0-2 after 3 months) was determined for each sampling point.ConclusionS100B is a useful marker for predicting short- and long-term functional outcomes in patients with ischemic stroke.

Project description:The Fast Assessment of Stroke and Transient Ischemic Attack to Prevent Early Recurrence trial raised concern that loading doses of clopidogrel may increase hemorrhagic complications. We investigated if similar rates of hemorrhage occur in patients with acute ischemic stroke (AIS) of varying severity.Patients meeting inclusion criteria were divided into 2 groups: the LOAD group and non-LOAD group. The LOAD group was defined as patients who were administered a loading dose of 300 mg or more of clopidogrel with or without aspirin within 24 hours of admission. The non-LOAD group was devised using propensity score (PS): 55 patients who received a loading dose of clopidogrel of 300 mg or more were matched on PS to 55 patients who did not receive loading doses. These patients were taken from a pool of 341 consecutive ischemic patients ineligible for intravenous or intra-arterial fibrinolysis, 162 of whom received a clopidogrel loading dose and the remainder of whom did not. The frequency of hemorrhage was compared between the 2 groups using Student t test and chi-square. Logistic regression was used to assess the relationship between loading dose and serious bleeding events (symptomatic intracerebral hemorrhage [sICH] or transfusion for systemic bleeding).AIS patients (N = 596) were screened during the 31-month period of this retrospective study. Of this sample, 170 patients were excluded: 149 patients were excluded because they were treated with intravenous tissue plasminogen activator (IV t-PA) alone, 11 were excluded because they were treated with IV t-PA combined with intra-arterial therapy (IAT), and 10 were excluded for treatment with IAT alone. An additional 85 patients were excluded because they were not admitted to the stroke service or because they had an in-hospital stroke. Baseline characteristics of the groups were well matched. There were no significant differences in the rates of sICH, transfusion, hemorrhagic transformation, or systemic bleeding. Clopidogrel loading was not associated with increased odds of serious bleeding events in the crude model (odds ratio [OR] .92, 95% confidence interval [CI] .27-3.13) or after adjusting for covariates and confounders of interest (OR 1.06, 95% CI .28-4.04).Contrary to our original hypothesis, patients with AIS receiving clopidogrel loading doses within 24 hours of symptom onset did not appear to experience a higher rate of new serious bleeding events during acute hospitalization when compared with patients who did not receive loading doses. The Platelet-Oriented Inhibition in New TIA and Minor Ischemic Stroke trial is expected to provide insight into the safety of clopidogrel loading as an acute intervention after cerebral ischemia.

Project description:ImportanceTenecteplase is an alternative to alteplase for emergency treatment of acute ischemic stroke. However, limited data are available comparing their clinical effectiveness in routine clinical practice.ObjectiveTo compare short-term effectiveness and safety outcomes for patients with ischemic stroke treated with intravenous tenecteplase vs alteplase.Design, setting, and participantsThis comparative effectiveness study used data prospectively collected from July 1, 2020, through June 30, 2022, from the Get With The Guidelines-Stroke registry.ExposureConsecutive patients with ischemic stroke treated with either tenecteplase or alteplase within 4.5 hours from last known well time were included.Main outcomes and measuresThe primary end point was functional independence on discharge (modified Rankin Scale [mRS] score, 0-2). Secondary effectiveness end points included disability free at discharge (mRS score, 0-1), discharge home, and independent ambulation at discharge. Safety end points included symptomatic intracranial hemorrhage (sICH) within 36 hours and combined in-hospital mortality or hospice discharge. Generalized linear mixed models were fit to evaluate associations between exposure to tenecteplase (vs alteplase) and end points after adjustment for demographic, clinical, and hospital-level variables. Adjusted odds ratios (AORs) with 95% CIs were computed.ResultsAmong 79 550 patients treated with intravenous thrombolysis, the mean (SD) age was 68.6 (14.8) years, 38 596 (48.5%) were female, and the median National Institutes of Health Stroke Scale (NIHSS) score was 7 (IQR, 4-13). Of these patients, 9465 (11.9%) received tenecteplase (mean [SD] age, 69.6 [14.7] years; median NIHSS score, 7 [IQR, 4-14]; 4504 [47.6%] female) and 70 085 (88.1%) received alteplase (mean [SD] age, 68.5 [14.8] years; median NIHSS score, 7 [IQR, 4-13]; 34 092 [48.6%] female). After adjustment for covariates, no significant differences were found between tenecteplase and alteplase in effectiveness or safety outcomes for the overall cohort, including functional independence at discharge (AOR, 1.00; 95% CI, 0.93-1.07), sICH (AOR, 0.96; 95% CI, 0.83-1.11), and in-hospital mortality or hospice discharge (AOR, 0.98; 95% CI, 0.89-1.07), but significant improvement was found in discharge home (AOR, 1.26; 95% CI, 1.03-1.53), in-hospital mortality (AOR, 0.63; 95% CI, 0.47-0.85), and composite in-hospital mortality or hospice discharge (AOR, 0.78; 95% CI, 0.62-0.97) among those who were eligible for but did not undergo endovascular thrombectomy.Conclusions and relevanceThis large, nationwide comparative effectiveness study using data from routine clinical practice demonstrated similar effectiveness and safety outcomes with tenecteplase compared with alteplase in patients with acute ischemic stroke. This study supports tenecteplase as a reasonable alternative to alteplase.

Dataset Information

Predicting short and long-term mortality after acute ischemic stroke using EHR.

Objective

Methods

Results

Conclusion

Publications

Predicting short and long-term mortality after acute ischemic stroke using EHR.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets