Predictors of discharge to home after thrombolytic treatment in right hemisphere infarct patients

Application of Machine Learning Techniques to Identify Data Reliability and Factors Affecting Outcome After Stroke Using Electronic Administrative Records

Aim: To use available electronic administrative records to identify data reliability, predict discharge destination, and identify risk factors associated with specific outcomes following hospital admission with stroke, compared to stroke specific clinical factors, using machine learning techniques. Method: The study included 2,531 patients having at least one admission with a confirmed diagnosis of stroke, collected from a regional hospital in Australia within 2009-2013. Using machine learning (penalized regression with Lasso) techniques, patients having their index admission between June 2009 and July 2012 were used to derive predictive models, and patients having their index admission between July 2012 and June 2013 were used for validation. Three different stroke types [intracerebral hemorrhage (ICH), ischemic stroke, transient ischemic attack (TIA)] were considered and five different comparison outcome settings were considered. Our electronic administrative record based predictive model was compared with a predictive model composed of "baseline" clinical features, more specific for stroke, such as age, gender, smoking habits, co-morbidities (high cholesterol, hypertension, atrial fibrillation, and ischemic heart disease), types of imaging done (CT scan, MRI, etc.), and occurrence of in-hospital pneumonia. Risk factors associated with likelihood of negative outcomes were identified. Results: The data was highly reliable at predicting discharge to rehabilitation and all other outcomes vs. death for ICH (AUC 0.85 and 0.825, respectively), all discharge outcomes except home vs. rehabilitation for ischemic stroke, and discharge home vs. others and home vs. rehabilitation for TIA (AUC 0.948 and 0.873, respectively). Electronic health record data appeared to provide improved prediction of outcomes over stroke specific clinical factors from the machine learning models. Common risk factors associated with a negative impact on expected outcomes appeared clinically intuitive, and included older age groups, prior ventilatory support, urinary incontinence, need for imaging, and need for allied health input. Conclusion: Electronic administrative records from this cohort produced reliable outcome prediction and identified clinically appropriate factors negatively impacting most outcome variables following hospital admission with stroke. This presents a means of future identification of modifiable factors associated with patient discharge destination. This may potentially aid in patient selection for certain interventions and aid in better patient and clinician education regarding expected discharge outcomes.

Inconsistent Classification of Mild Stroke and Implications on Health Services Delivery

OBJECTIVE

To conduct a scoping review on classifications of mild stroke based on stroke severity assessments and/or clinical signs and symptoms reported in the literature.

DATA SOURCES

Electronic searches of PubMed, PsycINFO (Ovid), and Cumulative Index to Nursing and Allied Health (CINAHL-EBSCO) databases included keyword combinations of mild stroke, minor stroke, mini stroke, mild cerebrovascular, minor cerebrovascular, transient ischemic attack, or TIA.

STUDY SELECTION

Inclusion criteria were limited to articles published between January 2003 and February 2018. Inclusion criteria included studies (1) with a definition of either mild or minor stroke, (2) written in English, and (3) with participants aged 18 years and older. Animal studies, reviews, dissertations, blogs, editorials, commentaries, case reports, newsletters, drug trials, and presentation abstracts were excluded.

DATA EXTRACTION

Five reviewers independently screened titles and abstracts for inclusion and exclusion criteria. Two reviewers independently screened each full-text article for eligibility. The 5 reviewers checked the quality of the included full-text articles for accuracy. Data were extracted by 2 reviewers and verified by a third reviewer.

DATA SYNTHESIS

Sixty-two studies were included in the final review. Ten unique definitions of mild stroke using stroke severity assessments were discovered, and 10 different cutoff points were used. The National Institutes of Health Stroke Scale was the most widely used measure to classify stroke severity. Synthesis also revealed variations in classification of mild stroke across publication years, time since stroke, settings, and medical factors including imaging, medical indicators, and clinical signs and symptoms.

CONCLUSIONS

Inconsistencies in the classification of mild stroke are evident with varying use of stroke severity assessments, measurement cutoff scores, imaging tools, and clinical or functional outcomes. Continued work is necessary to develop a consensus definition of mild stroke, which directly affects treatment receipt, referral for services, and health service delivery.

Ambulatory blood pressure variability within the first 24 hours after admission and outcomes of acute ischemic stroke

Our purpose was to evaluate the value of blood pressure variability within the first 24 hours after admission in predicting outcomes of patients with acute ischemic stroke (AIS). A greater variability in systolic blood pressure (adjusted odds ratio [OR] = 1.801, 95% confidence interval [CI] = 1.167-2.779) was associated with poor discharge outcome, especially for nondiabetics (adjusted OR = 1.948, 95% CI = 1.184-3.205) and cardioembolism-related patients with AIS (OR = 7.650, 95% CI = 1.370-42.713). However, this correlation was not observed with a long-term (3-month or 6-month) outcome in patients with AIS. There was no association between diastolic blood pressure variability within the first 24 hours after admission and outcome. In conclusion, systolic blood pressure variability within the first 24 hours after admission is a critical predictor for short-term outcome of patients with AIS.