iScore for predicting institutional care after ischemic stroke: a population-based study

Machine learning decision support model for discharge planning in stroke patients

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.

Most Important Factors for Deciding Rehabilitation Provision for Severe Stroke Survivors Post Hospital Discharge: A Study Protocol for a Best-Worst Scaling Experiment

Efficient decision-making is crucial to ensure adequate rehabilitation with optimal use of healthcare resources. Establishing the factors associated with making decisions concerning rehabilitation provision is important to guide clinical staff towards person-centred decisions for rehabilitation after severe stroke. In this study we conduct a best–worst scaling (BWS) experiment to identify the most important factors and their relative weight of importance for deciding the type of ongoing rehabilitation services a person with severe stroke might receive post hospital discharge. Fractional, efficient designs are applied regarding the survey design. Key multidisciplinary staff regularly involved in making decisions for rehabilitation in a stroke unit will be recruited to participate in an online BWS survey. Hierarchical Bayes estimation will be used as the main analysis method, with the best–worst count analysis as a secondary analysis. The survey is currently being piloted prior to commencing the process of data collection. Results are expected by the end of September 2021. The research will add to the current literature on clinical decision-making in stroke rehabilitation. Findings will quantify the preferences of factors among key multi-disciplinary clinicians working in stroke units in the UK, involved in decision-making concerning rehabilitation after stroke.

Thinking About the Future: A Review of Prognostic Scales Used in Acute Stroke

Background: There are many prognostic scales that aim to predict functional outcome following acute stroke. Despite considerable research interest, these scales have had limited impact in routine clinical practice. This may be due to perceived problems with internal validity (quality of research), as well as external validity (generalizability of results). We set out to collate information on exemplar stroke prognosis scales, giving particular attention to the scale content, derivation, and validation.

Methods: We performed a focused literature search, designed to return high profile scales that use baseline clinical data to predict mortality or disability. We described prognostic utility and collated information on the content, development and validation of the tools. We critically appraised chosen scales based on the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies (CHARMS).

Results: We chose 10 primary scales that met our inclusion criteria, six of which had revised/modified versions. Most primary scales used 5 input variables (range: 4–13), with substantial overlap in the variables included. All scales included age, eight included a measure of stroke severity, while five scales incorporated pre-stroke level of function (often using modified Rankin Scale), comorbidities and classification of stroke type. Through our critical appraisal, we found issues relating to excluding patients with missing data from derivation studies, and basing the selection of model variable on significance in univariable analysis (in both cases noted for six studies). We identified separate external validation studies for all primary scales but one, with a total of 60 validation studies.

Conclusions: Most acute stroke prognosis scales use similar variables to predict long-term outcomes and most have reasonable prognostic accuracy. While not all published scales followed best practice in development, most have been subsequently validated. Lack of clinical uptake may relate more to practical application of scales rather than validity. Impact studies are now necessary to investigate clinical usefulness of existing scales.

Risk assessment tools to predict location of discharge and need for supportive services for medical patients after discharge from hospital: a systematic review protocol

BACKGROUND

Patients who are discharged from hospital after an acute medical illness often have impaired function that prevents them from returning to their previous place of residence. Assessing each patient's post-discharge needs takes time and resources but is important in order to reduce unplanned readmissions and adverse events post-discharge.

METHODS/DESIGN

We will conduct a systematic review to synthesize the evidence on prognostic models and their reported accuracy in predicting the location of discharge after a medical admission to an acute care hospital. We will perform searches in MEDLINE, EMBASE, CINAHL, and COCHRANE databases. Pre-defined study, population, and model characteristics will be reported. We will write a narrative summary of included studies. Methodological quality of the studies will be assessed using the QUIPS tool, and the quality of evidence will be evaluated using the GRADE tool.

DISCUSSION

Early and accurate assessment of patient needs for supportive services after discharge has the potential to improve patient outcomes and health system efficiency. This systematic review will identify factors that can accurately predict location of discharge using existing tools and identify priority knowledge gaps to inform future research.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42016037144.