The SOAR stroke score predicts hospital length of stay in acute stroke: an external validation study

Prediction of hospitalization time and independence level with functional outcomes for patients with acute stroke: a retrospective study

OBJECTIVES

The objective of this study was to develop predictive models for estimating the length of stay (LOS) with standardized clinical outcome measures (Functional Independence Measure, Trunk Impairment Scale, Postural Assessment Scale for Stroke Patients, Fugl Meyer Assessment Scale, and Functional Ambulation Category) during acute care setting.

METHODS

One hundred sixty-nine patients were included in the retrospective study. Predictors chosen for the LOS included scores of functional outcome measures at admission. We used Spearman's rank correlation coefficients to calculate correlations among clinical outcome measures and LOS, stepwise multiple regression analysis to develop a predictive model, and receiver operating characteristics curve to analyze the predictive value of explanatory factors obtained from the previous model for discharge Functional Independence Measure score.

RESULTS

The predictive equation explained 81% of the variance in LOS. The most important predictors were trunk impairment, motor function of the upper extremity, walking ability, and independence level at admission. The receiver operating characteristic curve was obtained with a cut-off score of 13 points for the Trunk Impairment Scale, 47 points for Fugl Meyer Assessment-Upper Extremity, and 2 points for Functional Ambulation Category, demonstrating the highest percentage of the accurately predicted ability of independence level at discharge.

DISCUSSION

The models presented in this study could help clinicians and researchers to predict the LOS and discharge independence level of clinical outcomes for patients with acute stroke enrolled in an acute care setting.

Prediction of acute cerebrovascular stroke disability using mSOAR score (Stroke subtype, Oxfordshire Community Stroke Project, age, mRS and NIHSS)

Background

Stroke is among the most prevalent causes of disability. An easy reliable tool to predict stroke outcomes will help manage neurological and non-neurological events and rehabilitation. The modified SOAR (mSOAR) score, which includes stroke subtype, Oxfordshire Community Stroke Project (OCSP) classification, age, pre-stroke modified Rankin score (mRS), and National Institutes of Health Stroke Scale (NIHSS) is simple and easily calculated prognostic tool. The objective of this research was to test the ability of the mSOAR score to predict post-stroke disability as measured by mRS at discharge and 1 month after stroke onset.

Results

One hundred stroke patients (aged ≥ 18 years) were included. All subjects underwent complete neurologic examination, non-contrast head computed tomography. OCSP classification, Stroke subtype, NIHSS, and mRS score on discharge and 1 month after stroke onset were assessed for all patients. The mSOAR score was significantly correlated with mRS on discharge, after 1 month of stroke, and with the length of hospital stay. mSOAR score had high sensitivity and specificity for predicting moderate-to-severe disability on discharge and after 1 month of stroke onset.

Conclusion

The mSOAR is an excellent and accurate tool for predicting the severity of disability on discharge and 1-month post-stroke.

Development of a scoring tool for predicting prolonged length of hospital stay in peritoneal dialysis patients through data mining

Background

The hospital admission rate is high in patients treated with peritoneal dialysis (PD), and the length of stay (LOS) in the hospital is a key indicator of medical resource allocation. This study aimed to develop a scoring tool for predicting prolonged LOS (pLOS) in PD patients by combining machine learning and traditional logistic regression (LR).

Methods

This study was based on patient data collected using the Hospital Quality Monitoring System (HQMS) in China. Three machine learning methods, classification and regression tree (CART), random forest (RF), and gradient boosting decision tree (GBDT), were used to develop models to predict pLOS, which is longer than the average LOS, in PD patients. The model with the best prediction performance was used to identify predictive factors contributing to the outcome. A multivariate LR model based on the identified predictors was then built to derive the score assigned to each predictor. Finally, a scoring tool was developed, and it was tested by stratifying PD patients into different pLOS risk groups.

Results

A total of 22,859 PD patients were included in our study, with 25.2% having pLOS. Among the three machine learning models, the RF model achieved the best prediction performance and thus was used to identify the 10 most predictive variables for building the scoring system. The multivariate LR model based on the identified predictors showed good discrimination power with an AUROC of 0.721 in the test dataset, and its coefficients were used as a basis for scoring tool development. On the basis of the developed scoring tool, PD patients were divided into three groups: low risk (≤5), median risk [5–10], and high risk (>10). The observed pLOS proportions in the low-risk, median-risk, and high-risk groups in the test dataset were 11.4%, 29.5%, and 54.7%, respectively.

Conclusions

This study developed a scoring tool to predict pLOS in PD patients. The scoring tool can effectively discriminate patients with different pLOS risks and be easily implemented in clinical practice. The pLOS scoring tool has a great potential to help physicians allocate medical resources optimally and achieve improved clinical outcomes.

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.

Hyperglycaemia and the SOAR stroke score in predicting mortality

BACKGROUND

We assessed the association between admission blood glucose levels and acute stroke mortality and examined whether there was any incremental value of adding glucose status to the validated acute stroke mortality predictor - the SOAR (stroke subtype, Oxford Community Stroke Project classification, age, and pre-stroke modified Rankin) score.

METHODS

Data from Norfolk and Norwich University Hospital stroke and Transient Ischaemic Attack register (2003-2013) and Anglia Stroke Clinical Network Evaluation Study (2009-2012) were analysed. Multivariable logistic regression analysis assessed the association between admission blood glucose levels with inpatient and 7-day mortality. The prognostic ability of the SOAR score was then compared with the SOAR with glucose score.

RESULTS

A total of 5575 acute stroke patients (ischaemic stroke: 89.2%) with mean age (standard deviation) of 76.97 ( ± 11.88 ) years were included. Both borderline hyperglycaemia (7.9-11.0 mmol/L) and hyperglycaemia (>11.0 mmol/L) when compared to normoglycaemia (4.0-7.8 mmol/L) were associated with both 7-day and inpatient mortality after controlling for sex, age, Oxford Community Stroke Project classification and pre-stroke modified Rankin score. Both the SOAR stroke score and SOAR-G score were good predictors of inpatient stroke mortality [area under the curve: 0.82 (95% confidence interval: 0.81-0.84) and 0.83 (95% confidence interval: 0.81-0.84)], respectively. These scores were also good at predicting outcomes in both patients with and without diabetes.

CONCLUSION

High blood glucose levels at admission were associated with worse acute stroke mortality outcomes. The constituents of the SOAR stroke score were good at predicting mortality after stroke.

Determinants of Length of Stay Following Total Anterior Circulatory Stroke

Identification of factors that determine length of stay (LOS) in total anterior circulatory stroke (TACS) has potential for targeted intervention to reduce the associated health care burden. This study aimed to determine which factors predict LOS following either ischaemic or haemorrhagic TACS. The study sample population was drawn from the Norfolk and Norwich Stroke and Transient Ischemic Attack (TIA) Register (1996–2012), a prospective registry. 2965 patients admitted with TACS verified by a stroke specialist team were included. Primary analysis identified predictors of length of stay (LOS) in either haemorrhagic or ischaemic TACS. Secondary analyses identified predictors of LOS in patients who were discharged alive or who died during admission separately. Moderate (p = 0.014) to severe disability (p = 0.015) and history of congestive heart failure (p = 0.027) in the primary analysis and pre-stroke residence in a care facility among patients who survived to discharge (p = 0.013) were associated with a shorter length of stay. Factors associated with increased length of stay included presence of neurological lateralisation in the primary analysis (p = 0.004) and amongst patients who died (p = 0.003 and p = 0.014 for ischaemic and haemorrhagic stroke, respectively). Patients with advanced age (≥85 years) with haemorrhagic stroke had longer LOS regardless of mortality outcome. Patients with low pre-morbid disability (modified Rankin score ≤2 who died following haemorrhagic TACS also had longer LOS. Our study found predictors of LOS following TACS include neurological lateralisation, pre-stroke disability status, congestive heart failure, pre-morbid residence and age. The identification of such factors would assist in resource allocation and discharge planning.

Predicting hospital stay, mortality and readmission in people admitted for hypoglycaemia: prognostic models derivation and validation

AIMS/HYPOTHESIS

Hospital admissions for hypoglycaemia represent a significant burden on individuals with diabetes and have a substantial economic impact on healthcare systems. To date, no prognostic models have been developed to predict outcomes following admission for hypoglycaemia. We aimed to develop and validate prediction models to estimate risk of inpatient death, 24 h discharge and one month readmission in people admitted to hospital for hypoglycaemia.

METHODS

We used the Hospital Episode Statistics database, which includes data on all hospital admission to National Health Service hospital trusts in England, to extract admissions for hypoglycaemia between 2010 and 2014. We developed, internally and temporally validated, and compared two prognostic risk models for each outcome. The first model included age, sex, ethnicity, region, social deprivation and Charlson score ('base' model). In the second model, we added to the 'base' model the 20 most common medical conditions and applied a stepwise backward selection of variables ('disease' model). We used C-index and calibration plots to assess model performance and developed a calculator to estimate probabilities of outcomes according to individual characteristics.

RESULTS

In derivation samples, 296 out of 11,136 admissions resulted in inpatient death, 1789/33,825 in one month readmission and 8396/33,803 in 24 h discharge. Corresponding values for validation samples were: 296/10,976, 1207/22,112 and 5363/22,107. The two models had similar discrimination. In derivation samples, C-indices for the base and disease models, respectively, were: 0.77 (95% CI 0.75, 0.80) and 0.78 (0.75, 0.80) for death, 0.57 (0.56, 0.59) and 0.57 (0.56, 0.58) for one month readmission, and 0.68 (0.67, 0.69) and 0.69 (0.68, 0.69) for 24 h discharge. Corresponding values in validation samples were: 0.74 (0.71, 0.76) and 0.74 (0.72, 0.77), 0.55 (0.54, 0.57) and 0.55 (0.53, 0.56), and 0.66 (0.65, 0.67) and 0.67 (0.66, 0.68). In both derivation and validation samples, calibration plots showed good agreement for the three outcomes. We developed a calculator of probabilities for inpatient death and 24 h discharge given the low performance of one month readmission models.

CONCLUSIONS/INTERPRETATION

This simple and pragmatic tool to predict in-hospital death and 24 h discharge has the potential to reduce mortality and improve discharge in people admitted for hypoglycaemia.

Addition of sodium criterion to SOAR stroke score

OBJECTIVES

To examine the usefulness of including sodium (Na) levels as a criterion to the SOAR stroke score in predicting inpatient and 7-day mortality in stroke.

MATERIALS AND METHODS

Data from the Norfolk and Norwich University Hospital Stroke & TIA register (2003-2015) were analysed. Univariate and then multivariate models controlling for SOAR variables were used to assess the association between admission sodium levels and inpatient and 7-day mortality. The prognostic ability of the SOAR and SOAR Na scores for mortality outcomes at both time points were then compared using the Area Under the Curve (AUC) values from the Receiver Operating Characteristic curves.

RESULTS

A total of 8493 cases were included (male=47.4%, mean (SD) 77.7 (11.6) years). Compared with normonatremia (135-145 mmol/L), hypernatraemia (>145 mmol/L) was associated with inpatient mortality and moderate (125-129 mmol/L) and severe hypontraemia (<125 mmol/L) with 7-day mortality after adjustment for stroke type, Oxfordshire Community Stroke Project classification, age, prestroke modified Rankin score and sex. The SOAR and SOAR-Na scores both performed well in predicting inpatient mortality with AUC values of .794 (.78-.81) and .796 (.78-.81), respectively. 7-day mortality showed similar results. Both scores were less predictive in those with chronic kidney disease (CKD) and more so in those with hypoglycaemia.

CONCLUSION

The SOAR-Na did not perform considerably better than the SOAR stroke score. However, the performance of SOAR-Na in those with CKD and dysglycaemias requires further investigation.

A 6-Point TACS Score Predicts In-Hospital Mortality Following Total Anterior Circulation Stroke

Background and Purpose

Little is known about the factors associated with in-hospital mortality following total anterior circulation stroke (TACS). We examined the characteristics and comorbidity data for TACS patients in relation to in-hospital mortality with the aim of developing a simple clinical rule for predicting the acute mortality outcome in TACS.

Methods

A routine data registry of one regional hospital in the UK was analyzed. The subjects were 2,971 stroke patients with TACS (82% ischemic; median age=81 years, interquartile age range=74–86 years) admitted between 1996 and 2012. Uni- and multivariate regression models were used to estimate in-hospital mortality odds ratios for the study covariates. A 6-point TACS scoring system was developed from regression analyses to predict in-hospital mortality as the outcome.

Results

Factors associated with in-hospital mortality of TACS were male sex [adjusted odds ratio (AOR)=1.19], age (AOR=4.96 for ≥85 years vs. <65 years), hemorrhagic subtype (AOR=1.70), nonlateralization (AOR=1.75), prestroke disability (AOR=1.73 for moderate disability vs. no symptoms), and congestive heart failure (CHF) (AOR=1.61). Risk stratification using the 6-point TACS Score [T=type (hemorrhage=1 point) and territory (nonlateralization=1 point), A=age (65–84 years=1 point, ≥85 years=2 points), C=CHF (if present=1 point), S=status before stroke (prestroke modified Rankin Scale score of 4 or 5=1 point)] reliably predicted a mortality outcome: score=0, 29.4% mortality; score=1, 46.2% mortality [negative predictive value (NPV)=70.6%, positive predictive value (PPV)=46.2%]; score=2, 64.1% mortality (NPV=70.6, PPV=64.1%); score=3, 73.7% mortality (NPV=70.6%, PPV=73.7%); and score=4 or 5, 81.2% mortality (NPV=70.6%, PPV=81.2%).

Conclusions

We have identified the key determinants of in-hospital mortality following TACS and derived a 6-point TACS Score that can be used to predict the prognosis of particular patients.