Development and validation of clinical prediction model for functional independence measure following stroke rehabilitation

 Survivors don't need useless prediction models. They want EXACT 100% RECOVERY PROTOCOLS! Why are you doing useless research? I'd have everyone here fired!

Send me hate mail on this: oc1dean@gmail.com. I'll print your complete statement with your name and my response in my blog. Or are you afraid to engage with my stroke-addled mind? When these persons become the 1 in 4 per WHO that has a stroke: they'll want 100% recovery and by then it will be too late. 

Development and validation of clinical prediction model for functional independence measure following stroke rehabilitation

Author links open overlay panel,

, , , , , ,

https://doi.org/10.1016/j.jstrokecerebrovasdis.2024.108185

Get rights and content

Under a Creative Commons license

open access

Abstract

Objectives

To develop and internally validate a clinical prediction model that includes balance ability and nutritional indices for the motor-functional independence measure (M-FIM) at 90 days post-stroke stroke.

Materials and Methods

This retrospective, single-center study included 566 patients with stroke undergoing rehabilitation at our rehabilitation hospital. The primary outcome was the M-FIM score of >61 at 3 months post-strokes onset. Stepwise conditional forward selection was first used to identify predictors for the achievement of M-FIM>61 at 90 days post-stroke, from 25 potential predictors at admission. The selected predictors were dichotomized with cut-off values to establish scoring systems, resulting in the B-ADL model, which includes postural balance (B), albumin level, age, arm function (A), days since stroke onset (D), and level of activities of daily living (ADL) (L). For internal validation, we corrected the optimism of the area under the curve of receiver operating characteristic curve (AUROC) induced by overfitting the original data using the bootstrap validation method. Calibration capacity was assessed using a calibration plot.

Results

We developed a clinical model to predict the M-FIM at 90 days post-stroke onset. The AUROC of the B-ADL model was 0.92 (sensitivity, 93.7%; specificity, 89.7%). The B-ADL model showed high accuracy with an AUROC of 0.970 in the internal validation. The scoring system in the validation cohort had a cut-off value of 5.5/12 points to predict the achievement of M-FIM>61 (AUROC: 0.950; 95% CI 0.930–0.970).

Conclusions

The B-ADL model accurately predicted M-FIM >61 at 90 days post-stroke on the day of admission to the recovery rehabilitation ward. The B-ADL model is useful for optimizing rehabilitation programs and resource allocation, allowing for targeted interventions after stroke.

Previous article in issue

Next article in issue

Keywords

Stroke

Prediction

Activities of daily living

Functional independence measure

Rehabilitation

Introduction

Stroke significantly affects the activities of daily living (ADL), with reports indicating that between 13%–35% of stroke survivors require assistance with physical activities.^1,2 Furthermore, a decline in ADL among individuals with stroke is associated with their discharge destinations and decreased quality of life (QOL).^3,4 Therefore, accurate prediction of future ADL levels is essential for planning and tailoring rehabilitation programs to address individual needs and potential recovery trajectories after stroke.

The level of ADL after stroke can be influenced by various factors. Previous studies have shown that the important factors affecting the ADL during stroke rehabilitation include age, sex, stroke subtype, nutritional status, extent of motor impairment, postural balance, cognitive function and muscle strength of the ipsilesional (less affected) upper and lower limbs.5, 6, 7, 8, 9, 10, 11 Specifically, there are reports that the postural balance ability and nutritional status of stroke patients at the time of admission are related to ADL at the end of rehabilitation.^6,11 Therefore, the clinical practice of stroke rehabilitation requires comprehensive assessment of factors affecting ADL levels.

However, the clinical utility of existing clinical prediction models for ADL in stroke rehabilitation is limited for several reasons. First, existing clinical prediction models for FIM after the subacute phase lack consideration of postural balance and blood test assessment including nutritional status as predictive indicators for the future level of ADL.^6,12 Second, most prediction models exclude severe cases with sudden deterioration following the time of prediction implementation; thus, the predictive models for severe cases are insufficient.⁷ Third, there have been reports of insufficient validation and poor utility of these models at an individual level.¹³ Therefore, it is crucial to develop a clinical prediction model that encompasses comprehensive predictors and is applicable developing a clinical prediction model that encompasses comprehensive predictors and is applicable to a broad spectrum of patients with subacute stroke.

This study aimed to develop a clinical prediction model to predict the achievement of M-FIM>61 stroke rehabilitation by adding assessments of postural balance and blood tests during the subacute stroke phase. We hypothesized that incorporating these factors would improve the accuracy of the prediction model.

More at link.