Outcome Prediction by Combining Initial Clinical Severity With Corticospinal Tract Lesion Load in Patients With Intracerebral Hemorrhage

 Predicting failure to recover is TOTALLY FUCKING USELESS! You're fired!

Outcome Prediction by Combining Initial Clinical Severity With Corticospinal Tract Lesion Load in Patients With Intracerebral Hemorrhage 

Toshiki Yasukawa • Yuki Uchiyama • Tetsuo Koyama • Kazuhisa Domen

Published: April 17, 2025 DOI: 10.7759/cureus.82430  Peer-Reviewed Cite this article as: Yasukawa T, Uchiyama Y, Koyama T, et al. (April 17, 2025) Outcome Prediction by Combining Initial Clinical Severity With Corticospinal Tract Lesion Load in Patients With Intracerebral Hemorrhage. Cureus 17(4): e82430. doi:10.7759/cureus.82430

Abstract

Objective: 

This study aimed to assess the predictive accuracy of motor outcomes in patients with intracerebral hemorrhage by integrating the initial severity of hemiparesis and the corticospinal tract lesion load (CST-LL).

Materials and methods: 

A retrospective analysis was conducted on patients diagnosed with putaminal and/or thalamic hemorrhage who underwent computed tomography (CT) shortly after stroke onset. The CT images were aligned with a standardized brain template to calculate CST-LL. The initial severity of hemiparesis was evaluated using the summed Brunnstrom Recovery Stage (BRS total; range: 3-18). Motor outcomes at the time of discharge from a rehabilitation facility were assessed using the motor component total score of the Stroke Impairment Assessment Set (SIAS-motor total; range: 0-25). A multivariate regression analysis was performed with BRS total and CST-LL as independent variables and SIAS-motor total as the dependent variable.

Results: 

A total of 61 patients were included in the analysis. The median CST-LL was 1.974 mL (interquartile range (IQR): 1.113-3.311 mL), the median BRS total was 8 (IQR: 4-13), and the median SIAS-motor total was 20 (IQR: 9.5-24.5). Both BRS total and CST-LL were found to be significant predictors of motor outcomes. The estimated t-values were 4.79 for BRS total and −3.29 for CST-LL, indicating comparable contributions of both factors. The developed regression model explained 60.4% of the variance in SIAS-motor outcomes.

Conclusions: 

The combination of initial clinical severity and CST-LL enhances the predictive accuracy of motor recovery in patients with intracerebral hemorrhage.

Introduction

Predicting patient outcomes is crucial(NO, it's not you blithering idiots! Try thinking like a patient for once in your life. They don't want to hear they aren't going to recover!)  for planning effective rehabilitation strategies for individuals who have experienced a stroke [1]. Among the various factors influencing recovery, the severity of clinical symptoms in the early stages is particularly important, as it provides critical insights into stroke impact and guides therapeutic and rehabilitative interventions [2]. Therefore, assessing(Assessments do ABSOLUTELY NOTHING FOR RECOVERY! If you think so; GET THE HELL OUT OF STROKE!) clinical manifestations during the acute phase is essential for predicting outcomes and determining appropriate management strategies in stroke rehabilitation.

Beyond initial clinical seserity, the integrity of the corticospinal tract (CST) has been identified as a key factor in predicting functional outcomes, particularly motor recovery in the extremities [3,4]. Studies utilizing magnetic resonance imaging (MRI) have demonstrated that the overlap between the stroke lesion and the CST, known as CST lesion load (CST-LL), correlates with motor function outcomes [5,6]. In addition, computed tomography (CT), which is commonly used in stroke management, especially for hemorrhagic stroke, has been investigated as a potential tool for estimating CST-LL. Some reports suggest that CST-LL derived from CT imaging may aid in outcome prediction, particularly in cases involving putaminal or thalamic hemorrhage [7,8].

Various predictive models incorporating techniques such as machine learning and functional MRI have been developed to estimate stroke outcomes [9-11]. However, these methods often require significant computational resources and prolonged processing times, limiting their feasibility for routine clinical use. In contrast, integrating initial clinical severity assessment with CST-LL derived from standard CT scans offers a practical approach that can be readily implemented in daily clinical practice [8,12]. This study aims to evaluate the clinical utility of combining early clinical severity and CST-LL in predicting outcomes for patients with intracerebral hemorrhage.

Novel Risk Score to Predict Poor Outcome After Endovascular Treatment in Anterior Circulation Occlusive Acute Ischemic Stroke

 This is the problem, predicting failure to recover rather than DELIVERING RECOVERY! I'd have you all fired!

Novel Risk Score to Predict Poor Outcome After Endovascular Treatment in Anterior Circulation Occlusive Acute Ischemic Stroke

Dong Yang, MD https://orcid.org/0000-0002-2695-0499, Kang Yuan, MD https://orcid.org/0000-0002-4482-2503, Wusheng Zhu, MD, PhD, Min Lin, MD, PhD https://orcid.org/0000-0002-6865-5148 35604214@qq.com, and Xinfeng Liu, MD, PhD https://orcid.org/0000-0002-8182-9632 xfliu2@vip.163.comAuthor Info & Affiliations

Journal of the American Heart Association

New online

https://doi.org/10.1161/JAHA.124.036329

• Information & Authors
• Metrics & Citations
• View Options
• References
• Figures
• Tables

• Share

Abstract

Background

We aimed to develop and validate a prognostic score to predict outcomes after endovascular treatment in acute ischemic stroke.

Methods

The prognostic score was developed based on the ACTUAL (Endovascular Treatment for Acute Anterior Circulation Ischemic Stroke) registry. The validation cohort was derived from the Captor trial. Independent predictors of poor outcome after endovascular treatment were obtained from the least absolute shrinkage and selection operator regression and multivariable logistic regression. Corresponding regression coefficients were used to generate point scoring system. The area under the receiver operating characteristic curve and the Hosmer–Lemeshow goodness‐of‐fit test were used to assess model discrimination and calibration. The predictive properties of the developed prognostic score were validated and the discriminative power was compared with other validated tools.

Results

A 17‐point Age, Collateral Status, Blood glucose, Alberta Stroke Program Early Computed Tomography Score, and National Institutes of Health Stroke Scale score scale was developed from the set of independent predictors, including age, admission National Institutes of Health Stroke Scale score, Alberta Stroke Program Early Computed Tomography Score on initial computed tomography scan, blood glucose, and collateral status. The scale showed good discrimination in the derivation cohort (area under the receiver operating characteristic curve, 0.79 [95% CI, 0.75–0.82]) and validation cohorts (area under the receiver operating characteristic curve, 0.77 [95% CI, 0.70–0.84]). The scale was well calibrated (Hosmer–Lemeshow test) in the derivation cohort (P=0.57) and validation cohort (P=0.75).

Conclusions

The Age, Collateral Status, Blood glucose, Alberta Stroke Program Early Computed Tomography score, and National Institutes of Health Stroke Scale score scale is a valid tool for predicting outcomes and may be useful for endovascular stroke treatment in anterior circulation large vessel occlusions.

A novel approach to developing and validating a predictive model of functional recovery for adults with stroke in post-acute rehabilitation

This is totally wrong, predicting recovery rather than DELIVERING RECOVERY! I'd fire everybody involved!

 A novel approach to developing and validating a
predictive model of functional recovery for adults with
stroke in post-acute rehabilitation

Alison Cogan, Dongze Ye, Dingyi Nie, Mary Lawlor and

Nicolas Schweighofer

University of Southern California

OBJECTIVES/GOALS: 

To use patient-level Center for Medicare and Medicaid Services (CMS) mandated quality metrics for inpatient rehabilitation facilities (IRFs) to develop and validate predictive

models of functional recovery and interactions of baseline characteristics with therapy time. 

METHODS/STUDY POPULATION:

Retrospective cohort study of a national US sample of ~40,000 adults with a primary diagnosis of stroke admitted to IRFs in 2023. Records will be randomly allocated to equal training and validation samples.

We will use a random forest approach to generate predictive models for self-care and mobility functional outcomes using patient baseline and demographic data from a CMS-mandated assessment for IRFs(Section GG). We will also examine how predictive variables modulate the effects of occupational, physical, and speech-language therapy minutes. The random forest is a machine-learning approach

that trains multiple models and combines their predictions to improve their overall performance. 

RESULTS/ANTICIPATED

RESULTS: 

Predictive models developed from the training sample will be applied to the validation sample to confirm their capacity to support new observations. Preliminary results will be reported,

including the F1 score and area under the curve (AUC), with 95% confidence intervals. A unique feature of this study is the large sample, which contrasts with prior research in stroke rehabilitation using machine learning approaches. This study will produce powerful models that will inform the design of a clinical decision-support tool for application into clinical practice in a future study. 

DISCUSSION/

SIGNIFICANCE OF IMPACT: 

By using CMS-mandated quality metrics that are collected as part of standard clinical practice in IRFs, results will support clinical interpretation and application of

metrics and inform the development of a clinician-facing intervention to support personalized rehabilitation approaches.

Machine learning-based scoring model for predicting mortality in ICU-admitted ischemic stroke patients with moderate to severe consciousness disorders

 

What possible use of predicting failure to recover helps survivors? WHY THE FUCK AREN'T YOU DOING RESEARCH THAT DELIVERS RECOVERY?

Machine learning-based scoring model for predicting mortality in ICU-admitted ischemic stroke patients with moderate to severe consciousness disorders

Zhou Zhou^1,2Bo Chen²Zhao-Jun Mei^1,2Wei Chen^1,2Wei Cao³En-Xi Xu²Jun Wang²Lei Ye^1*Hong-Wei Cheng^1*

• ¹Department of Neurosurgery, The First Affiliated Hospital of Anhui Medical University, Hefei, China
• ²Department of Neurosurgery, Affiliated People’s Hospital of Jiangsu University, Jiangsu, China
• ³Department of Neurology, Affiliated People’s Hospital of Jiangsu University, Jiangsu, China

Background: Stroke is a leading cause of mortality and disability globally. Among ischemic stroke patients, those with moderate to severe consciousness disorders constitute a particularly high-risk subgroup. Accurate predictive models are essential for guiding clinical decisions in this population. This study aimed to develop and validate an automated scoring system using machine learning algorithms for predicting short-term (3- and 7-day) and relatively long-term (30- and 90-day) mortality in this population.

Methods: This retrospective observational study utilized data from the MIMIC-IV database, including 648 ischemic stroke patients with Glasgow Coma Scale (GCS) scores ≤12, admitted to the ICU between 2008 and 2019. Patients with GCS scores indicating speech dysfunction but clear consciousness were excluded. A total of 47 candidate variables were evaluated, and the top six predictors for each mortality model were identified using the AutoScore framework. Model performance was assessed using the area under the curve (AUC) from receiver operating characteristic (ROC) analyses.

Results: The median age of the cohort was 76.8 years (IQR, 64.97–86.34), with mortality rates of 8.02% at 3 days, 18.67% at 7 days, 33.49% at 30 days, and 38.89% at 90 days. The AUCs for the test cohort’s 3-, 7-, 30-, and 90-day mortality prediction models were 0.698, 0.678, 0.724, and 0.730, respectively.

Conclusion: We developed and validated a novel machine learning-based scoring tool that effectively predicts both short-term and relatively long-term mortality in ischemic stroke patients with moderate to severe consciousness disorders. This tool has the potential to enhance clinical decision-making and resource allocation for these patients in the ICU.(So, you can quickly triage them to the death intervention?)

Introduction

Stroke, including both ischemic and hemorrhagic types, remains one of the leading causes of mortality and long-term disability worldwide (1). Stroke mortality is projected to increase by 50% from 2020 to 2050 (2), significantly adding to the disease burden. The burden is particularly severe among patients who experience both severe ischemic stroke and consciousness disorders (3, 4), involving prolonged hospital stays, intensive rehabilitation efforts, and significant caregiver support (5). Consciousness disorders encompass a range of conditions, including coma, vegetative state, and minimally conscious state (6, 7), and are associated with significantly worse prognoses compared to ischemic stroke patients without consciousness disorders (8).

In this study, we focus on a distinct and challenging subgroup: ischemic stroke patients with moderate to severe consciousness disorders (GCS ≤ 12) at admission, excluding those with a GCS score of 4-1-6 or 4-2-6, as they are classified as having speech dysfunction with clear consciousness (9, 10). All these severe ischemic stroke patients were admitted to the ICU (11).

Patients in this category are typically incapable of independently deciding on interventions such as mechanical ventilation, artificial nutrition, surgical decompression, or even the withdrawal of life-sustaining treatment. In many severe stroke cases, however, physicians and patient surrogates must make decisions under conditions of prognostic uncertainty and ambiguous definitions of acceptable outcomes (12). Accurate prediction of outcomes in these patients is essential for guiding clinical decisions, managing resources, and providing appropriate counseling for patients’ families. Prognostic models that accurately predict outcomes for patients with severe stroke are currently insufficient. Traditional assessment tools, such as the GCS and the Modified Rankin Scale (mRS), often overlook the complexities inherent in these patients’ conditions. Moreover, these models tend to rely on static clinical evaluations and do not take advantage of the massive data available from modern healthcare databases. Recent advancements in machine learning (ML) have shown potential in developing more precise and individualized prognostic models (13, 14). ML techniques can analyze large datasets to identify patterns often missed by traditional methods, enhancing prognostic accuracy for patients (15, 16). Despite its potential, research applying machine learning to predict outcomes in severe ischemic stroke patients remains limited. This gap underscores the need for innovative approaches to improve prognostic accuracy in this high-risk population.

Therefore, the primary objective of this study is to develop an automated scoring model using machine learning techniques to estimate mortality for severe ischemic stroke patients with moderate to severe consciousness disorders. By enhancing the interpretability and accuracy of the predictive model, we aim to facilitate its integration into clinical workflows and decision-making processes.

More at link.

Association between the hemoglobin-to-red cell distribution width ratio and three-month unfavorable outcome in older acute ischemic stroke patients: a prospective study

 What possible use of predicting failure to recover helps survivors? WHY THE FUCK AREN'T YOU DOING RESEARCH THAT DELIVERS RECOVERY?

Association between the hemoglobin-to-red cell distribution width ratio and three-month unfavorable outcome in older acute ischemic stroke patients: a prospective study

Luwen Huang^1†Linlin Li^1†Qing-rong Ouyang¹Ping Chen²Ming Yu^1*‡Lei Xu^1*‡

• ¹Department of Neurology, Suining Central Hospital, Suining, Sichuan Province, China
• ²Department of Pharmacy, Suining Central Hospital, Suining, Sichuan Province, China

Objective: Acute ischemic stroke (AIS) is a prevalent acute condition among older individuals. This study is the first investigation of the link between the HRR and unfavorable three-month outcome in older AIS patients.

Methods: This secondary research used data from a sample of 1,470 older AIS patients collected from a South Korean hospital between January 2010 and December 2016. Multiple imputation was applied to account for absent values. Binary logistic regression analysis was used to examine the relationship between the baseline HRR and adverse outcome at three-month. Restricted cubic spline analysis was employed to evaluate the correlation between HRR levels and adverse outcome. Interaction tests were performed to discern variations among subgroups.

Results: At 3 months, the overall incidence of adverse events was 31.43%, with a median HRR of 9.49. Compared to those with a lower HRR (Q1), the adjusted odds ratios (ORs) for the HRR in Q2, Q3, and Q4 were 0.61 (95% CI: 0.41–0.92, p = 0.017), 0.49 (95% CI: 0.31–0.78, p = 0.003), and 0.54 (95% CI: 0.31–0.92, p = 0.025), respectively. The correlation between the HRR and adverse outcome was non-linear (p < 0.05). An inflection point threshold of 10.70 was established via RCS analysis. Each 1-unit increase in HRR on the left side of the infection point was associated with a 24.0% decrease in the likelihood of adverse outcomes (OR = 0.76, 95% CI: 0.66–0.86, p < 0.001). ROC analysis revealed that HRR had the highest AUC (0.64, 95% CI: 0.61–0.67), followed by hs-CRP (0.60, 95% CI: 0.57–0.63), FPG/HbA1c (0.59, 95% CI: 0.55–0.63), and WBC (0.55, 95% CI: 0.51–0.58).

Conclusion: A lower HRR was correlated with a higher risk for adverse outcome in older AIS patients.

1 Introduction

Stroke is the second leading cause of mortality worldwide and the third major contributor to disability in non-communicable diseases; acute ischemic stroke (AIS) constituted approximately 62.4 to 67.7% of all stroke incidents in 2021 (1). AIS is a common illness among the older population. Between 1990 and 2019, the prevalence of ischemic stroke among older adults was markedly greater than that among younger adults worldwide (2). Consequently, it is imperative to determine appropriate and effective clinical indicators to predict AIS prognosis in geriatric patients, guide clinical care, and improve treatment outcome.

Red blood cell distribution width (RDW), which reflects the variability in red blood cell volume, has traditionally been used for the diagnosis and differential diagnosis of anemia (3). Clinical studies have demonstrated that RDW is increasingly acknowledged as an independent risk factor for recurrence, hemorrhagic transformation, in-hospital mortality, and poststroke fatigue in patients with AIS (4–7). Moreover, recent research has identified RDW as a potential inflammatory marker significantly associated with stroke-associated pneumonia (SAP) and as a valuable tool for enhancing SAP risk stratification in thrombolyzed AIS patients when integrated into established prediction models (8). Nevertheless, a study including 1,504 patients indicated that RDW could not predict the severity or functional results of AIS (9). Therefore, novel and dependable markers are needed to predict AIS outcome. These limitations underscore the urgent need for novel, dependable biomarkers to improve AIS outcome prediction.

The hemoglobin-to-red blood cell distribution width ratio (HRR) is a novel biomarker first introduced by Peng et al. in their research on the progression of esophageal squamous cell cancer (10). HRR has demonstrated a strong correlation with inflammatory levels and has been associated with adverse outcomes in various diseases (10–16). Compared to single inflammatory markers such as WBC or hs-CRP, HRR offers a unique advantage by simultaneously reflecting red blood cell metabolism and systemic inflammation. As a simple and easily obtainable parameter, HRR may provide a more comprehensive prediction of unfavorable outcomes in AIS patients. Importantly, studies have also shown a negative association between HRR and poor outcome in AIS patients (17–19).

Nonetheless, the correlation between HRR and negative outcome in elderly AIS patients remains unclear. This study aimed to address this gap by investigating the correlation between HRR and unfavorable outcome. The ultimate goal is to establish HRR as a simple and accessible biomarker that can aid clinicians in early risk stratification, thereby improving patient management and enhancing quality of life.

More at link.

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.

Parietal operculum and motor cortex activities predict motor recovery in moderate to severe stroke

 Predicting failure to recover is ABSOLUTELY USELESS! Survivors would like their researchers to deliver EXACT RECOVERY PROTOCOLS!  I'd fire everyone involved!

Parietal operculum and motor cortex activities predict motor recovery in moderate to severe stroke

Firdaus Fabrice Hannanu a,b , Thomas A. Zeffiro b,c , Laurent Lamalle a,d,e,f , Olivier Heck g,h , Félix Renard i , Antoine Thuriot i,k , Alexandre Krainik a,d,e,f,g,h , Marc Hommel b,i,j , Olivier Detante b,h,k , Assia Jaillard a,b,i, ⁎, on behalf of the ISIS-HERMES Study Group K. Garambois 1 , M. Barbieux-Guillot 2 , I. Favre-Wiki 2 , S. Grand 3 , J.F. Le Bas 4 , A. Moisan 5 , M.J. Richard 6 , F. De Fraipont 6 , J. Gere 7 , S. Marcel 7 , W. Vadot 8 , G. Rodier 8 , D. Perennou 9 , A. Chrispin 9 , P. Davoine 9 , B. Naegele 2 , P. Antoine 2 , I. Tropres 10 , F. Renard 11 1 Stroke Unit Centre Hospitalier UniversitaireGrenoble Alpes [CHUGA], France 2 Stroke Unit CHUGA, France 3 Neuroradiology CHUGA, France 4 Neuroradiologie CHUGA, France 5 Unité Mixte de Thérapie Cellulaire [UMTC] CHUGA, France 6 UMTC, France 7 Stroke Unit, CH Chambéry, France 8 Stroke Unit, CH Annecy, France 9 Rehabilitation Unit CHUGA, France 10 IRMaGe UGA, France 11 AGEIS-UGA, France a Unité IRM 3T-Recherche- UMS IRMaGe – Centre Hospitalier Universitaire (CHU) Grenoble Alpes, France b Laboratoire MATICE - Pôle Recherche – CHU Grenoble-Alpes, France c Neurometrika, Potomac, MD, United States d IRMaGe - Inserm US-017, France e IRMaGe - CNRS UMS-3552, France f IRMaGe - Université Grenoble-Alpes -, France g Neuroradiologie et IRM-Centre Hospitalier Universitaire Grenoble-Alpes, France h Grenoble Institut des Neurosciences (GIN) Inserm U836-UJF-CEA-CHU, France i AGEIS, EA-UGA 7407 Université Grenoble Alpes, France j Clinatec - CHU Grenoble-Alpes, France k Unité neurovasculaire - CHU Grenoble-Alpes, France abstract article info Article history: Received 9 November 2016 Received in revised form 9 January 2017 Accepted 22 January 2017 Available online 26 January 2017 

While motor recovery following mild stroke has been extensively studied with neuroimaging, mechanisms of recovery after moderate to severe strokes of the types that are often the focus for novel restorative therapies remain obscure. We used fMRI to: 1) characterize reorganization occurring after moderate to severe subacute stroke, 2) identify brain regions associated with motor recovery and 3) to test whether brain activity associated with passive movement measured in the subacute period could predict motor outcome six months later. Because many patients with large strokes involving sensorimotor regions cannot engage in voluntary movement, we used passive flexion-extension of the paretic wrist to compare 21 patients with subacute ischemic stroke to 24 healthy controls one month after stroke. Clinical motor outcome was assessed with Fugl-Meyer motor scores (motor-FMS) six months later. Multiple regression, with predictors including baseline (one-month) motor-FMS and sensorimotor network regional activity (ROI) measures, was used to determine optimal variable selection for motor outcome prediction. Sensorimotor network ROIs were derived from a meta-analysis of arm voluntary movement tasks. Bootstrapping with 1000 replications was used for internal model validation. During passive movement, both control and patient groups exhibited activity increases in multiple bilateral sen- sorimotor network regions, including the primary motor (MI), premotor and supplementary motor areas (SMA), NeuroImage: Clinical 14 (2017) 518–529 ⁎ 

Enhancement Of Finger State Progress Model for Markerless Virtual Fine Motor Stroke Rehabilitation

I'd have everyone fired here for producing useless predictions rather that delivering EXACT REHAB PROTOCOLS!

 Enhancement Of Finger State Progress Model for Markerless Virtual Fine
Motor Stroke Rehabilitation

Mohd Amir Idzham Iberahim1, Syadiah Nor Wan Shamsuddin2*,

Mokhairi Makhtar2, Yousef A.Baker El-Ebiary3

1Faculty of Computer Science and Mathematics, Universiti Malaysia Terengganu (UMT),

Terengganu Malaysia.

2Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin (UniSZA),

Terengganu, Malaysia, syadiah@unisza.edu.my

3Faculty of Informatics and Computing, UniSZA University, Malaysia

The use of machine learning as a tool for analyzing and pattern extraction from the results is widely

applied in various medical applications in stroke rehabilitation. It will help the therapist to make a

consistent and precise evaluation for a viable recommendation for an optimal future exercise to

improve the patient’s progress. The objective of this study is to produce a prediction model to

analyze patient finger rehabilitation progress by comparing four regression classifiers' efficiency.

In this study, we proposed an Enhancement of the Finger State Progress (E-FSP) model to produce

prediction results of progress and performance which also consists of a markerless VR application

using markerless motion sensors and can capture kinematic data through Time-based Simplified

Denavit Heartenberg (TSDH) model and measure the results of rehabilitation exercises through the

integration of Finger State Progress (FSP) model. 30 patients have undergone rehabilitation

sessions using VR applications in the Kuala Nerus Rehabilitation and Hemodialysis Health

Organization. The study shows the result of an optimum evaluation is the RandomForest classifier

which has the lowest Mean Absolute Error (MAE) value of 8.26 and Root Mean Square Error

(RMSE) value of 12.38. In conclusion, The VR application and machine learning can produce a

very promising combination of attractive visual and viable prediction analysis for virtual fine motor

stroke rehabilitation.

Enhancing Ischemic Stroke Management: Leveraging Machine Learning Models for Predicting Patient Recovery After Alteplase Treatment

I'd fire anyone working on useless predicting failure to recover, rather than doing the research that leads to patient recovery!

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? I would like to know exactly what you think stroke research is for.

 Enhancing Ischemic Stroke Management: Leveraging Machine Learning Models for Predicting Patient Recovery After Alteplase Treatment

Babak Khorsand, Atena vaghf, Vahide Salimi, Maryam Zand, Seyed Abdolreza Ghoreishi

Aim: 

 Ischemic stroke remains a leading global cause of morbidity and mortality, emphasizing the need for timely treatment strategies. This study aimed to develop a machine learning model to predict clinical outcomes in ischemic stroke patients undergoing Alteplase therapy, thereby supporting more personalized care. 

Methods: 

Data from 457 ischemic stroke patients were analyzed, including 50 demographic, clinical, laboratory, and imaging variables. Five machine learning algorithms, k-nearest neighbors (KNN), support vector machines (SVM), Naïve Bayes (NB), decision trees (DT), and random forest (RF), were evaluated for predictive accuracy. The primary evaluation metrics were sensitivity and F-measure, with an additional feature importance analysis to identify high-impact predictors. Results: The Random Forest model showed the highest predictive reliability, outperforming other algorithms in sensitivity and F-measure. Furthermore, by using only the top-ranked features identified from the feature importance analysis, the model maintained comparable performance, suggesting a streamlined yet effective predictive approach. 

Conclusion: 

Our findings highlight the potential of machine learning in optimizing ischemic stroke treatment outcomes. Random Forest, in particular, proved effective as a decision-support tool, offering clinicians valuable insights for more tailored treatment approaches. This model's use in clinical settings could significantly enhance patient outcomes by informing better treatment decisions.

Ischemic Stroke

Neurology

Related Articles

Multiple imputation integrated to machine learning: predicting post-stroke recovery of ambulation after intensive inpatient rehabilitation

 Great, more blithering idiots that think that predicting failure to recover is helpful to stroke survivors! I'D HAVE YOU ALL FIRED!

Multiple imputation integrated to machine learning: predicting post-stroke recovery of ambulation after intensive inpatient rehabilitation

• Alice Finocchi,
• Silvia Campagnini,
• Andrea Mannini,
• Stefano Doronzio,
• Marco Baccini,
• Bahia Hakiki,
• Donata Bardi,
• Antonello Grippo,
• Claudio Macchi,
• Jorge Navarro Solano,
• Michela Baccini &
• Francesca Cecchi 

Scientific Reports volume 14, Article number: 25188 (2024) Cite this article

• 269 Accesses

• 1 Altmetric

• Metrics details

Abstract

Good data quality is vital for personalising plans in rehabilitation. Machine learning (ML) improves prognostics but integrating it with Multiple Imputation (MImp) for dealing missingness is an unexplored field. This work aims to provide post-stroke ambulation prognosis, integrating MImp with ML, and identify the prognostic influential factors. Stroke survivors in intensive rehabilitation were enrolled. Data on demographics, events, clinical, physiotherapy, and psycho-social assessment were collected. An independent ambulation at discharge, using the Functional Ambulation Category scale, was the outcome. After handling missingness using MImp, ML models were optimised, cross-validated, and tested. Interpretability techniques analysed predictor contributions. Pre-MImp, the dataset included 54.1% women, 79.2% ischaemic patients, median age 80.0 (interquartile range: 15.0). Post-MImp, 368 non-ambulatory patients on 10 imputed datasets were used for training, 80 for testing. The random forest (the validation best-performing algorithm) obtained 75.5% aggregated balanced accuracy on the test set. The main predictors included modified Barthel index, Fugl-Meyer assessment/motricity index, short physical performance battery, age, Charlson comorbidity index/cumulative illness rating scale, and trunk control test. This is among the first studies applying ML, together with MImp, to predict ambulation recovery in post-stroke rehabilitation. This pipeline reliably exploits the potential of incomplete datasets for healthcare prognosis, identifying relevant predictors.