Hemoglobin-albumin-lymphocyte-platelet score and early neurological deterioration in acute ischemic stroke: a single-center retrospective cohort study

 Describing a problem or predictions and 'associations'  DO NOTHING TOWARDS RECOVERY! You're all fired!

Hemoglobin-albumin-lymphocyte-platelet score and early neurological deterioration in acute ischemic stroke: a single-center retrospective cohort study

• 

  Ci Zhang 1,2†

• 

  Wei Zhang 1†

• Y

  Yinyang Zhang 3

• 

  Guosong Xue 1*

• 1. Department of Neurology, Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China

• 2. Department of Neurology, Suqian Hospital of Nanjing Drum Tower Hospital Group, Suqian, Jiangsu, China

Abstract

Purpose: 

To investigate the association between the hemoglobin-albumin-lymphocyte-platelet (HALP) score and early neurological deterioration (END) in individuals with stroke and to develop an exploratory prediction model for END.

Patients and methods: 

Clinical data from 595 patients with acute ischemic stroke (AIS) admitted to the Affiliated Hospital of Xuzhou Medical University from April 2022 to April 2024 were retrospectively analyzed. Patients were randomly divided into a training set and a validation set in a 7:3 ratio. Multivariable logistic regression analysis was utilized in the training data to examine END risk variables and build a corresponding predictive model. Model performance was evaluated using receiver operating characteristic (ROC) curves to assess discrimination and the Hosmer–Lemeshow goodness-of-fit test to evaluate calibration. Clinical decision curve analysis (DCA) was further applied to determine the model’s clinical value. To improve interpretability, the importance of included predictors was assessed using the SHapley Additive exPlanation (SHAP) method.

Results: 

Of the 595 patients, 186 (31.3%) developed early neurological deterioration (END), while the remaining 409 (68.7%) comprised the non-END group. The training cohort consisted of 416 randomly assigned participants. Multivariate logistic regression showed that the large artery atherosclerosis (LAA) subtype, elevated baseline National Institutes of Health Stroke Scale (NIHSS) score, and lower HALP score constituted independent determinants for END development (p < 0.05). In further stepwise-adjusted analyses, the association between HALP and END remained statistically significant after controlling for demographic characteristics, vascular risk factors, and treatment-related variables. A nomogram incorporating HALP score, LAA subtype, and baseline NIHSS score showed moderate discrimination in both the training and validation sets.

Conclusion: 

A lower HALP score was associated with END in patients with AIS. A nomogram incorporating HALP score, LAA subtype, and baseline NIHSS score demonstrated moderate discrimination and may provide useful information for early risk stratification in AIS. This prediction model requires validation in a larger, prospective clinical study.

More at link.

Lesion-informed connectome diffusion modelling for individualized prediction of post-stroke brain atrophy

Predictions don't get you recovered! Where are the protocols that PREVENT BRAIN ATROPHY?  You're all fired for massive incompetence!

 Lesion-informed connectome diffusion modelling for individualized prediction of post-stroke brain atrophy

Gaolang Gong  Beijing Normal University https://orcid.org/0000-0001-5788-022X Jing Yang  Beijing Normal University Yixin Gao  Beijing Normal University Liyuan Yang  Tianjin Normal University Yaya Jiang  Beijing International Studies University Wan Bin  University Hospitals of Genève Şeyma Bayrak  Max Planck Institute for Human Cognitive and Brain Sciences Xinyu Liang  Fudan University Sofie Valk  Max Planck Institute for Human Cognitive and Brain Sciences Maurizio Corbetta  Padova Neuroscience Center (PNC), University of Padova

Posted Date: August 5th, 2026 DOI: https://doi.org/10.21203/rs.3.rs-9954362/v1

Abstract 

 Remote brain atrophy after stroke is clinically consequential but difficult to predict at the individual-patient level. Here we developed a lesion-informed connectome diffusion modelling framework to forecast distributed grey matter volume (GMV) atrophy after focal stroke. Using longitudinal MRI data from two stroke cohorts spanning the hyperacute, subacute and chronic stages, we first showed that post-stroke GMV atrophy was more strongly constrained by structural than by functional connectivity. We then initialized network diffusion models with each patient’s lesion map and found that the resulting simulations captured individualized atrophy patterns at 3 and 12 months post-stroke, whereas model performance was weak within the first week after stroke. The model-derived propagation stage was not a simple proxy for chronological time, but varied with lesion topography, lesion size, structural-network topology and the molecular context of lesioned regions. Finally, lesion-derived features enabled out-of sample prediction of individualized atrophy patterns without requiring longitudinal imaging. These findings establish a computational framework for forecasting remote structural degeneration after stroke from early lesion information, with potential utility for patient stratification and individualized monitoring.

Subtype-specific optimal cut-off values of the Berg Balance Scale for predicting independent walking in inpatient stroke rehabilitation: a multicentre cohort study

 I consider the Berg Balance Scale ABSOLUTELY USELESS! There are NO protocols to address any failure points in it! Testing with no interventions available DOES NOTHING TO GET SURVIVORS RECOVERED! And you haven't figured that out yet?

Subtype-specific optimal cut-off values of the Berg Balance Scale for predicting independent walking in inpatient stroke rehabilitation: a multicentre cohort study

• eong-Soo KimDepartment of Physical Therapy, College of Health Science, Yonsei University, Wonju, Republic of Korea; Department of Mirae Rehabilitation Research, Seoul Rehabilitation Hospital, Seoul, Republic of Koreahttps://orcid.org/0000-0001-9994-9360
• In-Geon HwangDepartment of Mirae Rehabilitation Research, Seoul Rehabilitation Hospital, Seoul, Republic of Koreahttps://orcid.org/0009-0007-6345-1297
• Eu-Jeong KoDepartment of Recovery Rehabilitation Medicine, Seoul Rehabilitation Hospital, Seoul, Republic of Koreahttps://orcid.org/0000-0001-8796-9655

DOI:

https://doi.org/10.2340/jrm.v58.45663

Keywords:

balance, Berg Balance Scale, gait, prediction, rehabilitation, stroke

Abstract

Objective: To determine whether admission Berg Balance Scale score independently predicts independent walking on discharge after adjustment for major confounders, and to derive subtype-specific optimal cut-off values for ischaemic and haemorrhagic stroke.

Design: Multicentre retrospective cohort study.

Subjects/Patients: A total of 565 stroke patients (316 ischaemic, 249 haemorrhagic) admitted to 3 inpatient rehabilitation centres in the Republic of Korea.

Methods: Multivariable logistic regression was used to evaluate the independent predictive value of the Berg Balance Scale. Optimal cut-off values were derived using receiver operating characteristic curve analysis and the Youden index. Bootstrap internal validation, calibration analysis, and decision curve analysis were performed.

Results: Admission Berg Balance Scale was a significant independent predictor of independent walking (adjusted odds ratio 1.053, 95% confidence interval 1.030–1.076). The difference in discriminative ability between the Berg Balance Scale only and multivariable models was not statistically significant (p = 0.097). The overall optimal cut-off was 24 points; subtype-specific cut-offs were 33 for ischaemic and 12 for haemorrhagic stroke.

Conclusion: The Berg Balance Scale has different optimal cut-off values by stroke subtype and, as a standalone assessment, maintains discriminative ability equivalent to a multivariable model, providing clinical evidence for subtype-specific precision rehabilitation strategies.

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability

 Predicting shit like this is useless, Survivors want recovery! DELIVER THAT!

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability

About the Authors

Qian Ye

Roles Data curation, Writing – original draft

‡ QY, GF also contributed equally to this work and share first authorship.

Affiliation Department of Rehabilitation Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China

https://orcid.org/0009-0006-7823-5899

Guilin Fang

Roles Data curation, Formal analysis

‡ QY, GF also contributed equally to this work and share first authorship.

Affiliation Department of Nephrology, Nanjing Jinling Hospital, General Hospital of Eastern Theatre Command, Nanjing, Jiangsu, China

Liping Li

Roles Data curation

Affiliation Department of Rehabilitation Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China

Qinggui Li

Roles Investigation

Affiliation Department of Rehabilitation Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China

Yun Yang

Roles Investigation

Affiliation Department of Rehabilitation Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China

Lingling Liu

Roles Formal analysis, Methodology, Writing – review & editing

* E-mail: 1209674467@qq.com

Affiliation Department of Rehabilitation Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China

https://orcid.org/0000-0003-4392-3676

Competing Interests

The authors have declared that no competing interests exist.

Abstract

Purpose

We aimed to develop a machine learning model to predict activities of daily living (ADL) at discharge in stroke patients and identify key predictors to guide rehabilitation decisions.

Materials and methods

Data of 589 stroke inpatients (2019–2024) were split into good (BI ≥ 60) and poor (BI < 60) ADL groups. Continuous variables were processed using Z-score normalization, followed by preliminary univariate regression screening (P < 0.05) and final feature selection via LASSO regression (lambda.1se = 0.0488). The screened features were used to train and validate ten machine learning algorithms; 30% of the dataset (n = 177) was allocated as an independent test set for model evaluation, and SHAP analysis was performed to interpret the optimal model.

Results

Six of 41 features were retained. Random forest achieved the best performance (AUC = 0.958; accuracy = 0.936; sensitivity = 0.934; specificity = 0.950). SHAP identified the top drivers: admission Barthel Index, standing balance, Brunnstrom stages (upper and lower limb), dressing, and grooming abilities.

Conclusion

The ADL risk prediction model constructed using machine learning, particularly the random forest model, shows excellent predictive performance and clinical interpretability, making it valuable for individualized risk assessment of daily living skills in stroke patients at discharge.

Figures

  

Citation: Ye Q, Fang G, Li L, Li Q, Yang Y, Liu L (2026) Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability. PLoS One 21(7): e0351468. https://doi.org/10.1371/journal.pone.0351468

Editor: Fan Zhang, Longhua Hospital Shanghai University of Traditional Chinese Medicine, CHINA

Received: November 28, 2025; Accepted: May 26, 2026; Published: July 2, 2026

Copyright: © 2026 Ye et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All relevant data for this study are publicly available from the Zenodo repository (https://doi.org/10.5281/zenodo.20629742).

Funding: The author(s) received no specific funding for this work.

Competing interests: The authors have declared that no competing interests exist.

Grip Strength: An Indispensable Biomarker For Older Adults

 My doctor and therapists COMPLETELY FAILED AT RECOVERING MY LEFT HAND! So this really has no basis for me, but my right hand is stronger than ever. 

I'd fire anyone doing prediction, biomarkers, prognistication or assessments. None of them do a damn thing at getting survivors recovered! All they do is turn on anxiety and depression!

Grip Strength: An Indispensable Biomarker For Older Adults

Richard W Bohannon ^1,✉

PMCID: PMC6778477  PMID: 31631989

Abstract

Grip strength has been proposed as a biomarker. Supporting this proposition, evidence is provided herein that shows grip strength is largely consistent as an explanator of concurrent overall strength, upper limb function, bone mineral density, fractures, falls, malnutrition, cognitive impairment, depression, sleep problems, diabetes, multimorbidity, and quality of life. Evidence is also provided for a predictive link between grip strength and all-cause and disease-specific mortality, future function, bone mineral density, fractures, cognition and depression, and problems associated with hospitalization. Consequently, the routine use of grip strength can be recommended as a stand-alone measurement or as a component of a small battery of measurements for identifying older adults at risk of poor health status.

Development and validation of a prediction model for activities of daily living dysfunction among stroke survivors: insights from the CHARLS cohort

 I'd fire anyone doing prediction, biomarkers, prognistication or assessments. None of them do a damn thing getting survivors recovered! All they do is turn on anxiety and depression!

Development and validation of a prediction model for activities of daily living dysfunction among stroke survivors: insights from the CHARLS cohort

• Hongying Ren,
• Wen Wang,
• Li Tao,
• Xiaoshu Song,
• Bin Bai,
• Min Wang &
• Xiaoyan Li 

We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing. Please note there may be errors present which affect the content, and all legal disclaimers apply.

Abstract

Background

Activities of daily living (ADL) dysfunction is prevalent in stroke survivors and places a significant burden on both patients and healthcare systems. Improved identification of individuals with ADL dysfunction may facilitate more targeted rehabilitation strategies.

Methods

The China Health and Retirement Longitudinal Study (CHARLS) provided the data. A training set (n = 906) and a validation set (n = 389) were randomly selected from a total of 1,295 stroke survivors. Least absolute shrinkage and selection operator (LASSO) regression and multivariable logistic regression were used to select predictors and develop a prediction model, which was visualized using a nomogram. SHapley Additive exPlanations (SHAP) were applied for model interpretation. The area under the receiver operating characteristic curve (AUC), calibration analysis, and decision curve analysis (DCA) were used to evaluate the model’s performance.

Results

Ten predictors were identified, including CES-D scores, age, sleep time duration, drinking, lung disease, social contact, falls, hypertension, arthritis, and sex. SHAP analysis identified CES-D scores as the most influential predictors. The model demonstrated acceptable discriminative ability in both the training set (AUC: 0.76, 95% CI: 0.73–0.79) and validation set (AUC: 0.76, 95% CI: 0.72–0.81). Calibration was satisfactory in both the training and validation sets (Hosmer–Lemeshow test, P = 0.16 and P = 0.99, respectively). Positive clinical usefulness was suggested by DCA analysis.

Conclusions

The model demonstrated acceptable predictive performance and may assist in identifying individuals with prevalent ADL dysfunction. Further external validation is required before broader clinical application.

Development and validation of a risk identification model for frailty in stroke survivors: new evidence from CHARLS

 This doesn't get anyone recovered, does it? SO, FUCKING USELESS FOR SURVIVORS, YOU'RE ALL FIRED!

Where are the protocols that prevent frailty? That is the research that is needed, not this useless crapola!

Development and validation of a risk identification model for frailty in stroke survivors: new evidence from CHARLS

• Jiaxian Wang,
• Rick Yiu Cho Kwan,
• Lorna Kwai Ping Suen,
• Simon Ching Lam &
• Ning Liu 

• 4830 Accesses

• 3 Citations

• Explore all metrics

Summary

Background

Stroke survivors with frailty exhibit elevated rates of complications, mortality, disability, and hospital readmission. As frailty represents an early, reversible, and preventable stage of disability, developing a reliable risk identification model is essential. This study aimed to develop and validate a risk model for frailty among stroke survivors using data from the China Health and Retirement Longitudinal Study (CHARLS).

Methods

Data were extracted from the CHARLS database. Stroke survivors were identified and assessed across 30 indicators, including socio-demographic, physical, psychological, cognitive, and social variables. The data were divided by year, with 2013 and 2015 as the development set and 2018 and 2020 as the validation set. Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed for variable selection. Logistic regression models were then developed based on univariate and LASSO-selected predictors. A nomogram was constructed to facilitate risk visualization. Calibration curves and decision curve analysis were used to evaluate model calibration and clinical utility.

Findings

A total of 2,188 stroke survivors from the 2013, 2015, 2018, and 2020 follow-ups were included. Approximately 68% exhibited symptoms of frailty. Significant group differences were found by age, marital status, living alone, hypertension, and self-reported health status (all p < 0.05). Age, poor sleep quality, impaired balance, nervousness/anxiety, and living alone emerged as independent risk factors for frailty. The area under the receiver operating characteristic (ROC) curve for the development and validation sets was 0.833 and 0.838, respectively. Interpretation: The model derived from CHARLS data identified 5 readily assessable predictors (age, sleep quality, balance, anxiety, and living alone), allowing for early screening of frailty without specialized instruments. It demonstrated superior discriminatory performance compared to models from smaller-sample studies, supporting targeted interventions and providing valuable insights for identifying high-risk stroke survivors.

Interpretation

The model derived from CHARLS data identified 5 readily assessable predictors (age, sleep quality, balance, anxiety, and living alone), allowing for early screening of frailty without specialized instruments. It demonstrated superior discriminatory performance compared to models from smaller-sample studies, supporting targeted interventions and providing valuable insights for identifying high-risk stroke survivors.

Comparison of logistic regression and machine learning methods for predicting depression risks among disabled elderly individuals: results from the China Health and Retirement Longitudinal Study

 Predicting depression rather than preventing depression IS THE HEIGHT OF STUPIDITY IN THIS RESEARCH!  You're all fired!

Comparison of logistic regression and machine learning methods for predicting depression risks among disabled elderly individuals: results from the China Health and Retirement Longitudinal Study

• Shanshan Hong,
• Bingqian Lu,
• Shaobing Wang &
• Yan Jiang 

• 5637 Accesses

• 16 Citations

• 5 Altmetric

• 1 Mention

• Explore all metrics

Abstract

Background

Given the accelerated aging population in China, the number of disabled elderly individuals is increasing, and depression is a common mental disorder among older adults. This study aims to establish an effective model for predicting depression risks among disabled elderly individuals.

Methods

The data for this study was obtained from the 2018 China Health and Retirement Longitudinal Study (CHARLS). In this study, disability was defined as a functional impairment in at least one activity of daily living (ADL) or instrumental activity of daily living (IADL). Depressive symptoms were assessed by using the 10-item Center for Epidemiologic Studies Depression Scale (CES-D10). We employed SPSS 27.0 to select independent risk factor variables associated with depression among disabled elderly individuals. Subsequently, a predictive model for depression in this population was constructed using R 4.3.0. The model’s discrimination, calibration, and clinical net benefits were assessed using receiver operating characteristic (ROC) curves, calibration plots, and decision curves.

Results

In this study, 3,107 elderly individuals aged 60 years and older with disabilities were included. Poor self-rated health, pain, absence of caregivers, cognitive impairment, and shorter sleep duration were identified as independent risk factors for depression in disabled elderly individuals. The XGBoost model demonstrated superior performance in the training set, while the logistic regression model outperformed it in the validation set, with AUCs of 0.76 and 0.73, respectively. The calibration curve and Brier score (Brier: 0.20) indicated a good model fit. Moreover, decision curve analysis confirmed the clinical utility of the model.

Conclusions

The predictive model exhibits outstanding predictive efficacy, greatly assisting healthcare professionals and family members in evaluating depression risks among disabled elderly individuals. Consequently, it enables the early identification of elderly individuals at high risk for depression.

Promising Tool to Predict Poststroke Cognitive Impairment

 WHAT FUCKING STUPIDITY; PREDICTION NOT RECOVERY OR PREVENTION! You're all fired for incompetence! I'd have to say you don't even have two neurons to rub together for a spark of intelligence!

Promising Tool to Predict Poststroke Cognitive Impairment

• Madeline Russell, MD, @maddyrussell16

Ferreira J, Pereira G, Alves F, Fonseca L, Moreira G, Azevedo E, Castro P. Microemboli Detection in Acute Ischemic Stroke Could Be an Early Marker of Poor Cognitive Outcome. Stroke. 2026;57:116–124.

Can transcranial Doppler imaging help predict cognitive impairment after stroke? In posing this question, this study sheds light on two growing areas of interest in the field: the use of transcranial Doppler imaging (TCD) and the burden of cognitive impairment in stroke survivors.

Over recent years, there has been increasing use for TCD in the setting of ischemic stroke. In addition to providing real-time information on vessel hemodynamics that cannot be captured on CT or MR angiography, TCDs can also be used to detect microemboli. Microembolic signals have been shown to correlate with stroke recurrence and, more recently, to correlate with cognitive impairment after carotid intervention.

In this study, the study authors theorize that patients with microemboli signals (MES) are more likely to have ischemic events and the eventual development of cognitive impairment. In short, they ask: Can we use TCD findings of microemboli to predict cognitive outcomes after stroke?

The study was conducted at Centro Hospitalar Universitario de Sao Joao in Portugal and was prospective in design. Patients were included if they had acute ischemic stroke, TCDs could be performed within 72 hours, and prestroke mRS was <4. Patients were excluded if they had conditions that would confound TCD findings or cognitive assessment, including severe aphasia, large infarct size, pre-existing cognitive impairment.

Microemboli detection portion of TCDs was performed for a total of 60 minutes per patient, with 30 minutes each for the anterior circulation (bilateral M1 segments) and posterior circulation (bilateral P2 segments). Presence of MES was defined as at least one positive signal, as analyzed by single experience and blinded reader.

Identifying key predictors of post-stroke depression and cognitive impairment in acute stroke survivors

 

You're supposed to solve problems, NOT just predict them you blithering idiots. Hoping comeuppance hits you really hard when you are the 1 in 4 per WHO that has a stroke! 

Why are you incompetently? predicting failure to recover than delivering recovery?

Laziness? Incompetence? Or just don't care? NO leadership? NO strategy? Not my job? Not my Problem!

Had you been thinking at all you would be solving the  5 causes of the neuronal cascade of death in the first week saving hundreds of million to billions of neurons! Thus, preventing cognitive impairment and depression. Or don't you have two functioning neurons to rub together for a spark of intelligence?

Identifying key predictors of post-stroke depression and cognitive impairment in acute stroke survivors

• 

  Zhiwen Yan 1†

• H

  Huan Zhao 1†

• 

  Jianjun Chen 2

• F

  Fang Liu 1

• L

  Lei Gong 1

• 

  Yingli Li 1

• J

  Jie Zhang 1

• M

  Mi Xiao 1

• 

  Jun Mu 1*

• 1. Department of Neurology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China

• 2. Chongqing Key Laboratory of Neurobiology, Institute of Neuroscience, Chongqing Medical University, Chongqing, China

Abstract

Background: 

Post-stroke depression (PSD) and post-stroke cognitive impairment (PSCI) are prevalent complications in aging stroke survivors and are often overlooked due to the lack of early diagnostic indicators, leading to poor prognosis. Identifying reliable predictors is crucial for timely intervention.

Methods: 

This prospective cohort study followed 78 acute stroke survivors for 6 months. A composite neuropsychological outcome—defined as the development of PSD and/or PSCI—was determined using the Diagnostic and Statistical Manual of Mental Disorders-5th Edition (DSM-5) and NINDS-CSN criteria. To account for the limited sample size, multivariable Firth’s penalized logistic regression was employed to identify independent predictors, generating robust odds ratios (ORs) and 95% confidence intervals (CIs). An exploratory classification and regression tree (CART) analysis was also conducted for hypothesis generation.

Results: 

The final cohort comprised 78 acute ischemic stroke survivors with a median age of 62 years (IQR 51–71). Among these participants, 26.0% were women, and the median admission score on the National Institutes of Health Stroke Scale (NIHSS) was 3 (IQR 1–5). Within 6 months, 56 patients (71.8%) developed the composite outcome (13 experienced PSCI alone, 24 had PSD alone, and 19 had both conditions). A multivariable analysis revealed that right hemisphere lesions (OR = 9.019, 95% CI: 1.329–61.213, p = 0.016), greater baseline emotional distress (higher 9-item Patient Health Questionnaire (PHQ-9) scores; OR = 5.157, 95% CI: 1.835–14.494, p < 0.001), and pre-existing cognitive vulnerability (lower Mini–Mental State Examination (MMSE) scores; OR = 0.714, 95% CI: 0.517–0.984, p = 0.023) were independent predictors of poor neuropsychological outcomes. Advanced age (p = 0.094) and elevated urea levels (p = 0.095) showed only marginal trends. Exploratory CART modeling highlighted the hierarchical interaction of these baseline clinical scores for risk stratification.

Conclusion: 

Right hemisphere lesions, early emotional distress, and baseline cognitive vulnerability independently predicted a high risk of composite neuropsychological impairment at 6 months post-stroke. Rather than serving merely as novel biomarkers, high baseline PHQ-9 scores and low MMSE scores reflected the persistence of early distress and poor cognitive reserve, respectively. These highly accessible clinical parameters facilitate early risk stratification, emphasizing the absolute need for immediate psychological triage and integrated, long-term cognitive-emotional monitoring.