Development and validation of a machine learning model for predicting stroke-associated pneumonia in older patients with acute ischemic stroke

 What fucking stupidity; predicting pneumonia rather that creating a protocol to prevent it! You're all fired!

You've known about this problem for a long time. SOLVE IT! 

Just maybe this vaccine!

Pneumonia Vaccine (3 posts to July 2020)

• 11% Stroke-associated pneumonia (17 posts to October 2020)

Development and validation of a machine learning model for predicting stroke-associated pneumonia in older patients with acute ischemic stroke

• W

  Wen-Jie Chu 1

• S

  Si-Ran Zhang 2*

• Q

  Qi-Lun Lai 2

• J

  Jing-Ying Yu 2

• Y

  Yi-Qian Xu 2

• 1. Department of Hospital Infections, Zhejiang Hospital, Hangzhou, China

• 2. Department of Neurology, Zhejiang Hospital, Hangzhou, China

Abstract

Objective: 

Stroke-associated pneumonia (SAP) is a common and serious complication in older patients with acute ischemic stroke (AIS). However, early identification of high-risk patients remains challenging. This study aimed to develop and validate an interpretable machine learning model for predicting SAP risk in older AIS patients.

Methods: 

This retrospective study included 1,011 eligible patients (aged ≥65 years) with AIS who were consecutively admitted to Zhejiang Hospital in China from September 1, 2018, to December 31, 2023. A total of 1,011 patients were randomly divided into training and testing sets (7:3 ratio). Demographics, comorbidities, laboratory test results, and admission assessments were collected to evaluate the risk of SAP. The synthetic minority oversampling technique (SMOTE) was used to address the imbalanced training data. The Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to filter the predictive features. Eight machine learning models, including Logistic Regression (LR), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Gradient Boosting Decision Tree (GBDT), Multi-layer Perceptron (MLP), and Random Forest (RF), were applied to identify the best prediction model. The optimal model was interpreted using the SHapley Additive exPlanations (SHAP).

Results: 

SAP incidence was 18.79%. LASSO identified 12 predictive features. The SVM demonstrated acceptable and stable predictive performance, achieving an accuracy of 0.773, sensitivity of 0.667, specificity of 0.798, F1 score of 0.524, Brier score of 0.156, and AUC of 0.794 (95% CI: 0.748–0.839) in the test set. SHAP analysis identified key factors influencing model predictions. An online platform was developed for clinical use.

Conclusion: 

This study demonstrates that an interpretable SVM-based machine learning model can effectively predict the risk of SAP in older patients with AIS using routinely available clinical and laboratory data. SHAP analysis further improved the model’s clinical interpretability by elucidating feature contributions. Our online prediction platform could serve as a promising tool for identifying high-risk older patients and facilitating the early prophylactic management of SAP.

Timing of nasogastric tube placement after endovascular thrombectomy and risk of stroke-associated pneumonia: a retrospective cohort study

 So nothing on preventing pneumonia via vaccine! Can't anyone in stroke actually think that stroke problems should be solved; NOT JUST DESCRIBED?

You've known about this problem for a long time. SOLVE IT! 

Just maybe this vaccine!

Pneumonia Vaccine (3 posts to July 2020)

• 11% Stroke-associated pneumonia (17 posts to October 2020)

Timing of nasogastric tube placement after endovascular thrombectomy and risk of stroke-associated pneumonia: a retrospective cohort study

• X

  Xiao-Fei Hu 1

• 

  Bai-Ling Pan 2

• 

  Li Han 1*

• 1. Department of Neurology, Taizhou Hospital of Zhejiang Province, Affiliated to Wenzhou Medical University, Linhai, Zhejiang, China

• 2. Department of Endocrinology, Taizhou Hospital of Zhejiang Province, Affiliated to Wenzhou Medical University, Linhai, Zhejiang, China

Abstract

Background: 

Stroke-associated pneumonia (SAP) is a common complication following endovascular thrombectomy (EVT), yet the impact of nasogastric tube (NGT) placement timing on SAP risk has not been examined.

Methods: 

We conducted a single-center retrospective cohort study of 331 patients who underwent successful EVT and received NGT placement between June 2022 and May 2025. The primary exposure was time from reperfusion to NGT placement. Multivariable logistic regression and restricted cubic splines were used to examine the association between NGT timing and SAP, adjusting for age, sex, admission NIHSS score, serum albumin, hypertension, atrial fibrillation, and diabetes mellitus.

Results: 

Stroke-associated pneumonia occurred in 227 patients (68.6%), reflecting the cohort’s restriction to EVT patients requiring NGT placement, a high-aspiration-risk subgroup. Each 12-h delay in NGT placement was associated with a 33% increase in the adjusted odds of SAP (aOR 1.33, 95% CI 1.06–1.68, p = 0.015). Patients with NGT placement more than 8 h after reperfusion had significantly higher odds of SAP than those with earlier placement (aOR 1.73, 95% CI 1.04–2.90, p = 0.036). Restricted cubic spline analysis demonstrated a monotonically increasing dose–response relationship (P overall = 0.073). The association appeared stronger in patients without atrial fibrillation (aOR 2.38) than in those with atrial fibrillation (aOR 1.08).

Conclusion: 

In EVT-treated patients requiring NGT placement, longer time to NGT insertion was associated with higher SAP risk after adjustment for measured covariates. These findings suggest that NGT placement timing may be a potentially modifiable factor in post-EVT care, and provide a hypothesis-generating basis for prospective evaluation.

Predicting pneumonia algorithm in stroke patients

You don't belong in stroke if you are doing predictions rather that delivering EXACT PROTOCOLS FOR RECOVERY!  

Didn't your competent? doctor already have protocols to prevent pneumonia? NO? So COMPLETELY FUCKING INCOMPETENT THEN?

For pneumonia maybe you want the vaccine if your doctor is competent enough to know about it.

You've known about this problem for a long time. SOLVE IT! 

Just maybe this vaccine!

• Pneumonia Vaccine (3 posts to July 2020)

 

• 11% Stroke-associated pneumonia (2 posts to October 2020)

 Predicting pneumonia algorithm in stroke patients

Jong Weon Lee^1,2Hyun-Joung Lee³Hyeon Ju Jang²Yeseul Yun⁴Deog Young Kim^1,2*

• ¹Department of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
• ²Research Institute of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
• ³Department of Speech-Language Pathology, Wonkwang Digital University, Seoul, Republic of Korea
• ⁴Research Institute for Future Medicine, Samsung Medical Center, Seoul, Republic of Korea

Background: Pneumonia is a serious complication of stroke, particularly in patients with dysphagia during inpatient rehabilitation, as it significantly increases morbidity, prolongs hospital stays, and impairs functional recovery. Early identification of patients at risk for pneumonia is crucial for improving outcomes and reducing post-stroke complications. This study aimed to develop a comprehensive algorithm for predicting post-stroke pneumonia risk by integrating clinical assessments of defense mechanisms against pneumonia.

Methods: This case-control study enrolled stroke patients at a single tertiary hospital and followed them for 4 weeks to assess pneumonia incidence. A total of 812 patients aged 20 years or older with ischemic or hemorrhagic stroke and signs of dysphagia were screened. Of these, 484 were excluded based on the following criteria: inability to maintain a sitting posture with back support, dyspnea requiring oxygen supplementation, concurrent aspiration pneumonia before enrollment, infectious diseases requiring isolation, and refusal to participate. Final cohort of 328 patients was enrolled. All participants underwent evaluations, including a videofluoroscopic swallowing study (VFSS), a modified cough reflex test (mCRT), and assessments of nutritional status (serum albumin) and cognitive function [Mini-Mental State Examination (MMSE)]. Pneumonia was diagnosed using the Mann criteria, and predictive factors were analyzed using univariate logistic regression and classification and regression tree (CART) analysis.

Results: Among 328 participants, 28 (8.5%) developed pneumonia. Significant predictors included tracheostomy status (OR 9.34), VFSS-confirmed aspiration (OR 8.21) and bilateral stroke lesions (OR 5.91). CART analysis revealed tracheostomy, VFSS-confirmed aspiration, cough frequency, albumin levels, and MMSE scores as key predictors. The algorithm demonstrated a predictive accuracy of 92.7% with an AUC of 0.89 (95% CI: 0.82–0.95).

Conclusion: This study developed a highly accurate predictive algorithm for post-stroke pneumonia, emphasizing the role of defense mechanisms against pneumonia. Implementing this algorithm in clinical practice could enable early preventive measures, reduce pneumonia incidence, and improve patient outcomes.

Elevated systemic immune-inflammation index is associated with stroke-associated pneumonia in acute ischemic stroke: a retrospective cohort study

Fuck, we don't need predictions of pneumonia you blithering idiots, solve the problem of preventing that pneumonia in the first place.  I'd have you all fired.

You've known about this problem for a long time. GET THERE! 

Just maybe this vaccine!

Pneumonia Vaccine (3 posts to July 2020)

11% Stroke-associated pneumonia (2 posts to October 2020)

 Elevated systemic immune-inflammation index is associated with stroke-associated pneumonia in acute ischemic stroke: a retrospective cohort study

Tingting Duan¹Ming Yang¹Yiming Zhang^2†Chunyan Zhu^2†Zichen Rao^2*†

• ¹Department of Neurology, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, Zhejiang, China
• ²Department of Endocrinology, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, Zhejiang, China

Stroke-associated pneumonia (SAP) is a frequent complication of acute ischemic stroke (AIS) that contributes to poor clinical outcomes. The systemic immune-inflammation index (SII), derived from neutrophil, lymphocyte, and platelet counts, may reflect post-stroke immune imbalance, but its role in predicting SAP remains unclear. In this retrospective study, we analyzed 1,767 AIS patients and evaluated the association between log₂-transformed SII and the occurrence of SAP using multivariable logistic regression, generalized additive models, and two-piecewise regression. SAP developed in 21.3% of patients during hospitalization. Higher SII levels were independently associated with increased SAP risk after adjustment for age, sex, vascular risk factors, comorbidities, baseline National Institutes of Health Stroke Scale (NIHSS) score, and dysphagia assessed by Kubota Water Drinking Test (KWDT). Patients in the highest SII quartile had a significantly greater likelihood of developing SAP compared to those in the lowest quartile (adjusted odds ratio = 2.03, 95% confidence interval: 1.21–3.38, p = 0.0069). A non-linear, threshold-dependent relationship was identified, with SAP risk increasing substantially beyond log₂-SII ≈ 8.5. Receiver operating characteristic (ROC) analysis demonstrated moderate predictive performance of SII for SAP (area under the curve (AUC) = 0.726), while C-reactive protein (CRP) showed superior discrimination (AUC = 0.826 p < 0.0001). Supplementary sensitivity analyses, including a fully adjusted model without NIHSS and KWDT and an alternative model replacing these with the A2DS2 score (Age, Atrial fibrillation, Dysphagia, Sex, Stroke Severity), showed consistent results, supporting the robustness of our findings. These findings suggest that SII may serve as a cost-effective and accessible biomarker to aid early identification of high-risk AIS patients.

Introduction

Stroke remains one of the leading causes of mortality and long-term disability worldwide, with acute ischemic stroke (AIS) accounting for approximately 80% of all cases (1). Despite advances in acute stroke management, complications during hospitalization, particularly stroke-associated pneumonia (SAP), continue to pose significant challenges (2). SAP occurs in 10 to 30% of AIS patients and is closely associated with prolonged hospital stays, increased healthcare costs, and worse functional outcomes, including higher mortality rates (3). Early identification of high-risk patients is essential to guide preventative interventions and improve prognosis (4).

Emerging evidence suggests that systemic inflammation plays a pivotal role in the development of SAP by disrupting immune homeostasis and enhancing susceptibility to pulmonary infections following AIS (5). Conventional inflammatory biomarkers such as CRP, white blood cell (WBC) count, and neutrophil-to-lymphocyte ratio (NLR) have been widely used to assess systemic inflammation; however, their predictive accuracy for SAP remains suboptimal (6). The systemic immune-inflammation index (SII) calculated from platelet count, neutrophil count, and lymphocyte count, is a novel composite marker that reflects the balance between pro-inflammatory and immune-regulatory responses (7). Recent studies have demonstrated its prognostic value in various cardiovascular and oncologic conditions, but its predictive utility in SAP remains underexplored (8). In this study, we focused on SII as a comprehensive marker of immune-inflammatory balance, and compared it with CRP, a widely used reference biomarker in stroke research, to assess whether SII provides additional or complementary prognostic value beyond CRP. Moreover, existing studies evaluating inflammatory markers in SAP have primarily focused on linear relationships, potentially overlooking complex non-linear and threshold effects (9). For example, Kuang et al. (10) examined the association between SII and SAP risk in a smaller, mixed cohort of acute stroke patients and reported a linear relationship, without investigating potential non-linear patterns or thresholds. Whether elevated SII levels exhibit a dose–response relationship or specific thresholds beyond which SAP risk dramatically increases has not been fully elucidated. Addressing these knowledge gaps is critical for refining clinical risk stratification and informing targeted preventative strategies (11).

We posited that early elevation of the SII, as a marker of post-stroke immune disequilibrium, would identify AIS patients at independently higher risk of SAP, and that the exposure–response might be non-linear with a clinically relevant threshold. To test this hypothesis, we investigated the association between SII and the development of SAP in patients with AIS by analyzing a large, retrospective cohort. Specifically, we examined the predictive value of log₂-transformed SII, explored potential non-linear and threshold effects through advanced modeling approaches, and compared the diagnostic performance of SII with established inflammatory biomarkers such as CRP.

More at link.

Development and validation of a machine learning-based risk prediction model for stroke-associated pneumonia in older adult hemorrhagic stroke

Predictions aren't needed; PREVENTION IS! GET THERE! I'd have you all fired!

You've known about this problem for a long time. SOLVE IT! 

Just maybe this vaccine!

• Pneumonia Vaccine (3 posts to July 2020)

 

• 11% Stroke-associated pneumonia (2 posts to October 2020)

Is everyone in stroke so blitheringly stupid that they don't realize that you solve and prevent problems? Rather than lazily describing them? Serious question!

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? Your patients need an explanation of why you aren't trying to get survivors recovered.

Why isn't your 'professional' solving stroke?

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

 Development and validation of a machine learning-based risk prediction model for stroke-associated pneumonia in older adult hemorrhagic stroke

Yi Cao^1,2†Haipeng Deng^1†Shaoyun Liu^1†Xi Zeng¹Yangyang Gou²Weiting Zhang²Yixinyuan Li²Hua Yang^1*Min Peng^3*

• ¹Department of Neurosurgery, Affiliated Hospital of Guizhou Medical University, Guiyang, China
• ²School of Nursing, Guizhou Medical University, Guiyang, China
• ³Department of Nursing Quality Management, Affiliated Hospital of Guizhou Medical University, Guiyang, China

Objective: To develop and validate a machine learning (ML)-based model for predicting stroke-associated pneumonia (SAP) risk in older adult hemorrhagic stroke patients.

Methods: A retrospective collection of older adult hemorrhagic stroke patients from three tertiary hospitals in Guiyang, Guizhou Province (January 2019–December 2022) formed the modeling cohort, randomly split into training and internal validation sets (7:3 ratio). External validation utilized retrospective data from January–December 2023. After univariate and multivariate regression analyses, four ML models (Logistic Regression, XGBoost, Naive Bayes, and SVM) were constructed. Receiver operating characteristic (ROC) curves and area under the curve (AUC) were calculated for training and internal validation sets. Model performance was compared using Delong's test or Bootstrap test, while sensitivity, specificity, accuracy, precision, recall, and F1-score evaluated predictive efficacy. Calibration curves assessed model calibration. The optimal model underwent external validation using ROC and calibration curves.

Results: A total of 788 older adult hemorrhagic stroke patients were enrolled, divided into a training set (n = 462), an internal validation set (n = 196), and an external validation set (n = 130). The incidence of SAP in older adult patients with hemorrhagic stroke was 46.7% (368/788). Advanced age [OR = 1.064, 95% CI (1.024, 1.104)], smoking[OR = 2.488, 95% CI (1.460, 4.24)], low GCS score [OR = 0.675, 95% CI (0.553, 0.825)], low Braden score [OR = 0.741, 95% CI (0.640, 0.858)], and nasogastric tube [OR = 1.761, 95% CI (1.048, 2.960)] were identified as risk factors for SAP. Among the four machine learning algorithms evaluated [XGBoost, Logistic Regression (LR), Support Vector Machine (SVM), and Naive Bayes], the LR model demonstrated robust and consistent performance in predicting SAP among older adult patients with hemorrhagic stroke across multiple evaluation metrics. Furthermore, the model exhibited stable generalizability within the external validation cohort. Based on these findings, the LR framework was subsequently selected for external validation, accompanied by a nomogram visualization. The model achieved AUC values of 0.883 (training), 0.855 (internal validation), and 0.882 (external validation). The Hosmer-Lemeshow (H-L) test indicates that the calibration of the model is satisfactory in all three datasets, with P-values of 0.381, 0.142, and 0.066 respectively.

Conclusions: This study constructed and validated a risk prediction model for SAP in older adult patients with hemorrhagic stroke based on multi-center data. The results indicated that among the four machine learning algorithms (XGBoost, LR, SVM, and Naive Bayes), the LR model demonstrated the best and most stable predictive performance. Age, smoking, low GCS score, low Braden score, and nasogastric tube were identified as predictive factors for SAP in these patients. These indicators are easily obtainable in clinical practice and facilitate rapid bedside assessment. Through internal and external validation, the model was proven to have good generalization ability, and a nomogram was ultimately drawn to provide an objective and operational risk assessment tool for clinical nursing practice. It helps in the early identification of high-risk patients and guides targeted interventions, thereby reducing the incidence of SAP and improving patient prognosis.

1 Introduction

Stroke-associated pneumonia (SAP) refers to newly acquired pneumonia in non-mechanically ventilated patients within 7 days of stroke onset (1). First proposed by German scholar Hilker in 2003 (2), subsequent studies report its incidence rate ranging from 6.5 to 58.4%, with risk factors including advanced age, male sex, smoking, dysphagia, hyperglycemia, and lower Glasgow Coma Scale (GCS) scores (3–8). Compared to non-SAP patients, SAP significantly worsens prognosis, leading to increased disability and mortality rates, prolonged hospitalization, and elevated healthcare costs (3, 5, 8–10). Meanwhile, with the intensification of population aging in China, the nursing needs of older adult patients with hemorrhagic stroke are becoming increasingly prominent (11). Current nursing strategies have deficiencies in aspects such as infection prevention, individualized intervention, and uneven distribution of medical resources. Especially in the context of limited medical resources, there is a lack of validated tools to prioritize the identification of high-risk patients and optimize nursing priorities, which restricts the prevention and control of SAP.

Machine Learning (ML) a subset of artificial intelligence (AI), enables in-depth exploration and analysis of extensive datasets, offering novel methodologies and research frameworks for precise prediction. Its applications span diverse fields, particularly in medicine, where ML facilitates the development of automated tools for clinical decision-making based on multidimensional medical data (10, 12). Risk prediction models, initially applied in cardiothoracic surgery (13, 14), leverage patient-specific risk factors and ML algorithms to forecast disease progression, therapeutic responses, and outcomes. Recent studies have utilized ML to integrate vital signs, epidemiological data, and laboratory/imaging findings for diagnostic or prognostic purposes. However, there are currently few risk prediction models for SAP in older adult patients with hemorrhagic stroke based on ML algorithms. The absence of such models not only limits the clinical early-warning ability but also hinders the precise allocation of nursing resources. This need is particularly urgent considering the characteristics of older adult patients with multiple underlying diseases and a short window period for nursing intervention. In this study, the prediction of SAP in older adult patients with hemorrhagic stroke was defined as a binary classification problem. Therefore, four widely used ML algorithms for solving classification problems (Logistic regression, Naive Bayes, Support Vector Machine, and eXtreme Gradient Boosting algorithm) were selected to construct the risk prediction model. The effectiveness of the model was evaluated through internal and external validation, aiming to provide references for clinical nursing practice, prevention, and control.

More at link

Reducing stroke-associated pneumonia through pulmonary rehabilitation in moderate-to-severe acute ischemic stroke

 

Fuck, we don't need pulmonary rehabilitation you blithering idiots, solve the problem of preventing that pneumonia in the first place.  I'd have you all fired.

You've known about this problem for a long time. GET THERE! 

Just maybe this vaccine!

• Pneumonia Vaccine (3 posts to July 2020)

 

• 11% Stroke-associated pneumonia (2 posts to October 2020)

Reducing stroke-associated pneumonia through pulmonary rehabilitation in moderate-to-severe acute ischemic stroke

• QingSha Zhang,
• HongKun Liu,
• Jie Sun &
• HongGe Shi 

European Journal of Medical Research volume 30, Article number: 208 (2025) Cite this article

• 50 Accesses

• Metrics details

Abstract

Objectives

This study investigated the effect of a comprehensive pulmonary rehabilitation (CPR) program on stroke-associated pneumonia (SAP) in patients with moderate-to-severe acute ischemic stroke (AIS) after thrombolysis.

Methods

This study was a prospective randomized controlled intervention study. Eighty patients with moderate-to-severe AIS were divided into the conventional rehabilitation (CR) and CPR groups. Demographic and general clinical data were collected. Patients were evaluated by the Fatigue Severity Scale (FSS), Fugl–Meyer Assessment (FMA), and Fugl–Meyer balance (FMB). The incidence of pneumonia in the acute phase and the treatment efficacy were compared.

Results

FSS scores at T1 and T2 (2 weeks and 4 weeks after treatment), FMA scores, and FMB scores were higher than those at T0 (first day of admission). FSS scores in the CPR group were lower, while FMA and FMB scores were higher than those in the CR group at T1 and T2. The incidence of pneumonia was 10.00% in the CPR group and 25.00% in the CR group. The rehabilitation effective rate was 92.50% in the CPR group and 80.00% in the CR group, but the proportion of rehabilitation effect in the CPR group was higher than that in the CR group.

Conclusions

CPR program improves fatigue and motor function and reduces the occurrence of SAP in AIS patients.(Preventing SAP would make much more sense, why the hell aren't you working on that? Your mentors and senior researchers are that fucking incompetent?)

Introduction

Stroke is a clinical syndrome in which there is a sudden loss of brain function, either focal or global, that lasts for more than 24 h or results in death [1]. Stroke is now the second leading cause of death, characterized by high morbidity, mortality, and disability [2]. The incidence of acute cerebral infarction (ACI) is about 60–70% of all stroke patients [3]. Intravenous thrombolysis has become a common treatment for ACI [4,5,6]. After intravenous thrombolysis, rehabilitation aids patients in slowly recovering the functions of the affected limbs, such as muscle strength, coordination, and balance. Moreover, systematic rehabilitation can reduce the incidence of disability after stroke [7]. Pulmonary rehabilitation has been increasingly recognized and applied by healthcare professionals, since it was introduced in 1994. In 2016, the American Stroke Association recommended early intervention for post-stroke patients through pulmonary rehabilitation exercises, such as vibration expectoration, active exercises, and respiratory muscle training [8]. However, there are few studies that apply comprehensive pulmonary rehabilitation to patients with moderate-to-severe acute ischemic stroke (AIS).

Post-stroke fatigue (PSF) is the subjective feeling of extreme fatigue due to lack of mental and/or physical energy, which appears suddenly after a stroke event [9]. PSF is a common and long-lasting sequela of stroke, which affects the patient's recovery and increases disability and mortality rates [10,11,12]. Fatigue not only manifests itself in physical weakness, but also in mental lethargy, making it difficult for patients to adhere to the necessary rehabilitation treatments, which in turn hinders the process of neurological recovery [13]. Physical activity after stroke improves physical fitness and stimulates cortical excitability, which may help reduce fatigue [13]. Meanwhile, motor dysfunction is also a key problem for patients with moderate-to-severe AIS. Due to the damage of motor neurons caused by cerebral ischemia, patients often suffer from paralysis of limbs, loss of muscle strength, and poor motor coordination. This not only restricts the patient's ability to move independently, making it impossible for the patient to perform basic life actions, but also may lead to a series of complications, such as muscle atrophy, joint contracture, etc., which will further aggravate disability of the patient. In addition, stroke-associated pneumonia (SAP) is a common cause of death in clinical practice, and the incidence of SAP ranges from 3.0 to 56.6% [14]. Patients with moderate-to-severe AIS are highly susceptible to aspiration due to swallowing dysfunction, weakened cough reflex, and impaired consciousness, which can lead to lung infection [15]. Once SAP occurs, the patient's hospitalization time is prolonged, medical costs increase, and the prognosis becomes significantly worse [16]. The focus on preventing and controlling SAP in stroke treatment has increased, with research and guidelines worldwide showing that pulmonary rehabilitation can improve pulmonary function and daily activities in patients with stroke [17].

In recent years, comprehensive pulmonary rehabilitation (CPR) programs have gradually gained attention and been applied in clinical practice. Pulmonary rehabilitation aims to improve respiratory function, exercise capacity, and overall health through a series of planned and targeted interventions, including respiratory training, physical therapy, exercise training, nutritional support, and psychological counseling [18]. For patients with moderate-to-severe AIS, the implementation of a CPR program after thrombolysis is potentially important. On the one hand, respiratory training and physical therapy can improve patients' respiratory function, enhance the ability to cough up sputum, and reduce the risk of aspiration, thereby reducing the incidence of SAP [19]. On the other hand, systematic exercise training can promote the recovery of patients' motor function, improve muscle strength and motor coordination, reduce fatigue symptoms, and enhance patients' daily self-care ability and quality of life [20].

Although some studies have explored the application of pulmonary rehabilitation in stroke patients, there are still relatively few studies on the effects of CPR program on fatigue, motor function, and the incidence of SAP after thrombolysis in patients with moderate-to-severe AIS. It is of great theoretical and practical significance to conduct such studies to clarify the role and value of CPR programs in the treatment of patients with moderate-to-severe AIS to optimize the clinical treatment strategy and improve the rehabilitation effect and quality of life of patients. The aim of this study was to investigate the effects of a post-thrombolysis CPR program on fatigue, motor function, and the incidence of SAP in patients with moderate-to-severe AIS through rigorous clinical observation and data analysis, and to provide a reference for the implementation of integrated pulmonary rehabilitation in clinical practice.

More at link.