Stroke Risk Prediction with Hybrid Deep Transfer Learning Framework

Machine learning to predict stroke risk from routine hospital data: A systematic review

PURPOSE

Stroke remains a leading cause of morbidity and mortality. Despite this, current risk stratification tools such as CHA2DS2-VASc and QRISK3 are of limited accuracy, particularly in those without a diagnosis of atrial-fibrillation. Hence, there is a need for more accurate stroke risk prediction models. Machine-learning (ML) may provide a solution to this by leveraging existing routine hospital databases to build accurate stroke risk prediction models and identify novel risk factors for stroke.

AIMS

In this systematic review we appraise current research using ML to predict stroke risk from routine hospital data. Based on these findings we then highlight common methodological limitations and recommendations for future research.

METHODS

In this review we identify 49 original research (38 in the general population and 11 in AF specific populations) articles from the PUBMED database from January-2013 to December-2024 using ML and routine hospital data to predict the risk of stroke.

RESULTS

ML models were able to accurately predict stroke risk in both AF specific and general populations, with AUCs ranging from 0.64 to 0.99. Where tested, ML also consistently outperformed traditional risk stratification tool, such as CHA2DS2-VASc. ML also appeared useful in identifying several novel risk factors from electrocardiogram, laboratory test and echocardiography data. However, the quality of datasets were often limited, there was a high suspicion of overfitting and models often lacked calibration, external validation and explainability analysis.

CONCLUSION

Whilst ML has shown great potential in stroke prediction and identifying novel risk factors for stroke, improvements in study methodology is required prior to integration of ML into routine healthcare. Future research should adhere to the EQUATOR guidance on prediction models and encourage interdisciplinary collaboration between computer scientists and clinicians. Further prospective RCTs are also required to validate models in the clinical setting and the identify barriers of integrating ML into routine healthcare.

Artificial intelligence in stroke risk assessment and management via retinal imaging

Retinal imaging, used for assessing stroke-related retinal changes, is a non-invasive and cost-effective method that can be enhanced by machine learning and deep learning algorithms, showing promise in early disease detection, severity grading, and prognostic evaluation in stroke patients. This review explores the role of artificial intelligence (AI) in stroke patient care, focusing on retinal imaging integration into clinical workflows. Retinal imaging has revealed several microvascular changes, including a decrease in the central retinal artery diameter and an increase in the central retinal vein diameter, both of which are associated with lacunar stroke and intracranial hemorrhage. Additionally, microvascular changes, such as arteriovenous nicking, increased vessel tortuosity, enhanced arteriolar light reflex, decreased retinal fractals, and thinning of retinal nerve fiber layer are also reported to be associated with higher stroke risk. AI models, such as Xception and EfficientNet, have demonstrated accuracy comparable to traditional stroke risk scoring systems in predicting stroke risk. For stroke diagnosis, models like Inception, ResNet, and VGG, alongside machine learning classifiers, have shown high efficacy in distinguishing stroke patients from healthy individuals using retinal imaging. Moreover, a random forest model effectively distinguished between ischemic and hemorrhagic stroke subtypes based on retinal features, showing superior predictive performance compared to traditional clinical characteristics. Additionally, a support vector machine model has achieved high classification accuracy in assessing pial collateral status. Despite this advancements, challenges such as the lack of standardized protocols for imaging modalities, hesitance in trusting AI-generated predictions, insufficient integration of retinal imaging data with electronic health records, the need for validation across diverse populations, and ethical and regulatory concerns persist. Future efforts must focus on validating AI models across diverse populations, ensuring algorithm transparency, and addressing ethical and regulatory issues to enable broader implementation. Overcoming these barriers will be essential for translating this technology into personalized stroke care and improving patient outcomes.

Patient-specific game-based transfer method for Parkinson's disease severity prediction

Dysphonia is one of the early symptoms of Parkinson's disease (PD). Most existing methods use feature selection methods to find the optimal subset of voice features for all PD patients. Few have considered the heterogeneity between patients, which implies the need to provide specific prediction models for different patients. However, building the specific model faces the challenge of small sample size, which makes it lack generalization ability. Instance transfer is an effective way to solve this problem. Therefore, this paper proposes a patient-specific game-based transfer (PSGT) method for PD severity prediction. First, a selection mechanism is used to select PD patients with similar disease trends to the target patient from the source domain, which reduces the risk of negative transfer. Then, the contribution of the transferred subjects and their instances to the disease estimation of the target subject is fairly evaluated by the Shapley value, which improves the interpretability of the method. Next, the proportion of valid instances in the transferred subjects is determined, and the instances with higher contribution are transferred to further reduce the difference between the transferred instance subset and the target subject. Finally, the selected subset of instances is added to the training set of the target subject, and the extended data is fed into the random forest to improve the performance of the method. Parkinson's telemonitoring dataset is used to evaluate the feasibility and effectiveness. The mean values of mean absolute error, root mean square error, and volatility obtained by predicting motor-UPDRS and total-UPDRS for target patients are 1.59, 1.95, 1.56 and 1.98, 2.54, 1.94, respectively. Experiment results show that the PSGT has better performance in both prediction error and stability over compared methods.

Integrating domain knowledge for biomedical text analysis into deep learning: A survey

The past decade has witnessed an explosion of textual information in the biomedical field. Biomedical texts provide a basis for healthcare delivery, knowledge discovery, and decision-making. Over the same period, deep learning has achieved remarkable performance in biomedical natural language processing, however, its development has been limited by well-annotated datasets and interpretability. To solve this, researchers have considered combining domain knowledge (such as biomedical knowledge graph) with biomedical data, which has become a promising means of introducing more information into biomedical datasets and following evidence-based medicine. This paper comprehensively reviews more than 150 recent literature studies on incorporating domain knowledge into deep learning models to facilitate typical biomedical text analysis tasks, including information extraction, text classification, and text generation. We eventually discuss various challenges and future directions.

Deep Learning in Ischemic Stroke Imaging Analysis: A Comprehensive Review

Ischemic stroke is a cerebrovascular disease with a high morbidity and mortality rate, which poses a serious challenge to human health and life. Meanwhile, the management of ischemic stroke remains highly dependent on manual visual analysis of noncontrast computed tomography (CT) or magnetic resonance imaging (MRI). However, artifacts and noise of the equipment as well as the radiologist experience play a significant role on diagnostic accuracy. To overcome these defects, the number of computer-aided diagnostic (CAD) methods for ischemic stroke is increasing substantially during the past decade. Particularly, deep learning models with massive data learning capabilities are recognized as powerful auxiliary tools for the acute intervention and guiding prognosis of ischemic stroke. To select appropriate interventions, facilitate clinical practice, and improve the clinical outcomes of patients, this review firstly surveys the current state-of-the-art deep learning technology. Then, we summarized the major applications in acute ischemic stroke imaging, particularly in exploring the potential function of stroke diagnosis and multimodal prognostication. Finally, we sketched out the current problems and prospects.