AI BASED STROKE DISEASES PREDICTION
Abstract : Since stroke disease often causes death or serious disability, active primary prevention and early detection of prognostic symptoms are very important. Stroke diseases can be divided into ischemic stroke and hemorrhagic stroke, and they should be minimized by emergency treatment such as thrombolytic or coagulant administration by type. First, it is essential to detect in real time the precursor symptoms of stroke, which occur differently for each individual, and to provide professional treatment by a medical institution within the proper treatment window. However, prior studies have focused on developing acute treatment or clinical treatment guidelines after the onset of stroke rather than detecting the prognostic symptoms of stroke. In particular, in recent studies, image analysis such as magnetic resonance imaging (MRI) or computed tomography (CT) has mostly been used to detect and predict prognostic symptoms in stroke patients. Not only are these methodologies difficult to diagnose early in real-time, but they also have limitations in terms of a long test time and a high cost of testing. In this paper, we propose a system that can predict and semantically interpret stroke prognostic symptoms based on machine learning using the multi-modal bio-signals of electrocardiogram (ECG) and photoplethysmography (PPG) measured in real-time for the elderly. To predict stroke disease in real-time while walking, we designed and implemented a stroke disease prediction system with an ensemble structure that combines CNN and LSTM. The proposed system considers the convenience of wearing the bio-signal sensors for the elderly, and the bio-signals were collected at a sampling rate of 1,000Hz per second from the three electrodes of the ECG and the index finger for PPG while walking. According to the experimental results, C4.5 decision tree showed a prediction accuracy of 91.56% while RandomForest showed a prediction accuracy of 97.51% during walking by the elderly. In addition, the CNN-LSTM model using raw data of ECG and PPG showed satisfactory prediction accuracy of 99.15%. As a result, the real-time prediction of the elderly stroke patients simultaneously showed high prediction accuracy and performance.
• The existing RNN is a kind of ANN wherein information persists inside the neural network, and it has been used for image caption generation, automatic translation, etc.
• This method is said to have performed better when compared to the existing algorithms. This particular research is limited to very few types of strokes and cannot be used for any new stroke type in the future.
• The flexibility and ease of use of the random forest algorithm coupled with its consistency in producing good results, even with minimal tuning of the hyper- parameters makes this algorithm valuable in this application. The possibilities of over-fitting are limited by the number of trees existent in the forest.
• We observed that most of the existing features in the EHR dataset are highly correlated to each other, and therefore do not add any additional information to the original feature space.
• As a first important step to gaining trust, tools should comply with existing data protection requirements and be transparent as to how outcomes and recommendations are derived.
• The Res-CNN model solved the performance degradation problem using the residual unit, and it improved the model performance through data expansion.
• However, RNN has the disadvantage of its learning ability gradually decreasing due to the reduction in its slope when the distance between information grows, i.e., when the length of the input sequence increases.
• Understanding the hyperparameters is critical since there are relatively few of them, to begin with. Overfitting is a well-known problem in machine learning, although it occurs seldom with the arbitrary random forest classifier.
• The classification problems are addressed with LR, and the regression problems are addressed using linear regression.
• To identify the better machine learning techniques used to predict stroke, which will also help to understand and resolve the problem in more effective ways.
• It is wise to choose one among them based on the necessity of the individual problem statement.
• To overcome this issue, they used an L1 regularised feature selection algorithm, to prune the features before applying conservative mean features selection for fine-tuning.
• Stroke is a prominent cause of disability in adults and the elderly, resulting in a slew of social and financial issues.
• This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors.
• In this paper, we propose a system that enables the early detection and prediction of stroke disease based on deep learning using EEG raw data, power values, and relative values.
• They proposed a robust machine learning system that can potentially optimise the selection process for endovascular versus medical treatment in the management of acute stroke.
• They proposed a novel automatic feature selection algorithm that selects robust features based on their proposed conservative mean.
• A significant subject of AI in medication is utilized in this project. A machine learning model would take the patients information and propose a bunch of suitable Expectation.
• Due to these advantages, 24-h EEG measurements are considered a useful, low-cost method for monitoring stroke disease with high recurrence rates in daily life.
• CNNs can reduce computation volume through the use of basically shared parameters, and they have the advantage of mitigating overfitting.
• Moreover, CNNs are increasingly being used to research and develop models by extracting the optimal properties to improve classification and prediction performance.
• However, to improve the predictive accuracy and performance of realtime predictive models of stroke disease, analysis and predictive models should be studied by integrating health examination data and CT analysis information in a clinical setting.
• However, they realised that this feature selection algorithm may not work well in other datasets with highly correlated features as it evaluated the performance of each feature individually.
• It was observed that Neural networks performance had more accuracy when compared with other two classification techniques.
• The performance evaluation metrices were accuracy, Area Under RoC Curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value.
|