Obstructive sleep apnea (OSA) is a sleep condition characterized by the partial or full interruption of breathing while a person is asleep. Several techniques have been suggested for the automated recognition of OSA events. However, there has been little research on the prediction of these events using prior data, which is valuable for the advancement of medical devices that observe respiration while sleeping. In this research, we have proposed four techniques for forecasting OSA events by using a fusion of time-frequency representation (TFR) of electrocardiogram (ECG) signals and deep neural networks (Gabor-CNN, Wavelet-CNN, Wigner-CNN, and STFT-CNN). Overall, these techniques are called Predict-OSA. These techniques use raw single-lead ECG data collected at a sampling rate of 100 Hz without the inclusion of any manually extracted features. By analyzing the preceding 120 seconds of data, we can predict the occurrences of OSA (apnea) and regular breathing episodes in a lead time of 60 seconds. The findings obtained from analyzing a dataset consisting of more than 34270 60-second segments from 70 ECG recordings indicate that all four models had a high level of accuracy, surpassing 83%. The Wigner-CNN model demonstrated superior performance, achieving accuracy, specificity, and sensitivity of 89.75%, 91.89%, and 86.25%, respectively. The findings indicate that OSA occurrences may be reliably anticipated by analyzing single-lead ECG signals, which creates possibilities for designing devices that can prevent the incidence of OSA events from occurring during sleep. Our algorithms may be implemented in devices with limited storage space due to their ability to handle low sampling rates. This makes them well-suited for use in at-home environments.

Background: Freezing of gait (FoG) is a common and debilitating symptom in individuals with advanced Parkinson’s disease (PD), significantly increasing the risk of falls. Wearable devices have facilitated the detection of FoG and falls, but early prediction remains underexplored. This study investigates the use of multimodal sensor fusion and deep learning for the early prediction of FoG events in PD patients. Research Question: Can a multimodal sensor fusion deep learning model accurately predict FoG events well before time in Parkinson’s disease patients, and how robust is the model to noise and inter-subject variability? Methods: The proposed study utilized Inertial Measurement Unit (IMU), Electromyography (EMG), and Electroencephalography (EEG) signals from PD patients to develop and evaluate deep learning models. The CNN+LSTM architecture was employed and compared with other classifiers. Stratified ten-fold cross-validation was used to assess model accuracy. The robustness of IMU+EMG and IMU+EMG+EEG configurations to noise was tested, and inter-subject performance evaluation was conducted. Pre-FOG detection capabilities were also analyzed to emphasize the importance of temporal dynamics in the multimodal approach. Results: The CNN+LSTM model achieved a high accuracy of 94.45% in predicting FoG events. The IMU+EMG and IMU+EMG+EEG configurations demonstrated robust performance across inter-subject evaluations. The models showed resilience to noise, with the CNN+LSTM and IMU+EMG+EEG configurations maintaining high accuracy. Pre-FOG detection achieved 94.20% accuracy, highlighting the model’s effectiveness in capturing temporal dynamics. Significance: The CNN+LSTM model, particularly in the IMU+EMG+EEG configuration, proves to be a robust and accurate predictor of FoG events in PD patients. The study’s findings underscore the potential clinical impact of multimodal sensor fusion and deep learning in reducing false positives and negatives and enhancing precision, sensitivity, and specificity. These insights are crucial for deploying reliable FoG prediction systems in real-world settings and advancing PD management. Future research should explore additional sensor modalities, transferability to different PD cohorts, longitudinal data, and real-time deployment in clinical environments.

In the proposed research work; the COVID-19 is detected using transfer learning from CT scan images decomposed to three-level using stationary wavelet. A three-phase detection model is proposed to improve the detection accuracy and the procedures are as follows; Phase1- data augmentation using stationary wavelets, Phase2- COVID-19 detection using pre-trained CNN model and Phase3- abnormality localization in CT scan images. This work has considered the well known pre-trained architectures, such as ResNet18, ResNet50, ResNet101, and SqueezeNet for the experimental evaluation. In this work, 70% of images are considered to train the network and 30% images are considered to validate the network. The performance of the considered architectures is evaluated by computing the common performance measures.