Objective. Pneumonia is the single largest cause of death in children worldwide due to infectious diseases. According to WHO guidelines, fast breathing and chest indrawing are the key indicators of pneumonia in children requiring antibiotic treatments. The aim of this study was to develop a video based novel method for simultaneous monitoring of respiratory rate and chest indrawing without upsetting babies. Approach. Respiratory signals, corresponding to periodic movements of chest-abdominal walls during breathing, were extracted by analyzing RGB (red, green, blue) components in video frames captured by a smartphone camera. Respiratory rate was then obtained by applying fast Fourier transform on the de-noised respiratory signal. Chest indrawing was detected by analysing relative phases of regional chest-abdominal wall mobility. The performance of the developed algorithm was evaluated on both healthy and pneumonia children. Main results. The proposed method can measure respiratory rate with an overall mean absolute error of 1.8 bpm in the range 18–105 bpm. Phase difference between regional chest wall movements in the chest indrawing (pneumonia) cases was found to be 143 ± 23.9 degrees, which was significantly higher than that in the healthy cases 52.3 ± 32.6 degrees (p < 0.001). Significance. Being non-intrusive and non-subjective, this computer-aided method can be useful in the monitoring for respiratory rate and chest indrawing for the diagnosis of pneumonia and its severity in children.
Transcranial doppler (TCD) ultrasound is a non-invasive imaging technique that can be used for continuous monitoring of blood flow in the brain through the major cerebral arteries by calculating the cerebral blood flow velocity (CBFV). Since the brain requires a consistent supply of blood to function properly and meet its metabolic demand, a change in CBVF can be an indication of neurological diseases. Depending on the severity of the disease, the symptoms may appear immediately or may appear weeks later. For the early detection of neurological diseases, a classification model is proposed in this study, with the ability to distinguish healthy subjects from critically ill subjects. The TCD ultrasound database used in this study contains signals from the middle cerebral artery (MCA) of 6 healthy subjects and 12 subjects with known neurocritical diseases. The classification model works based on the maximal blood flow velocity waveforms extracted from the TCD ultrasound. Since the signal quality of the recorded TCD ultrasound is highly dependent on the operator’s skillset, a noisy and corrupted signal can exist and can add biases to the classifier. Therefore, a deep learning classifier, trained on a curated and clean biomedical signal can reliably detect neurological diseases. For signal classification, this study proposes a Self-organized Operational Neural Network (Self-ONN)-based deep learning model Self-ResAttentioNet18, which achieves classification accuracy of 96.05% with precision, recall, f1 score, and specificity of 96.06%, 96.05%, 96.06%, and 96.09%, respectively. With an area under the ROC curve of 0.99, the model proves its feasibility to confidently classify middle cerebral artery (MCA) waveforms in near real-time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.