A5068100344- Phonocardiography and Auscultation Techniques
- EEG and Brain-Computer Interfaces
- Anomaly Detection Techniques and Applications
- Functional Brain Connectivity Studies
- Respiratory and Cough-Related Research
- Neural dynamics and brain function
- Machine Learning and Data Classification
- Imbalanced Data Classification Techniques
- COVID-19 diagnosis using AI
- Fault Detection and Control Systems
- Machine Learning and Algorithms
- Clinical Reasoning and Diagnostic Skills
- Music and Audio Processing
École Polytechnique Fédérale de Lausanne
2021-2023
Johns Hopkins University
2023
The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize automate evaluation. We used 35.9 hours audio from 572 pediatric outpatients develop DeepBreath : a deep learning model identifying audible signatures acute respiratory illness in children. It comprises convolutional neural network followed by logistic regression classifier, aggregating estimates recordings eight thoracic sites...
Lung auscultation is fundamental to the clinical diagnosis of respiratory disease. However, a subjective practice and interpretations vary widely between users. The digitization acquisition interpretation particularly promising strategy for diagnosing monitoring infectious diseases such as Coronavirus-19 disease (COVID-19) where automated analyses could help decentralise care better inform decision-making in telemedicine. This protocol describes standardised collection lung auscultations...
Deep learning methods are at the forefront of automated epileptic seizure detection and onset zone localization using scalp-EEG. However, performance deep rely heavily on quality annotated training datasets. Scalp EEG is susceptible to high noise levels, which in turn leads imprecise annotations timing characteristics. This label presents a significant challenge model generalization. In this paper, we introduce novel statistical framework that informs ambiguity, thereby enhancing overall...