Adolescent Asthma Monitoring: A Preliminary Study of Audio and Spirometry Modalities.

Asthma patients' sleep quality is correlated with how well their asthma symptoms are controlled. In this paper, deep learning techniques are explored to improve forecasting of forced expiratory volume in one second (FEV1) by using audio data from participants and test whether auditory sleep disturbances are correlated with poorer asthma outcomes. These are applied to a representative data set of FEV1 collected from a commercially available sprirometer and audio spectrograms collected overnight using a smartphone. A model for detecting nonverbal vocalizations including coughs, sneezes, sighs, snoring, throat clearing, sniffs, and breathing sounds was trained and used to capture nightly sleep disturbances. Our preliminary analysis found significant improvement in FEV1 forecasting when using overnight nonverbal vocalization detections as an additional feature for regression using XGBoost over using only spirometry data.Clinical relevance- This preliminary study establishes up to 30% improvement of FEV1 forecasting using features generated by deep learning techniques over only spirometry-based features.

Robust Cough Detection With Out-of-Distribution Detection.

Cough is an important defense mechanism of the respiratory system and is also a symptom of lung diseases, such as asthma. Acoustic cough detection collected by portable recording devices is a convenient way totrack potential condition worsening for patients who have asthma. However, the data used in building current cough detection models are often clean, containing a limited set of sound categories, and thus perform poorly when they are exposed to a variety of real-world sounds which could be picked up by portable recording devices. The sounds that are not learned by the model are referred to as Out-of-Distribution (OOD) data. In this work, we propose two robust cough detection methods combined with an OOD detection module, that removes OOD data without sacrificing the cough detection performance of the original system. These methods include adding a learning confidence parameter and maximizing entropy loss. Our experiments show that 1) the OOD system can produce dependable In-Distribution (ID) and OOD results at a sampling rate above 750 Hz; 2) the OOD sample detection tends to perform better for larger audio window sizes; 3) the model's overall accuracy and precision get better as the proportion of OOD samples increase in the acoustic signals; 4) a higher percentage of OOD data is needed to realize performance gains at lower sampling rates. The incorporation of OOD detection techniques improves cough detection performance by a significant margin and provides a valuable solution to real-world acoustic cough detection problems.

Toward Automated Analysis of Fetal Phonocardiograms: Comparing Heartbeat Detection from Fetal Doppler and Digital Stethoscope Signals.

Longitudinal fetal health monitoring is essential for high-risk pregnancies. Heart rate and heart rate variability are prime indicators of fetal health. In this work, we implemented two neural network architectures for heartbeat detection on a set of fetal phonocardiogram signals captured using fetal Doppler and a digital stethoscope. We test the efficacy of these networks using the raw signals and the hand-crafted energy from the signal. The results show a Convolutional Neural Network is the most efficient at identifying the S1 waveforms in a heartbeat, and its performance is improved when using the energy of the Doppler signals. We further discuss issues, such as low Signal-to-Noise Ratios (SNR), present in the training of a model based on the stethoscope signals. Finally, we show that we can improve the SNR, and subsequently the performance of the stethoscope, by matching the energy from the stethoscope to that of the Doppler signal.