Regional respiratory sound abnormalities in pneumothorax and pleural effusion detected via respiratory sound visualization and quantification: case report

Development of a Pharyngeal Residue Level Assessment Index Using Artificial Intelligence (AI) Acoustic Analysis: A Study Protocol

The swallowing function is often compromised immediately after general anesthesia owing to the effects of anesthetic agents. Consequently, pharyngeal residue may accumulate, which increases the risk of aspiration during the perioperative period. Therefore, we designed a single-arm, open-label study, developing an artificial intelligence (AI)-based acoustic analyzer for quantifying pharyngeal residues and evaluating its efficacy. A sample of 30 patients aged ≥18 years scheduled for jaw deformity surgery will be enrolled in this study. Immediately after tracheal tube extubation, adventitious sounds from pharyngeal residues, such as saliva and blood, will be measured and quantified using an AI acoustic analysis system. Subsequently, the residual pharyngeal fluid will be suctioned and quantified by measuring the change in container weight before and after collection. The primary outcome measure will be the comparison of adventitious sounds before and after pharyngeal suction, and the secondary outcome will be the correlation between pharyngeal residue volume and adventitious sounds. The results of this study are expected to be drawn by 2025 upon its completion. This study will demonstrate the feasibility of AI-based acoustic monitoring for quantifying increased pharyngeal residues during perioperative management. This approach has the potential to reduce the risk of postoperative aspiration with a simple and inexpensive method.

High-sensitivity QCM humidity sensor based on chitosan/carboxymethylated multiwalled carbon nanotubes composite for non-contact respiratory monitoring

Respiratory humidity is an important indicator that can reflect respiratory disorders and is easily accessible in daily life, thus attracting attention in non-contact home respiratory monitoring systems. In this work, a high-sensitivity quartz crystal microbalance (QCM) humidity sensor based on a chitosan/carboxymethylated multiwalled carbon nanotubes composite coating is developed with a response time of 36 s and a recovery time of 38 s. The humidity variations from 11 to 97 % can be detected while the wet hysteresis is 0.95 % RH. The sensor also exhibits good repeatability and stability. The physicochemical characterizations of the materials reveal the mechanism of the rapid humidity response, i.e., compared to the physically blended CS with MWCNT, the crosslinking CS-MWCNT formed the new intercalation by stronger hydrogen and amide bonding, which leads to the homogeneous coverage of CS on MWCNT, exposing more active sites and facilitating the binding rate of water molecules. Combined with respiration monitoring, the sensor is able to accurately monitor human respiration rate and depth in real time, effectively predicting and differentiating between different types of obstructive sleep apnea syndromes, providing a fast and reliable solution for daily health monitoring.

The Usefulness of Continuous Respiratory Sound Monitoring for the Detection of Pulmonary Atelectasis in a Ventilated Extremely Low Birth Weight Infant

The assessment of auscultation using a stethoscope is unsuitable for continuous monitoring. Therefore, we developed a novel acoustic monitoring system that continuously, objectively, and visually evaluates respiratory sounds. In this report, we assess the usefulness of our revised system in a ventilated extremely low birth weight infant (ELBWI) for the diagnosis of pulmonary atelectasis and evaluation of treatment by lung lavage. A female infant was born at 24 weeks of age with a birth weight of 636 g after emergency cesarean section. The patient received invasive mechanical ventilation immediately after birth in our neonatal (NICU). After obtaining informed consent, we monitored her respiratory status using the respiratory-sound monitoring system by attaching a sound collection sensor to the right anterior chest wall. On day 26, lung-sound spectrograms showed that the breath sounds were attenuated simultaneously as hypoxemia progressed. Finally, chest radiography confirmed the diagnosis as pulmonary atelectasis. To relieve atelectasis, surfactant lavage was performed, after which the lung-sound spectrograms returned to normal. Hypoxemia and chest radiographic findings improved significantly. On day 138, the patient was discharged from the NICU without complications. The continuous respiratory-sound monitoring system enabled the visual, quantitative, and noninvasive detection of acute regional lung abnormalities at the bedside. We, therefore, believe that this system can resolve several problems associated with neonatal respiratory management and save lives.

Quantification of respiratory sounds by a continuous monitoring system can be used to predict complications after extubation: a pilot study

To show that quantification of abnormal respiratory sounds by our developed device is useful for predicting respiratory failure and airway problems after extubation. A respiratory sound monitoring system was used to collect respiratory sounds in patients undergoing extubation. The recorded respiratory sounds were subsequently analyzed. We defined the composite poor outcome as requiring any of following medical interventions within 48 h as defined below. This composite outcome includes reintubation, surgical airway management, insertion of airway devices, unscheduled use of noninvasive ventilation or high-flow nasal cannula, unscheduled use of inhaled medications, suctioning of sputum by bronchoscopy and unscheduled imaging studies. The quantitative values (QV) for each abnormal respiratory sound and inspiratory sound volume were compared between composite outcome groups and non-outcome groups. Fifty-seven patients were included in this study. The composite outcome occurred in 18 patients. For neck sounds, the QVs of stridor and rhonchi were significantly higher in the outcome group vs the non-outcome group. For anterior thoracic sounds, the QVs of wheezes, rhonchi, and coarse crackles were significantly higher in the outcome group vs the non-outcome group. For bilateral lateral thoracic sounds, the QV of fine crackles was significantly higher in the outcome group vs the non-outcome group. Cervical inspiratory sounds volume (average of five breaths) immediately after extubation was significantly louder in the outcome group vs non-outcome group (63.3 dB vs 54.3 dB, respectively; p < 0.001). Quantification of abnormal respiratory sounds and respiratory volume may predict respiratory failure and airway problems after extubation.