Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification

The analysis of lung sounds in infants and children with a history of wheezing/asthma using an automatic procedure

BACKGROUND

Lung sound analysis parameters have been reported to be useful biomarkers for evaluating airway condition. We developed an automatic lung sound analysis software program for infants and children based on lung sound spectral curves of frequency and power by leveraging machine learning (ML) technology.

METHODS

To put this software program into clinical practice, in Study 1, the reliability and reproducibility of the software program using data from younger children were examined. In Study 2, the relationship between lung sound parameters and respiratory flow (L/s) was evaluated using data from older children. In Study 3, we conducted a survey using the ATS-DLD questionnaire to evaluate the clinical usefulness. The survey focused on the history of wheezing and allergies, among healthy 3-year-old infants, and then measured lung sounds. The clinical usefulness was evaluated by comparing the questionnaire results with the results of the new lung sound parameters.

RESULTS

In Studies 1 and 2, the parameters of the new software program demonstrated excellent reproducibility and reliability, and were not affected by airflow (L/s). In Study 3, infants with a history of wheezing showed lower FAP0 and RPF75p (p < 0.001 and p = 0.025, respectively) and higher PAP0 (p = 0.001) than healthy infants. Furthermore, infants with asthma/asthma-like bronchitis showed lower FAP0 (p = 0.002) and higher PAP0 (p = 0.001) than healthy infants.

CONCLUSIONS

Lung sound parameters obtained using the ML algorithm were able to accurately assess the respiratory condition of infants. These parameters are useful for the early detection and intervention of childhood asthma.

Errors in Metered Dose Inhaler Use Amongst Pediatric Asthma Patients

Purpose

The aim of this paper is to use easily accessible smartphones as a straightforward means for physicians to objectively check Medical Device Inhaler (MDI) technique, without the need for additional devices. Additionally, we seek to assess the frequency of inhaler technique errors and their impact on asthma control.

Patients and Methods

Thirty-two children between the ages of 5 and 18 receiving asthma therapy through MDIs were included. Three surveys were administered to all participants to gauge device history, asthma control, and patient characteristics. Patient technique was scored using inhaler audio signals recorded with a smartphone. For subjects that were able, forced oscillation technique (FOT) was performed during tidal breathing conditions before and after corticosteroid administration.

Results

81% (25/31) of participants used their MDIs incorrectly with the most common errors being rapid shallow breathing, inadequate breath-holding, and excessive actuations. Poor inhaler technique correlated with poorly controlled asthma symptoms.

Conclusion

The use of smartphone recordings can a convenient way to evaluate technique errors and could allow patients to demonstrate and refine their technique and usage without a doctor's visit, ensuring proper technique and enhancing treatment effectiveness.

Real-Time Prediction of Joint Forces by Motion Capture and Machine Learning

Conventional biomechanical modelling approaches involve the solution of large systems of equations that encode the complex mathematical representation of human motion and skeletal structure. To improve stability and computational speed, being a common bottleneck in current approaches, we apply machine learning to train surrogate models and to predict in near real-time, previously calculated medial and lateral knee contact forces (KCFs) of 54 young and elderly participants during treadmill walking in a speed range of 3 to 7 km/h. Predictions are obtained by fusing optical motion capture and musculoskeletal modeling-derived kinematic and force variables, into regression models using artificial neural networks (ANNs) and support vector regression (SVR). Training schemes included either data from all subjects (LeaveTrialsOut) or only from a portion of them (LeaveSubjectsOut), in combination with inclusion of ground reaction forces (GRFs) in the dataset or not. Results identify ANNs as the best-performing predictor of KCFs, both in terms of Pearson R (0.89-0.98 for LeaveTrialsOut and 0.45-0.85 for LeaveSubjectsOut) and percentage normalized root mean square error (0.67-2.35 for LeaveTrialsOut and 1.6-5.39 for LeaveSubjectsOut). When GRFs were omitted from the dataset, no substantial decrease in prediction power of both models was observed. Our findings showcase the strength of ANNs to predict simultaneously multi-component KCF during walking at different speeds-even in the absence of GRFs-particularly applicable in real-time applications that make use of knee loading conditions to guide and treat patients.

Real-Time Sensor Networks and Systems for the Industrial IoT: What Next?

The Industrial Internet of Things (Industrial IoT-IIoT) is the emerging core backbone construct for the various cyber-physical systems constituting one of the principal dimensions of the 4th Industrial Revolution [...].