Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database-HF_Lung_V1.

A reliable, remote, and continuous real-time respiratory sound monitor with automated respiratory sound analysis ability is urgently required in many clinical scenarios-such as in monitoring disease progression of coronavirus disease 2019-to replace conventional auscultation with a handheld stethoscope. However, a robust computerized respiratory sound analysis algorithm for breath phase detection and adventitious sound detection at the recording level has not yet been validated in practical applications. In this study, we developed a lung sound database (HF_Lung_V1) comprising 9,765 audio files of lung sounds (duration of 15 s each), 34,095 inhalation labels, 18,349 exhalation labels, 13,883 continuous adventitious sound (CAS) labels (comprising 8,457 wheeze labels, 686 stridor labels, and 4,740 rhonchus labels), and 15,606 discontinuous adventitious sound labels (all crackles). We conducted benchmark tests using long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional LSTM (BiLSTM), bidirectional GRU (BiGRU), convolutional neural network (CNN)-LSTM, CNN-GRU, CNN-BiLSTM, and CNN-BiGRU models for breath phase detection and adventitious sound detection. We also conducted a performance comparison between the LSTM-based and GRU-based models, between unidirectional and bidirectional models, and between models with and without a CNN. The results revealed that these models exhibited adequate performance in lung sound analysis. The GRU-based models outperformed, in terms of F1 scores and areas under the receiver operating characteristic curves, the LSTM-based models in most of the defined tasks. Furthermore, all bidirectional models outperformed their unidirectional counterparts. Finally, the addition of a CNN improved the accuracy of lung sound analysis, especially in the CAS detection tasks.

Lung ventilation distribution in patients after traditional full sternotomy and minimally invasive thoracotomy: An observational study.

BACKGROUND: The aim of the study was to examine the post-operative ventilation distribution changes in cardiac surgical patients after traditional full sternotomy (FS) or minimally invasive thoracotomy (MIT). METHODS: A total of 40 patients scheduled for FS with two-lung ventilation or MIT with one-lung ventilation were included. Ventilation distribution was measured with electrical impedance tomography (EIT) at T1, before surgery; T2, after surgery in ICU before weaning; T3, 24 hours after extubation. EIT-based parameters were calculated to assess the ventilation distribution, including the left-to-right lung ratio, ventral-to-dorsal ratio, and the global inhomogeneity index. RESULTS: The global inhomogeneity index increased at T2 and T3 compared to T1 in all patients but only statistically significant in patients with MIT (FS, P = .06; MIT, P < .01). Notable decrease in the dorsal regions (FS) or in the non-ventilated side (MIT) was observed at T2. Ventilation distribution was partially improved at T3 but huge variations of recovery progresses were found in all patients regardless of the surgery types. Subgroup analysis indicated that operation duration was significantly lower in the MIT group (240 ± 40 in FS vs 205 ± 90 minutes in MIT, median ± interquartile range, P < .05) but the incidence of atrial fibrillation/flutter was significantly higher (5% in FS vs 50% in MIT, P < .01). Other exploratory outcomes showed no statistical differences. CONCLUSIONS: Ventilation distribution was impaired after cardiac surgery. The recovery process of ventilation homogeneity was strongly depending on individuals so that MIT was not always superior in this aspect. EIT may help to identify the patients requiring further care after surgery.