Key result
Deep learning model achieves 99% sensitivity in diagnosing pulmonary diseases from lung sounds.
Why the study?
Data were lacking on the ability of deep learning models utilizing deep convolutional neural networks and long short-term memory units to recognize respiratory diseases from lung sound signals.
Does a deep learning model based on CNN and BiLSTM accurately diagnose pulmonary diseases and heart failure from lung sounds in adults?
Observational (n=220)
Does a deep learning model based on CNN and BiLSTM accurately diagnose pulmonary diseases and heart failure from lung sounds in adults?
Answers are grounded in this paper and cite their sources.
A deep learning model combining CNN and BiLSTM can accurately classify lung sounds to diagnose respiratory conditions and heart failure, achieving 99% sensitivity.
No abstract yet. The journal hasn't published one we can show.
No takes yet. Share an insight, caveat, or question.
Panaskin et al. (2022) conducted an observational in Pulmonary diseases (asthma, pneumonia, COPD, heart failure) (n=220). Deep learning model (CNN + BiLSTM) vs. Physician diagnosis was evaluated on Diagnostic sensitivity. A deep learning model combining CNN and BiLSTM achieved 99% sensitivity and 98.5% specificity in diagnosing pulmonary diseases from lung sounds.
Synapse has enriched 10 related papers. Consider them for comparative context: