No abstract

Respiratory diseases constitute one of the leading causes of death worldwide and directly affect the patient’s quality of life. Early diagnosis and patient monitoring, which conventionally include lung auscultation, are essential for the efficient management of respiratory diseases. Manual lung sound interpretation is a subjective and time-consuming process that requires high medical expertise. The capabilities that deep learning offers could be exploited in order that robust lung sound classification models can be designed. In this paper, we propose a novel hybrid neural model that implements the focal loss (FL) function to deal with training data imbalance. Features initially extracted from short-time Fourier transform (STFT) spectrograms via a convolutional neural network (CNN) are given as input to a long short-term memory (LSTM) network that memorizes the temporal dependencies between data and classifies four types of lung sounds, including normal, crackles, wheezes, and both crackles and wheezes. The model was trained and tested on the ICBHI 2017 Respiratory Sound Database and achieved state-of-the-art results using three different data splitting strategies—namely, sensitivity 47.37%, specificity 82.46%, score 64.92% and accuracy 73.69% for the official 60/40 split, sensitivity 52.78%, specificity 84.26%, score 68.52% and accuracy 76.39% using interpatient 10-fold cross validation, and sensitivity 60.29% and accuracy 74.57% using leave-one-out cross validation.

Background Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals. Objective This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications. Methods The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches. Results We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models. Conclusions We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

Objective. In this paper, an automated stable tidal breathing period (STBP) identification method based on processing electrical impedance tomography (EIT) waveforms is proposed and the possibility of detecting and identifying such periods using EIT waveforms is analyzed. In wearable chest EIT, patients breathe spontaneously, and therefore, their breathing pattern might not be stable. Since most of the EIT feature extraction methods are applied to STBPs, this renders their automatic identification of central importance. Approach. The EIT frame sequence is reconstructed from the raw EIT recordings and the raw global impedance waveform (GIW) is computed. Next, the respiratory component of the raw GIW is extracted and processed for the automatic respiratory cycle (breath) extraction and their subsequent grouping into STBPs. Main results. We suggest three criteria for the identification of STBPs, namely, the coefficient of variation of (i) breath tidal volume, (ii) breath duration and (iii) end-expiratory impedance. The total number of true STBPs identified by the proposed method was 294 out of 318 identified by the expert corresponding to accuracy over 90%. Specific activities such as speaking, eating and arm elevation are identified as sources of false positives and their discrimination is discussed. Significance. Simple and computationally efficient STBP detection and identification is a highly desirable component in the EIT processing pipeline. Our study implies that it is feasible, however, the determination of its limits is necessary in order to consider the implementation of more advanced and computationally demanding approaches such as deep learning and fusion with data from other wearable sensors such as accelerometers and microphones.

No abstract