Multistage Classification And Ensemble Learning Techniques For Automated Respiratory Sound Analysis: A Comprehensive Review

In the last 2 years, medical researchers and clinical scientists have paid close attention to the problem of respiratory sound classification to classify COVID-19 disease symptoms. In the physical world, very few AI-based (Artificial Intelligence) techniques are often used to detect COVID-19/SARS-CoV-2 respiratory disease symptoms from the human respiratory system-generated acoustic sounds such as acoustic voice sound, breathing (inhale and exhale) sounds, and cough sound. We propose a light-weight Convolutional Neural Network (CNN) with Modified-Mel-frequency Cepstral Coefficient (M-MFCC) using different depths and kernel sizes to classify COVID-19 and other respiratory sound disease symptoms such as Asthma, Pertussis, and Bronchitis. The proposed network outperforms conventional feature extraction models and existing Deep Learning (DL) models for COVID-19/SARS-CoV-2 classification accuracy in the range of 4–10%. The model’s performance is compared with the COVID-19 crowdsourced benchmark dataset and gives a competitive performance. We applied different receptive fields and depths in the proposed model to get different contextual information that should aid in classification. And our experiments suggested 1 times 12 receptive fields and a depth of 5-Layer for the light-weight CNN to extract and identify the features from respiratory sound data. The model is also trained and tested with different modalities of data to showcase its effectiveness in classification.

Background/Objectives: Identifying and classifying abnormal lung sounds is essential for diagnosing patients with respiratory disorders. In particular, the simultaneous recording of auscultation signals from multiple clinically relevant positions offers greater diagnostic potential compared to traditional single-channel measurements. This study aims to improve the accuracy of respiratory sound classification by leveraging multichannel signals and capturing positional characteristics from multiple sites in the same patient. Methods: We evaluated the performance of respiratory sound classification using multichannel lung sound data with a deep learning model that combines a convolutional neural network (CNN) and long short-term memory (LSTM), based on mel-frequency cepstral coefficients (MFCCs). We analyzed the impact of the number and placement of channels on classification performance. Results: The results demonstrated that using four-channel recordings improved accuracy, sensitivity, specificity, precision, and F1-score by approximately 1.11, 1.15, 1.05, 1.08, and 1.13 times, respectively, compared to using three, two, or single-channel recordings. Conclusions: This study confirms that multichannel data capture a richer set of features corresponding to various respiratory sound characteristics, leading to significantly improved classification performance. The proposed method holds promise for enhancing sound classification accuracy not only in clinical applications but also in broader domains such as speech and audio processing.

Nearly half of Alzheimer's dementia could be prevented or delayed simply by addressing some modifiable risk factors. We aim to develop novel deep-learning (DL) models with fusion network and ensemble learning techniques for an automated detection of Alzheimer's Disease (AD) using retinal optical coherence tomography (OCT) to facilitate AD identification for timely intervention. We trained, validated, and tested DL models for classifying AD-dementia or no dementia using en face images and analysis reports of OCT (Cirrus HD-OCT device, Carl Zeiss Medite, Inc., Dublin, CA). Specifically, the optic nerve head (ONH)- and macula-centred en face images and three OCT conventional analysis reports were used, namely (1) retinal nerve fibre layer (RNFL) analysis, (2) macular thickness (MT) analysis, and (3) ganglion cell-inner plexiform layer (GCIPL) analysis. The RNFL and GCIPL analysis reports contain thickness and deviation maps, while the MT report only contains the thickness map. To analyze multiple inputs from a single eye for AD-dementia detection, we proposed a fusion network, including "Feature Extraction", "Feature Fusion", and "Feature Reconstruction". We developed fusion network-based DL models, including the ONH Model, Macula Model, and Integrated Model, using different inputs of OCT. We further incorporated the ensemble learning technique to integrate all inputs into a single model (i.e., Ensemble Model). For model training and internal validation, we retrospectively collected 3,228 paired OCT reports and en face images from 1,239 subjects with AD-dementia and 1,800 cognitively normal controls. For model external testing, we retrospectively collected 86 paired OCT reports and en face images from 38 subjects in Hong Kong as External-1, and 125 paired OCT reports and en face images from 60 subjects in Singapore as External-2. In the internal validation, External-1, and External-2, the ONH Model achieved accuracies of 85.4%, 76.3%, and 73.0%, respectively. The Macula Model achieved accuracies of 82.4%, 76.5%, and 70.7%, respectively. The Integrated Model achieved accuracies of 84.8%, 74.1%, and 71.7%, respectively. The Ensemble Model achieved accuracies of 90.5%, 80.3%, and 74.2%, respectively. Our proposed Ensemble Model that learned AD-related retinal features from OCT analysis shows a large potential to identify individuals with AD-dementia accurately.

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms.In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects.We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively.As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.

Diagnosing Intracranial Hemorrhage (ICH) at an early stage is difficult since it affects the blood vessels in the brain, often resulting in death. We propose an ensemble of Convolutional Neural Networks (CNNs) combining Squeeze and Excitation-based Residual Networks with the next dimension (SE-ResNeXT) and Long Short-Term Memory (LSTM) Networks in order to address this issue. This research work primarily used data from the Radiological Society of North America (RSNA) brain CT hemorrhage challenge dataset and the CQ500 dataset. Preprocessing and data augmentation are performed using the windowing technique in the proposed work. The ICH is then classified using ensembled CNN techniques after being preprocessed, followed by feature extraction in an automatic manner. ICH is classified into the following five types: epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural. A gradient-weighted Class Activation Mapping method (Grad-CAM) is used for identifying the region of interest in an ICH image. A number of performance measures are used to compare the experimental results with various state-of-the-art algorithms. By achieving 99.79% accuracy with an F-score of 0.97, the proposed model proved its efficacy in detecting ICH compared to other deep learning models. The proposed ensembled model can classify epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural hemorrhages with an accuracy of 99.89%, 99.65%, 98%, 99.75%, and 99.88%. Simulation results indicate that the suggested approach can categorize a variety of intracranial bleeding types. By implementing the ensemble deep learning technique using the SE-ResNeXT and LSTM models, we achieved significant classification accuracy and AUC scores.

Respiratory sound classification has emerged as a promising non-invasive and scalable tool for the early detection of respiratory disorders. While most previous studies have relied on a single feature extraction method-such as Melfrequency cepstral coefficients (MFCC), Mel-spectrograms, or Short-Time Fourier Transform (STFT)-this study provides a comprehensive comparative analysis of these three approaches, evaluated individually, in pairwise combinations, and in a combined three-method configuration. Experiments are conducted on the SPRSound dataset, a pediatric respiratory sound database comprising 6,656 annotated events from seven unbalanced classes. Three architectures are assessed under identical preprocessing and augmentation strategies: a custom convolutional neural network (CNN), and two pre-trained models (VGG16 and InceptionV3) fine-tuned via transfer learning. Results show that STFT consistently delivers the highest performance for CNN and VGG16 models, while MFCC achieves the best accuracy with InceptionV3. Specifically, VGG16 with STFT attained 93.43% accuracy (score: 0.9545), whereas InceptionV3 with MFCC achieved the top performance within its architecture. These findings highlight the importance of aligning feature extraction techniques with model architecture and provide a systematic benchmark for SPRSound-based respiratory sound classification.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

The respiratory sound classification paper focuses on analyzing sounds collected through the stethoscope at various chest positions to understand critical concerns of human breathing. Most doctors used a stethoscope for auscultation of lung sounds, along with heart sound, as a basic checkup and utilized later in predicting chest pathology. Using deep learning-based sound classification can build intelligent digital stethoscopes or understand overall health conditions later used along with other Lung organ analyses. The solution enables affordable and practical tools for remote parts of India, where doctors or specialists are not keen to work. Such solutions can be used as first analysis before further investigation by traveling to far-off specialist hospitals. The lung sound was prepared and hosted by a team from the University of Coimbra, Portugal; the University de Aveiro, Portugal; and the Aristotle University of Thessaloniki, Greece and the collaboration at Kaggle website lung sounds of patients who are Normal lung functioning and with some anomaly collected. The collected lung sounds are labeled as Normal, seven classes - Abnormal. Overall, eight levels are considered to classify using a deep learning model. The paper proposes a multipath convolution neural network (CNN) model for analyzing sound after exploring all approaches, like Recurrent Neural network (RNN), Machine learning models like SVM, and other CNN models as per paper [3]. Lung sound is processed using signal processing methods and converts wav files to Mel-frequency cepstral coefficients (MFCCs), Mel spectrogram, and chromatogram from a waveform or power spectrogram. Instead of using one feature among three, the paper built a Multipath CNN model to feed all three components to model and concatenate feature maps to classify the classes. The model was evaluated with various parameters like accuracy and F1 score. The proposed model gives 96.17% for the dataset used. The result implies data, and a multipath approach helps to fuse features extracted from different images and allows models to classify well.

Rationale Multimodal clinical audio data, including speech and breath sounds, play a critical role in assessing respiratory function in disorders affecting the thoracic cage, including neurodegenerative, infectious, and respiratory disorders. Machine learning (ML) has shown promise in identifying patterns to enhance predictive accuracy in these disorders due to its data processing power with chronic respiratory conditions that disrupt airflow, such as Chronic Obstructive Pulmonary Disease (COPD) and Interstitial Lung Disease (ILD), being notable examples. This study investigates the feasibility of using an ML model to predict clinical parameters including pulmonary function, smoking status, and disease presence by analyzing breath and vocal characteristics. Methods Two-hundred patients with various respiratory and thoracic pathologies were recruited via convenience sampling from a university medical center. Data were collected using digital stethoscopes and microphones to record breath sounds at eight anatomical locations along with vocal samples during a variety of vocal tasks (Figure 1). Audio data were converted into Mel-spectrograms and used to train a convolutional neural network (CNN) model to predict patient outcomes, including gender, smoking status, COPD, and ILD. The dataset was divided into a 90:10 training-to-validation ratio. Fig. 1. Representation of study workflow showing data collection, data transformation, and subsequent model training. Results In predicting smoking status, breath recordings achieved 80% accuracy, 95% specificity, 63% sensitivity, and an AUC of 0.82 compared to 65%, 69%, 57%, and 0.58 for the voice-based model. In COPD classification, breath data yielded 75% accuracy, 62% specificity, and 80% sensitivity in contrast to 62.5%, 80%, and 57% for the vocal model. In ILD classification, breath data yielded 65% accuracy, 58% specificity, and 75% sensitivity in contrast to 65%, 77%, and 55% for the vocal model. Additionally, in predicting pulmonary function via Forced Vital Capacity (FVC) and the FEV1/FVC ratio, breath sounds had lower mean squared error (MSE) values relative to voice models (0.7 vs. 10.2, and 111.6 vs. 2308.6), demonstrating superior performance. Conclusion Breath sounds offer significant predictive value in identifying pulmonary conditions and estimating functional metrics, outperforming vocal and cough data in most tasks. Given the low cost of obtaining clinical audio data, uncovering reliable biomarkers in audio patterns via ML methods may assist in diagnosis, risk stratification, and identification of patients in whom preventative care may be beneficial. Future work will require larger datasets to improve model robustness and explore more complex biomarker integration, such as combining breath and voice data, for enhanced clinical prediction.

A major worldwide health concern is chronic respiratory diseases (CRDs), which include disorders including asthma, pulmonary hypertension, occupational lung diseases, and chronic obstructive pulmonary disease (COPD). Improving clinical results and treatment efficacy requires an early and precise diagnosis. In order to classify respiratory sounds, this study presents a novel framework that incorporates auditory-inspired characteristics, such as Mel-Frequency Cepstral Coefficients (MFCCs), Mel Spectrograms, and Cochleograms, into a CNN-LSTM architecture. The framework uses sophisticated feature extraction techniques in conjunction with strong data augmentation approaches to address the issue of class imbalance and guarantee a thorough representation of a variety of respiratory sound patterns. Using the Respiratory Sound Database, the suggested model was assessed and showed remarkable performance, obtaining an F1 score of 98.94%, accuracy of 98.90%, specificity of 99.80%, sensitivity of 98.90%, and an ICBHI score of 99.40%. These findings demonstrate the model’s potential as a reliable and efficient tool for the early identification and evaluation of CRDs, which would significantly improve patient care and the management of respiratory illnesses. The outstanding performance further emphasizes the importance in clinical settings, enabling improved management and early identification of chronic respiratory conditions.

Fault diagnosis in induction machines (IM) require effective detection at early stages to prevent permanent machine failure. This requires fast sensing of disturbances as well as efficient diagnosis methods. Conventional signal measuring techniques are usually intrusive, sensitive, with a low signal-to-noise ratio, and may show limited performance at incipient fault stages. Moreover, traditional machine learning (ML) diagnosis techniques based on handcrafted feature extraction methods suffer from limitations that can be overcome by deep learning (DL) with automatic feature extraction capabilities. In this paper, an online, non-intrusive method is proposed for fault diagnosis in a three-phase IM based on infrared imaging. The proposed method integrates three convolutional neural network (CNN)-based DL models (Inception, Xception, and MobileNet) to identify IM health status, fault types, and stator Inter-turn faults (ITF) location and severity. Deep features obtained from these CNNs are merged through Discrete Wavelet Transform (DWT) resulting in spatial-time-frequency features. This fusion reduces the input features’ size and improves diagnostic accuracy. Merged features’ length is further reduced using the Principal Component Analysis (PCA) where these reduced features are then used for classification. Compared to DL-based diagnosis methods introduced in previous work, the proposed method shows superior performance. First, it uses the IR images directly without the need for clustering and segmentation steps, thus saving time and effort. Moreover, ensembled DL is applied via combining the three CNNs benefits altogether rather than applying an individual DL method. Finally, unlike the huge features’ number exhibited by previous studies, the proposed approach uses minimal features, thus reducing classification complexity and time while maintaining 100% classification accuracy.

Chronic obstructive pulmonary disease (COPD) is one of the most severe respiratory diseases, which can be diagnosed by several clinical modalities such as spirometric measures, lung function tests, parametric response mapping, wheezing events of lung sounds, etc. Since lung sounds are related to the respiratory irregularities caused by pulmonary illnesses, examining these sounds is more effective for identifying respiratory issues. In this paper, we propose a triplet time-frequency representation (TFR) driven multi-head self-organized operational neural network (MHSONN) for efficient detection of COPD-affected lung sound signals, which exploits the complex non-linear neural architecture in contrary to the linear neural perceptron model used by convolutional neural networks. The proposed framework consists of three stages: (a) pre-processing, (b) triplet TFR extraction, and (c) classification using the proposed MHSONN architecture. Upon experimental evaluation, the proposed work outperforms the existing noteworthy research works by achieving the highest performance rates of 99.81%, 99.85%, and 99.73% for accuracy, sensitivity, and specificity, respectively. The onboard implementation of the proposed framework on a Raspberry Pi-4 microcontroller also exhibits its viability for developing a point-of-care COPD detection system in real-world clinical scenarios.

BackgroundSepsis, an acute and potentially fatal systemic response to infection, significantly impacts global health by affecting millions annually. Prompt identification of sepsis is vital, as treatment delays lead to increased fatalities through progressive organ dysfunction. While recent studies have delved into leveraging Machine Learning (ML) for predicting sepsis, focusing on aspects such as prognosis, diagnosis, and clinical application, there remains a notable deficiency in the discourse regarding feature engineering. Specifically, the role of feature selection and extraction in enhancing model accuracy has been underexplored.ObjectivesThis scoping review aims to fulfill two primary objectives: To identify pivotal features for predicting sepsis across a variety of ML models, providing valuable insights for future model development, and To assess model efficacy through performance metrics including AUROC, sensitivity, and specificity.ResultsThe analysis included 29 studies across diverse clinical settings such as Intensive Care Units (ICU), Emergency Departments, and others, encompassing 1,147,202 patients. The review highlighted the diversity in prediction strategies and timeframes. It was found that feature extraction techniques notably outperformed others in terms of sensitivity and AUROC values, thus indicating their critical role in improving sepsis prediction models.ConclusionKey dynamic indicators, including vital signs and critical laboratory values, are instrumental in the early detection of sepsis. Applying feature selection methods significantly boosts model precision, with models like Random Forest and XG Boost showing promising results. Furthermore, Deep Learning models (DL) reveal unique insights, spotlighting the pivotal role of feature engineering in sepsis prediction, which could greatly benefit clinical practice.

In recent years, online shopping has surged in popularity, with customer reviews becoming a crucial aspect of the decision-making process. Reviews not only help potential customers make informed choices, but also provide businesses with valuable feedback and build trust. In this study, we conducted a thorough analysis of the Amazon reviews dataset, which includes several product categories. Our primary objective was to accurately classify sentiments using natural language processing, machine learning, ensemble learning, and deep learning techniques. Our research workflow encompassed several crucial steps. We explore data collection procedures; preprocessing steps, including normalization and tokenization; and feature extraction, utilizing the Bag-of-Words and TF–IDF methods. We conducted experiments employing a variety of machine learning algorithms, including Multinomial Naive Bayes, Random Forest, Decision Tree, and Logistic Regression. Additionally, we harnessed Bagging as an ensemble learning technique. Furthermore, we explored deep learning-based algorithms, such as CNNs, Bidirectional LSTM, and transformer-based models, like XLNet and BERT. Our comprehensive evaluations, utilizing metrics such as accuracy, precision, recall, and F1 score, revealed that the BERT algorithm outperformed others, achieving an impressive accuracy rate of 89%. This research provides valuable insights into the sentiment analysis of Amazon reviews, aiding both consumers and businesses in making informed decisions and enhancing product and service quality.

Many deep learning–based computerized respiratory sound analysis methods have previously been developed. However, these studies focus on either lung sound only or tracheal sound only. The effectiveness of using a lung sound analysis algorithm on tracheal sound and vice versa is rarely reported. Furthermore, no one knows whether using lung and tracheal sounds together in training a deep learning-based respiratory sound analysis model is beneficial. In this study, we first constructed a tracheal sound database, HF_Tracheal_V1, containing 10,448 15-s tracheal sound recordings, 21,741 inhalation labels, 15,858 exhalation labels, and 6414 continuous adventitious sound (CAS) labels collected from 227 participants undergoing a diagnostic/surgical procedure under monitored anesthesia care. HF_Tracheal_V1 and our previously built lung sound database, HF_Lung_V2, were either combined (mixed set), used one after the other (domain adaptation), or used alone to train convolutional neural network bidirectional gate recurrent unit models for inhalation, exhalation, and CAS detection in lung and tracheal sounds. The results revealed that the models trained using lung sound alone performed poorly in tracheal sound analysis and vice versa. However, mixed set training or domain adaptation improved the performance for 1) inhalation and exhalation detection in lung sounds and 2) inhalation, exhalation, and CAS detection in tracheal sounds compared to positive controls (the models trained using lung sound alone and used in lung sound analysis and vice versa). In particular, the model trained on the mixed set had great flexibility to serve two purposes, lung and tracheal sound analyses, at the same time.