Dataset Information

Diagnosis of Pneumonia by Cough Sounds Analyzed with Statistical Features and AI

ABSTRACT: Pneumonia is a serious disease often accompanied by complications, sometimes leading to death. Unfortunately, diagnosis of pneumonia is frequently delayed until physical and radiologic examinations are performed. Diagnosing pneumonia with cough sounds would be advantageous as a non-invasive test that could be performed outside a hospital. We aimed to develop an artificial intelligence (AI)-based pneumonia diagnostic algorithm. We collected cough sounds from thirty adult patients with pneumonia or the other causative diseases of cough. To quantify the cough sounds, loudness and energy ratio were used to represent the level and its spectral variations. These two features were used for constructing the diagnostic algorithm. To estimate the performance of developed algorithm, we assessed the diagnostic accuracy by comparing with the diagnosis by pulmonologists based on cough sound alone. The algorithm showed 90.0% sensitivity, 78.6% specificity and 84.9% overall accuracy for the 70 cases of cough sound in pneumonia group and 56 cases in non-pneumonia group. For same cases, pulmonologists correctly diagnosed the cough sounds with 56.4% accuracy. These findings showed that the proposed AI algorithm has value as an effective assistant technology to diagnose adult pneumonia patients with significant reliability.

SUBMITTER: Chung Y

PROVIDER: S-EPMC8586978 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundHospital-acquired pneumonia (HAP) is defined as radiologically confirmed pneumonia occurring ≥48h after hospitalization, in non-intubated patients. Empirical treatment regimens use broad-spectrum antimicrobials.AimTo evaluate the accuracy of the diagnosis of HAP and to describe the demographic and microbiological features of patients with HAP.MethodsMedical and surgical inpatients receiving intravenous antimicrobials for a clinical diagnosis of HAP at a UK tertiary care hospital between April 2013 and 2014 were identified. Demographic and clinical details were recorded.FindingsA total of 166 adult patients with a clinical diagnosis of HAP were identified. Broad-spectrum antimicrobials were prescribed, primarily piperacillin-tazobactam (57.2%) and co-amoxiclav (12.5%). Sputum from 24.7% of patients was obtained for culture. Sixty-five percent of patients had radiological evidence of new/progressive infiltrate at the time of HAP treatment, therefore meeting HAP diagnostic criteria (2005 American Thoracic Society/Infectious Diseases Society of America guidelines). Radiologically confirmed HAP was associated with higher levels of inflammatory markers and sputum culture positivity. Previous surgery and/or endotracheal intubation were associated with radiologically confirmed HAP. A bacterial pathogen was identified from 17/35 sputum samples from radiologically confirmed HAP patients. These were Gram-negative bacilli (N = 11) or Staphylococcus aureus (N = 6). Gram-negative bacteria tended to be resistant to co-amoxiclav, but susceptible to ciprofloxacin, piperacillin-tazobactam and meropenem. Five of the six S. aureus isolates were meticillin susceptible and all were susceptible to doxycycline.ConclusionIn ward-level hospital practice 'HAP' is an over-used diagnosis that may be inaccurate in 35% of cases when objective radiological criteria are applied. Radiologically confirmed HAP represents a distinct clinical and microbiological phenotype. Potential risk factors were identified that could represent targets for preventive interventions.

Project description:Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation lung (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by the overlapping symptoms (such as fever, cough, sore throat, etc.). Additionally, researchers and medical professionals make use of chest X-rays (CXR), cough sounds, and computed tomography (CT) scans to diagnose chest disorders. The present study aims to classify the nine different conditions of chest disorders, including COVID-19, LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for nine different chest disease classifications by extracting features from images. Furthermore, the proposed CNN employed several new approaches such as a max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), and multiple-way data generation (MWDG). The scalogram method is utilized to transform the sounds of coughing into a visual representation. Before beginning to train the model that has been developed, the SMOTE approach is used to calibrate the CXR and CT scans as well as the cough sound images (CSI) of nine different chest disorders. The CXR, CT scan, and CSI used for training and evaluating the proposed model come from 24 publicly available benchmark chest illness datasets. The classification performance of the proposed model is compared with that of seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, and Inception-V3, in addition to state-of-the-art (SOTA) classifiers. The effectiveness of the proposed model is further demonstrated by the results of the ablation experiments. The proposed model was successful in achieving an accuracy of 99.01%, making it superior to both the baseline models and the SOTA classifiers. As a result, the proposed approach is capable of offering significant support to radiologists and other medical professionals.

Dataset Information

Diagnosis of Pneumonia by Cough Sounds Analyzed with Statistical Features and AI

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets