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 | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Chung Youngbeen Y Jin Jie J Jo Hyun In HI Lee Hyun H Kim Sang-Heon SH Chung Sung Jun SJ Yoon Ho Joo HJ Park Junhong J Jeon Jin Yong JY

Sensors (Basel, Switzerland) 20211023 21

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 o ...[more]

PMID: 34770341

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:ObjectivesTo compare physical information, such as age, sex, height, weight, body mass index (BMI) and pulmonary function test (PFT) results, between cough variant asthma (CVA) and chronic cough (CC) and establish a diagnostic model of CVA.DesignA case-control study of patients with suspected CVA enrolled at The First Affiliated Hospital of Zhejiang Chinese Medical University.SettingOne leader unit of the National Key Specialised Pulmonary Disease Cooperation Group in China.ParticipantsEnrolled 545 patients who underwent PFT and bronchial provocation tests.Outcome measuresWe obtained physical information and pulmonary test data and established the model using logistic regression analysis. The Hosmer-Lemeshow goodness-of-fit test, area under the receiver operating characteristic curve (AUC), calibration plot and decision curve analysis were used to evaluate this model. All data were analysed using SPSS V.27 and RStudio software.ResultsThe CVA group had more female patients (%) (68.12% vs 51.48%, p value<0.001) and lower height (m) (1.61 (0.40) vs 1.65 (3.26), p value<0.001), weight (kg) (60 (56) vs 63 (85), p value<0.001) and BMI (kg/m2) (22.59 (17.91) vs 23.28 (21.81), p value=0.016) than the CC group. Differences between CVA and CC in forced vital capacity (FVC) in percent predicted values (FVC% pred)(94.4 (57.3) vs 91.60 (94.10), p value=0.006), forced expiratory volume in 1 s/FVC (FEV1/FVC) (%) (84.65±6.82 vs 86.91±6.71, p value<0.001), peak expiratory flow in per cent predicted values (PEF% pred) (93.00 (81.10) vs 98.00 (108.00), p value=0.005), maximal mid-expiratory flow in percent predicted values (MMEF% pred) (74.50 (100.60) vs 90.85 (170.30), p value<0.001), forced expiratory flow (FEF) at 50% of FVC in per cent predicted values (FEF50% pred) (78.9(113.50) vs 93.10(169.80), p value<0.001) and FEF at 75% of FVC in per cent predicted values (FEF75% pred) (69.70 (137.60) vs 85.60 (225.80), p value<0.001) were significant. Patients with CVA were more in number compared with patients with CC at a lower degree (<65%) of MMEF% pred (32.37% vs 14.50%, p value<0.001), FEF50% pred (26.09% vs 13.02%, p value<0.001) and FEF75% pred (39.13% vs 23.67%, p value<0.001). FVC% pred, FEV1/FVC, BMI and MMEF% pred aided in establishing a model with an AUC of 0.733 (95% CI: 0.6829 to 0.7831). The model was tested using internal and external data (p value=0.2865 and p value=0.3197, respectively).ConclusionBMI, FVC% pred, FEV1/FVC (%) and MMEF% pred were used to establish the diagnostic model. Our model potentially indicates CVA.Trial registration numberNCT06199830.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets