Deep Learning Diagnostic and Risk-stratification for IPF and COPD
DeepBreath
1 other identifier
observational
160
1 country
1
Brief Summary
Idiopathic pulmonary fibrosis (IPF), non-specific interstitial pneumonia (NSIP), and chronic obstructive pulmonary disease (COPD) are severe, progressive, irreversibly incapacitating pulmonary disorders with modest response to therapeutic interventions and poor prognosis. Prompt and accurate diagnosis is important to enable patients to receive appropriate care at the earliest possible stage to delay disease progression and prolong survival. Artificial intelligence (AI)-assisted digital lung auscultation could constitute an alternative to conventional subjective operator-related auscultation to accurately and earlier diagnose these diseases. Moreover, lung ultrasound (LUS), a relevant gold standard for lung pathology, could also benefit from automation by deep learning.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P50-P75 for all trials
Started Apr 2023
1 active site
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
First Submitted
Initial submission to the registry
March 30, 2022
CompletedFirst Posted
Study publicly available on registry
April 8, 2022
CompletedStudy Start
First participant enrolled
April 1, 2023
CompletedPrimary Completion
Last participant's last visit for primary outcome
October 6, 2024
CompletedStudy Completion
Last participant's last visit for all outcomes
October 31, 2024
CompletedApril 12, 2024
April 1, 2024
1.5 years
March 30, 2022
April 10, 2024
Conditions
Keywords
Outcome Measures
Primary Outcomes (3)
To differentiate ILD from control subjects based on digital lung sounds recordings and LUS.
To determine the predictive performance of the AI algorithm-evaluated lung auscultation and LUS in the identification and risk stratification of ILD signatures from control subjects described in terms of descriptive statistics, area under the receiver operating characteristic curve, sensitivity, specificity, positive and negative predictive values, and likelihood ratios (95% confidence intervals). Digital lung sounds will be transformed to Mel Frequency Cepstrum Coefficients. Several data augmentation techniques will be explored. The effect of each pre-processing method will be tested. The best performing approach according to sensitivity and specificity will be reported. This dataset will then be fed into a various deep learning networks with aggregation strategies for binary classification into positive vs negative for diagnostic results for: * ILD or control subjects * ILD or COPD * (If ILD+) IPF or NSIP The same prediction will also be made using LUS images.
During lung auscultation (10 minutes). Each patient will provide 10 recordings of 30 seconds. LUS images and 5 second video clips of each anatomic region (10 regions represented).
Predictive performance of the DeepBreath algorithm to stratify ILD severity based on human digital lung sounds recordings and LUS (i.e. physiological parameters) compared to grading scales.
To determine the ILD clinical severity predictive performance of the DeepBreath algorithm based on human digital lung sounds recordings and LUS, risk stratification will use multiclass or regression according to grading scales obtained from: * K-BILD and CAT impact of life questionnaire. * Lung function tests (Forced Expiratory Volume in 1 sec, Forced vital capacity, Forced Expiratory Volume in 1 sec/Forced vital capacity, Total lung capacity, functional respiratory capacity, Transfer capacity for carbon monoxide, Alveolar Volume). * High-Resolution Computed Tomography (severity markers that will be used are: traction bronchiectasis, presence of honeycombing, ground glass opacities, reticulation, emphysema. Chest CT-scans will be reviewed independently by two radiologists blinded to each other).
During lung auscultation (10 minutes). Each patient will provide 10 recordings of 30 seconds. LUS images and 5 second video clips of each anatomic region (10 regions represented).
Performance of the DeepBreath algorithm to subcategorize ILD by discriminating digital lung sounds recordings and LUS (i.e. physiological parameters).
The performance of the DeepBreath algorithm to determine the subcategories of ILD such as IPF and NSIP based on digital lungs sounds and LUS according to gold standard diagnosis: * IPF follows the Fleischner Society Consensus criteria. * NSIP diagnosis follows the American Thoracic Society classification.
During lung auscultation (10 minutes). Each patient will provide 10 recordings of 30 seconds. LUS images and 5 second video clips of each anatomic region (10 regions represented).
Secondary Outcomes (6)
Performance of human expert-identified acoustic signatures.
During the data analysis period (i.e., after the 60-minute study intervention period).
Agreement of human labels with objectively clustered pathological sounds by machine learning.
During the data analysis period (i.e., after the 60-minute study intervention period).
Diagnostic performance of DeepBreath to detect crackles in IPF patients.
During the data analysis period (i.e., after the 60-minute study intervention period).
To test whether performance of DeepBreath could be improved using clinical features (i.e., signs, respiratory symptoms, demographics, medical history and basic paraclinical tests).
During the data analysis period (i.e., after the 60-minute study intervention period)
K-BILD
Baseline
- +1 more secondary outcomes
Study Arms (4)
IPF patients (group 1)
Consenting adult patients \>18 years old with with already-diagnosed IPF
NSIP patients (group 2)
Consenting adult patients \>18 years old with with already-diagnosed non-specific interstitial pneumonia (NSIP)
COPD patients (group 3)
Consenting adult patients \>18 years old with with already-diagnosed chronic obstructive pulmonary disease (COPD)
Control subjects (group 4)
Consenting age-matched (+/- 2.5 years) never smokers patients with normal lung function (spirometry, lung volume and Transfer Factor for Carbon Monoxide (TLCO)) followed in the pulmonology outpatient clinic with similar quality of electronic medical records but for diseases other than the outcome of interest, namely: 1. patients with obstructive sleep apnea. 2. patients followed-up for occupational lung diseases (miners, chemical workers, etc.). 3. patients followed-up for pulmonary nodules (considered benign after 2 years).
Interventions
Digital lung auscultation with the Eko core digital stethoscope (Eko Devices, Inc., CA, USA).
Lung ultrasonography
Impact of the diseases on subjects' health-related quality of life measured with standardized questionnaires (K-BILD, CAT)
Spirometry, body-plethysmographic parameters and lung diffusion capacity for carbon monoxide will be measured.
Eligibility Criteria
Cases: 120 patients (80 ILD \[40 IPF, 40 NSIP\], 40 COPD) will be recruited from an outpatient pulmonology clinic in Switzerland in daily clinical practice on the day of intervention. Probable and definitive IPF diagnosis will be made according to the Fleischner Society Consensus, NSIP diagnosis with the American Thoracic Society classification, and COPD with the Global Initiative for Chronic Obstructive Lung Disease criteria. Controls: 40 age-matched (+/- 2.5 years) never smokers with normal lung function (spirometry, lung volume and transfer factor for carbon monoxide) followed in the pulmonology outpatient clinic with similar quality of electronic medical records but for diseases other than the outcome of interest (see eligibility criteria) will serve as the 1:1 control group.
You may qualify if:
- Written informed consent
- age \> 18 years old.
- patients with already-diagnosed IPF (group 1) prior to the consultation (index) date.
- patients with already-diagnosed NSIP (group 2) prior to the consultation (index) date.
- patients with already-diagnosed COPD (group 3) prior to the consultation (index) date.
- Control subjects must be followed-up at the pulmonology outpatient clinic for:
- obstructive sleep apnoea.
- occupational lung diseases (miners, chemical workers, etc.).
- pulmonary nodules (considered benign after 2 years).
You may not qualify if:
- patients who cannot be mobilized for posterior auscultation.
- patients known for severe cardiovascular disease with pulmonary repercussion.
- patients known for a concurrent, acute, infectious pulmonary disease (e.g., pneumonia, bronchitis).
- patients known for asthma.
- patients known or suspected of immunodeficiency, alpha-1-antitrypsin deficit, and or under immunotherapy.
- patients with physical inability to follow procedures.
- patients with inability to give informed consent.
Contact the study team to confirm eligibility.
Sponsors & Collaborators
- Pediatric Clinical Research Platformlead
- University Hospital, Genevacollaborator
- Swiss Federal Institute of Technologycollaborator
- Hôpital du Valaiscollaborator
Study Sites (1)
Centre Hospitalier du Valais Romand
Sion, Valais, 1951, Switzerland
Related Publications (1)
Siebert JN, Hartley MA, Courvoisier DS, Salamin M, Robotham L, Doenz J, Barazzone-Argiroffo C, Gervaix A, Bridevaux PO. Deep learning diagnostic and severity-stratification for interstitial lung diseases and chronic obstructive pulmonary disease in digital lung auscultations and ultrasonography: clinical protocol for an observational case-control study. BMC Pulm Med. 2023 Jun 2;23(1):191. doi: 10.1186/s12890-022-02255-w.
PMID: 37264374DERIVED
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Officials
- PRINCIPAL INVESTIGATOR
Pierre-Olivier Bridevaux, Prof.
Hôpital du Valais, Switzerland
- STUDY DIRECTOR
Johan N. Siebert, MD
Geneva University Hospitals, Switzerland
Central Study Contacts
Study Design
- Study Type
- observational
- Observational Model
- CASE CONTROL
- Time Perspective
- PROSPECTIVE
- Sponsor Type
- OTHER
- Responsible Party
- SPONSOR
Study Record Dates
First Submitted
March 30, 2022
First Posted
April 8, 2022
Study Start
April 1, 2023
Primary Completion
October 6, 2024
Study Completion
October 31, 2024
Last Updated
April 12, 2024
Record last verified: 2024-04
Data Sharing
- IPD Sharing
- Will share
- Shared Documents
- STUDY PROTOCOL, CSR
- Time Frame
- Data will be available beginning 6 months and ending 5 years following article publication.
- Access Criteria
- De-identified data will be available from the corresponding author on reasonable request upon approval of a proposal and with a signed data access agreement. Data will be made available for a specified research purpose to qualified external researchers whose proposed use of the data has been approved by their institutional review board. The request proposal must include a statistician. There are no plans to share the digitized lung sounds collected during the study procedure.
All pertinent data generated or analysed during this study will be included in the published articles (and supplementary information files). An anonymous copy of the final (anonymized) datasets (but not digitized lung sounds) used and/or analyzed during the current study will be available from the corresponding author (see access criteria).