An observational study in Dyspnea and Chest Pain, sponsored by Austral Diagnostics. Not yet recruiting at 1 site in France. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-06-17.
Sponsored by Austral Diagnostics · Observational
PAnDA-One is a prospective, multicenter, interventional study (10 centers, France) aimed at developing and validating a diagnostic support algorithm based on the ADx-One medical device, which non-invasively acquires thoracic vibrations using airborne ultrasound.
The study will enroll 2,500 patients presenting to the emergency department with acute dyspnea or non-traumatic chest pain, divided into a development cohort (N = 1,500) and an independent test cohort (N = 1,000). The deep learning algorithm will be trained to discriminate cardiovascular from non-cardiovascular origins of symptoms, and its performance will be assessed by AUROC, sensitivity, and specificity against a final diagnosis established by an expert adjudication committee.
Patient management will not be modified by study participation.
Acute dyspnea is a common reason for emergency department (ED) presentation, accounting for 7 to 12% of all consultations (Mockel et al., 2013). More than half of these patients are over 65 years of age - a population whose respiratory system is particularly vulnerable due to parenchymal degeneration and age-related decline in ventilatory and immune function (Boisguérin et Mauro, 2017). In the ED, the leading causes of acute dyspnea are acute heart failure, respiratory tract infections, exacerbations of asthma or chronic obstructive pulmonary disease, and pulmonary embolism (Ray et al., 2006). These episodes frequently lead to hospitalization and carry substantial mortality - reaching 10% in acute heart failure, for instance (Freund et al., 2020) - as well as a marked loss of autonomy, whether driven by the respiratory impairment itself or by the deconditioning that follows prolonged hospital stays.
Non-traumatic chest pain is another major reason for ED presentation, accounting for 5-10% of all visits, and shares with dyspnea the requirement for rapid etiological triage between life-threatening cardiovascular causes - acute coronary syndrome, pulmonary embolism, acute aortic syndrome, pericarditis, pneumothorax - and benign musculoskeletal or functional causes. Despite the ECG, high-sensitivity troponin and validated clinical scores, missed acute coronary syndrome at ED discharge has been reported in approximately 2% of patients (Pope et al., 2000), and the widespread use of "rule-out" strategies drives substantial use of coronary CTA and CT pulmonary angiography, with associated radiation exposure, costs and observation admissions. Diagnostic uncertainty is particularly pronounced in younger adults and in women, in whom the pretest probability of acute coronary syndrome is lower but pulmonary embolism, pneumothorax and pericarditis carry a non-negligible relative weight. Furthermore, several studies continue to highlight the increased use of irradiative imaging studies, with no clinical benefit in terms of diagnostic and prognostic (Roussel et al., 2023).
At present, the etiological work-up of acute dyspnea and chest pain relies on the combination of clinical examination, laboratory testing, and chest radiography (Olson et Davis, 2020; Miró et al., 2025). This strategy has well-documented limitations in the ED, particularly in older patients:
ADx-One is an airborne ultrasound device which relies on Surface Motion Camera technology.
The ADx-One device is based on the non-invasive acquisition of minute chest surface movements induced by cardiopulmonary activity (\~100 µm), using airborne ultrasound. These vibrations, resulting from mechanical interactions between the heart, lungs, and chest wall, constitute a physical signature that integrates multiple pathophysiological determinants (Shirkovskiy et al., 2018).
In particular, any modification in intrathoracic composition or mechanical properties-whether due to the presence of fluid (congestion, effusion), solid tissue changes (consolidation, atelectasis), or abnormal air presence (pneumothorax)-is likely to alter these vibratory signatures.
The overall purpose of this clinical investigation is to collect ADx-One acquisition data in emergency department patients in order to develop and evaluate on distinct cohorts a diagnostic support algorithm intended to assist discrimination of the origin of acute cardiopulmonary symptoms.
894 studies on the registry are indexed under Dyspnea; 189 are open to participants now.
This study's planned enrollment of 2,500 is above the median of 106 across 272 observational studies indexed under Dyspnea.
Browse Dyspnea studies →This is the only study on the registry with Austral Diagnostics as lead sponsor.
Counted across the registry records on this site, refreshed daily.
Patients presenting to the emergency department for one or more of the following symptoms of less than 14 days' duration: acute non-traumatic dyspnea, or recent worsening of chronic dyspnea, or non-traumatic chest pain.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Immediate need for life-saving intervention or clinical instability incompatible with study procedures.
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
All patients will follow the same intervention but data from this cohort will only be used for training the algorithm.
Device: All patients from both groups will be imaged with airborne ultrasound device
All patients will follow the same intervention but data from this cohort will only be used for testing the algorithm.
Device: All patients from both groups will be imaged with airborne ultrasound device
Patients from both cohorts will follow their usual routine, except for stepping in front of the machine so that one or two images of their chest and back can be taken.
Number of correct assignations for cardiovascular involvement by the algorithm trained on labeled data.
Diagnostic performance for distinguishing cardiovascular from non-cardiovascular involvement, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations for acute heart failure with pulmonary edema by the algorithm.
Diagnostic performance for the diagnosis of acute heart failure with pulmonary edema, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC
Time frame: Within the first hour after ED admission.
Number of correct assignations for COPD exacerbation by the algorithm.
Diagnostic performance for the diagnosis of chronic obstructive pulmonary disease, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for lower respiratory tract infection, defined as alveolar or interstitial involvement from an infectious cause.
Diagnostic performance for the diagnosis of lower respiratory tract infection, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for absence of pulmonary and cardiovascular involvement.
Diagnostic performance for the diagnosis of absence of both pulmonary and cardiovascular involvement, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for pulmonary involvement, either isolated or combined with cardiovascular involvement.
Diagnostic performance for distinguishing pulmonary from non-pulmonary involvement, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC. Pulmonary involvement is defined as any diagnosis of pulmonary or parenchymal lesion or bronchial involvement, including (but not limited to): upper respiratory tract infection, lower respiratory tract infection, exacerbation of obstructive ventilatory disorder such as asthma or COPD.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for lung interstitial syndrome.
Diagnostic performance for the diagnosis of interstitial syndrome, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for detecting an impaired left ventricular ejection fraction.
Diagnostic performance for the diagnosis of a left ventricular ejection fraction \< 55% at cardiac echography at any point in the month before or after the inclusion, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for pulmonary embolism.
Diagnostic performance for the diagnosis of pulmonary embolism, diagnosed either at computed tomography pulmonary angiogram or V/Q scan, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for upper respiratory tract infection.
Diagnostic performance for the diagnosis of upper respiratory tract infection, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for atelectasis.
Diagnostic performance for the diagnosis of atelectasis, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for alveolar syndrome.
Diagnostic performance for the diagnosis of alveolar syndrome, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for pleural effusion.
Diagnostic performance for the diagnosis of pleural effusion, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC.
Time frame: Within the first hour after ED admission.
Number of correct assignations by the algorithm for pneumothorax.
Diagnostic performance for the diagnosis of pneumothorax, including sensitivity, specificity, positive and negative predictive values, likelihood ratios, and AUROC
Time frame: Within the first hour after ED admission.
Plan to share: Undecided — Need to check this internally, also on IP.
No publications or documents are linked to this record.
This study is not yet recruiting, as verified in Jun 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.