Contactless Ultrasound Data Acquisition in Emergency Departments to Discriminate the Origin of Dyspnea and Chest Pain

Prospective Study for Data Acquisition in Emergency Departments to Develop a Discrimination Algorithm for the Origin of Dyspnea and Chest Pain Using the ADx-One Medical Device

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:

• Clinical examination lacks discriminative power. Signs and symptoms are rarely disease-specific, and they may be blunted - or altogether absent - in the elderly (Metlay, Kapoor et Fine, 1997; Lien et al., 2002).
• Chest radiography is often suboptimal. Films are frequently acquired with the patient supine, stooped, or unable to hold a full inspiration; the underlying parenchymal changes of ageing further compromise interpretation, and the radiographic signs themselves are notoriously nonspecific (Mueller-Lenke et al., 2006; Hawkins et al., 2009; Self et al., 2013).
• Interpretation is poorly reproducible, and the initial ED diagnosis proves incorrect in nearly one third of cases (Hopstaken et al., 2004; Claessens et al., 2015).

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.

Inclusion Criteria:

• Presentation 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.
• Patient able to sit on a chair or on the edge of the bed
• Affiliation to national health insurance
• Able to receive study information, understand the study, and provide written informed consent

Exclusion Criteria:

• • Immediate need for life-saving intervention or clinical instability incompatible with study procedures.

  • Shock or severe hemodynamic instability, for example systolic blood pressure <90 mmHg for at least 30 minutes or associated signs of hypoperfusion.
  • Altered mental status or any condition preventing provision of valid informed consent.
  • Known cognitive impairment preventing informed consent.
  • Transfer to another care site before the ADx-One acquisition can be performed.
  • Known pregnancy
  • Minor, legally protected adult, or person deprived of liberty.
  • Participation in another interventional clinical study judged incompatible with this study.