CORELSA - Remote stethoscope system for fast and standardized auscultations of large numbers of patients with respiratory syndromes
Ides, K.; Aerts, A.; baeyens, R.; Balemans, N.; Bosschaerts, T.; Cazaerck, J.; Ceulemans, D.; De Mey, F.; Jansen, W.; Kerstens, R.; Laurijssen, D.; Lauwers, E.; Schenck, A.; Schouten, G.; Simon, R.; Verellen, T.; Verreycken, E.; Jorens, P.; Verhulst, S.; Daems, W.; Steckel, J.
Show abstract
One of the major impacts of the current COVID-19 pandemic is the immense strain that is being put on the intensive care units. As a typical SARS-CoV-2 infection often leads to severe acute respiratory syndromes, one of the most basic essential examinations is lung auscultation. There are different categories of lung sounds that can be assessed with a stethoscope like crackles, wheezes, rhonchi and coarse breath sounds. Each of these malicious lung sounds contribute to a clinical assessment and follow-up of the patients airways and lungs and can indicate the development of pneumonia. Therefore, auscultation on a regular basis is essential, but it also takes a lot of time for the physicians. Moreover, because of the risk of infection for health care workers, it is becoming increasingly difficult or sometimes impossible to safely use a stethoscope. Here we introduce a remote stethoscope system that can help to reduce the workload of physicians and nurses, diminishes the risk of contamination and leads to more standardized auscultation, which can also be stored and reevaluated. We provide a detailed description of our system, which consists of parts that are low cost, easily available in most parts of the world, or can be 3D printed. We provide instructions and an open source software stack to run such a system for a large number of patients which can be remotely auscultated from a central computer. We believe that the system described in this paper can allow various institutes to replicate the system, and increase the safety and reduce the overall workload in the intensive care units around the world.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Multimodal Pain Recognition in Postoperative Patients: A Machine Learning Approach 92%
- The Remote Analysis Of Breath Sound In COVID-19 Patients: A Series Of Clinical Cases 91%
- Diagnosing Chronic Obstructive Airway Disease: a diagnostic accuracy study of a smartphone delivered algorithm combining patient-reported symptoms and cough analysis for use in acute care consultations. 91%
Similar papers in this journal
- A Cross-sectional Feasibility Study to Evaluate the Usability and Efficacy of “Swaasa”: An AI-Platform for Rapid Respiratory Health Assessment 95%
- Development and Clinical Validation of Swaasa AI Platform for screening and prioritization of Pulmonary TB 94%
- Transformers for rapid detection of airway stenosis and stridor 94%
Similar papers in this journal
Similar papers in this journal
- Early Prediction of Hemodynamic Shock in the Intensive Care Units with Deep Learning on Thermal Videos 94%
- CardioMEA: Comprehensive Data Analysis Platform for Studying Cardiac Diseases and Drug Responses 92%
- Effective Assessments of a Short-duration Poor Posture on Upper Limb Muscle Fatigue before Physical Exercise 91%
Similar papers in this journal
- Automated Image Transcription for Perinatal Blood Pressure Monitoring Using Mobile Health Technology 94%
- A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms 94%
- From theoretical models to practical deployment: A perspective and case study of opportunities and challenges in AI-driven healthcare research for low-income settings 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.