Acute chest syndrome (ACS) is a leading cause of death for those with sickle cell disease (SCD). ACS is defined by the development of a new pulmonary infiltrate on chest X-ray, with fever and respiratory symptoms. Efforts have been made to apply various technologies in the hospital setting to provide earlier detection of ACS than X-ray, but they are expensive, increase radiation exposure to the patient, and are not technologies that are easily transferrable for home use to help with early diagnosis. We present preliminary studies on patients suggesting that acoustical measurements recorded quantitatively with contact sensors (electronic stethoscopes) and analyzed using advanced computational analysis methods may provide an earlier diagnostic indicator of the onset of ACS than is possible with current clinical practice. Novel in silico models of respiratory acoustics utilizing image-based and algorithmically developed lungs with full conducting airway trees support and help explain measured acoustic trends and provide guidance on the next steps in developing and translating a diagnostic approach. More broadly, the experimental and computational techniques introduced herein, while focused on monitoring and predicting the onset of ACS, could catalyze further advances in mobile health (mhealth)-enabled, computer-based auscultative diagnoses for a wide range of cardiopulmonary pathologies.
A 17‐Year‐Old Patient with Pulmonary Infiltrate and Rash