AI-facilitated home monitoring for cystic fibrosis exacerbations across pediatric and adult populations.

Abstract

Background: AI-aided home stethoscopes offer the opportunity of continuous remote monitoring of cystic fibrosis (CF) patients, reducing the need for clinic visits.

Aim: This study aimed to analyze the possibility of detecting CF pulmonary exacerbations (PEx) at home using an AI-aided stethoscope (AIS).

Materials and methods: In a six-month study, 129 CF patients (85 children, 44 adults) used AIS for at least weekly self-examinations, recording various parameters: wheezes, rhonchi, crackles intensity, respiratory and heart rate, and inspiration-to-expiration ratio. Health state surveys were also completed. Physicians evaluated 5160 examinations to identify PEx. Machine learning models were trained using those parameters, and AUCs were calculated for PEx detection.

Results: 522 self-examinations were diagnosed clinically as exacerbated. AI-aided home stethoscopes detected 415 exacerbated self-examinations (sensitivity 79.5 % at specificity 89.1 %). Among the single-parameter discriminators, coarse crackles intensity exhibited an AUC of 70 % (95% CI: 65-75) for young children, fine crackles intensity demonstrated an AUC of 75 % (95 % CI: 72-78) for older children, and an AUC of 93 % (95 % CI: 92-93) was achieved for adults using fine crackles intensity. The combination of parameters yielded the highest efficacy, with AUC exceeding 83% for objective parameters from the AI module alone and exceeding 90 % when incorporating both objective and subjective parameters across all groups.

Conclusions: The AI-aided home stethoscope has proven to be a reliable tool for detecting PEx with greater accuracy than self-assessment alone. Implementing this technology in healthcare systems has the potential to provide valuable insights for timely intervention and management of PExes.