Potential of acoustic voice analysis in diagnostics of noncommunicable diseases: a systematic review and meta-analysis

Aim. To determine the potential of using acoustic voice analysis parameters in diagnosis of noncommunicable diseases (NCDs). Material and methods . The information search was carried out according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) in the PubMed, Google Scholar, Clinical Trials, Cyberleninka and eLibrary databases. Four publications, including six studies, were selected for the final analysis of full-text articles. These studies included acoustic voice analysis in diabetes type 1 and 2, asthma, chronic obstructive pulmonary disease, pneumonia. The meta-analysis assessed changes in voice frequency (Jitter) and amplitude (Shimmer) in patients with NCDs compared to healthy volunteers. Results. The meta-analysis based on Jitter and Shimmer included 203 patients with NCDs and 132 healthy volunteers. Jitter in patients with NCDs was significantly higher compared to patients without diseases (standardized mean difference 2,23, 0,83-3,62, I2=97,03%, p=0,002). Shimmer in patients with the diseases under study also turned out to be significantly higher compared to patients without diseases (standardized mean difference 0,81, 0,11-1,52, I2=91,06%, p=0,024). Conclusion. The current systematic review and meta-analysis demonstrated the possibility of using acoustic voice analysis in the diagnosis of NCDs.