| Abstrakt: |
A recent study conducted by researchers at the Luxembourg Institute of Health has developed a digital vocal biomarker that can accurately determine smoking status using audio recordings. The study found that certain voice features, such as fundamental frequency and formants, were lower in female smokers compared to non-smokers. The biomarker achieved an accuracy of 0.71 and an AUC of 0.76 for female participants, and 0.65 and 0.68 for male participants. This research provides a rapid and scalable method for assessing smoking status in clinical and epidemiological research. [Extracted from the article] |
