AI can help detect early larynx cancer from sound of voice: Study

AI can now detect early signs of larynx cancer by analyzing subtle changes in a person's voice. Researchers studied over 12,000 voice recordings, identifying key differences in pitch and noise levels. The technology shows promise for early diagnosis, particularly in men. This breakthrough could significantly improve survival rates for laryngeal cancer patients.

"Here we show that with this dataset we could use vocal biomarkers to distinguish voices from patients with vocal fold lesions from those without such lesions." – Dr. Phillip Jenkins

A team of US scientists showed that Artificial Intelligence (AI) can help detect early larynx or voice box cancer from the sound of the patient’s voice.

Key Points

1 AI analyzes pitch and noise variations to detect vocal fold lesions

2 Study focused on 12,523 voice recordings from 306 participants

3 Early detection could improve laryngeal cancer survival rates

4 Findings currently more effective for men than women

Cancer of the voice box is an important public health burden. In 2021, there were an estimated 1.1 million cases of laryngeal cancer worldwide, and approximately 100,000 people died from it.

 

Risk factors include smoking, alcohol abuse, and infection with human papillomavirus.

The prognosis for laryngeal cancer ranges from 35 per cent to 78 per cent survival over five years when treated, depending on the tumour’s stage and its location within the voice box.

Now, researchers from the Oregon Health & Science University showed that abnormalities of the vocal folds can be detected from the sound of the voice using AI.

Such ‘vocal fold lesions’ can be benign, like nodules or polyps, but may also represent the early stages of laryngeal cancer.

These proof-of-principle results open the door for a new application of AI: namely, to recognise the early warning stages of laryngeal cancer from voice recordings, said the team in the paper published in the journal Frontiers in Digital Health.

“Here we show that with this dataset we could use vocal biomarkers to distinguish voices from patients with vocal fold lesions from those without such lesions,” said Dr Phillip Jenkins, postdoctoral fellow in clinical informatics at Oregon.

In the study, Jenkins and team analysed variations in tone, pitch, volume, and clarity with 12,523 voice recordings of 306 participants from across North America.

A minority were from patients with known laryngeal cancer, benign vocal fold lesions, or two other conditions of the voice box: spasmodic dysphonia and unilateral vocal fold paralysis.

The researchers focused on differences in a number of acoustic features of the voice: for example, the mean fundamental frequency (pitch); jitter, variation in pitch within speech; shimmer, variation of the amplitude; and the harmonic-to-noise ratio, a measure of the relation between harmonic and noise components of speech.

They found marked differences in the harmonic-to-noise ratio and fundamental frequency between men without any voice disorder, men with benign vocal fold lesions, and men with laryngeal cancer.

They didn’t find any informative acoustic features among women, but it is possible that a larger dataset would reveal such differences.

Variation in the harmonic-to-noise ratio can be helpful to monitor the clinical evolution of vocal fold lesions, and to detect laryngeal cancer at an early stage, at least in men, the researchers said.

https://www.newkerala.com/news/o/ai-help-detect-early-larynx-cancer-sound-voice-study-647