AI Shows Promise in Early Detection of Laryngeal Cancer Through Voice Analysis

AI detects early signs of laryngeal cancer from voice recordings

FrontiersAug 12 2025 Cancer of the voice box or larynx 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% to 78% survival over five years when treated, depending on the tumor's stage and its location within the voice box. Catching cancer early is key for a patient's prospects. At present, laryngeal cancers are diagnosed through video nasal endoscopy and biopsies - onerous, invasive procedures. Getting to a specialist who can perform these procedures can take time, causing delays in diagnosis. But now, researchers have shown in Frontiers in Digital Health that abnormalities of the vocal folds can be detected from the sound of the voice. 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 recognize the early warning stages of laryngeal cancer from voice recordings. 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, postdoctoral fellow in clinical informatics at Oregon Health & Science University, and study's corresponding author Voice messages Jenkins and his colleagues are members of the 'Bridge2AI-Voice' project within the US National Institute of Health's 'Bridge to Artificial Intelligence' (Bridge2AI) consortium, a nationwide endeavor to apply AI to complex biomedical challenges. Here, they analyzed variations in tone, pitch, volume, and clarity within the first version of the public Bridge2AI-Voice dataset, 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. The researchers 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. The authors concluded that especially 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. "Our results suggest that ethically sourced, large, multi‑institutional datasets like Bridge2AI‑Voice could soon help make our voice a practical biomarker for cancer risk in clinical care," said Jenkins. Building a bridge to AI Now that the proof-of-principle has been established, the next step is to use these algorithms on more data and test them in clinical settings on patient voices. "To move from this study to an AI tool that recognizes vocal fold lesions, we would train models using an even larger dataset of voice recordings, labeled by professionals. We then need to test the system to make sure it works equally well for women and men," said Jenkins. "Voice-based health tools are already being piloted. Building on our findings, I estimate that with larger datasets and clinical validation, similar tools to detect vocal fold lesions might enter pilot testing in the next couple of years," predicted Jenkins. Frontiers Journal reference: Jenkins, P., et al. (2025) Voice as a Biomarker: Exploratory Analysis for Benign and Malignant Vocal Fold Lesions. Frontiers in Digital Health. doi.org/10.3389/fdgth.2025.1609811.

AI voice test could help spot dangerous throat lesions before symptoms appear

By Dr. Sanchari Sinha Dutta, Ph.D.Reviewed by Lauren HardakerAug 14 2025 By measuring subtle changes in voice quality, AI could help doctors detect dangerous vocal fold lesions before symptoms worsen. Study: Voice as a biomarker: exploratory analysis for benign and malignant vocal fold lesions. Image Credit: 3dMediSphere / Shutterstock An exploratory study reveals that subtle changes in voice patterns, especially variability in harmonic-to-noise ratio, could serve as early warning signs of vocal fold lesions, paving the way for future AI-powered screening tools. A new study led by Oregon Health and Science University and Portland State University researchers identified distinct vocal features that may serve as potential biomarkers for early detection of benign and malignant vocal fold lesions. The study is published in the journal Frontiers in Digital Health. Background Alterations in voice pitch, loudness, and quality characterize vocal disorders. Various factors can potentially trigger these disorders, including vocal fold pathology, neurologic conditions, or functional voice use patterns. Individuals with voice disorders often experience poor quality of life, low self-esteem, work-related difficulties, and social isolation. These experiences are particularly more pronounced among individuals whose professional roles significantly depend on voice communication. Both benign and malignant vocal fold lesions (laryngeal cancer) are associated with voice disorders. While benign lesions substantially affect voice quality and cause morbidity, malignant lesions are often life-threatening if left untreated. Dysphonia (a condition characterized by abnormal voice) is one of the first symptoms of vocal fold lesions, which requires a diagnostic process including visualization of the larynx and assessment of the lesion's morphology through video endoscopy. The larynx is an anatomical structure in the neck where vocal folds are located. Recent advancements in artificial intelligence (AI) technologies have facilitated human voice analysis for early detection of a variety of health conditions, including laryngeal pathology, neurological and psychological disorders, head and neck cancers, and diabetes. The use of voice as a digital biomarker provides a promising platform for non-invasive detection and screening of these potentially life-threatening conditions. The Voice to AI project, as part of the National Institutes of Health (NIH) Bridge to Artificial Intelligence (Bridge2AI) consortium, aims to analyze voice as a biomarker of health for use in clinical care. In the current study, researchers analyzed the Bridge2AI-Voice dataset to identify specific acoustic features that effectively distinguish laryngeal cancer and benign vocal fold lesions from other vocal pathologies and healthy voice function. Acoustic features refer to measurable voice properties, including pitch, loudness, and quality. The study The dataset analyzed in the study includes 12,523 recordings of 306 participants collected across five sites in North America. Acoustic analyses focused on Rainbow Passage recordings (180 recordings from 176 participants) with features pre-extracted using openSMILE software. The main aim of the study was the identification of acoustic features that can distinguish the voices of participants with vocal fold lesions from those without any vocal disorders, as well as distinguish the voices of participants with lesions from those with other vocal disorders. The participants were categorized into two groups based on lesion type and vocal disorder diagnosis. The first group included participants with laryngeal cancer, benign lesions, or no voice disorder, and the second group included participants with laryngeal cancer or benign lesions without other voice disorders, as well as those with other vocal disorders (spasmodic dysphonia or vocal fold paralysis). Transgender participants were excluded from sex-stratified analyses because prior voice-altering care could not be verified. Four acoustic features plus the variability (standard deviation) of HNR, fundamental frequency, jitter, shimmer, and harmonic-to-noise ratio (HNR) were extracted from the voice recordings of participants for comparative analysis. Fundamental frequency refers to the frequency at which the vocal cords vibrate; jitter is the measure of fundamental frequency fluctuations; shimmer is the measure of fluctuations in the amplitude of sound waves; and HNR is the ratio of the periodic to aperiodic component in a speech signal. Key findings The analysis of acoustic features revealed that participants with benign lesions have significantly different mean HNR and fundamental frequency compared to those without any voice disorder, and significantly different HNR variability (SD) compared to laryngeal cancer. HNR variability (SD) was not significantly different between benign lesions and no voice disorder. Mean HNR and fundamental frequency did not differ significantly between benign lesions and laryngeal cancer. The gender-related comparison revealed in cisgender men similar differences in mean HNR and HNR variability vs no voice disorder and HNR variability vs laryngeal cancer, but not in female participants, which might be due to the smaller sample size. No significant differences were found for jitter or shimmer in any comparison, and no acoustic feature significantly distinguished lesion groups from other vocal disorders in the second analysis group. Study significance The study identifies harmonic-to-noise ratio variability (standard deviation) as a promising voice-related biomarker for early detection and monitoring of vocal fold lesions. The periodic component of this ratio arises from regular glottal pulses during phonation, and the aperiodic component is the noise produced from turbulence as air flows through the glottis (the center of the larynx). Both the mean and the standard deviation of the harmonic-to-noise ratio were measured in the study, as the researchers believed that this variability would help measure consistency in vocal production. The observed differences in standard deviation between benign and malignant lesion groups suggest that this feature may serve as a useful marker for monitoring lesion progression and detecting laryngeal cancer at an early stage. However, the study could not detect significant differences in the harmonic-to-noise ratio and its variability between participants with benign or malignant lesions and those with other vocal disorders. This indicates that distinguishing lesions from other vocal pathologies may be more challenging. Notably, the study could not detect significant differences in the harmonic-to-noise ratio and its variability among female participants. This highlights the need for analyzing additional acoustic features in order to consider voice as a promising early indicator of vocal fold lesions. The authors emphasise that these are exploratory findings and do not constitute a validated screening test. They call for larger, more diverse cohorts and additional acoustic features to be assessed, particularly in women, before integration into clinical tools. Overall, the study findings highlight the future potential of validated AI-based voice screening tools to identify individuals with subtle voice changes who may not otherwise seek care, especially in primary care or telehealth settings. Such tools could prompt earlier referrals to voice specialists, help prioritize urgent cases, and reduce diagnostic delays. Journal reference: Jenkins P. 2025. Voice as a biomarker: exploratory analysis for benign and malignant vocal fold lesions. Frontiers in Digital Health.DOI: 10.3389/fdgth.2025.1609811, https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1609811/full

AI could soon detect early voice box cancer from the sound of your voice

Cancer of the voice box or larynx 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% to 78% survival over five years when treated, depending on the tumor's stage and its location within the voice box. Catching cancer early is key to a patient's prospects. At present, laryngeal cancers are diagnosed through video nasal endoscopy and biopsies -- onerous, invasive procedures. Getting to a specialist who can perform these procedures can take time, causing delays in diagnosis. But now, researchers have shown in Frontiers in Digital Health that abnormalities of the vocal folds can be detected from the sound of the voice. 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 recognize the early warning stages of laryngeal cancer from voice recordings. "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, a postdoctoral fellow in clinical informatics at Oregon Health & Science University, and the study's corresponding author. Voice messages Jenkins and his colleagues are members of the "Bridge2AI-Voice" project within the US National Institute of Health's "Bridge to Artificial Intelligence" (Bridge2AI) consortium, a nationwide endeavor to apply AI to complex biomedical challenges. Here, they analyzed variations in tone, pitch, volume, and clarity within the first version of the public Bridge2AI-Voice dataset, 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. The researchers 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. The authors concluded that especially 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. "Our results suggest that ethically sourced, large, multi‑institutional datasets like Bridge2AI‑Voice could soon help make our voice a practical biomarker for cancer risk in clinical care," said Jenkins. Building a bridge to AI Now that the proof-of-principle has been established, the next step is to use these algorithms on more data and test them in clinical settings on patient voices. "To move from this study to an AI tool that recognizes vocal fold lesions, we would train models using an even larger dataset of voice recordings, labeled by professionals. We then need to test the system to make sure it works equally well for women and men," said Jenkins. "Voice-based health tools are already being piloted. Building on our findings, I estimate that with larger datasets and clinical validation, similar tools to detect vocal fold lesions might enter pilot testing in the next couple of years," predicted Jenkins.

AI could detect early voice box cancer from the sound of your voice - Earth.com

Your voice might reveal more than just what you say. It could hold hidden clues about benign conditions that you carry, like nodules or polyps, and even early stages of voice box cancer. A recent study found that our voice could signal abnormalities in the vocal cords, potentially helping detect issues early. The researchers developed an AI tool that could record the voice, analyze it, and predict the early signs of laryngeal cancer. "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, the author of the study and a postdoctoral fellow in clinical informatics at Oregon Health & Science University (OHSU). Dr. Jenkins and his colleagues are part of the "Bridge2AI-Voice" project, and have been exploring the applications of AI to solve biomedical challenges. They studied 12,523 voice recordings from 306 participants across North America. Understanding how the voice is produced and how cancer alters it helps explain why AI can detect problems early. The larynx, commonly known as the voice box, is a hollow tube situated in the middle of the neck that helps us make sounds including whispering, singing, or shouting. When we make sound, the vocal cords, muscle bands found in the larynx, vibrate and produce voice. Laryngeal cancer, commonly known as voice box cancer, poses a growing public health concern. It can be caused by certain types of human papillomavirus (HPV) and is also strongly linked to the frequent use of tobacco and alcohol. Epidemiological studies suggest that in 2021 alone, doctors diagnosed around 1.1 million laryngeal cancer cases worldwide, and approximately 100,000 people died from it. If it is detected early and the tumor is located in a favorable spot, the chances of survival are high. If detected at an advanced stage, however, treatment can be more challenging. Currently, biopsies and video nasal endoscopies are used to diagnose voice box anomalies. A biopsy involves taking a small piece of tissue from the tumor and examining it under a microscope. It is an invasive procedure. A nasal endoscopy involves inserting a thin, flexible tube with a camera, called an endoscope, through the nasal passage to view the larynx. While this is minimally invasive and offers a direct view of the affected site, it can still cause discomfort, pain, and in some cases, bleeding or fainting. Since not all doctors can perform these diagnostic procedures, patients often face delays in searching for the right specialists for diagnosis. These drawbacks call for a safer, less invasive, and more accessible diagnostic approach, like the recently developed AI tool. The team measured the acoustic features - the physical characteristics - of the voice, such as quality, pitch, and loudness. Participants included individuals with diagnosed laryngeal cancer, benign vocal cord lesions, or other voice disorders. The researchers analyzed the Harmonic-to-noise ratio (HNR), which measures sound clarity. For instance, if you have a high HNR, your sound is clear, with clear harmonics and less noise. People with laryngeal anomalies, on the other hand, tend to have a low HNR. They also watched the fundamental frequency closely. This refers to the average pitch of the voice. By comparing these measurements across participants, the team identified distinct patterns that were linked to vocal health. The study found clear differences in the voice parameters among men with no voice disorder, those with benign vocal cord lesions, and those with laryngeal cancer. They did not spot clear differences in these parameters among women participants, but hope that a larger dataset could reveal them. The authors concluded that this approach could clinically evaluate vocal fold lesions and early laryngeal cancer, at least in men. "Our results suggest that ethically sourced, large, multi-institutional datasets like Bridge2AI-Voice could soon help make our voice a practical biomarker for cancer risk in clinical care," said Dr. Jenkins. Since the authors showed that AI can be effective in the early diagnosis of laryngeal cancer, the next step is to test it with more voice samples in clinical settings. To turn this into a useful AI tool, the researchers need to analyze more voice recordings using the same approach. "We then need to test the system to make sure it works equally well for women and men," said Dr. Jenkins. According to the study, AI health tools for voice analysis are still not ready for use in clinics or hospitals. However, they could move into early-stage testing within the next couple of years. The AI tool could offer a promising addition to the current diagnostic methods. Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

AI could help detect throat cancer from voice recordings, study says

Researchers say AI could be used to analyse short voice recordings to flag abnormalities in the vocal folds, ranging from harmless nodules to the first signs of laryngeal cancer. A simple voice recording could one day help doctors spot early signs of throat cancer, according to new research. In a study published in Frontiers in Digital Health, scientists found that artificial intelligence (AI) could potentially detect abnormal growths on the vocal cords, from benign nodules to early-stage laryngeal cancer, by analysing short voice recordings. The findings could support efforts to find an easier, faster way to diagnose cancerous lesions on the vocal cords, also known as folds. "With this dataset we could use vocal biomarkers to distinguish voices from patients with vocal fold lesions from those without such lesions," said Phillip Jenkins, the study's lead author and a postdoctoral researcher in clinical informatics at Oregon Health and Science University in the United States. Why early detection of throat cancer matters Cancer of the voice box, or larynx, affects more than a million people worldwide and kills roughly 100,000 every year. It is the 20th most common cancer in the world. Smoking, alcohol use, and certain strains of HPV (human papillomavirus) are key risk factors, and survival rates vary from around 35 per cent to 90 per cent depending on how early the disease is diagnosed, according to Cancer Research UK. One of the most common warning signs for laryngeal cancer is hoarseness or changes in the voice that last more than three weeks. Other symptoms include a persistent sore throat or cough, difficulty or pain when swallowing, a lump in the neck or throat, and ear pain. Early detection of laryngeal cancer is crucial because it significantly improves survival rates and treatment outcomes. Yet current diagnostic methods, including nasal endoscopies and biopsies, are invasive, uncomfortable, and often slow, requiring specialist equipment and expertise that many patients struggle to access quickly. Developing a simple tool to flag early signs of vocal fold abnormalities through a quick voice recording could transform how throat cancer is detected - making it faster, more affordable and accessible to a wider population. The next steps for AI-driven diagnosis The research team examined about 12,500 voice recordings from 306 people across North America. They looked for subtle acoustic patterns, such as changes in pitch, loudness, and harmonic clarity. The team identified clear differences for men in the harmonic-to-noise ratio and pitch between those with healthy voices, benign lesions, and cancer. No significant patterns were found in women, but the researchers say this may be due to the smaller dataset. Jenkins said that the results indicate large datasets "could soon help make our voice a practical biomarker for cancer risk in clinical care". The next step is to train AI models on larger, professionally labelled datasets and test them in clinical settings. The team would also need to test the system to make sure it works well for both men and women, he said. "Voice-based health tools are already being piloted," Jenkins said. "Building on our findings, I estimate that with larger datasets and clinical validation, similar tools to detect vocal fold lesions might enter pilot testing in the next couple of years".