AI Article Synopsis
- Voice changes can indicate laryngeal cancer, often diagnosed through laryngoscopy, and early detection could improve with voice screenings.
- This study introduces an AI model that differentiates between healthy voices, laryngeal cancer voices, and other laryngeal issues using collected voice samples.
- While the model shows high accuracy (0.85-0.97) distinguishing healthy voices from laryngeal diseases, multiclass classification accuracy is lower (0.75-0.83), indicating both the challenges and potential of AI in voice-based cancer diagnosis.
Article Abstract
Voice change is often the first sign of laryngeal cancer, leading to diagnosis through hospital laryngoscopy. Screening for laryngeal cancer solely based on voice could enhance early detection. However, identifying voice indicators specific to laryngeal cancer is challenging, especially when differentiating it from other laryngeal ailments. This study presents an artificial intelligence model designed to distinguish between healthy voices, laryngeal cancer voices, and those of the other laryngeal conditions. We gathered voice samples of individuals with laryngeal cancer, vocal cord paralysis, benign mucosal diseases, and healthy participants. Comprehensive testing was conducted to determine the best mel-frequency cepstral coefficient conversion and machine learning techniques, with results analyzed in-depth. In our tests, laryngeal diseases distinguishing from healthy voices achieved an accuracy of 0.85-0.97. However, when multiclass classification, accuracy ranged from 0.75 to 0.83. These findings highlight the challenges of artificial intelligence-driven voice-based diagnosis due to overlaps with benign conditions but also underscore its potential.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11549102 | PMC |
| http://dx.doi.org/10.1038/s41598-024-58817-x | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Endosonography in head and neck imaging and surgery.
Ultraschall Med
December 2024
Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital Regensburg, Germany.
This CME article explores the evolving role of endosonography in otorhinolaryngology and head and neck surgery. Endosonography offers significant potential to improve imaging inside the upper respiratory tract, particularly with advancements in probe technology and imaging resolution. The article will describe the sonoanatomy of the oral cavity, pharynx, and larynx and the selection of probes and scanning techniques used for the various anatomical sites.
View Article and Find Full Text PDFDefining the Thyroid-RLN Entry Triangle for Enhanced Recurrent Laryngeal Nerve Exposure in TOETVA: A Retrospective Study.
J Otolaryngol Head Neck Surg
December 2024
Department of Thyroid Surgery, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University/Hunan Cancer Hospital, Changsha, P.R. China.
Background: Injury to the recurrent laryngeal nerve (RLN) and parathyroid glands (PGs) are the most common and serious complications during the transoral endoscopic thyroidectomy vestibular approach (TOETVA), and their exposure and protection are the most important factors affecting the operation time. Here, we report a novel anatomical landmark and surgical method to shorten the operative time and reduce the chance of injury to the RLN and PGs.
Methods: According to the different exposure methods of the RLN, patients were divided into the experimental group (from top to bottom, E-group) and the comparison group (from outside to inside, C-group), and 1:1 propensity score-matching (PSM) was performed.
Nomogram for predicting early death in elderly patients with laryngeal squamous cell carcinoma: A population-based SEER study.
PLoS One
December 2024
Department of Otorhinolaryngology of Longgang Center Hospital, The Ninth People's Hospital of Shenzhen, Shenzhen, China.
Background: The disease and mortality rates of patients with laryngeal squamous cell carcinoma (LSCC) stabilize after peaking at the age of 60 years. This study aimed to identify risk factors associated with early death (death within 6 months) in elderly (≥60 years) patients with LSCC and to establish predictive nomograms to aid clinicians in developing individualized treatment plans.
Methods: Data pertaining to elderly patients with LSCC between 2004 and 2015 was obtained from the Surveillance, Epidemiology, and End Results database (version 8.
Infrahyoid Myocutaneous Flaps with Common Wall of Hypopharyngeal and Esophageal Serosas for Voice Rehabilitation After Total Laryngectomy.
J Otolaryngol Head Neck Surg
December 2024
ENT Institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan University, Shanghai, China.
Importance: Patients who undergo total laryngectomy lose the voice function permanently. It is important to reconstruct the voice function of the patients after total laryngectomy.
Objective: To explore a novel method for voice rehabilitation by suturing infrahyoid myocutaneous flaps to the hypopharyngeal and esophageal serosas after total laryngectomy and investigate its clinical efficacy.
A feasibility study of using virtual noncontrast images synthesized from dual-energy computed tomography for radiotherapy treatment planning.
Quant Imaging Med Surg
December 2024
Department of Radiotherapy, Peking Union Medical College Hospital, Beijing, China.
Background: In the traditional computed tomography (CT) simulation process, patients need to undergo CT scans before and after injection of iodine-based contrast agent, resulting in a cumbersome workflow and additional imaging dose. Contrast-enhanced spectral CT can synthesize true contrast-enhanced (TCE) images and virtual noncontrast (VNC) images in a single scan without geometric misalignment. To improve work efficiency and reduce patients' imaging dose, we studied the feasibility of using VNC images for radiotherapy treatment planning, with true noncontrast (TNC) images as references and explored its dosimetric advantages compared to using TCE images.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!