A Machine Learning-Based Risk Prediction Model for Head and Neck Cancerous Lesions (ML-HNC-Risk)

A Machine Learning-Based Risk Prediction Model for Head and Neck Cancerous Lesions: A Multidimensional Feature Study Integrating Demographics and Clinical Symptomatology

This study aims to develop and validate a clinical prediction model for the risk of head and neck cancerous lesions using deep learning combined with AI algorithms, based on multi-center clinical data.

Study Overview

• Status: Not yet recruiting
• Conditions: Head and Neck Cancer; Laryngeal Cancer; Hypopharyngeal Cancer

Detailed Description

Vocal health has emerged as a prominent public health challenge. Phonation relies on precise neuromuscular and respiratory coordination, a physiological process frequently compromised by systemic senescence, multimorbidity, and neuromuscular degeneration. This complex pathophysiological interplay makes it exceedingly difficult to clinically distinguish early-stage laryngeal malignancies from common benign voice disorders (e.g., vocal fold cysts, vocal process granulomas, and Reinke's edema). Because both entities typically present with non-specific hoarseness or globus sensation, the difficulty of early screening and accurate differential diagnosis is substantially amplified.

Currently, the diagnosis of voice disorders relies heavily on laryngoscopy. However, owing to the unequal distribution of medical resources, primary and community care settings generally lack effective screening tools for laryngeal malignancies during initial consultations, often leading to delayed referrals for high-risk patients. Furthermore, there is a profound disparity in endoscopic interpretation expertise across different healthcare tiers. The visual features of certain precancerous lesions (such as dysplastic leukoplakia) and early-stage malignancies overlap considerably, resulting in a high risk of missed diagnoses or unnecessary biopsies of benign lesions. Therefore, systematically incorporating multidimensional indicators-including demographics (e.g., age), smoking and alcohol history, and clinical symptomatology-into risk assessment is crucial for the early detection of malignancies and the optimal allocation of healthcare resources.

In recent years, deep learning-based artificial intelligence (AI) has demonstrated tremendous potential in medical image feature extraction, capable of capturing subtle morphological textures imperceptible to the human eye. However, the oncogenesis and progression of laryngeal malignancies are driven by a confluence of multidimensional factors. When confronted with complex, real-world clinical scenarios, unimodal imaging models often suffer from decreased generalizability and elevated false-positive rates due to the absence of the patient's demographic, symptomatic, and behavioral exposure context. Real-world clinical decision-making is not an isolated image-interpretation task; rather, it requires the systematic integration of visual features with multidimensional clinical metadata. Developing an intelligent diagnostic framework capable of fusing multimodal data is therefore essential to overcome the application bottlenecks of current unimodal AI imaging tools.

Addressing these clinical pain points and technical limitations, this study leveraged a national multicenter cohort encompassing approximately 11,000 patients with voice disorders to develop and validate a two-stage, multimodal AI risk stratification and diagnostic framework. In the first stage, by integrating demographic characteristics, behavioral exposures, and clinical symptomatology, the investigators developed a non-invasive, low-cost Clinical Screening Model. This tool is designed to provide primary care settings and patients with an immediate, efficient early-warning system for malignancies. In the second stage, building upon this initial risk stratification, the investigators employed deep learning algorithms to extract microscopic visual features from endoscopic images, culminating in a Multimodal Diagnostic Model. This model achieves precise multiclass classification among laryngeal malignancies, common benign vocal fold lesions, and normal laryngeal anatomy. Furthermore, the investigators deployed a cloud-based web application to facilitate real-time risk estimation.

Ultimately, by providing this clinical-grade AI diagnostic assistant, this study aims to optimize the hierarchical screening and diagnostic pathways for voice disorders, thereby empowering general practitioners and primary care otolaryngologists to enhance the quality of clinical decision-making and diagnostic accuracy.

• Study Type: Observational
• Enrollment (Estimated): 3000

Contacts and Locations

• Study Contact: Name: junyi Wang, master; Phone Number: +86 13309609232; Email: songjiu3411@outlook.com

Study Locations

• China
  • Jiangsu
    • Nanjing, Jiangsu, China
      • Nanjing Drum Tower Hospital
      • Contact: junyi Wang, master; Phone Number: +86 13309609232; Email: songjiu3411@outlook.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

The study cohort comprised outpatients and inpatients from the otolaryngology departments of the participating medical centers, who underwent laryngoscopy primarily for initial presenting symptoms such as pharyngeal discomfort and hoarseness.

Description

Inclusion Criteria:

Age ≥ 18 years old. Patients with complete clinical data information and laryngoscopic images.

Exclusion Criteria:

Refusal to sign the informed consent form. Incomplete clinical data. Known diagnosis of other head and neck malignancies (thyroid cancer, malignant parotid tumors, etc.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
Patients with head and neck malignancies; Comprised patients with histopathologically confirmed head and neck malignant lesions, primarily including laryngeal and hypopharyngeal carcinomas.
Patients without head and neck malignancies; Consisted of patients absent of malignant findings, encompassing individuals with normal laryngeal anatomy and those diagnosed with benign vocal fold lesions (e.g., polyps, cysts, and nodules).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Laryngoscopic report diagnosis	those data will be collected via medical history records，"The laryngoscopic report diagnosis" primarily consists of detailed diagnostic classifications for various vocal fold and laryngeal pathologies.	During the first outpatient visit (Day 1)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Demographic data	Demographic data primarily includes demographic characteristics, behavioral habits, medical history, and lifestyle factors.	During the first outpatient visit （Day 1）
VHI-10	those data will be collected via questionnaire ，Voice-related quality of life was assessed using the Voice Handicap Index (VHI). Total scores range from 0 to 120. Higher scores indicate greater voice-related daily life handicap (worse outcome).	During the first outpatient visit（Day 1）

Collaborators and Investigators

• Sponsor: The Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School
• Collaborators: Zhongda Hospital; Nanjing Children's Hospital; Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine; Affiliated Cixi Hospital of Wenzhou Medical University; Taikang Xianlin Drum Tower Hospital; Nanjing Tongren Hospital; Gansu Provincial Maternal and Child Health Care Hospital; Changzhou Fourth People's Hospital; Shanghai Putuo District People's Hospital; Wuxi Huishan District People's Hospital; Fengyang County Hospital of Traditional Chinese Medicine

Study record dates

Study Major Dates

• Study Start (Estimated): April 30, 2026
• Primary Completion (Estimated): November 30, 2029
• Study Completion (Estimated): November 30, 2030

Study Registration Dates

• First Submitted: April 5, 2026
• First Submitted That Met QC Criteria: April 12, 2026
• First Posted (Actual): April 16, 2026

Study Record Updates

• Last Update Posted (Actual): April 16, 2026
• Last Update Submitted That Met QC Criteria: April 12, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: machine learning; AI; Laryngeal cancer; Hypopharyngeal cancer; Head and neck malignant lesions; AI-assisted diagnosis
• Additional Relevant MeSH Terms: Stomatognathic Diseases; Neoplasms by Site; Neoplasms; Respiratory Tract Diseases; Respiratory Tract Neoplasms; Otorhinolaryngologic Diseases; Pharyngeal Neoplasms; Otorhinolaryngologic Neoplasms; Pharyngeal Diseases; Laryngeal Diseases; Head and Neck Neoplasms; Laryngeal Neoplasms; Hypopharyngeal Neoplasms
• Other Study ID Numbers: 2025123101

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Raw data will not be directly shared and will only be provided when necessary. All research codes involved in this study will be made publicly available.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No