A Machine Learning-Based Risk Prediction Model for Head and Neck Cancerous Lesions

NCT07532538 | Not Yet Recruiting DMC

• 1 other identifier: 2025123101
• Study Type: observational
• Target: 3,000
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Hypopharyngeal Cancer; Laryngeal Cancer; Head and Neck Cancer

Keywords

Head and neck malignant lesions; Hypopharyngeal cancer; Laryngeal cancer; AI; machine learning; AI-assisted diagnosis

Outcome Measures

Primary Outcomes (1)

• 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 Outcomes (2)

• Demographic data

  During the first outpatient visit （Day 1）

• VHI-10

  During the first outpatient visit（Day 1）

Study Arms (2)

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).

Eligibility Criteria

• Age: 18 Years - 100 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• 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.

You may qualify if:

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

You may not qualify if:

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

Sponsors & Collaborators

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

Study Sites (1)

Nanjing Drum Tower Hospital

Nanjing, Jiangsu, China

Location

MeSH Terms

Conditions

Hypopharyngeal Neoplasms; Laryngeal Neoplasms; Head and Neck Neoplasms

Condition Hierarchy (Ancestors)

Pharyngeal Neoplasms; Otorhinolaryngologic Neoplasms; Neoplasms by Site; Neoplasms; Pharyngeal Diseases; Stomatognathic Diseases; Otorhinolaryngologic Diseases; Laryngeal Diseases; Respiratory Tract Diseases; Respiratory Tract Neoplasms

Central Study Contacts

junyi Wang, master

CONTACT

+86 13309609232; songjiu3411@outlook.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 6 Months
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: April 5, 2026
• First Posted: April 16, 2026
• Study Start: April 30, 2026
• Primary Completion (Estimated): November 30, 2029
• Study Completion (Estimated): November 30, 2030
• Last Updated: April 16, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)