Machine learning helps predict head and neck cancer risk from patient data and images
Official title: A Machine Learning-Based Risk Prediction Model for Head and Neck Cancerous Lesions: A Multidimensional Feature Study Integrating Demographics and Clinical Symptomatology
Run by The Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School · NCT07532538 · Data updated 2026-11-12
Researchers are testing a deep learning model to see if AI can predict the risk of head and neck cancer in adults using clinical data and laryngoscopic images.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 100 Years |
| Sex | All |
| Enrollment | 3000 (estimated) |
| Sponsor | The Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School Academic / other |
| Locations | 1 site (Nanjing, Jiangsu) |
| Status | Recruiting |
| Started | April 30, 2026 |
| Main results expected | November 30, 2028 |
| Study ends | November 30, 2030 |
| Registry record updated | September 2, 2026 |
| Trial ID | NCT07532538 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults (18 years or older) with complete clinical data and laryngoscopic images who consent to participate.
✕Probably not a fit
Patients without available complete data or images, or those who decline consent, may not benefit from the model.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational study aims to develop and validate a predictive model for head and neck cancer risk by integrating deep learning with clinical information gathered across multiple centers. The approach combines AI algorithms with diverse data to distinguish early cancers from benign voice disorders. The study focuses on conditions including hypopharyngeal and laryngeal cancers and uses patients’ demographics, lifestyle history, and imaging data. It is designed to identify high-risk individuals to support earlier referral and diagnosis. Participation involves adults with complete clinical data and laryngoscopic images, under centers in Nanjing, China.
Why it matters
Potential benefit: If successful, the model could improve early detection and reduce missed diagnoses of laryngeal and hypopharyngeal cancers.
How similar studies have gone: Previous work using AI with clinical and imaging data has shown promise in cancer risk prediction, though this exact approach is being evaluated in head and neck cancers.
Who can join: the full rules
Show full inclusion / exclusion criteria
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.
Where it's running
-
Nanjing Drum Tower Hospital
Nanjing, Jiangsu, China Recruiting
Study contacts
- Study coordinator: junyi Wang, master
- Email: songjiu3411@outlook.com
- Phone: +86 13309609232
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Study of immune biomarkers in head and neck cancer
This study is testing if certain immune markers in patients with newly diagnosed head and neck cancer can help predict their treatment outcomes and guide their care.
-
Docetaxel and SX-682 in head and neck cancers and prostate cancer
This trial tests a new drug SX-682 together with docetaxel in adults whose head and neck cancers or prostate cancer have returned or spread.
-
Neoadjuvant chemoimmunotherapy with PD-1 blockade to reduce surgery for advanced head and neck cancer
This approach will try a short course of chemotherapy plus the PD-1 drug toripalimab before standard treatment for people with advanced head and neck cancers to shrink tumors and allow less extensive surgery or radiation.
-
Using voice recordings to monitor laryngeal and hypopharyngeal cancer recurrence
This study is testing if regular voice recordings can help keep track of cancer returning in patients who have finished treatment for laryngeal and hypopharyngeal cancer.
-
A resource for collecting cancer data and biospecimens
This study is creating a resource to collect health information and samples from cancer patients and healthy individuals to help improve cancer prevention and treatment strategies.
-
Phenotype-based Pain Guidance for Head and Neck Cancer-Related Pain (pilot)
This pilot test sees if tailoring pain treatment to a patient’s pain type can reduce head and neck cancer pain in adults who haven’t started cancer treatment yet.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.