Toward a Better Paradigm for Head and Neck Cancer Treatment Applying AI (HNC-TACTIC) - Protocol for an International Cohort Study of Electronic Health Records

Sep 23, 2026

Head and neck squamous cell carcinomas (HNSCCs) lead to substantial morbidity and mortality, while multimodal therapy often produces meaningful toxicity and options remain limited for recurrent disease. Immunotherapy is promising, yet patient response variability requires stronger predictive markers. This study applies artificial intelligence to build two predictive models for progression/recurrence after primary curative treatment and for long-term survival after immunotherapy, using electronic health record data.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Background and Objective

Methods

Results

Conclusions

Trial Registration

Introduction

Background and Rationale

JMIR RESEARCH PROTOCOLS Mehanna et al Protocol Toward a Better Paradigm for Head and Neck Cancer Treatment Applying AI (HNC-TACTIC): Protocol for an International Cohort Study of Electronic Health Records | Hisham Mehanna 1 , PhD; Jacobo Rogado2 , MD, PhD; Alejandro Castro Calvo3 , MD; Víctor González4 , MD; Francina Aguilar5 ; Dorian Culié6 , MD; Álvaro Sanabria7 , MD; Sergio Fabian Zuñiga Pavia8 , MD; Marta Guix9 , MD; Sujith Baliga 10 , MD; Roland Giger11 , MD; Sara-Lynn Hool 11 , MD; Olgun Elicin 12 , MD; Matthaeus Stoehr13 , MD; Ahmad K Abou-Foul 1 , MD; Melvin L K Chua14 , MD; Pablo Parente15 , MD; Andreas Dietz 13 , MD; John R de Almeida 16 , MD; Christian Simon17 , MD; F Christopher Holsinger18 , MD; Robert Ferris19 , MD; Raul Giglio20 , MD; Kate Hutcheson21 , MD; David Casadevall22 , MD; Miren Taberna22 , MD | | --- | | 1Institute of Cancer and Genomic Sciences, Birmingham, United Kingdom
2Hospital Universitario Infanta Leonor, Madrid, Spain 3Hospital Universitario La Paz, Madrid, Spain 4Hospital Universitario de Móstoles, Madrid, Spain 5Hospital General de Granollers, Barcelona, Spain
6Centre Antoine Lacassagne, Institut Universitaire de la Face et du Cou, Nice, France
7Department of Surgery, School of Medicine, Universidad de Antioquia-Hospital Alma Mater de Antioquia Medellín, Antioquia, Colombia 8Hospital Universitario Nacional de Colombia, Bogotá, Colombia
9Hospital del Mar Research Institute, Barcelona, Spain 10Massachusetts General Hospital, Boston, MA, United States
11Oto-Rhino-Laryngology, Head and Neck Surgery, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland 12Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland
13Universitätsklinikum Leipzig, Leipzig, Germany
14National Cancer Centre Singapore, Duke-NUS Medical School, Singapore, Singapore 15Hospital Universitario de A Coruña, A Coruña, Spain
16University of Toronto, Toronto, ON, Canada
17Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland 18Stanford University School of Medicine, Stanford, CA, United States
19UPMC (University of Pittsburgh Medical Center) Hillman Cancer, Pittsburgh, PA, United States 20Hospital Roffo, Buenos Aires, Argentina
21MD Anderson Cancer Centre, Houston, TX, United States 22Savana Research, S.L, Madrid, Spain
Corresponding Author:
Miren Taberna, MD Savana Research, S.L Calle Larra, 12-BJ IZ Madrid 28004
Spain
Phone: 34 910696902
[Email:](Email: mtaberna@savanamed.com)[ ](Email: mtaberna@savanamed.com)[mtaberna@savanamed.com](Email: mtaberna@savanamed.com)
Abstract | Background: Head and neck squamous cell carcinomas (HNSCCs) cause considerable morbidity and mortality. Multimodal treatment strategies can cause significant toxicity, and therapy options are limited for recurrent disease. Immunotherapy has emerged as a promising approach. However, patient response variability underscores the need for better predictive markers. Objective: This study aims to use artificial intelligence to develop two predictive models in patients with HNSCC to assess (1) progression or recurrence following primary curative treatment and (2) long-term survival after immunotherapy schemes in [https://www.researchprotocols.org/2026/1/e83598](https://www.researchprotocols.org/2026/1/e83598) JMIR Res Protoc 2026 | vol. 15 | e83598 | p. 1 (page number not for citation purposes) JMIR RESEARCH PROTOCOLS Mehanna et al recurrent and metastatic disease. This study will also describe the characteristics of patients with early, locally advanced, andrecurrent or metastatic cancers . Methods: This is a retrospective, observational study of data captured in electronic health records (EHRs) from participating hospitals between January 1, 2014, and December 31, 2021. This study’s population comprises adults diagnosed with HNSCCat any stage. Study variables, including demographics, comorbidities, clinical var

FAQs

What is the main objective of the HNC-TACTIC protocol?

To use artificial intelligence to develop two predictive models for patients with HNSCC: progression/recurrence after primary curative treatment and long-term survival after immunotherapy schemes.

What type of study and data sources are used?

A retrospective observational study using electronic health records (EHRs) from participating hospitals.

How are predictive variables and outcomes extracted from EHRs?

Study variables are extracted using EHRead, which applies natural language processing and machine learning to obtain structured and unstructured clinical information from deidentified EHRs.

Sep 23, 2026

Uploaded by Guten tag