Online search in earlier detection of lung cancers Version 1.0
Research type
Research Study
Full title
Evaluation of the use of online search queries for an earlier detection of lung cancers
IRAS ID
340664
Contact name
Ingemar Cox
Contact email
Sponsor organisation
University College London
Clinicaltrials.gov Identifier
UCL Data Protection Registration Number, Z6364106/2024/10/160 cancer research
Duration of Study in the UK
0 years, 4 months, 30 days
Research summary
We propose to evaluate the use of online search queries as a tool to help clinicians provide an earlier diagnosis of lung cancer. Patients with a Google account will be invited to take part in this study and have their search history analysed for patterns, symptoms, and risk factors, and compared with clinical information from health questionnaires.
Earlier detection of lung cancer gives an opportunity for accessing curative treatment with a better outcome. Lung cancer accounts for the majority of cancer deaths, and there is a need for screening tools to aid early detection. While Low-Dose Computed Tomography screening reduces lung cancer related mortality, screening pathways require optimisation to help improve efficiency and effectiveness.
Extracting information from online searches has shown promise in identifying those at risk of cancers including lung and pancreatic. Recently, we collaborated with Imperial College in a study that used online search activity for the earlier detection of gynaecological malignancy (Barcroft et al, 2024). This was the first study based on clinical diagnoses to demonstrate that web searches could identify patients at higher risk of cervical cancer.
We aim to start a collaboration with the SUMMIT study to evaluate the findings from the previous study on cervical cancer on a larger cohort of patients and extend the methodology to a different type of cancer. The SUMMIT study is the largest lung screening study of its kind in the UK. The study has over 13,000 people, in the 55-77 age bracket, from London. They are people at higher risk of lung cancer due to their smoking history. It is estimated that a pool of ~400 participants could be recruited. We propose to access Google search data in the two years prior to diagnosis, to determine key patterns of disease and develop a predictive algorithm capable of identifying those at higher risk
REC name
London - Westminster Research Ethics Committee
REC reference
25/PR/1032
Date of REC Opinion
22 Sep 2025
REC opinion
Further Information Favourable Opinion