Publications

This deliverable has been conceived in the frame of T4.3 “General population screening”, T4.4 “Diagnosis and precision follow-up and stratification” and T4.5 “Contextual-empirical investigations to evaluate the realization of identified values”. These tasks are devoted to the recruitment of a prospective cohort of around 3,000 volunteers that will be followed up for 2 years and on the diagnosis, including Indeterminate Pulmonary Nodules (IPN) characterization, with an accentuation on the Never Smokers and Reduced Smokers (NSRS) patients, incorporating Breath Analyser (BAN), Wide-biomarker-spectrum Multi-Use Sensing Patch (WBSP) and spectrometry-on-card (SPOC) into clinical studies.

Regarding Task 4.5, it examines whether identified socio-technical values (in WP1-3) (e.g., transparency, bias, accountability, explanability) are realized when the technology is used. To achieve this goal, the different contexts of the use of technology are to be analysed as different contextual variables come into play to impact the way values are understood.

Volunteers have been recruited from different clinical centers (“Servicio Andaluz de Salud” (SAS) and “Osakidetza Servicio Vasco de Salud” (OSA), in Spain; “Centre Hospitalier Universitaire de Liège” (CHUL) in Belgium, and “Centre for Tuberculosis and Lung Diseases (CTLD) of Riga East University Hospital (REUH)” in Latvia). Non-invasive devices such as Breath Analyzer (BAN), Multiomics (MO) and spectrometry-on-card (SPOC) are monitoring these participants.

The entire study cohort is currently being followed up. For 2 years, participants of the study will attend to 4 visits: baseline, month 6, month 12 and month 24. During these visits, the following tests and procedures will be carried out:

– Baseline visit: blood test, spirometry, lifestyle questionnaires, sociodemographic data, medical record data, exposure to harmful agents data, physical exploration, LDCT scan and new lung cancer screening devices testing (breath analyzer and spectrometry-on-card)
– 6 months visit: remote visit where sociodemographic data, medical record data and exposure to harmful agents data will be recorded.
– 12 months visit: spirometry, lifestyle questionnaires, sociodemographic data, medical record data, exposure to harmful agents’ data and physical exploration.
– 24 months visit: spirometry, ifestyle questionnaires, sociodemographic data, medical record data, exposure to harmful agents’ data, physical exploration, low-dose computed tomography (LDCT) scan and new lung cancer screening devices testing (breath analyzer and spectrometry-on-card).

(See the following of the Executive Summary in file).

How is the LUCIA Project Study Conducted in Latvia

Read the Blogpost

Read the Blogpost

This newsletter provides an update about the project activities.

This newsletter presents the activities of the project under the Prevention & Early Detection (Screening) cluster: DIOPTRA, LUCIA, MammoScreen, ONCOSCREEN, PANCAID and SANGUINE.

Read the Blogpost

Read the Blogpost

The most well-established risk factor for lung cancer (LC) is smoking, responsible for approximately 85% of cases. The Lung Cancer Risk Assessment Tool (LCRAT) is a key advancement in this field, which predicts individual risk based on factors like smoking habits, demographic details, personal and family medical history, and environmental exposures. This paper proposes a model with fewer features that improves state of the art performance, using a simplified stacking ensemble, making it more accessible and easier to implement in routine healthcare practice. The data used in this work were derived from two cohorts in the United States: The National Lung Screening Trial (NLST) and the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial. Both our model and LCRAT achieve an AUC of 0.799 and 0.782 on test respectively. In terms of percentage of positives, in the 50% of the population, both detect 0.766 and 0.754 of the cases. The ensemble of different survival models enhances robustness by mitigating the weakness of individual models and directly impacts the efficiency of the model, increasing the efficiency and generalizability.