Abstract 1289TiP
Background
Lung cancer is a highly fatal cancer with poor prognosis and management despite recent therapeutic advancements. However, Artificial Intelligence (AI) presents an opportunity to leverage multiple omics datasets to create accurate predictive models for better lung cancer care. These models can be used individually or integrated into multi-omics Digital Human Avatars (DHAs) to assist in clinical decision-making and revolutionize care and research. DHAs combine various omics-based variables with clinical factors for a comprehensive understanding of the disease, enabling personalized treatment decisions to improve patient outcomes. Introducing DHAs in clinical practice can help uncover previously unexplored links among variables and significantly enhance the understanding of lung cancer.
Trial design
Trial design: The LANTERN study is a three-year, multicenter observational clinical study funded by ERA PerMed JTC2022 that aims to develop predictive models for the diagnosis and histological characterization of lung cancer, as well as personalized treatments and feedback data loops for preventive health strategies and quality of life management. The study involves a consortium of five European institutions and will collect multi-omics data from 600 non-small cell lung cancer patients, including demographic and physiological data, medical history, clinic functional and lab data, histo-pathological, immunological and genomic data, radiomics and quantitative imaging data, and IoT-derived data. The study will develop a dedicated database for all omics domains considered and perform a comprehensive molecular characterization and genomic profiling of tumor samples. The second phase of the project will focus on building multivariate models trained through advanced ML and AI techniques. Finally, the developed models will be validated to test their robustness, transferability, and generalizability, leading to the development of Digital Human Avatars (DHAs). The LANTERN study is committed to allowing the reuse of research data according to the FAIR principles and hopes that this model will eventually be utilized in clinical routine to personalize the strategy of care in lung cancer patients.
Clinical trial identification
NCT05802771.
Editorial acknowledgement
Legal entity responsible for the study
Prof. Filippo Lococo.
Funding
ERA PerMed JTC2022.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
1265P - Toripalimab plus chemotherapy as neoadjuvant treatment for resectable stage IIB-IIIB NSCLC (RENAISSANCE study): A single-arm, phase II trial
Presenter: Shi Yan
Session: Poster session 04
1266P - Prediction of lung cancer risk in ground-glass nodules using deep learning from CT images
Presenter: Anil Vachani
Session: Poster session 04
1267P - Enhancing pulmonary nodule diagnosis: A combinatorial model of cfDNA methylation, plasma proteins and LDCT imaging
Presenter: Meng Yang
Session: Poster session 04
1268P - Liquid biopsy and CT-based multi-omics fusion enhances differential diagnosis of early-stage lung adenocarcinoma
Presenter: Yanwei Zhang
Session: Poster session 04
1269P - Machine learning model for predicting lung cancer recurrence after surgical treatment: A retrospective study using NLST and European hospital data
Presenter: Ann Valter
Session: Poster session 04
1272P - Postoperative survival prediction in non-small cell lung cancer patients based on driver genotypes
Presenter: Huiting Wang
Session: Poster session 04
1273P - The prognostic value evaluation of a tissue Comprehensive Genomic Profiling (CGP)-informed personalized MRD detection assay in NSCLC
Presenter: Wei Gao
Session: Poster session 04
1274P - Early dynamics of circulating tumor DNA following curative hypofractionated radiotherapy related to disease control in lung cancer
Presenter: Kyungmi Yang
Session: Poster session 04
1275P - Genomic analysis of lung adenocarcinoma with micropapillary component: Identification of micropapillary-related subtypes and development of a prognostic model
Presenter: Yuechun Lin
Session: Poster session 04