[Advanced Data-Aided Medicine part lung cancer]

The ADAM project is RADar’s first major vlaio project in which real medical data from different sources was harmonized. This data served as input for 2 use cases, where the lung case focuses on predicting patient outcomes to predict the optimal treatment plan for advanced lung cancer patients.

---

Objective

Developing and validating an AI model that supports physicians in their decision process for treating advanced lung cancer patients. This AI model needs to predict the probability/evolution of the outcomes, based on clinical data and simulated lung cancer treatment plans. The outcome probabilities can be evaluated through different treatment plans to identify the optimal treatment plan for a patient.

Methodology

Automatic unlocking, collection & transformation of lung cancer datapoints to OMOP common data model so that data is readily available for further research & analysis. Training and validating supervised machine learning models with a limited feature set as input to predict advanced lung cancer patient outcomes. Constructing a digital patient by training an AI model fed with all data available in OMOP common data model. Validating a digital patient & optimal feature selection to enhance AI model performance via supervised and unsupervised learning techniques.

Impact and future directions

Careful analysis of the collected data using artificial intelligence tools might support physicians & advanced lung cancer patients in their treatment decision process.

General info and contact

Keywords (#): Advanced lung cancer, machine learning, treatment, CDSS

RADar project research lead: M.Sc. Louise Berteloot

Principal investigator: Prof. MD Ingel Demedts

Timeline: 2021-2024

Status: Ongoing validation experiments with external partners (Maastro, …). Further development of models with FHIN consortium.

Publications / presentations:

• Berteloot, L., Demedts, I., Himpe, U., Dupulthys, S., Lammertyn, P.-J., & De Jaeger, P. (2023). 213P Development of an explainable clinical decision support tool for advanced lung cancer patients. Journal of Thoracic Oncology, 18(4), S154–S155. https://doi.org/10.1016/S1556-0864(23)00466-5
• Best poster award in category general interest at European Lung Cancer Congress 2023 Copenhagen.

Partners: UGent IDLab

Funding: Vlaio O&O

• GitHub