|
THE ERA OF PRECISION ONCOLOGY AND ARTIFICIAL INTELLIGENCE
Outline
1. The cancer landscape in Vietnam (current and future outlook)
2. Limitations and challenges in cancer diagnosis and treatment in Vietnam
3. Global trends and new treatment models (precision oncology)
4. The necessity of clinical decision support systems (general)
5. Genomate Solution – Digital drug assignment (DDA),
6. Breakthrough significance and achievements of Genomate
7. GenousTM services (Large Gene Panel + Genomate Report + Molecular Tumor Board)
8. Key stakeholder benefits in implementing GenousTM services
9. Prospects and objectives for deploying GenousTM in treatment facilities in Vietnam
THE ERA OF PRECISION ONCOLOGY AND ARTIFICIAL INTELLIGENCE
Genomate - Digital drug assignment (DDA)
Presenter:
PhD., MD. Nguyen Hai Tuan
Bioinformatics Consultant at Digosys
23/8/2024
A computational approach to prioritizing targeted therapies in precision oncology: performance analysis in the SHIVA01 trial
Precision oncology currently relies on pairing molecularly targeted drugs (MTAs) with single predefined driver genes or biomarkers. Each tumor contains a large number of potential genetic alterations across multiple driver genes in a complex network, which limits the potential of this approach.
We developed an artificial intelligence (AI)-powered computational approach, the distributed drug assignment (DDA), to prioritize potential MTAs for individual cancer patients based on their complex tumor molecular profiles.
We analyzed the clinical benefit of the DDA system on clinical and molecular outcome data of patients treated in the SHIVA01 precision oncology clinical trial, MTAs paired with genetic alterations or tumor biomarkers of individual patients.
We found that the DDA score of MTA was significantly higher in patients with controlled disease than in patients with progressive disease (1523 vs. 580, P=0.037). The median progression-free survival (PFS) was also significantly longer in patients receiving MTA with a high DDA score (1000+ <) than in patients with a low DDA score (<0) (3.95 vs. 1.95 months, P=0.044).
Our results indicate that AI-based systems, such as DDA, are promising new tools to help oncologists improve precision oncology outcomes. npj Precision Oncology (2021) 5:59; https://doi.org/10.1038/s41698-021-00191-2
Real-world performance analysis of a novel computational approach in precision oncology for pediatric tumors
The routine use of extensive molecular profiling methods for pediatric tumors remains controversial due to the large number of genetic mutations of unknown significance or low evidence and the lack of standardized and personalized decision support methods.
AI-based drug assignment (DDA) is a novel computational approach to prioritize treatment options by synthesizing multiple relevant evidences based on multiple drivers, targets, and targeted drugs.
The DDA system was validated to support personalized treatment decisions based on data from adult patients treated in the SHIVA01 clinical trial. The objective of this study was to evaluate the utility of DDA in pediatric oncology. Of the 100 cases with comprehensive molecular diagnostic data, 88 had WES results and 12 had targeted panel sequencing results. DDA identified off-label (potentially treatable) targeted treatment options in 72/100 cases (72%), while 57/100 cases (57%) demonstrated potential resistance.
Availability reached 88% (29/33) in 2020 due to continuous updating of the evidence base. MTB selected clinical use indications in 56/72 cases with options identified by the DDA (78% consensus).
Therapies selected for use by MTB had a significantly higher overall evidence level (AEL) than those excluded.
Filtering WES results to obtain targeted gene panels misses important mutations that influence therapy selection.
PUBLICATION
Monographs and scientific publications on precision oncology and artificial intelligence applied in cancer treatment
