Optimising the PDAC ecosystem
(beyond scientific discovery)
A critical question for the PDAC field is how many potentially valuable yet currently untapped resources exist that could substantially strengthen the PDAC ecosystem. At present, this remains unknown.
We believe, however, that recent advances in Machine Learning (ML) and Deep Learning (DL), within the broader domain of Artificial Intelligence (AI), may offer an unprecedented opportunity to optimise the PDAC landscape at a systems level. This reframing is important, as it suggests that, at present, the most relevant applications of ML/AI in this context may not lie primarily in biological discovery, but rather in their deployment as systems-level optimisers capable of improving the performance of a highly complex, multi-actor, and resource-constrained global research and advocacy environment.
The objective is to optimise the political, organisational, financial partnerships, communication, and operational machineries surrounding pancreatic cancer research, in much the same way that ML/AI have already been successfully applied to improve the efficiency and strategic functioning of large-scale industrial and institutional systems.
Identify systemic inefficiencies, detect hidden negative patterns, reveal underutilised leverage points, discover opportunities for new financial resources, and support more effective strategic decisions across multiple interacting domains.
In simpler words, ML/AI applied to the PDAC ecosystem will facilitate:
- network analysis
- landscape scanning & opportunity detection
- resource allocation
- coalition optimisation
- operational bottleneck analysis
- media/policy tracking
- company and investor untapped opportunities