Related Experiment Video
Updated: May 27, 2026
10:27
Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts
Published on: July 25, 2020
Sequencing AI Automation and Data Interoperability in Oncology Using a Scenario-Planning Framework Coupled With
Peter May1, Sabine D Brookman-May2, Edward Garrahy3
1Department of Medicine III, School of Medicine and Health, Technical University of Munich, Ismaninger Str. 22, Munich, Bavaria, 81675, Germany, 49 89-4400 ext 8753.
Journal of Medical Internet Research
|May 25, 2026
Summary
Integrating artificial intelligence (AI) into oncology care can improve patient throughput and reduce treatment times. However, successful AI adoption requires robust data infrastructure to avoid bottlenecks and ensure system resilience.
Area of Science:
- Health systems research
- Artificial intelligence in healthcare
- Operational modeling
Background:
- Health systems face uncertainty integrating autonomous artificial intelligence (AI) agents into oncology workflows.
- Traditional forecasting methods are inadequate for predicting AI's second-order operational impacts, such as governance saturation and bottleneck migration.
- System-level dynamics influenced by AI integration affect diagnosis, treatment, and health system resilience.
Purpose of the Study:
- To develop a proof-of-concept framework for evaluating oncology AI adoption strategies.
- To couple qualitative scenario planning with quantitative discrete-event simulation for stress-testing AI integration.
Main Methods:
- Defined a strategic state space using AI automation intensity and data interoperability, creating four distinct future scenarios.
- Translated qualitative scenarios into a discrete-event simulation model with a 3-year operational horizon.
- Quantified system performance metrics including referral-to-treatment interval (RTTI), throughput, volatility, and resource constraints.
Main Results:
- The fully integrated AI scenario maximized capacity and halved the mean RTTI, comparable to major pathway redesigns.
- Isolated AI adoption without data infrastructure reduced performance, increasing RTTI by 26% and decreasing throughput due to governance saturation.
- Identified bottleneck migration and demonstrated that prioritizing data interoperability reduced transition volatility compared to an automation-first approach.
Conclusions:
- Integrating qualitative scenario planning with quantitative simulations provides a systematic method for evaluating oncology AI adoption.
- The framework offers a replicable approach for health leaders to model digital transformation scenarios amidst uncertainty.
- Future work should incorporate financial and health equity dimensions, establishing simulation-based scenario planning as a key tool in medical futures studies.
