A research report has been published in Frontiers in Digital Health that explores the use of digital twin technology to advance new methods for precision and predictive cancer care.
Entitled ‘Exploring approaches for predictive cancer patient digital twins: Opportunities for collaboration and innovation’, the report focuses on a review of five pilot projects in which the digital twin technology of using continuously updated data to mirror real-world behaviour is explored.
The authors set the context for their research, noting that “we are rapidly approaching a future in which cancer patient digital twins will reach their potential to predict cancer prevention, diagnosis, and treatment in individual patients.”
One of the pilot projects explored by the researchers focused on cancer patient digital twin exploratory projects at Georgetown University. The goal of this project was to develop methods that connect the progression, therapeutic interventions, and outcomes from a cohort of pancreatic cancer patients to simulation results.
Other projects explored the approaches of virtual cancer digital twin projects, personalisation of treatment, and the use of digital twins for an adaptive approach to monitoring treatment response and resistance.
Another project the researchers explored used a “patient-specific multi-scale digital twin for the exploration of optimal treatment pathways for non-small cell lung cancer” in which the researchers noted it recorded the patient’s past state, monitored the patient’s present state, and forecasted the patient’s future state.
From the study, the researchers highlighted one of the main challenges in the area is the lack of data to support mathematical modelling. They also noted a limitation of the number of computational models for rare cancer types.
Summarising the report, the researchers said that each project used a form of AI or machine learning and that there is a need for an expanded community effort to improve the state of cancer patient digital twins, notably a “critical need for additional patient-specific longitudinal data, particularly across populations that are representative of the community the digital twin is anticipated to support”.
The researchers highlighted that “the five projects all demonstrated that biological and clinical domain knowledge, machine intelligent-driven analysis of large-scale multimodal datasets, and mechanistic modelling can be merged to create modular, reusable frameworks for cancer patient digital twins.”
The authors closed by adding “the early outcomes of the cancer patient digital twin pilot projects as well as the results from other cancer patient digital twin efforts provide a sense of real promise for the future of the cancer patient digital twin.”
To read the paper, please click here.
Citation: Stahlberg EA, Abdel-Rahman M, Aguilar B, Asadpoure A, Beckman RA, Borkon LL, Bryan JN, Cebulla CM, Chang YH, Chatterjee A, Deng J, Dolatshahi S, Gevaert O, Greenspan EJ, Hao W, Hernandez-Boussard T, Jackson PR, Kuijjer M, Lee A, Macklin P, Madhavan S, McCoy MD, Mohammad Mirzaei N, Razzaghi T, Rocha HL, Shahriyari L, Shmulevich I, Stover DG, Sun Y, Syeda-Mahmood T, Wang J, Wang Q and Zervantonakis I (2022) Exploring approaches for predictive cancer patient digital twins: Opportunities for collaboration and innovation. Front. Digit. Health 4:1007784. doi: 10.3389/fdgth.2022.1007784
