Background: Currently, selection of patients for sequential versus concurrent chemotherapy and radiation regimens lacks evidentiary support and it is based on locally optimal decisions for each step. Objective: We aim to optimize the multistep treatment of patients with head and neck cancer and predict multiple patient survival and toxicity outcomes, and we develop, apply, and evaluate a first application of deep Q-learning (DQL) and simulation to this problem. Methods: The treatment decision DQL digital twin and the patient’s digital twin were created, trained, and evaluated on a data set of 536 patients with oropharyngeal squamous cell carcinoma with the goal of, respectively, determining the optimal treatment decisions with respect to survival and toxicity metrics and predicting the outcomes of the optimal treatment on the patient. Of the data set of 536 patients, the models were trained on a subset of 402 (75%) patients (split randomly) and evaluated on a separate set of 134 (25%) patients. Training and evaluation of the digital twin dyad was completed in August 2020. The data set includes 3-step sequential treatment decisions and complete relevant history of the patient cohort treated at MD Anderson Cancer Center between 2005 and 2013, with radiomics analysis performed for the segmented primary tumor volumes. Results: On the test set, we found mean 87.35% (SD 11.15%) and median 90.85% (IQR 13.56%) accuracies in treatment outcome prediction, matching the clinicians’ outcomes and improving the (predicted) survival rate by +3.73% (95% CI –0.75% to 8.96%) and the dysphagia rate by +0.75% (95% CI –4.48% to 6.72%) when following DQL treatment decisions. Conclusions: Given the prediction accuracy and predicted improvement regarding the medically relevant outcomes yielded by this approach, this digital twin dyad of the patient-physician dynamic treatment problem has the potential of aiding physicians in determining the optimal course of treatment and in assessing its outcomes.

Although visualization design models exist in the literature in the form of higher-level methodological frameworks, these models do not present a clear methodological prescription for the domain characterization step. This work presents a framework and end-to-end model for requirements engineering in problem-driven visualization application design. The framework and model are based on the activity-centered design paradigm, which is an enhancement of human-centered design. The proposed activity-centered approach focuses on user tasks and activities, and allows an explicit link between the requirements engineering process with the abstraction stage - and its evaluation - of existing, higher-level visualization design models. In a departure from existing visualization design models, the resulting model: assigns value to a visualization based on user activities; ranks user tasks before the user data; partitions requirements in activity-related capabilities and nonfunctional characteristics and constraints; and explicitly incorporates the user workflows into the requirements process. A further merit of this model is its explicit integration of functional specifications, a concept this work adapts from the software engineering literature, into the visualization design nested model. A quantitative evaluation using two sets of interdisciplinary projects supports the merits of the activity-centered model. The result is a practical roadmap to the domain characterization step of visualization design for problem-driven data visualization. Following this domain characterization model can help remove a number of pitfalls that have been identified multiple times in the visualization design literature.

Visualization research often seeks designs that first establish an overview of the data, in accordance to the information seeking mantra: “Overview first, zoom and filter, then details on demand”. However, in computational fluid dynamics (CFD), as well as in other domains, there are many situations where such a spatial overview is not relevant or practical for users, for example when the experts already have a good mental overview of the data, or when an analysis of a large overall structure may not be related to the specific, information-driven tasks of users. Using scientific workflow theory and, as a vehicle, the problem of viscous finger evolution, we advocate an alternative model that allows domain experts to explore features of interest first, then explore the context around those features, and finally move to a potentially unfamiliar summarization overview. In a model instantiation, we show how a computational back-end can identify and track over time low-level, small features, then be used to filter the context of those features while controlling the complexity of the visualization, and finally to summarize and compare simulations. We demonstrate the effectiveness of this approach with an online web-based exploration of a total volume of data approaching half a billion seven-dimensional data points, and report supportive feedback provided by domain experts with respect to both the instantiation and the theoretical model.

We present the design and evaluation of an integrated problem solving environment for cancer therapy analysis. The environment intertwines a statistical martingale model and a K Nearest Neighbor approach with visual encodings, including novel interactive nomograms, in order to compute and explain a patient's probability of survival as a function of similar patient results. A coordinated views paradigm enables exploration of the multivariate, heterogeneous and few-valued data from a large head and neck cancer repository. A visual scaffolding approach further enables users to build from familiar representations to unfamiliar ones. Evaluation with domain experts show how this visualization approach and set of streamlined workflows enable the systematic and precise analysis of a patient prognosis in the context of cohorts of similar patients. We describe the design lessons learned from this successful, multi-site remote collaboration.

Promoting a wider range of contribution types can facilitate healthy growth of the visualization community, while increasing the intellectual diversity of visualization research papers. In this paper, we discuss the importance of contribution types and summarize contribution types that can be meaningful in visualization research. We also propose several concrete next steps we can and should take to ensure a successful launch of the contribution types.