E-Science technologies in a workflow for personalized medicine using cancer screening as a case study

Abstract

Objective: We provide an e-Science perspective on the workflow from risk factor discovery and classification of disease to evaluation of personalized intervention programs. As case studies, we use personalized prostate and breast cancer screenings.

Materials and methods: We describe an e-Science initiative in Sweden, e-Science for Cancer Prevention and Control (eCPC), which supports biomarker discovery and offers decision support for personalized intervention strategies. The generic eCPC contribution is a workflow with 4 nodes applied iteratively, and the concept of e-Science signifies systematic use of tools from the mathematical, statistical, data, and computer sciences.

Results: The eCPC workflow is illustrated through 2 case studies. For prostate cancer, an in-house personalized screening tool, the Stockholm-3 model (S3M), is presented as an alternative to prostate-specific antigen testing alone. S3M is evaluated in a trial setting and plans for rollout in the population are discussed. For breast cancer, new biomarkers based on breast density and molecular profiles are developed and the US multicenter Women Informed to Screen Depending on Measures (WISDOM) trial is referred to for evaluation. While current eCPC data management uses a traditional data warehouse model, we discuss eCPC-developed features of a coherent data integration platform.

Discussion and conclusion: E-Science tools are a key part of an evidence-based process for personalized medicine. This paper provides a structured workflow from data and models to evaluation of new personalized intervention strategies. The importance of multidisciplinary collaboration is emphasized. Importantly, the generic concepts of the suggested eCPC workflow are transferrable to other disease domains, although each disease will require tailored solutions.

Keywords: cancer; data integration; e-Science; modeling; personalized screening; simulation.

Figure 1.

eCPC workflow to illustrate the process from data and modeling to evaluation of new population programs via 4 nodes. Prediction and natural history models are applied to assess individual risk. Model parameters are estimated using molecular data, nationwide Swedish registers, and cohort data. Bioinformatics and image analysis allow for discovery of novel biomarkers and other predictors in order to improve risk discrimination. Microsimulation is used to plan trials and evaluate protocols for public policy shifts. The process is iterative.

Figure 2.

Screen capture of the web-based microsimulation user interface for the prostate cancer model for a risk-stratified screening protocol, where men at low risk are rescreened every 8 years and men at medium risk are rescreened every 4 years.

Figure 3.

Automated mammography breast segmentation and feature extraction for breast cancer research. The figure shows the output of our preprocessing of mammograms: (A) original full-field digital mammograms, (B) pseudo-color generation after applying the horizontal and vertical cropping, (C) positive signal in the Q component in the NTSC color space, detecting the reddish area, (D) convex hull of the negative (c), (E) final extracted breast mask, and (F) breast region after applying the contrast limited adaptive histogram equalization. Note that to get the dense tissue region, one could perform a logical AND operation of the input images (C and D).