Journal article
DASS Good: Explainable Data Mining of Spatial Cohort Data
Computer graphics forum, Vol.42(3), pp.283-295
06/2023
DOI: 10.1111/cgf.14830
Abstract
Developing applicable clinical machine learning models is a difficult task when the data includes spatial information, for example, radiation dose distributions across adjacent organs at risk. We describe the co‐design of a modeling system, DASS, to support the hybrid human‐machine development and validation of predictive models for estimating long‐term toxicities related to radiotherapy doses in head and neck cancer patients. Developed in collaboration with domain experts in oncology and data mining, DASS incorporates human‐in‐the‐loop visual steering, spatial data, and explainable AI to augment domain knowledge with automatic data mining. We demonstrate DASS with the development of two practical clinical stratification models and report feedback from domain experts. Finally, we describe the design lessons learned from this collaborative experience.
Details
- Title: Subtitle
- DASS Good: Explainable Data Mining of Spatial Cohort Data
- Creators
- A. Wentzel - University of Illinois Urbana-ChampaignC. Floricel - University of Illinois Urbana-ChampaignG. Canahuate - University of IowaM.A. Naser - The University of Texas MD Anderson Cancer CenterA.S. Mohamed - The University of Texas MD Anderson Cancer CenterC D Fuller - The University of Texas MD Anderson Cancer CenterL. van Dijk - The University of Texas MD Anderson Cancer CenterG.E. Marai - University of Illinois Urbana-Champaign
- Resource Type
- Journal article
- Publication Details
- Computer graphics forum, Vol.42(3), pp.283-295
- DOI
- 10.1111/cgf.14830
- ISSN
- 0167-7055
- eISSN
- 1467-8659
- Number of pages
- 13
- Grant note
- NIH NLM (R01‐LM012527) NSF (CDSE‐1854815; CNS‐1828265) NCI (R01‐CA258827)
- Language
- English
- Date published
- 06/2023
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984438959102771
Metrics
15 Record Views