RiskFix: Supporting Expert Validation of Predictive Timeseries Models in High-Intensity Settings

Simple item page
dc.contributor.authorMorgenshtern, Gabrielaen_US
dc.contributor.authorVerma, Arnaven_US
dc.contributor.authorTonekaboni, Sanaen_US
dc.contributor.authorGreer, Roberten_US
dc.contributor.authorBernard, Jürgenen_US
dc.contributor.authorMazwi, Mjayeen_US
dc.contributor.authorGoldenberg, Annaen_US
dc.contributor.authorChevalier, Fannyen_US
dc.contributor.editorHoellt, Thomasen_US
dc.contributor.editorAigner, Wolfgangen_US
dc.contributor.editorWang, Beien_US
dc.date.accessioned2023-06-10T06:34:32Z
dc.date.available2023-06-10T06:34:32Z
dc.date.issued2023
dc.description.abstractMany real-world machine learning workflows exist in longitudinal, interactive machine learning (ML) settings. This longitudinal nature is often due to incremental increasing of data, e.g., in clinical settings, where observations about patients evolve over their care period. Additionally, experts may become a bottleneck in the workflow, as their limited availability, combined with their role as human oracles, often leads to a lack of ground truth data. In such cases where ground truth data is small, the validation of interactive machine learning workflows relies on domain experts. Only those humans can assess the validity of a model prediction, especially in new situations that have been covered only weakly by available training data. Based on our experiences working with domain experts of a pediatric hospital's intensive care unit, we derive requirements for the design of support interfaces for the validation of interactive ML workflows in fast-paced, high-intensity environments. We present RiskFix, a software package optimized for the validation workflow of domain experts of such contexts. RiskFix is adapted to the cognitive resources and needs of domain experts in validating and giving feedback to the model. Also, RiskFix supports data scientists in their model-building work, with appropriate data structuring for the re-calibration (and possible retraining) of ML models.en_US
dc.description.sectionheadersVA and Perception
dc.description.seriesinformationEuroVis 2023 - Short Papers
dc.identifier.doi10.2312/evs.20231036
dc.identifier.isbn978-3-03868-219-6
dc.identifier.pages13-17
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/evs.20231036
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evs20231036
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Model verification and validation; Human-centered computing -> Open source software; Applied computing -> Health care information systems
dc.subjectComputing methodologies
dc.subjectModel verification and validation
dc.subjectHuman centered computing
dc.subjectOpen source software
dc.subjectApplied computing
dc.subjectHealth care information systems
dc.titleRiskFix: Supporting Expert Validation of Predictive Timeseries Models in High-Intensity Settingsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
013-017.pdf
Size:
1.59 MB
Format:
Adobe Portable Document Format
Download
Collections
EuroVisShort2023