Applying Human-Centered Data Science to Healthcare: Hyperlocal Modeling of COVID-19 Hospitalizations

Simple item page
dc.contributor.authorChui, Victoria
dc.contributor.authorPater, Jessica
dc.contributor.authorToscos, Tammy
dc.contributor.authorGuha, Shion
dc.date.accessioned2023-03-17T22:49:08Z
dc.date.available2023-03-17T22:49:08Z
dc.date.issued2023
dc.description.abstractAlgorithms as a component of decision-making in healthcare are becoming increasingly prevalent and AI in healthcare has become a topic of mass consideration. However, pursuing these methods without a human-centered framework can lead to bias, thus incorporating discrimination on behalf of the algorithm upon implementation. By examining each step of the design process from a human-centered perspective and incorporating stakeholder motivations, algorithmic implementation can become vastly useful, and more accurately tailored to stakeholder needs. We examine previous work in healthcare executed with a human-centered design, to analyze the multiple frameworks which effectively create human-centered application, as extended to healthcare.en
dc.identifier.doi10.1145/3565967.3570979
dc.identifier.urihttps://dl.eusset.eu/handle/20.500.12015/4647
dc.language.isoen
dc.publisherAssociation for Computing Machinery
dc.relation.ispartofCompanion Proceedings of the 2023 ACM International Conference on Supporting Group Work
dc.subjecthuman-centered data science
dc.subjectspeculative design
dc.subjecthealthcare
dc.subjectparticipatory design
dc.titleApplying Human-Centered Data Science to Healthcare: Hyperlocal Modeling of COVID-19 Hospitalizationsen
dc.typeText/Conference Paper
gi.citation.startPage24–26
gi.conference.locationHilton Head, SC, USA

Files

Collections

GROUP 2023