Situated visual alarm displays support machine fitness assessment for nonexplainable automation

MF Rayo, CR Horwood, MC Fitzgerald… - … on Human-Machine …, 2022 - ieeexplore.ieee.org
Determine if situated visual alarm displays can support machine fitness assessment (MFA),
facilitating improved hazard recognition and alarm accuracy assessment in the presence of …

Applying human factors engineering to address the telemetry alarm problem in a large medical center

ES Patterson, MF Rayo, JR Edworthy… - Human …, 2022 - journals.sagepub.com
Objective Address the alarm problem by redesigning, reorganizing, and reprioritizing to
better discriminate alarm sounds and displays in a hospital. Background Alarms in hospitals …

Monitoring vital signs with time-compressed speech.

PM Sanderson, B Brecknell, SY Leong… - Journal of …, 2019 - psycnet.apa.org
Spearcons—time-compressed speech phrases—may be an effective way of communicating
vital signs to clinicians without disturbing patients and their families. Four experiments tested …

Situated Interpretation and Data: Explainability to Convey Machine Misalignment

DA Morey, MF Rayo - IEEE Transactions on Human-Machine …, 2023 - ieeexplore.ieee.org
Explainable AI must simultaneously help people understand the world, the AI, and when the
AI is misaligned to the world. We propose situated interpretation and data (SID) as a design …

Breaking away from brittle machines: Evaluating simultaneous inference and data (SID) displays to facilitate machine fitness assessment

DA Morey - 2021 - rave.ohiolink.edu
Capable computational technology is a necessary but not a sufficient condition for
engineering a high-performing human-machine team (HMT). The interactions between …

Early Investments for Teaming Dividends: A Human-Centered Approach to a Patient Decompensation Prediction Algorithm

DA Morey, RC Gifford, MF Rayo - Proceedings of the …, 2024 - journals.sagepub.com
Deployments of artificial intelligence (AI) and machine learning (ML) in healthcare can both
help and harm patient outcomes, amplifying calls for a human-centered approach to AI/ML …

The IMPActS Framework: the necessary requirements for making science-based organizational impact

MC Fitzgerald - 2019 - rave.ohiolink.edu
Despite growing pressure for organizations to implement more science-based solutions into
practice, efforts to successfully achieve this task have been known to fail due to the tensions …

The importance of testing sets of clinical alarm sounds and navigating tradeoffs to translate research findings into implementation

M Fitzgerald, MF Rayo, ME Reynolds… - Proceedings of the …, 2019 - journals.sagepub.com
Despite noticeable efforts over the last 30 years to try and resolve the clinical alarm problem,
the utilization of opinion-based and nonscientific alarm interventions has resulted in …

Targeted Design Choices in Machine Learning Architectures Can Both Improve Model Performance and Support Joint Activity

R Gifford - 2024 - search.proquest.com
Opaque models do not support Joint Activity and create brittle systems that fail rapidly when
the model reaches the edges of its operating conditions. Instead, we should use models …

Jointness Still Matters: Adding AI Without Designing for Joint Activity Likely Degrades Performance

DA Morey - 2023 - search.proquest.com
As the push for increased artificial intelligence (AI) and machine learning (ML) in safety-
critical domains continues to grow stronger, calls for responsible AI have emphasized the …