Ecological Interface Design in Neuro-Critical Care
Bibliographic record
Abstract
Neuro-critical care is a data-intensive environment that requires physicians to integrate information \nacross multiple screens, sources, and software. Despite the advances in neuromonitoring techniques, \ninterfaces that allow for viewing and analyzing of historic data are not common. However, historical \ndata is critical to identify patterns important for patient care. Instead, physicians view the trends of a \npatient’s neurophysiological variables by continuously watching the bedside monitor or they rely on \nchecking the paper (or digital) charts for a patient where variables have been recorded periodically \n(usually once an hour). In neuro-critical care, physicians need to understand the historic and current \nstate as well as predict the future state of intracranial pressure (ICP). ICP is the most monitored brain-specific physiologic variable in the Intensive Care Unit (ICU) and is considered a biomarker for \nsecondary brain injury. As a result, ICP would benefit greatly from showing key patterns important to \npatient state and care. \n \nThe ICU is a stressful, dynamic, and time-sensitive environment where the performance of physicians \nand their ability to correctly diagnose and manage patient treatment has a significant impact on \npatient outcomes. Physicians rely on the bedside physiologic monitor to detect changes in physiologic \nvariables. The monitor must provide the information required to understand the patient’s condition so \nphysicians can determine the optimal treatment plan. With the high cognitive demands and complex \nsociotechnical environment of the ICU, an opportunity exists for improved neuro-critical care \nmonitoring to support physicians’ decision-making. Ecological Interface Design (EID) is an approach \nto interface design that has proven effective for complex, sociotechnical, real-time, and dynamic \nsystems. Research suggests that an EID approach combined with user-centered design has a positive \nimpact on performance, especially in unfamiliar scenarios. \n \nThe objective of this research is to explore an EID design approach combined with user-centered \ndesign to enhance the bedside physiologic monitor through the addition of visualizations that help \nsupport physicians' understanding of complex relationships and concepts in neuro-critical care. The \nhope is that providing more-advanced visualizations on the bedside physiologic monitor will lead to \nimproved situation awareness, decreased mental workload, and expertise development acceleration of \nnovice clinicians in the neuro-ICU. \n \nThe work presented in this thesis builds on the Cognitive Work Analysis (CWA) and observations in \nthe ICU already completed by Uereten et al (2020). The design of the visualizations for use on the \nbedside physiologic monitor was highly iterative and involved the inputs from the CWA and \nobservations as well as ongoing feedback and focus areas provided by Dr. Victoria McCredie, our \nclinical collaborator and critical care physician at Toronto Western Hospital. The visualizations were \nevaluated and validated in semi-structured interviews with trainees (fellows) and experts (staff \nphysicians) in neuro-critical care. The semi-structured interviews with trainees were used as a \npreliminary usability assessment of the visualizations and the interviews with staff physicians were \nused to iterate and refine the designs. The results from both sets of interviews were used to create a \nfinal design prototype that is currently being tested in a usability study with trainee physicians \n(January-March 2023).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.032 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".