MétaCan
Menu
Back to cohort
Record W4229003880 · doi:10.2196/33967

Enhancing Clinical Information Display to Improve Patient Encounters: Human-Centered Design and Evaluation of the Parkinson Disease-BRIDGE Platform

2022· article· en· W4229003880 on OpenAlexvenueno aff
Ethan Brown, Erica Schleimer, Ian O. Bledsoe, William Rowles, Nicolette Miller, Stephan Sanders, Katherine P. Rankin, Jill L. Ostrem, Caroline M. Tanner, Riley Bove

Bibliographic record

VenueJMIR Human Factors · 2022
Typearticle
Languageen
FieldMedicine
TopicParkinson's Disease Mechanisms and Treatments
Canadian institutionsnot available
Fundersnot available
KeywordsBridge (graph theory)UsabilityVariety (cybernetics)Health careRelevance (law)PsychologyComputer scienceMedicineHuman–computer interactionApplied psychologyArtificial intelligence

Abstract

fetched live from OpenAlex

BACKGROUND: People with Parkinson disease (PD) have a variety of complex medical problems that require detailed review at each clinical encounter for appropriate management. Care of other complex conditions has benefited from digital health solutions that efficiently integrate disparate clinical information. Although various digital approaches have been developed for research and care in PD, no digital solution to personalize and improve communication in a clinical encounter is readily available. OBJECTIVE: We intend to improve the efficacy and efficiency of clinical encounters with people with PD through the development of a platform (PD-BRIDGE) with personalized clinical information from the electronic health record (EHR) and patient-reported outcome (PRO) data. METHODS: Using human-centered design (HCD) processes, we engaged clinician and patient stakeholders in developing PD-BRIDGE through three phases: an inspiration phase involving focus groups and discussions with people having PD, an ideation phase generating preliminary mock-ups for feedback, and an implementation phase testing the platform. To qualitatively evaluate the platform, movement disorders neurologists and people with PD were sent questionnaires asking about the technical validity, usability, and clinical relevance of PD-BRIDGE after their encounter. RESULTS: The HCD process led to a platform with 4 modules. Among these, 3 modules that pulled data from the EHR include a longitudinal module showing motor ratings over time, a display module showing the most recently collected clinical rating scales, and another display module showing relevant laboratory values and diagnoses; the fourth module displays motor symptom fluctuation based on an at-home diary. In the implementation phase, PD-BRIDGE was used in 17 clinical encounters for patients cared for by 1 of 11 movement disorders neurologists. Most patients felt that PD-BRIDGE facilitated communication with their clinician (n=14, 83%) and helped them understand their disease trajectory (n=11, 65%) and their clinician's recommendations (n=11, 65%). Neurologists felt that PD-BRIDGE improved their ability to understand the patients' disease course (n=13, 75% of encounters), supported clinical care recommendations (n=15, 87%), and helped them communicate with their patients (n=14, 81%). In terms of improvements, neurologists noted that data in PD-BRIDGE were not exhaustive in 62% (n=11) of the encounters. CONCLUSIONS: Integrating clinically relevant information from EHR and PRO data into a visually efficient platform (PD-BRIDGE) can facilitate clinical encounters with people with PD. Developing new modules with more disparate information could improve these complex encounters even further.

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 imitation

Not 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.

metaresearch head score (Codex)0.048
metaresearch head score (Gemma)0.056
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.048
Threshold uncertainty score0.255

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0480.056
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0030.002
Open science0.0020.005
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

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.

Opus teacher head0.078
GPT teacher head0.359
Teacher spread0.281 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

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".

Quick stats

Citations9
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Human FactorsSame topicParkinson's Disease Mechanisms and TreatmentsFrench-language works237,207