2nd European Conference on Diagnostic Error in Medicine August 30-31, 2018, Bern, Switzerland
Bibliographic record
Abstract
Background: The process of formulating a working diagnosis in the inpatient setting requires that diagnosticians working in complex and hectic hospital environments gather, filter, integrate, and interpret substantial amounts of information within a short time.Several years ago, the information needed for diagnosis was gathered primarily at the bedside.More recently and with the advance of new technologies, this information is collected through a series of communication exchanges (e.g., pagers, emails) and interactions with the electronic health record (EHR).In this study, we examined challenges and opportunities for improvement in clinician-to-clinician communication and data sharing during the diagnostic process.Methods: We performed a qualitative, multi-method, focused ethnographic study.Data were gathered between January and May 2016 at two affiliated teaching hospitals.Eight inpatient medicine teams (which included attending physicians, senior residents, interns, and medical students) were observed during morning rounds and in the afternoon on call and non-call days.Focus groups and interviews were then conducted with team members to better understand challenges and opportunities for improvement.Unstructured field notes were taken during observations.All focus groups and interviews were recorded and transcribed.Data were analyzed using qualitative content analysis.Results: Observation data showed that physicians faced a data-gathering and communication environment that made integration and interpretation of information for diagnosis challenging.Notably, data flow and communication for each patient was fragmented over time and diagnostic information was pieced together from multiple sources.Pagers were inefficient and did not support dialogue needed for diagnosis.Suggestions for improvement during interviews and focus groups included: 1) replacing pagers with two-way communication technologies; 2) improving EHR design to support diagnosis by increasing data integration while reducing data overload and information fragmentation; 3) identifying more efficient ways to access the EHR during morning rounds and while in patient rooms; 4) increasing face-to-face communication between clinicians.Conclusion: Teaching hospitals are complex environments.The way patient information is shared and communicated among clinicians has changed with the adoption of electronic health records.Physicians are confronted with data overload, frequent interruptions, fragmented information, and little time to think about diagnosis.Although improvement opportunities suggested by front line physicians for patient diagnosis were identified, how best to implement these ideas remains to be determined.
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 | 0.014 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.007 | 0.004 |
| Open science | 0.002 | 0.007 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.147 | 0.083 |
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".