Interdisciplinary development and application of computational methods in informatics for clinical applications
Bibliographic record
Abstract
This focus issue serves to highlight the challenging but highly valuable work of interdisciplinary teams collaborating across traditional scientific silos.1–25 There were several points of origin that motivated our choice to highlight interdisciplinary work. One point of origin that initially motivated us as guest associate editors of this focus issue was our shared personal experiences on high-impact clinical informatics projects.26–30 A second point of origin comes from talking to others who are engaged in similarly scoped efforts like the ICU Cockpit.31,32 For example, Dr Keller who led the ICU Cockpit work has spoken of similar roadblocks, shared experiences, need for time spent communicating and listening, and of how few people understand how difficult and time-consuming these efforts are—often 10-15 years from beginning to deployment. The projects we have been part of, and projects of similar scope whose leaders we have commiserated with, took years of collaborative effort from large interdisciplinary teams drawing members across the research and deployment pipelines. The collaborative clinical informatics projects that motivated this focus issue included highly engaged experts spanning a range of diverse teams of practicing clinicians, computational scientists, human–computer interaction and implementation science researchers, informaticians, and operational engineers who run the day-to-day electronic health record (EHR) systems. Interestingly, we observed that experts from diverse teams who presented components of these collaborative projects outside of their direct field of application were met with misunderstandings which manifested in dismissal of ideas, underestimation of the difficulty of another field’s problems, underestimation of the deep innovation required to translate and assemble the science, and general undervaluation of translating research to operations within the clinical informatics space. It is well known that open communication across highly distinct scientific domains is required to solve complex real-world problems and is the reason why, for instance, Oppenheimer fought so hard for open dialog between all scientists working on the Manhattan project.33 A third point of origin was our belief that clinical informatics communities could increase their engagement in interdisciplinary work and that missed opportunities for impact abound when collaborative interdisciplinary expertise is lacking. The goal of increasing dialog between distinct fields to drive increased interdisciplinary work served as a motivation for the Banff International Research Station titled: Dynamics and Data Assimilation, Physiology and Bioinformatics: Mathematics at the Interface of Theory and Clinical Applications in 2022 comprising researchers from a wide variety of interdisciplinary fields including several of the focus issue guest associate editors who were motivated to move these ideas forward through a journal focus issue. Despite some high-profile examples of interdisciplinary work, our anecdotal experience has been that examples of cross-field communication and interdisciplinary teams are hard to identify in peer-reviewed literature. We would like to see this change.
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 | 0.090 | 0.131 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.004 | 0.007 |
| Scholarly communication | 0.012 | 0.011 |
| Open science | 0.004 | 0.017 |
| Research integrity | 0.006 | 0.014 |
| Insufficient payload (model declined to judge) | 0.011 | 0.003 |
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".