Problem Oriented Medical Translational Services based on GraphQL Connectivity
Bibliographic record
Abstract
Research in translational medicine (TM) is growing rapidly due to the growing believe that most valuable data source for the biomedical discoveries come from the basic research on clinical care extracted from patient cases descriptions. Bridging the clinical care findings at the bedside with the biomedical knowledge at the bench provide insights that can improve patient outcomes and lead to the development of new drugs and therapies. Research on translational medicine gained a great deal of prominence through the establishment of governmental and institutional boards like the US Clinical and Translational Science Awards (CTSA) and the EU Seventh Framework Program (FP7). TM research is ultimately requires data integration on a massive scale between variety of clinical data. In order to accelerate medical discovery, the integration of biomedical data needs to happen both at the physician point of care level via the electronic health records (EHRs) and at bench top applications and repositories. However, data integration is a great challenge to healthcare as the legacy technologies used are built around the REST APIs to get data into these biomedical applications and systems. The REST protocol is aging as it has been the technology used for the last 20 years. Major information technology venders like Facebook and Google have replaced REST with GraphQL allowing changes on the client side to fetch new data from the server without the need for extra work on the server. In this paper we are describing our efforts to integrate the problem oriented medical record (called QL4POMR that is based on GraphQL) which has been defined around the notion of SOAP (Subjective, Objective, Assessment and Planning) to describe patient cases with the HL7 FHIR electronic record and the HL7 IPS patient summary as well as with other external biomedical repositories like the OpenTargets and the Drug Bank. The integration has been described via adding a data layer on top of the QL4POMR to enable the schema integration and querying from all these external sources via the GraphQL server. Our initial experimentations show success in discovering drug adverse events and in recommending alternative drugs at the time of prescribing new medication to patients and completing the planning section of SOAP. More research will continue to draw other translational associations based on the integration provided by our QL4POMR framework with OpenTargets and Drug Bank.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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 teacher head, 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".