265-OR: Identifying Adults at Risk of Unintentional Severe Hypoglycemia in Hospital Using Artificial Intelligence (RUSHH-AI)
Bibliographic record
Abstract
Background: Machine learning carries great promise to improve healthcare delivery. Clinical outcomes that are routinely and objectively measured, and have serious consequences that can be prevented, are ideal targets for prediction and intervention. Hypoglycemia, defined as a blood glucose less than 3.9 mmol/L (70 mg/dL), meets these criteria. The purpose of this study was to predict hypoglycemia using artificial intelligence models in patients hospitalized to general internal medicine (GIM) and cardiovascular surgery (CV) at a tertiary-care teaching hospital in Toronto, Ontario. Methods: Models were built using routinely-collected clinical data from the hospital’s electronic health record. Models were trained using data from Jan 2013-Apr 2017, tested using data from Apr 2017-Mar 2018, and validated using held-out test data from Apr 2018-Mar 2019. Three models were generated using supervised machine learning: LASSO regression, gradient boosted trees, and a recurrent neural network. Each model included baseline patient data and time-varying data. Natural language processing was used to incorporate text data from physician and nursing notes. Results: We included 8492 GIM admissions and 8044 CV admissions. The average age of patients was 68 years, 35% were women, the baseline creatinine was 90 μmol/L (1.0mg/dL) and the baseline A1C was 7%. Hypoglycemia occurred in 15% of GIM admissions and 13% of CV admissions. The area under the curve for the model in the held-out validation set was approximately 0.80 on the GIM ward and 0.82 on the CV ward. When the threshold for hypoglycemia was lowered to 2.9 mmol/L (52 mg/dL), similar results were observed. Among the patients at the highest decile of risk, the positive predictive value was approximately 50% and the sensitivity was 99%. Conclusion: Using natural language processing and machine learning we were able to accurately identify patients at high risk of hypoglycemia in hospital. Disclosure M. Fralick: None. D. Dai: None. C. Pou-Prom: None. A.A. Verma: None. M. Mamdani: None.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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.
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".