State Based Hidden Markov Models for Temporal Pattern Discovery in Critical Care
Bibliographic record
Abstract
We are studying the challenge of finding a good set of features that represent well the temporal aspects in time series data. We argue that discovery of such features could be crucial to understanding hidden relationships in data. In particular, in critical care where time oriented data is generated every second on patients physiological features, discovery of any hidden relationships could aid in discovery of unknown and potentially life threatening conditions before they happen. Additionally, this discovery could help in better dissemination of healthcare services leading to better outcomes and experiences for patients. To facilitate this process, this research explores two research questions; (a) can discovery of temporal relationships in data help in learning hidden aspects in differing patient cohort and (b) with respect to elderly patients receiving telehealth services, can detection of abnormal patterns help in identifying patients at risk of adverse events before they happen. In this paper, we introduce a model for temporal pattern mining by; (1) applying principles from finite state machines augmented with hidden markov models and temporal abstraction for identifying temporal relations in data, (2) generating temporal patterns by augmenting similar relationships, (3) formulating a process for mining frequently occurring temporal patterns and (4) using the resulting mined patterns to build a temporal classification system. Such a classification system can be effective at characterizing normal and abnormal behaviors in patients data and flag when a patient is at risk of a potential adverse event.
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 | 0.003 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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 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".