Development of a Context-aware Telemedicine Framework and it's use in Promoting Safe Aging in Place through Wearable and Smart Home Technology
Bibliographic record
Abstract
The present work focused on building a framework for context-aware telemedical systems which can leverage physiological data from sensors within its context to quantify the likelihood of medical events, conditions, and diseases for users. A context-aware smart home system was built for both validating the framework and demonstrating how it could be used to build medical applications. A systematic review was conducted in order to identify which contexts are most prevalent in context-aware medical systems and what the various categories of context-aware medical applications were. A total of 23 articles passed all screening levels and underwent data extraction. The most common contexts used were the user location (8/23 studies), demographic info (5/23 studies), movement status/activity level (6/23 studies), time of day (5/23 studies), phone usage patterns (5/23 studies), lab/vitals (7/23 studies), and patient history data (8/23 studies). The important contexts discovered used to build a framework for context-aware medical systems that converts sensor data into contexts/situations in order to run clinical tests and quantify the likelihood a patient has a given condition, disease or adverse event. Context probabilities, clinical test/situation results, and post-test probabilities for Parkinson’s and falling within 12 months were compared between experiments where healthy users emulated mobility impaired and unimpaired adults who had a positive or negative outcome for common clinical tests. The post-test probabilities determined by the system for falling within 12 months or having Parkinson’s were statistically significantly (p < 0.05) higher in the mobility impaired group relative to the unimpaired group, thus validating the theory's utility in autonomously establishing contexts and using them to conduct tests. This framework was then used to develop a smart home system with a context-aware emergency alert application that could utilize mobility and heart rate data within its context to determine if physiological data was (or was not) indicative of an emergency. The context-unaware alarm triggered an emergency when the user's heart rate was elevated during exercise, whereas the context-aware alarm was not triggered as it was able to recognize the active context for the user. The context-unaware alarm also triggered while the user emulated sleeping, whereas the context-aware alarm was not triggered since it could recognize the time of day was within normal sleeping hours. Lastly, the system was piloted in older adults’ homes and it was demonstrated that select contexts such as immobility time, the time users started or ended their day, and whether users were moving between rooms could be determined autonomously using the framework.
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 | 0.008 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".