MétaCan
Menu
← Back to cohort
Record W7132990447

Assessing Frailty Using Sensors and Machine Learning in Home Settings

2022· dissertation· W7132990447 on OpenAlexaff
C.B. Bian

Bibliographic record

VenueTSpace · 2022
Typedissertation
Language
FieldMedicine
TopicFrailty in Older Adults
Canadian institutionsVector Institute
Fundersnot available
KeywordsClassifier (UML)Gradient boostingFrailty IndexScale (ratio)Identification (biology)Receiver operating characteristicActivities of daily livingFocus group
DOInot available

Abstract

fetched live from OpenAlex

Frailty is a condition in which the individual is in a vulnerable state at increased risk of adverse health outcomes or dying when exposed to a stressor. Frailty can increase dependence and decrease the quality of life for older adults and family members. Early identification of frailty can reverse or delay the development of frailty. However, it is challenging to identify frailty early in clinical settings due to its hidden and gradually progressing nature, which is more reflected in daily life than during clinic visits. The recent development in sensors and artificial intelligence enables remote health sensing and advanced data analytics, allowing early identification of frailty by monitoring frailty indicators reflected in older adults' daily lives. The overall goal of this thesis is to design, develop and validate a multi-sensor-based system for assessing frailty in home settings. To achieve this goal, we first conducted a systematic review and a focus group study to understand gaps in home-based frailty screening technologies and older adults’ opinions on potential technologies. Guided by the review and focus group findings, a novel multi-sensor-based frailty monitoring system, Frailty Toolkit, was developed. The concurrent validity of the sensor measurements was validated. Additionally, machine learning algorithms were implemented on a large health survey dataset with more than 27,000 samples to classify frailty using the behavioral and physical health features. As a result, the system prototype showed excellent concurrent validity for all ambient sensors but the weight scale in lab tests. The gradient boosting classifier yielded the highest area under the receiver operating characteristic curve (0.95) for classifying frailty. The highest area under the precision-recall curve of 0.70 achieved with the gradient boosting classifier was a significant improvement over a no-skill classifier. In conclusion, this thesis developed and validated a multi-sensor-based system and machine learning models for assessing frailty in home settings. The proposed system is unique because it involves older adults’ voices in the design process and measures a novel set of behavioral and physical health signs of frailty using less invasive ambient sensors. This work has significant implications for home-based frailty assessment.

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 imitation

Not 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.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.019
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.032

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.019
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.047
GPT teacher head0.380
Teacher spread0.333 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueTSpace→Same topicFrailty in Older Adults→French-language works237,207→