Leveraging Natural language Processing and Machine Learning Techniques to find Frailty Deficits from Clinical Dataset
Bibliographic record
Abstract
Introduction Frailty is a syndrome that is often associated with aging. It can be identified through specific frailty scales or a comprehensive assessment by a healthcare provider. In Alberta, it appears that there are no specific billing or diagnostic codes for frailty. So, healthcare providers may use specific assessments or codes related to conditions such as muscle weakness or decreased physical activity to identify frailty. Purpose This project aims to leverage Natural Language Processing algorithms to extract frailty keywords from structured and Unstructured clinical datasets to identify frailty deficits and classify patients into frail and non-frail classes using Machine Learning algorithms. Methods The dataset included 450 patients over the age of 60, medical information related to diseases, and clinical frailty scales. We first clean medical notes using NLP techniques and removing negation terms, then extract keywords from clinical notes and structured datasets, and finally, we use resampling techniques to deal with imbalanced clinical datasets, and we feed these extracted keywords into machine learning classifiers to classify patients as frail or not frail. Results There are many different types of machine learning classifiers that have been used for this task, Random Forest and Decision Three with 0.95 performed better than LR, KNN, NB, SVM, and neural network models. Conclusion Natural Language Processing algorithms can effectively extract frailty keywords using Electronic Medical Record (EMR) notes. Moreover, comparing the results shows that using both structured and unstructured data gives better results than using only structured data.
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 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".