Application of Language Processing Techniques to Capture the Use of Nursing Clinical Terms from Narrative Statements: Report of a Pilot Study
Bibliographic record
Abstract
OBJECTIVE: The authors piloted the use of the "General Architecture for Text Engineering" (GATE) program in an analysis of writings from the nursing literature to determine if this standard language processing technique could be used to capture the use of complex nursing terms. This work was undertaken as an initial step in evaluating if widely-available natural language processing methods could be applied to narrative nursing notes in a way that a nursing diagnosis could be identified and extracted from a narrative text. METHODS: For purposes of the pilot study, the complex nursing term "powerlessness", which is identified as a NANDA-I nursing diagnosis, was selected as the test case. A PubMed search was performed on the term "powerlessness" limited to articles in the nursing literature that contained abstracts, resulting in 232 articles published between 1981 to 2010 meeting the criteria. Three-sentence extracts from each abstract were analyzed by applying GATE to identify noun and adjective roots occurring in close proximity to the index word, and then identifying if these proximal words reflected the standardized defining characteristics, adjectives and qualifiers of the diagnostic term. RESULTS: The analysis resulted identification 2,174 unique terms. While a few terms coincided with the NANDA-I defining characteristics of "powerlessness", most of the established defining characteristics were not reflected in the use of the term. CONCLUSIONS: Machine language processing techniques are promising in identifying meanings and contextual use of words related to nursing concepts, but the use of such words in published papers does not represent definitions found in standard nursing nomenclature. Nursing writers use terms that are also understood outside the disciplinary domain, making standardization and coding particularly challenging. Future research in Nursing should apply the techniques described to clinical reports and to evaluate the match between clinical usage and standardized meanings.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".