Research on Entity Recognition and Knowledge Graph Construction Based on Tcm Medical Records
Bibliographic record
Abstract
Traditional Chinese medicine (TCM) medical records contain valuable medical information, and are important resources for personalized knowledge analysis, auxiliary diagnosis and treatment, clinical decision support, and drug to use pattern mining of famous TCM doctors. As an effective and novel knowledge management technology, knowledge graph can provide a new way for the inheritance and development of TCM. Constructing medical knowledge graph can potentially help to discover knowledge from clinical data, assist clinical decision-making and personalized treatment recommendation. However, the construction of TCM knowledge graph is still mainly based on structured data, and unstructured texts such as medical records, literature and electronic medical records urgently need to be extracted for mining and analysis. Aiming at the difficulties of word segmentation, entity variety and ambiguity in TCM medical records, this paper proposes a named entity recognition method of deep learning hybrid model based on two-way long-term memory (BILSTM) network and conditional random field (CRF); then by analyzing the process of TCM diagnosis and treatment, the core concepts of TCM are extracted and the ontology layer is constructed; finally, the knowledge graph is constructed by Neo4j, which can provide retrieval, visualization and other functions to help the learning and sharing of TCM knowledge.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.006 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".