MétaCan
Menu
Back to cohort
Record W4361015898 · doi:10.2196/40805

Visualization of Traditional Chinese Medicine Formulas: Development and Usability Study

2023· article· en· W4361015898 on OpenAlexvenueno aff
Zhiyue Wu, Suyuan Peng, Liang Zhou

Bibliographic record

VenueJMIR Formative Research · 2023
Typearticle
Languageen
FieldMedicine
TopicTraditional Chinese Medicine Studies
Canadian institutionsnot available
Fundersnot available
KeywordsVisualizationUsabilityComputer scienceTraditional Chinese medicineFlexibility (engineering)Traditional medicineMathematicsData miningMedicineHuman–computer interactionAlternative medicineStatistics

Abstract

fetched live from OpenAlex

BACKGROUND: Traditional Chinese medicine (TCM) formulas are combinations of Chinese herbal medicines. Knowledge of classic medicine formulas is the basis of TCM diagnosis and treatment and is the core of TCM inheritance. The large number and flexibility of medicine formulas make memorization difficult, and understanding their composition rules is even more difficult. The multifaceted and multidimensional properties of herbal medicines are important for understanding the formula; however, these are usually separated from the formula information. Furthermore, these data are presented as text and cannot be analyzed jointly and interactively. OBJECTIVE: We aimed to devise a visualization method for TCM formulas that shows the composition of medicine formulas and the multidimensional properties of herbal medicines involved and supports the comparison of medicine formulas. METHODS: A TCM formula visualization method with multiple linked views is proposed and implemented as a web-based tool after close collaboration between visualization and TCM experts. The composition of medicine formulas is visualized in a formula view with a similarity-based layout supporting the comparison of compositing herbs; a shared herb view complements the formula view by showing all overlaps of pair-wise formulas; and a dimensionality-reduction plot of herbs enables the visualization of multidimensional herb properties. The usefulness of the tool was evaluated through a usability study with TCM experts. RESULTS: Our method was applied to 2 typical categories of medicine formulas, namely tonic formulas and heat-clearing formulas, which contain 20 and 26 formulas composed of 58 and 73 herbal medicines, respectively. Each herbal medicine has a 23-dimensional characterizing attribute. In the usability study, TCM experts explored the 2 data sets with our web-based tool and quickly gained insight into formulas and herbs of interest, as well as the overall features of the formula groups that are difficult to identify with the traditional text-based method. Moreover, feedback from the experts indicated the usefulness of the proposed method. CONCLUSIONS: Our TCM formula visualization method is able to visualize and compare complex medicine formulas and the multidimensional attributes of herbal medicines using a web-based tool. TCM experts gained insights into 2 typical medicine formula categories using our method. Overall, the new method is a promising first step toward new TCM formula education and analysis methodologies.

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)0.014
metaresearch head score (Gemma)0.035
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.014
Threshold uncertainty score0.073

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.035
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.001
Scholarly communication0.0020.002
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

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 head0.152
GPT teacher head0.471
Teacher spread0.319 · 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 designObservational
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

Citations8
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative ResearchSame topicTraditional Chinese Medicine StudiesFrench-language works237,207