A Network Visualization Query System for Multi-Drug Compatibility Based on a WeChat Mini Program: A Preliminary Usability and Efficiency Evaluation (Preprint)
Bibliographic record
Abstract
BACKGROUND: Intravenous (IV) drug incompatibility is a significant medication safety hazard, particularly in complex multi-drug regimens. Traditional text-based, pairwise query methods are inefficient and impose a substantial cognitive load on clinicians. While network visualization has the potential to address these challenges, its application in drug compatibility queries remains underexplored. OBJECTIVE: This study aimed to design, develop, and evaluate a novel drug compatibility query system based on a WeChat Mini Program. The system integrates diverse data sources and employs network visualization to present complex compatibility relationships. We sought to empirically assess its impact on efficiency and user experience. METHODS: A preliminary crossover usability and efficiency evaluation was conducted. Phase 1 involved the construction of a drug compatibility knowledge base from authoritative handbooks and drug labels, and the development of the query system. Phase 2 comprised a system evaluation with 36 pharmacists, 6 physicians, and 5 nurses. The evaluation included a scenario-based task completion time analysis comparing the system (Mode A) with traditional print-based resources (Mode B), a quality assessment using the Mobile Application Rating Scale (MARS), and structured post-task user feedback to gather insights on user experience. RESULTS: The query system demonstrated a substantial reduction in task completion time, with median time savings of 2.85 minutes (IQR = 1.98-4.15), 5.45 minutes (IQR = 3.95-7.20) and 31.2 minutes (IQR = 27.5-35.1) respectively in three scenarios with different complexity. The system received a high mean overall quality score of 3.88 (SD=0.35) on the MARS. The Functionality dimension scored the highest (M=4.21, SD=0.51), while Engagement scored the lowest (M=3.21, SD=0.62). Post-task structured feedback revealed five major areas of user feedback: (1) baseline experience and first impressions, (2) user experience with network visualization, (3) perceived efficiency and cognitive load, (4) trust and information quality, and (5) future application considerations. Users praised the system's efficiency and intuitive design but expressed a strong need for transparent data sources and management advice to build trust. CONCLUSIONS: A query system based on network visualization demonstrates potential to support the efficiency of multi-drug compatibility queries within this preliminary evaluation. It may mitigate cognitive load and offer an at-a-glance understanding of complex drug relationships. However, formal clinical accuracy validation remains a mandatory precondition before bedside clinical deployment is considered.
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 | 0.008 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".