OBJECTIVE To explore the transformation of the dispensing and drug pickup process in traditional Chinese medicine pharmacy （TCM Pharmacy） in our hospital based on data-intelligence-driven， aiming to improve pharmacists’ work efficiency and patients’ drug pickup experience. METHODS Value stream mapping and journey mapping were used to systematically identify non-value-added links in pharmacists’ dispensing process and key pain points in patients’ drug pickup under the traditional process. An intelligent dispensing and drug pickup system for the TCM Pharmacy was developed based on the C# and Android television platforms， and a machine-learning model was adopted to predict patients’ drug pickup waiting time. A comprehensive evaluation was performed from three perspectives： system performance， prediction accuracy， and satisfaction of pharmacists and patients. RESULTS The system successfully streamlined non-value-added links such as “waiting for writing on the board” and “searching for drugs”， and realized multimodal dynamic prompts of dispensing status through auditory （number calling） and visual （television terminal） channels. The constructed model for predicting drug pickup waiting time exhibited good fitting degree and generalization ability （mean absolute error＝4.28 min， R 2 ＝0.882）. The comprehensive satisfaction scores of pharmacists and patients in the traditional mode were significantly increased from （70.99±1.74） and （73.58±1.98） to （90.02±1.30） and （88.61±2.08） in the new system， respectively （ P ＜0.01）. CONCLUSIONS The transformation of the intelligent drug dispensing and pickup system for TCM pharmacy based on data-intelligence-driven effectively improves the efficiency of pharmacists’ dispensing work， realizes process transparency and waiting time predictability， and significantly enhances patients’ drug pickup experience.

OBJECTIVE To construct a predictive model for timely medication retrieval of outpatients， accurately identify high-risk patients with delayed medication retrieval， and provide data support for the development of differentiated registration strategies and resource optimization allocation in smart pharmacies. METHODS Based on 680 568 valid outpatient prescription records from January to March 2025 at the First Affiliated Hospital of Xi’an Jiaotong University， a dual-clustering analysis was conducted using K-means algorithm and Gaussian mixture model （GMM）. An adaptive threshold for medication retrieval time difference was determined by combining contour coefficients， and “timely medication retrieval” and “delayed medication retrieval” were divided to construct binary objective variables； six types of features were screened through a multi-method fusion strategy； the performance of 6 kinds of base learners and 4 kinds of ensemble learning models were evaluated from three dimensions： discrimination， overall performance， and calibration， and explanatory analysis of the models were conducted. RESULTS The results of the dual-clustering analysis showed that the silhouette coefficient of GMM was better than K-means （0.702 4 vs. 0.698 8）， and the final adaptive threshold was determined to be 49.82 min. Among the prescriptions included， 74.99% were for timely medication retrieval and 25.01% were for delayed medication retrieval. Among the 10 candidate models， the Stacking model performed the best， with an area under the test set curve of 0.954 4， F1 score of 0.942 4， accuracy of 0.911 5， Brier score of 0.066， and good discrimination and calibration. The explanatory analysis results of the model showed that its predictions were driven by multiple factors such as patient historical behavior， and diagnostic related characteristics. CONCLUSION This study constructed a timely medication retrieval prediction model for outpatients based on a two-stage adaptive threshold ensemble learning algorithm， which has high accuracy and stability， and can achieve dynamic judgment of patient medication retrieval behavior.

Objective To explore how digital and intelligent technologies can optimize the storage allocation and picking paths for Traditional Chinese medicine decoction pieces.Methods Based on prescription information and medicine data from the hospital information system(HIS),this study employs MATLAB programming to use an integer linear programming(ILP)algorithm for optimizing the storage allocation of Traditional Chinese medicine decoction pieces.Additionally,a greedy algorithm is applied to optimize the picking paths to reduce the picking distance for pharmacists.Finally,an independent samples paired t-test is used to analyze the experimental data to verify the significance of the optimizations.Results A total of 7 734 prescriptions were collected from the HIS.The results of storage optimization showed that the total distance before optimization was(87.58±0.29)m,which was reduced to(85.35±0.28)m after optimization(P﹤0.000 1).The picking path optimization results showed that the picking path was(85.35±0.28)m before optimization and(40.06±0.11)m after optimization(P﹤0.000 1).The results of the independent samples paired t-test indicate that the path was significantly reduced after both storage and picking path optimizations,with statistical significance.Conclusion By using digital and intelligent methods,informatics pharmacists can effectively shorten the picking paths for Traditional Chinese medicine decoction pieces,improve dispensing efficiency,and reduce patient waiting times.

Objective To explore how digital and intelligent technologies can optimize the storage allocation and picking paths for Traditional Chinese medicine decoction pieces.Methods Based on prescription information and medicine data from the hospital information system(HIS),this study employs MATLAB programming to use an integer linear programming(ILP)algorithm for optimizing the storage allocation of Traditional Chinese medicine decoction pieces.Additionally,a greedy algorithm is applied to optimize the picking paths to reduce the picking distance for pharmacists.Finally,an independent samples paired t-test is used to analyze the experimental data to verify the significance of the optimizations.Results A total of 7 734 prescriptions were collected from the HIS.The results of storage optimization showed that the total distance before optimization was(87.58±0.29)m,which was reduced to(85.35±0.28)m after optimization(P﹤0.000 1).The picking path optimization results showed that the picking path was(85.35±0.28)m before optimization and(40.06±0.11)m after optimization(P﹤0.000 1).The results of the independent samples paired t-test indicate that the path was significantly reduced after both storage and picking path optimizations,with statistical significance.Conclusion By using digital and intelligent methods,informatics pharmacists can effectively shorten the picking paths for Traditional Chinese medicine decoction pieces,improve dispensing efficiency,and reduce patient waiting times.

ObjectiveTo study the effects of matrine derivative C4 on migration， invasion and apoptosis of non-small cell lung cancer cells by targeting heat shock protein 90. MethodMolecular docking and Western blot were used to detect the regulation of matrine derivative C4 （0， 1， 2， 4， 8 μmol·L^-1） on heat shock protein 90 （Hsp90）. methyl thiazolyl-tetrazolium （MTT） assay was conducted to observe the effects of C4 （0， 0.25， 0.5， 1， 2， 4， 8， 16 μmol·L^-1） on viability of A549 cells. The impacts of different concentrations of C4 （0， 2， 4， 8 μmol·L^-1） on the proliferation， migration， invasion and apoptosis of A549 cells were explored by clone formation assay， wound healing assay， Transwell assay， and flow cytometry， respectively. Western blot was employed to detect the effects of C4 （0， 1， 2， 4， 8 μmol·L^-1） on the protein expression of A549 protein kinase B （Akt）， phosphorylated protein kinase B （p-Akt）， epidermal growth factor receptor （EGFR）， phosphatidylinositol 3 kinase （PI3K）， p-PI3K， cysteine aspartate protease 9 （Caspase-9）， B-cell lymphoma 2 （Bcl-2）-associated X （Bax）， Bcl-2， and Bcl-2-associated agonist of cell death （Bad）. ResultMatrine derivative C4 could effectively interact with Hsp90 protein through a water-mediated hydrogen bond network with residues of asparagine-51 （ASN-51）， glycine-135 （GLY-135）， and phenylalanine-138 （PHE-138）， and the π-π stacking interaction with the phenyl ring of PHE-138 contributed to its affinity. In addition， compared with blank group， C4 down-regulated the protein expression of Hsp90 in A549 cells （P<0.05， P<0.01）， and reduced the cell viability （P<0.05， P<0.01）. The half-maximal inhibitory concentrations （IC₅₀） of C4 on A549 cells were （12.32±0.14）， （7.79±0.16） and （3.26±0.09） μmol·L^-1 at 24， 48 and 72 h， respectively. Compared with the conditions in the blank group， the clone formation ability of A549 cells in C4 （2， 4， 8 μmol·L^-1） groups was decreased （P<0.05， P<0.01） in a concentration-dependent manner， and C4 inhibited the migration and invasion of A549 cells （P<0.05， P<0.01）， with the most significant inhibition observed at 8 μmol·L^-1 （P<0.01）. Moreover， C4 induced apoptosis of A549 cells （P<0.01）， and the apoptosis rates at 0， 2， 4 and 8 μmol·L^-1 were （2.28±0.35）%， （4.97±0.36）%， （8.86±0.50）% and （20.67±0.99）%， respectively. It also up-regulated the protein expression of Caspase-9， Bax and Bad （P<0.05， P<0.01）， while down-regulated those of PI3K， p-PI3K， p-Akt， EGFR and Bcl-2 to varying degrees （P<0.05， P<0.01）， and the protein expression level of Akt did not change significantly. ConclusionMatrine derivative C4 played an anti-tumor role by inhibiting cell viability， proliferation， migration and invasion and promoting apoptosis response， which might be realized by inhibiting Hsp90/PI3K/Akt signaling pathway.