Data-driven engineering framework with AI algorithm of Ginkgo Folium tablets manufacturing.

Smart manufacturing still remains critical challenges for pharmaceutical manufacturing. Here, an original data-driven engineering framework was proposed to tackle the challenges. Firstly, from sporadic indicators to five kinds of systematic quality characteristics, nearly 2,000,000 real-world data points were successively characterized from Ginkgo Folium tablet manufacturing. Then, from simplex to the multivariate system, the digital process capability diagnosis strategy was proposed by multivariate Cpk integrated Bootstrap-t. The Cpk of Ginkgo Folium extracts, granules, and tablets were discovered, which was 0.59, 0.42, and 0.78, respectively, indicating a relatively weak process capability, especially in granulating. Furthermore, the quality traceability was discovered from unit to end-to-end analysis, which decreased from 2.17 to 1.73. This further proved that attention should be paid to granulating to improve the quality characteristic. In conclusion, this paper provided a data-driven engineering strategy empowering industrial innovation to face the challenge of smart pharmaceutical manufacturing.

[Criticalquality attribute assessment of big brand traditional Chinese medicine: visualization method for quality control of Ginkgo Leaves Tablets based on spatial distribution uniformity].

Spatial distribution uniformity is the critical quality attribute(CQA) of Ginkgo Leaves Tablets, a variety of big brand traditional Chinese medicine. The evaluation of the spatial distribution uniformity of active pharmaceutical ingredients(APIs) in Ginkgo Leaves Tablets is important in ensuring their stable and controllable quality. In this study, hyperspectral imaging technology was used to construct the spatial distribution map of API concentration based on three prediction models, further to realize the visualization research on the spatial distribution uniformity of Ginkgo Leaves Tablets. The region of interest(ROI) was selected from each Ginkgo Leaves Tablet, with length and width of 50 pixels, and a total of 2 500 pixels. Each pixel had 288 spectral channels, and the number of content prediction data could reach 1×10~5 for a single sample. The results of the three models showed that the Partial Least Squares(PLS) model had the highest prediction accuracy, with calibration set determination coefficient R_(pre)~2 of 0.987, prediction set determination coefficient R_(pre)~2 of 0.942, root mean square error of calibration(RMSEC) of 0.160%, and root mean square error of prediction(RMSEP) of 0.588%. The classical least-squares(CLS) model had a greater prediction error, with the RMSEP of 0.867%. Multivariate Curve Resolution-Alternating Least Square(MCR-ALS) model showed the worst predictive ability among the three models, and it couldn't realize content prediction. Based on the prediction results of PLS and CLS models, the spatial distribution map of APIs concentration was obtained through three-dimensional data reconstruction. Furthermore, histogram method was used to evaluate the spatial distribution uniformity of API. The data showed that the spatial distribution of APIs in Ginkgo Leaves Tablets was relatively uniform. The study explored the feasibility of visualization of spatial distribution of Ginkgo Leaves Tablets based on three models. The results showed that PLS model had the highest prediction accuracy, and MCR-ALS model had the lowest prediction accuracy. The research results could provide a new strategy for the visualization method of quality control of Ginkgo Leaves Tablets.

[Critical quality attribute assessment of big brand traditional Chinese medicine: process quality control method of Suhuang Zhike Capsules intermediate based on physical properties of powder and granules].

The physical properties of powder and granules are the critical quality attributes for the process control of Suhuang Zhike Capsules, a big brand traditional Chinese medicine. This paper took the production of 25 batches of real-world Suhuang Zhike Capsules dry extract powder and granules intermediates as the research object. Firstly, a method for testing the physical properties of Suhuang Zhike Capsules powder and granules with 19 physical indicators was established. The results showed that the granules of dry extract powder after granulation had a smaller particle size, wider particle size distribution range and poor fluidity, which easily caused the problem of over-limit capsule loading. Secondly, correlation analysis, principal component analysis and cluster analysis were used for mathematical statistics. The correlation analysis showed that the density of dry extract powder could affect the chroma and fluidity. At the same time, the particle size in the granules had a stronger effect on the chroma and fluidity than the density. The study also found that the particle size and hygroscopicity of dry extract powder were potentially key physical properties that affected the physical properties of granules. Furthermore, the results of principal component analysis and cluster analysis showed that the consistency of the physical properties between the dry extract powder and intermediate granules was relatively poor. To this end, similarity analysis was carried out, and the quality control method of powder and granules based on physical fingerprint was established. The results showed that the physical fingerprint similarity of 25 batches of dry extract powder was 0.639-0.976, and the physical fingerprint similarity of the gra-nules was 0.716-0.983. With the similarity of 0.85 as the threshold, the batches with abnormal physical properties could be identified. In this study, the process quality control method of Suhuang Zhike Capsules based on the physical properties of powder and granules was established finally, which realized the identification of abnormal batches, and provided a reference for the process quality control of Suhuang Zhike Capsules.