TABLE 2.
Application of AI in TCM data mining.
| Aim of study | AI methods | Results | REF |
|---|---|---|---|
| Propose a multi-graph convolution network (MGCN) prescription recommendation model | Multi-graph convolutional network | MGCN significantly improved the accuracy of TCM herbal prescription recommendations | Zhao et al. (2022) |
| Propose a TCM prescription recommendation model (TCMPR) | Deep learning | TCMPR has high performance on TCM prescription recommendation | Dong et al. (2022) |
| Generate TCM prescriptions from a few medical records and TCM documentary resources | a two-stage transfer learning model, TCMBERT model | TCMBERT model outperforms the state-of-the-art methods in all comparison baselines on the TCM prescription generation task | Liu et al. (2022b) |
| Examine and propagate the medication experience and group formula of TCM Master XIONG Jibo in diagnosing and treating arthralgia syndrome (AS) | Frequency analysis, association rule analysis, cluster analysis, and visual analysis | Customized NLP model could improve the efficiency of data mining in TCM | Wenxiang et al. (2022) |
| Propose an intelligent formula recommendation system (FordNet) | Deep learning, convolution neural network | FordNet can learn from the effective experience of TCM masters and get excellent recommendation results | Zhou et al. (2021) |
| Propose mechanism about a TCM prescription | PageRank algorithm, network pharmacology | Provided a new unsupervised learning strategy for polypharmacology research about TCM | Xiong et al. (2022) |
| Explore the mechanism of eight classic TCM formulae in the treatment of different types of coronary heart disease | Screening, network clustering, hierarchical clustering, network topology | Showed that each formula’s targets were significantly correlated with CHD associated genes and overlapped with the targets of 9 classes of drugs for cardio vascular diseases (CVD) to some degree | Yang et al. (2020) |
| Explore the effects and mechanisms of Ge-Gen-Qin-Lian decoction treatment in acute lung injury | Network pharmacology | Suggested that GQD did have a better therapeutic effect on acute lung injury | Ding et al. (2020) |
| Quantify the interactions in herb pairs | Network-based modeling | Provided a network pharmacology framework to quantify the degree of herb interactions | Wang et al. (2021b) |
| Explore the patterns of TCM use and its efficacy in children with cancer | Association rule mining | ARM showed that Radix Astragali, the most commonly used medicinal herb (58.0%), was associated with treating myelosuppression, gastrointestinal complications, and infection | Lam et al. (2022b) |
| Explore the potential therapeutic effect of TCM on coronavirus disease 2019 (COVID-19) | Data mining, frequency and association analysis, network pharmacology analysis, bioinformatics analysis | Collected a total of 173 prescriptions which were involved in the anti-inflammatory, anti-viral, and neuroprotective effects | Sun et al. (2020b) |
| Investigate the potential mechanism of Biyuan Tongqiao granule (BYTQ) against allergic rhinitis (AR) | Network pharmacology | Found the potential protein targets and mechanism for BYTQ to treat AR | Wang et al. (2024) |