ABSTRACT
ObjectiveTo achieve high-dimensional prediction of class imbalanced of adverse drug reaction（ADR） of traditional Chinese medicine（TCM） and to classify and identify risk factors affecting the occurrence of ADR based on the post-marketing safety data of TCM monitored centrally in real world hospitals. MethodThe ensemble clustering resampling combined with regularized Group Lasso regression was used to perform high-dimensional balancing of ADR class-imbalanced data， and then to integrate the balanced datasets to achieve ADR prediction and the risk factor identification by category. ResultA practical example study of the proposed method on a monitoring data of TCM injection performed that the accuracy of the ADR prediction， the prediction sensitivity， the prediction specificity and the area under receiver operating characteristic curve（AUC） were all above 0.8 on the test set. Meanwhile， 40 risk factors affecting the occurrence of ADR were screened out from total 600 high-dimensional variables. And the effect of risk factors on the occurrence of ADR was identified by classification weighting. The important risk factors were classified as follows：past history， medication information， name of combined drugs， disease status， number of combined drugs and personal data. ConclusionIn the real world data of rare ADR with a large amount of clinical variables， this paper realized accurate ADR prediction on high-dimensional and class imbalanced condition， and classified and identified the key risk factors and their clinical significance of categories， so as to provide risk early warning for clinical rational drug use and combined drug use， as well as scientific basis for reevaluation of safety of post-marketing TCM.
ABSTRACT
Docetaxel is the widely-used first-line therapy to treat lung cancer around the world. However, tumor progression and severe side effect occurred in some patients with docetaxel treatment. Most of the side effects were caused by immunocompromise, which limits the long-term use of docetaxel. Shenqi Fuzheng (SQFZ) injection has been used as adjuvant therapy to treat lung cancer which may enhance immunity as well. Owing to the complexity of drug combination, the mechanism of SQFZ injection in combination with docetaxel on lung cancer remains unclear. Therefore, a network pharmacology-based strategy was proposed in this study to help solve this problem. Network pharmacology approach comprising multiple components, candidate targets of component and therapeutic targets, has been used in this study. Also, in vivo and in vitro experiment was applied to verify the predicted targets from network pharmacology We established mouse lung cancer model and inject with docetaxel and SQFZ injection. Tumour weight, spleen index, thymus index, immunohistochemical staining and ELISA were conducted to evaluate the effect and underlying mechanisms of docetaxel and SQFZ injection. Besides A549 cells were also administrated by docetaxel and SQFZ.The indexes BCL2, CASP3 and CASP9 were determined after administration. The results indicated that combination of SQFZ and docetaxel could reduce tumour weight, enhance the spleen index, thymus index. Meanwhile, it could improve the activity of caspase-3 and IL-2 in mice and caspase-3, caspase-9 in A549 cell and inhibit the activity of BCL-2 in A549 cell, which verified the potential protective targets predicted by network pharmacology. In conclusion, combination of SQFZ and docetaxel could increase the curative effect by inducing tumour to apoptosis and play a key role on immunoprotection to reduce side effects.