ABSTRACT
BACKGROUND: The misestimation of surgical risk is a serious threat to the lives of patients when implementing surgical risk calculator. Improving the accuracy of postoperative risk prediction has received much attention and many methods have been proposed to cope with this problem in the past decades. However, those linear approaches are inable to capture the non-linear interactions between risk factors, which have been proved to play an important role in the complex physiology of the human body, and thus may attenuate the performance of surgical risk calculators. METHODS: In this paper, we presented a new surgical risk calculator based on a non-linear ensemble algorithm named Gradient Boosting Decision Tree (GBDT) model, and explored the corresponding pipeline to support it. In order to improve the practicability of our approach, we designed three different modes to deal with different data situations. Meanwhile, considering that one of the obstacles to clinical acceptance of surgical risk calculators was that the model was too complex to be used in practice, we reduced the number of input risk factors according to the importance of them in GBDT. In addition, we also built some baseline models and similar models to compare with our approach. RESULTS: The data we used was three-year clinical data from Surgical Outcome Monitoring and Improvement Program (SOMIP) launched by the Hospital Authority of Hong Kong. In all experiments our approach shows excellent performance, among which the best result of area under curve (AUC), Hosmer-Lemeshow test ([Formula: see text]) and brier score (BS) can reach 0.902, 7.398 and 0.047 respectively. After feature reduction, the best result of AUC, [Formula: see text] and BS of our approach can still be maintained at 0.894, 7.638 and 0.060, respectively. In addition, we also performed multiple groups of comparative experiments. The results show that our approach has a stable advantage in each evaluation indicator. CONCLUSIONS: The experimental results demonstrate that NL-SRC can not only improve the accuracy of predicting the surgical risk of patients, but also effectively capture important risk factors and their interactions. Meanwhile, it also has excellent performance on the mixed data from multiple surgical fields.
Subject(s)
Algorithms , Area Under Curve , Hong Kong , Humans , Risk Assessment , Risk FactorsABSTRACT
AIM: To study the effect of MHC class II transactivator(CIITA ) on the expression of MHC class I/II molecules, CD80 and CD86 molecules on dendritic cells(DCs), and explor the use of DCs modified by CIITA gene in the biotherapy of tumors. METHODS: We transfected the mouse CIITA gene by lipofectamine into DCs drived from mouse bone marrow. The expression of MHC class I/II, CD80, and CD86 molecules was detected by flow cytometry. 40 mice bearing hepatcellular carcinoma were divided into 4 groups: group 1 were treated with a para-tumor injection of PBS, group 2 DCs, group 3 modified DCs, and group 4 modified DCs pulsed with H22 tumor antigen. Then the anti-tumor effect of DCs modified by mCIITA was evaluated by measuring the tumor size. RESULTS: After transfection of mCIITA, the expression rate of MHC class I/II molecules of DCs increased from 74.2%/66.7% to 93.6%/91.4%, and that of CD80/CD86 increased from 52.3%/60.5% to 89.7%/91.5%. After immunization, the growth of H22 tumors in group 4 mice was significantly inhibited compared with that in other three groups (P<0.05 at 3, 4, 5, 6, and 7 weeks versus groups 1, 2; P<0.05 at 5, 6, 7 weeks versus group 3). CONCLUSION: The expression of MHC I/II, CD80 and CD86 on DCs was regulated markedly by transfection of mCIITA. mCIITA transfection also enhanced the anti-tumor effect of DCs. Our results provided a new method for biotherapy of tumors with DCs.
