The paper quantizes symptom data through binary coding,divides 8 syndromes summed up by experts into excess and de-ficiency syndromes,values and quantizes them,and establishes the model for classification of excess and deficiency syndromes of colorec-tal cancer based on BP neural network and decision tree.The result shows that BP neural network classification model is more applicablefor the handling of the nonlinear mapping relation compared with decision tree classification model.

ObjectiveTo compare and analyze conventional plan and inverse optimized plan in dosemetric of cervical cancer. MethodTwenty cases of cervical cancer treated with combination radical radiotherapy of EBT were selected,every case had two plans: one was conventional plan based A point prescription dose, the other was inverse optimized plan (IPSA, inverse planning with simulated annealing)based volume object dose.ResultsIPSA plans provided better values compared with the conventional plans in 90％ prescription dose volume V90[ (94 ± 15 )％ vs. (60 ± 17 )％], 100％ prescription dose volume V100[(90 ± 18)％ vs. (56 ± 14)％]and 100％ treatment volume dose D100[(54 ± 10)％ vs. (29 ±9)％](P ＜0.05),respectively. Meanwhile the organ at risk received lower dose volume. ConclusionsPlans generated using IPSA provide higher dose to the target volume but with lower dose to normal structure and less time. This study can help to guide the clinical application.

Objective:To predict the dose of lumbosacral spine (LS) and pelvic bone marrow (PBM) based on kernel density estimation (KDE) in patients with gynecological tumors.Methods:Fifteen patients with gynecological tumors receiving radiotherapy plans with dose limitation for LS and PBM in our hospital were selected as training data for machine learning. Another 10 cases were selected as the data for model validation. The minimum directional distance between the dose point in the organs and the edge of the planned target volume for the LS and PBM was calculated. Model training was performed by KDE. The accuracy of the model prediction was evaluated by the root mean square error. The model was utilized to predict the actual planned doses of the LS and PBM, and a linear fitting was performed on the predicted dose volume histogram (DVH) and actual results. The prediction effect was assessed by the goodness of fit R 2. Results:In terms of the DVH parameters required by the planner, the prediction doses from the model were similar to those of the verification plans: the difference of PBM V 40Gy was 2.0%, the difference of the mean dose was 1.6 Gy, and the difference of LS V 10Gy was -0.4%. In the unrequired DVH parameters, except for the PBM V 10Gy, the predicted values of the model were significantly high. The difference between the DVH predicted by the model and the actual plan was small, and the R 2 of the LS and PBM were 0.988 and 0.995, respectively. Conclusions:The model based on KDE method can accurately predict the doses of the LS and PBM. This model can also be used as a method to ensure the quality of the plan, and improve the consistency and quality of the plan.

Objective:To evaluate the new model of group screening combined with opportunistic screening for the diagnosis and treatment of gastric cancer.Methods:Group screening combined with opportunistic screening was used for gastric cancer screening. (1) Group screening. Cluster sampling was used to screen gastric cancer by endoscopy in high-risk population (aged 40-<70 years) of rural residents in Weihai from July 2017 to December 2020, and biopsy was obtained for histopathology if necessary. Main collection parameters included the detection rate of advanced gastric cancer, early gastric cancer and high-grade intraepithelial neoplasia (HGIN). (2) Opportunistic screening. The changes of the detection rates of early gastric cancer in opportunistic screening in 2 hospitals in Weihai area were observed during the same period of time.Results:(1) In group screening, from July 2017 to December 2020, the first batch of 8 000 cases of gastric cancer screening were completed. The cases of advanced gastric cancer, early gastric cancer and HGIN were 36, 28, and 62, respectively. The detection rates of gastric cancer and early gastric cancer were 0.80% (64/8 000) and 43.75% (28/64), respectively. The proportion of early gastric cancer+HGIN who received endoscopic submucosal dissection (ESD) was 77.78% (70/90), and the rate of curative resection was 100.00%(70/70). (2) Opportunistic screening: from July 2017 to December 2020, the annual early gastric cancer detection rates in opportunistic screening in Wendeng District Traditional Chinese and Western Medicine Hospital were 16.67% (1/6), 20.00% (3/15), 23.53% (4/17), and 33.33% (6/18) in the consecutive 4 years, respectively. The annual detection rates of early gastric cancer in opportunistic screening in Ru Shan Peoples Hospital were 14.74% (14/95), 23.80% (60/252), 25.49% (65/255), and 24.04% (50/208), respectively. The detection rates of opportunistic screening for early gastric cancer in hospitals in Weihai city increased year by year.Conclusion:In areas with high incidence of gastric cancer, a certain scale of group screening can lead to a wider range of opportunistic screening, resulting in the increase of the detection rate of early gastric cancer. The new model of diagnosis and treatment of gastric cancer is worth recommendation.