RESUMO
Objective:To compare the prediction efficiency of traditional linear regression model and four machine learning models on the learning behavior of clinical medical postgraduates, and to explore the pros and cons and applicability of different prediction models.Methods:A total of 6,922 clinical medical postgraduates were surveyed, their comprehensive learning behavior scores were obtained through the learning behavior scale. In the training set, Lasso linear regression and artificial neural network, decision tree, Bootstrap random forest, and lifting tree were used to build prediction models respectively. The above models were used to predict the validation set data and compare the prediction efficiency.Results:The comprehensive learning behavior score of clinical medical postgraduates was (3.31±0.54) points, and the overall compliance rate was 74.02%. In the linear regression model, the influence of age, school level, degree type, learning interest, pressure and satisfaction on learning behavior were statistically significant. In the prediction of validation set, the sensitivity, specificity, and accuracy of the linear regression model were 0.484, 0.914, and 0.801, respectively. The indexes of the four machine learning models were higher than those of the traditional linear regression model, and the Bootstrap random forest had the highest elevation.Conclusion:The linear regression model has a good prediction effect on learning behavior, and machine learning is superior to linear regression model in terms of accuracy of prediction. However, traditional linear regression models are superior to machine learning models in computational efficiency and interpretability.
RESUMO
With the development of minimally invasive surgery, many open surgery has been replaced by intracavity surgery. In laparoscopic surgery, an electric fibroid morcellator must be used to remove large tissue specimens from a small abdominal incision. Of course, there are some complications in the use, in order to follow the principle of no tumor, the doctor used the laparoscopic pouch in clinical operation to reduce the risk of spreading potential tumor tissue. There are various kinds of pouches, which are classified according to their existing state before use, it can be classified into two categories:overlapping and non-overlapping. The advantages and disadvantages of different bags and pockets are also analyzed. It provides a theoretical basis for technological innovation and equipment improvement.
Assuntos
Laparoscopia , Procedimentos Cirúrgicos Minimamente InvasivosRESUMO
Objective To calibrate contact parameters of liver tissue discrete element model. Methods Based on MATLAB image processing technology, the accumulation angle of liver tissues was measured. The ‘Hertz-Mindlin with JKR’ contact model was used to simulate the accumulation angle of liver tissues. The orthogonal experiment was designed with the coefficient of rolling friction and the energy of JKR surface as factors. The parameters of the contact model were calibrated by batch processing, and the optimal parameter combination was verified by secondary simulation calibration. Results The accumulation angle obtained by the physical test was 11.2°±0.86°. In the orthogonal experiment, the accumulation angle of the 6th set of parameter combinations was 11.8°, and the relative error was 5.1%. The simulation test and the physical test had a high similarity in accumulation angle and shape. The sequence of factors affecting the accumulation angle was the JKR surface energy between the tissue particles and the stainless steel plate > the rolling friction coefficient between the tissue particles and the stainless steel plate > the JKR surface energy between the tissue particles and the tissue particles=the rolling friction coefficient between the tissue particles and the tissue particles. Conclusions The optimization parameter could be used to further conduct the discrete element simulation between the tissue particles and the pulverizer, so as to reveal the accumulation and flow state of the tissue particles under the action of myoma pulverizer.
RESUMO
Objective To calibrate contact parameters of liver tissue discrete element model. Methods Based on MATLAB image processing technology, the accumulation angle of liver tissues was measured. The ‘Hertz-Mindlin with JKR’ contact model was used to simulate the accumulation angle of liver tissues. The orthogonal experiment was designed with the coefficient of rolling friction and the energy of JKR surface as factors. The parameters of the contact model were calibrated by batch processing, and the optimal parameter combination was verified by secondary simulation calibration. Results The accumulation angle obtained by the physical test was 11.2°±0.86°. In the orthogonal experiment, the accumulation angle of the 6th set of parameter combinations was 11.8°, and the relative error was 5.1%. The simulation test and the physical test had a high similarity in accumulation angle and shape. The sequence of factors affecting the accumulation angle was the JKR surface energy between the tissue particles and the stainless steel plate > the rolling friction coefficient between the tissue particles and the stainless steel plate > the JKR surface energy between the tissue particles and the tissue particles=the rolling friction coefficient between the tissue particles and the tissue particles. Conclusions The optimization parameter could be used to further conduct the discrete element simulation between the tissue particles and the pulverizer, so as to reveal the accumulation and flow state of the tissue particles under the action of myoma pulverizer.