Construction and evaluation of a liver cancer risk prediction model based on machine learning

BACKGROUND Liver cancer is one of the most prevalent malignant tumors worldwide,and its early detection and treatment are crucial for enhancing patient survival rates and quality of life.However,the early symptoms of liver cancer are often not obvious,resulting in a late-stage diagnosis in many patients,which significantly reduces the effectiveness of treatment.Developing a highly targeted,widely applicable,and practical risk prediction model for liver cancer is crucial for enhancing the early diagnosis and long-term survival rates among affected individuals.AIM To develop a liver cancer risk prediction model by employing machine learning techniques,and subsequently assess its performance.METHODS In this study,a total of 550 patients were enrolled,with 190 hepatocellular carcinoma(HCC)and 195 cirrhosis patients serving as the training cohort,and 83 HCC and 82 cirrhosis patients forming the validation cohort.Logistic regression(LR),support vector machine(SVM),random forest(RF),and least absolute shrinkage and selection operator(LASSO)regression models were developed in the training cohort.Model performance was assessed in the validation cohort.Additionally,this study conducted a comparative evaluation of the diagnostic efficacy between the ASAP model and the model developed in this study using receiver operating characteristic curve,calibration curve,and decision curve analysis(DCA)to determine the optimal predictive model for assessing liver cancer risk.RESULTS Six variables including age,white blood cell,red blood cell,platelet counts,alpha-fetoprotein and protein induced by vitamin K absence or antagonist II levels were used to develop LR,SVM,RF,and LASSO regression models.The RF model exhibited superior discrimination,and the area under curve of the training and validation sets was 0.969 and 0.858,respectively.These values significantly surpassed those of the LR(0.850 and 0.827),SVM(0.860 and 0.803),LASSO regression(0.845 and 0.831),and ASAP(0.866 and 0.813)models.Furthermore,calibration and DCA indicated that the RF model exhibited robust calibration and clinical validity.CONCLUSION The RF model demonstrated excellent prediction capabilities for HCC and can facilitate early diagnosis of HCC in clinical practice.

Short text classification based on strong feature thesaurus

Data sparseness, the evident characteristic of short text, has always been regarded as the main cause of the low ac- curacy in the classification of short texts using statistical methods. Intensive research has been conducted in this area during the past decade. However, most researchers failed to notice that ignoring the semantic importance of certain feature terms might also contribute to low classification accuracy. In this paper we present a new method to tackle the problem by building a strong feature thesaurus （SFT） based on latent Dirichlet allocation （LDA） and information gain （IG） models. By giving larger weights to feature terms in SFT, the classification accuracy can be improved. Specifically, our method appeared to be more effective with more detailed classification. Experiments in two short text datasets demonstrate that our approach achieved improvement compared with the state-of-the-art methods including support vector machine （SVM） and Naive Bayes Multinomial.

Numerical simulation of the 3D flow field in a ring die pellet mill considering viscous heating

Viscous heating has a substantial influence on the extrusion forming process and product quality of powder materials.This study selected the MUZL420 ring die pellet mill as the research object,from which a 3D flow physical model was established.The numerical simulation of 3D nonisothermal flow in the extrusion pelletizing process of granulated alfalfa was performed with POLYFLOW.The distribution laws of pressure,velocity,shear rate,viscosity,viscous heating and temperature in the flow field were revealed to thoroughly investigate the pelletizing process and provide a reference for structural optimization and process control.The results showed that two extrusion zones in the pelleting chamber were symmetrical with respect to the center,and the significant pressure gradient along the rotating direction of the ring die and the roller caused the material to flow back in the opposite direction.There were larger velocity gradients,shear rates and viscous heating levels in the deformation and compaction zone,the negative pressure zone behind the extrusion zone and the die holes.The distribution of viscosity was opposite to that of the shear rate.The temperature increase area caused by viscous heating gradually expanded from the material inlet to the bottom of the extrusion chamber along the Z-axis direction,and the temperature increased accordingly.The extrusion force and the forming temperature in the extrusion forming zone were captured in the numerical simulation.The extrusion forming density was calculated with the regression prediction model established through the simulation experiment of pelletizing with a ring die.Through a comparison with the results of mean alfalfa pellet density from the ring die pellet mill experiment,the relative error was less than 5%,which indicated that the numerical simulation method was reliable.