Design and application of tumor prediction model based on statistical method

Recent Applications of Artificial Intelligence in Early Cancer Detection

Cancer is a deadly disease often caused by the accumulation of various genetic mutations and pathological alterations. The death rate can only be reduced when it is detected in the early stages because treatment of cancer when the tumor has not metastasized in many regions of the body is more effective. However, early cancer detection is fraught with difficulties. Advances in artificial intelligence (AI) have developed a new scope for efficient and early detection of such a fatal disease. AI algorithms have a remarkable ability to perform well on a variety of tasks that are presented or fed to the system. Numerous studies have produced machine learning and deep learning-assisted cancer prediction models to detect cancer from previously accessible data with better accuracy, sensitivity, and specificity. It has been observed that the accuracy of prediction models in classifying fed data as benign, malignant, or normal is improved by implementing efficient image processing techniques and data segmentation augmentation methodologies, along with advanced algorithms. In this review, recent AI-based models for the diagnosis of the most prevalent cancers in the breast, lung, brain, and skin have been analysed. Available AI techniques, data preparation, modeling processes, and performance assessments have been included in the review.

Prediction of 3-month treatment outcome of IgG4-DS based on BP artificial neural network

OBJECTIVE

The study aimed to establish an effective back-Propagation artificial neural network (BP-ANN) model for automatic prediction of 3-month treatment outcome of IgG4-DS.

METHODS

A total of 26 IgG4-DS patients at Shanghai Ninth People's Hospital from January 2018 to December 2019 were involved in the study. They were all followed for >3 months. The primary outcome was reduction of serum IgG4 (sIgG4) after 3-month treatment. The association between risk factors and reduction of sIgG4 was analyzed by Spearman's rank correlation test. According to the R values, we built a BP-ANN model by MATLAB R2019b.

RESULTS

The average reduction of sIgG4 was 5.55 ± 5.03. After Spearman's rank correlation test, ESR, sIgG4, and sIgG were independently associated with reduction of sIgG4 (p < .05) and were selected as input variables. Take into account these parameters, BP-ANN model was developed and the coefficient of determination (R² ) model was 0.95512.

CONCLUSION

The BP-ANN model based on ESR, sIgG4, and sIgG could predict the 3-month reduction of sIgG4 for IgG4-DS patients. It showed potential clinical application value.