Artificial intelligence for screening and early diagnosis of pancreatic neoplasms in the context of centralization of the laboratory service in the region.

Abstract

Objective. Determination of the optimal machine learning model for the creation of software for screening and early diagnosis of pancreatic neoplasms in the context of centralization of the laboratory service in the region. Material and Methods. The clinical material was based on 1254 patients who were examined in the centralized laboratory of the Volgograd Consultative and Diagnostic Polyclinic No. 2. Of these, 139 were subsequently operated on at the Volgograd Regional Clinical Oncology Dispensary for pancreatic malignancies. In 65 (46.7 %) cases, distal pancreatic resection was performed, and in 74 (53.3 %) cases, pancreaticoduodenectomy was performed. In 28 (20.1 %) cases, at the time of tumor detection, patients did not have clinical symptoms. Statistical processing of the data was carried out using the Python programming language. Five different classifiers were used for machine learning. Results. In the course of factor analysis, 11 parameters were selected from 62 laboratory blood parameters, the dynamics of changes in which should be specifically assessed at the stages of screening and early diagnosis of pancreatic neoplasms. A comparative assessment of machine learning techniques showed that the best option for creating the appropriate software was Hist Gradient Boosting (diagnostic accuracy 0.909, sensitivity 0.642, specificity 0.965, negative predictability 0.928, positive predictability 0.794, F1 0.828, logistic regression loss function 0.352, area under the ROC curve 0.89). Conclusion. The creation of software based on the selected algorithm will make it possible to clarify the real effectiveness of machine learning on a larger population of patients with pancreatic neoplasms.