Systematic mapping in improving the extraction of Cancer Pathology information using RPA orchestration

Abstract

Integrating  medical data manipulation and maintenance of cancer has a significant impact  in combining the  cancer data registry with electronic health records. Patients with cancer, can map their various treatment routes , which can now be implemented as an electronic bot health record (EBHR) , resulting in new data for visualization and analysis. An accurate intraoperative diagnosis for cancer patients is highly required for personalized treatment. The medical data needs an efficient method to provide higher accuracy in maintaining the data.  An efficient methodology is introduced for to extract quantitative information from the unstructured cancer data.  Integrating computational intelligence in Robotic Process Automation can be done to process this data and automate repetitive activities for evaluating patients clinical pathology report. The observational study was undertaken to examine factors influencing the survival rate in order to improve treatment management. The data has various stages of information like patient information, Grade of cancer, medical history and treatment undergone. Consideration was given to automate programming employing 24 features from 767 individuals. The pathologist considers particular terms for data pieces to specify the NLP's semantic rules. On the chosen specimens with 24 data items, the suggested RPA NLP technique obtained accuracy scores of 98.67%, recall as 98.55% and F-measure scores of 98.45%. The feasibility and precision of autonomously extracting pre-defined data from clinical narratives for cancer research has been established in this work. Thus, Enhanced RPA implemented automates repetitive tasks by analyzing daily interactions for cancer patients who receive personalized care and an accurate intraoperative diagnosis.

URN:NBN:sciencein.jist.2023.v11.561