In-depth annotation for patient level liver cancer staging

Abstract

Cancer stages, which summarizes extent of cancer progression, is an important tool for evidence-based medical research. However, they are not always recorded in the electronic medical record. In this paper, we describe work for annotating a medical text corpus with the goal of predicting patient level liver cancer staging in hepatocellular carcinoma (HCC) patients.Our annotation consisted of identifying 11 parameters, used to calculate liver cancer staging, at the text span level as well as at the patient level. Also at the patient level, we annotated stages for three commonly-used liver cancer staging schemes. Our inter-rater agreement showed text annotation consistency 0.73 F1 for partial text match and 0.91 F1 at the patient level.After annotation, we performed several document classification experiments for the text span annotations using standard machine learning classifiers, including decision trees, maximum entropy, naive Bayes and support vector machines. Thereby, we identified baseline performances for our task at 0.63 F1 as well as strategies for future improvement.

Method for Designing Semantic Annotation of Sepsis Signs in Clinical Text

“…Otherwise, the annotations required to answer a research question might be missing or too general. Thus, many studies opt to develop their own annotated clinical corpus tailored to capture and extract the necessary information for their research (Yim et al, 2015;Rama et al, 2018;South et al, 2009;Oliveira et al, 2022).…”