Article Preview
Top1. Introduction
The paper annotation practice is very common. Indeed, during our reading, we are all accustomed to writing our comments in the margin of the document, highlighting or circling part of the text to enrich and add value to information (Khalil Chehab, Kalboussi, & Kacem, 2019; Anis Kalboussi, Mazhoud, Omheni, & Kacem, 2014; Anis Kalboussi, Omheni, Mazhoud, & Kacem, 2015a). Annotation is a central practice in many professions: teachers annotate copies of students; professors’ exchange annotated documents during their work; engineer co-builds engines by annotating sketches of plans to make them evolve, doctors’ comment on the patient records...etc. (K. Chehab, Kalboussi, & Kacem, 2018; A. Kalboussi, Mazhoud, Hadj Kacem, & Omheni, 2013; Anis Kalboussi, Mazhoud, & Kacem, 2016b). The practice of pencil-and-paper annotation, among healthcare professionals (PHC) in the patient record is common and contributes to the enrichment of knowledge and skills of health professionals (PHC). With the emergence of new information and communication technologies, the field of digital health (Dingli & Seychell, 2014; Yu & Yilayavilli, 2010), also called e-health, has undergone a significant and promising technical revolution over the last decade (Charlet et al., 1998). This revolution allowed health professionals to take full advantage of the computerized medical services by sharing the important data, the necessary knowledge and the key skills in a digital world (Anis Kalboussi, Mazhoud, & Kacem, 2013). Among the applications that are covered by this digital revolution, there are the annotation systems (Dutta, Mondal, & Paul, 2020; Kraljevic et al., 2019; Ma & Meng, 2018; Philbrick et al., 2019; Segura et al., 2017) dedicated to healthcare professionals (local application/web application/plug-in) that have been developed to manage digitally the annotations of these latter. Here, annotations can cover different domains of healthcare and can have different types. Moreover, they can be private, public, or shared, according to the annotated content (Bringay, Barry, & Charlet, 2004). As a result, these systems are becoming increasingly claimed and felt by the different medical actors, hence, they offer the necessary means to explain and enrich the information with personal observations and permit ideas sharing which in turn improve collaborative working practices.
In this work, we started with an exhaustive reading for the available papers on annotation systems in general and medical annotation systems in particular. Although the medical annotation systems have already been studied in a variety of contexts (doctor, nurse, biologist, radiologist), yet when it comes to the PHC to choose which system to use based on the functionalities offered by these latter is difficult. Also it is not a trivial task for a researcher he wants to identify future research areas based on existing annotation systems. This is because the annotation systems are so common and many of them share similar objectives which can either be to create annotations or to manipulate them with fairly classic functionalities. Moreover, there are no formal criteria to facilitate the comparison between those systems and to guide PHC choice or a researcher. As a result, there is a fragmented picture of these annotation tools. As far as we know, this is the first work to consider the classification of medical annotation system. The purpose of this paper is to provide a unified idea about the annotation systems used by healthcare professionals. This panoramic view is based on a classification of fifty different annotation systems developed in literature over the past two decades by industry and researchers. The concentration of the difference permits to conclude the classifications criteria and to highlight the challenges in this research field. In this paper, first, the organization of annotation systems is built on the basis of five generic criteria (Azouaou, 2006; Anis Kalboussi, Omheni, Mazhoud, & Kacem, 2015b): standard annotation (computational / cognitive); category of the annotation system (application / plug-in / website); type of annotative activity (manual / semi-automatic / automatic); annotated resource type (text / video / image / doc / HTML / pdf/ etc.) and practitioner that is a PHC. A second comparison is made based on the functionalities offered by the medical annotation systems. Moreover, based on the extensive review of the existing annotation systems we identify the limitation according to the defined criteria.