In the literature, a wide number of annotation systems in the e-health sector have been implemented. These systems are distinguished by a number of aspects. In fact, each of these systems is based on a different paradigm, resulting in a jumbled and confused vision. The purpose of this study is to categorize medical annotation systems in order to provide a standardized overview. To accomplish this, we combed through twenty years’ worth of scientific literature on annotation systems. Then, we utilized five filters to determine which systems would proceed to the classification phase. The following filters have been chosen: accessible, free, web-based or stand-alone, easily installable, functional, availability of documentation. The classification step is performed on systems that evaluate “true” for all of these filters. This classification is based on three modules: the publication module, the general information module and the functional module. This research gave us the chance to draw attention to the issues that healthcare professionals may face when using these systems in their regular work.
1 Introduction
Annotative activity had previously occurred in medieval Latin society. The examination of palimpsests discovered throughout history shows that, at that time, many people annotated the same manuscript, which resulted in the accumulation of several layers of annotations. So, we can say that annotation was a necessary and crucial activity that allowed messages to be passed down to future generations.
Since the invention of printing, each person has had their own annotation support where they can write private notes. In this way, only the owner of the annotated support has been able to read the annotation [1].
Advertisement
Annotative activity is now widely used in almost every aspect of life. In this regard, consider the case of a student who highlights essential passages in a text and makes notes in the margin. Also, we can cite the example of a teacher who deciphers a number next to a word and then consults the bottom of the page to discover the associated note. Annotation types and functions differ widely, and they are classified depending on a lot of factors, such as the annotator’s type, the goal, the spatiotemporal frame, and so on [2].
Traditionally, annotation is done on material supports. The researchers were interested in this approach; therefore, they took the required measures to help it evolve by implementing computer systems to manipulate annotations. These systems offer new functionalities that facilitate the tasks of the annotator. Such as: storing the annotations in files or databases separate from the original document, combining annotated documents, exchanging data, etc. [3].
When it comes to the medical field, annotation is a critical skill. Therefore, healthcare practitioners annotate medical records that are both written on paper and stored electronically. The purpose of this research is to offer some insight into the annotation systems used in the medical field. Therefore, we will try to obtain a standardized and clear overview of the various medical annotation systems that have been developed in the literature. To achieve our goal, we will identify a strategy that brings together the filtration and classification of these systems. In the literature there is little research on the classification of medical annotation systems. However, no work has been done to implement a filtration strategy for these systems. Our method enables health professionals to select the appropriate annotation system for their specialties while also ensuring that the system is operational and available.
This strategy has the following form: To begin, we will filter the annotation systems that were chosen throughout the search phase. This filtering is based on five filters: {F1: accessible, F2: web-based or quick installation, F3: functional, F4: free, F5: availability of documentation}. To be elected for the phase of classification, an annotation system must have the value ‘true’ for all filters. The phase of classification enables the elected systems to be classified according to three classification modules: publication module, general information module and functional module.
Advertisement
The following sections comprise this article:
The second section is labeled “Annotation Systems Filtering”. This section includes a strategy for filtering annotation systems. This part will aid us in weeding out systems that do not meet our needs.
The third section, “Annotation Systems Classification” will classify annotation systems using three classification modules.
In the fourth section, “Observations”, we will discuss our observations regarding the study of these systems.
Finally, we will conclude our paper and give various viewpoints to round out our study.
2 Annotation Systems Filtering
Due to the important number of annotation systems, we discovered, we omitted plugins and standalone software that require the user much effort to install them locally. Indeed, our main attention should be the annotation activity., avoiding all installation and configuration complications.
An annotation system must be accessible, i.e., the scientific publication should contain a functional link that allows access to the tool.
It must also be functional, in the sense that he completes the duties that have been given to him appropriately.
An annotation system must have a documentation in order to study its internal structure.
The following is a list of the election filters that we have fixed:
F1: accessible
F2: free of charge
F3: web based or standalone easily installable
F4: functional
F5: documentation availability
A system must have the value’ true’ for all filters in order to be elected. Elected systems will be thoroughly investigated in the classification stage.
The following figure (Fig. 1) shows the process of filtering annotation systems.
Fig. 1.
Filtering process
×
3 Annotation Systems Classification
3.1 Publication Module
We cannot examine an annotation system in isolation from the facts surrounding its publishing. This module describes elements of both the tools and its scientific publication. These are crucial aspects to evaluate the tool’s originality. The following are the publication criteria that we have selected [4, 5].
Paper title
Publication year
Type of the paper
Publication medium
The following table (Table 1) summarizes the publication criteria for each paper.
Relationship-Based Access Control for an Open- Source Medical Records System
2015
Conference paper
Proceedings of the 20th ACM symposium on Access control Models and technologies
3.2 General Information Module
[3, 27] The annotation activity begins by selecting the anchor and the shape of the annotation from the software toolbar. Then, the annotation must be attached to a well- defined target in order to satisfy all of the annotation’s requirements. This annotation activity can be classified into three broad types.
Manual format: this format gives complete responsibility to the user for the annotating process. He begins by selecting the annotation’s shape, followed by the anchor and lastly the annotation itself. This is comparable to how annotating on paper is handled.
Automatic format: the machine is programmed to carry out the entire annotation process without human intervention.
Semi-automatic format: in this situation, the user initiates the process. The algorithm eventually learns and understands how the user annotates. It then suggests automated annotations based on an annotation model developed with rules in development. When no adjustments are made and the suggested rules are fully accepted, human intervention is cancelled and the process becomes fully automated.
Annotation can be classified into two types.
Cognitive annotation: this type of annotation has a visible form on the document. Because it is employed by human agents, comprehending it requires cognitive and mental effort.
Computational annotation: sometimes referred to as ‘meta-data’. The annotation is treated and manipulated by software agents.
The annotation has two types of structures:
Unstructured annotation: in this situation, each annotator annotates in accordance with his requirements.
Structured annotation: the annotation can be based on well-defined models and forms; in most cases, this type of annotation is carried out as a result of agreements reached amongst a group of people working together.
The information in the table below (Table 2) highlights a classification of annotation systems based on the following characteristics:
Link allowing access to the tool
Concerned medical field: {biology, radiology, doctor, biochemistry, all healthcare professions}
Each annotation system has a particular variety of features [3, 28].
Sharing Features:
Annotation export: the annotator wishes to send all or a portion of the annotations that have been written on a document.
Annotation import: the user can receive annotations. This feature enables him to add new annotations to a document as if it had been annotated by two different annotators.
Sending a message: A healthcare professional sends a message with an annotated document or record. So that healthcare professionals can converse asynchronously.
Memorization Features:
Annotation creation: there are two methods for creating annotations:
Annotation modification: the annotator has the ability to change all of the annotation’s parameters (shape, color, content etc.).
Delete of annotation: the annotation can be removed without being archived.
Annotation saving: an annotation can be saved in a variety of formats (text, XML, etc.)
Reading and browsing the document: access to the document should be granted to the user. If that’s the case, the reader opens the annotation system and chooses an existing document. He can use the mouse, keyboard arrows, and the elevator to navigate to the next and previous pages, as well as the beginning on finish of each page.
Visualization of the annotation in the document: the annotations are scattered throughout the main document.
Reuse Features:
Filtering: the reader is looking for one or more annotations that meet certain requirements.
Manual: Depending on the user’s preferences, the health care provider can choose to see only a subset of annotations.
Automatic: Only annotations that have been granted permission to be seen by the healthcare professional are visible to him.
Visualization of the annotation outside the document: annotations are displayed in a different location than the primary document.
Segmentation: image segmentation is a type of image processing that seeks to group pixels together based on established criteria.
Sorting: the list of displayed annotations is organized by sorting annotations based on their attributes.
Merging of annotated documents: this feature allows the user to create a report that includes annotated documents. Based on the annotation, the merging produces a summary of the patient’s condition. This process enables experts to share documents.
Comparison of annotations: this comparison seeks to determine whether or not two given annotations have the same meaning.
Redefinition of an annotation: the practitioner manually traces any annotation, and then the machine automatically intervenes to retrace it.
Recommendation: this feature allows the user to provide suggestions for possible annotations.
Localization of the annotation and calculation of the area of the annotated zone: this functionality allows the user to specify the coordinates of the anomalous component (sick) and determine its interface by locating the annotation and calculating the area of the annotated zone.
Annotation search: looking for an annotation based on a number of parameters.
Standardize annotations: transform annotations into a standard format.
The following table (Table 3) includes a classification of annotation systems according to functionalities.
Table 3.
Functional module
4 Observations
This survey allowed us to address the research question posed in the introduction of the article, which serves to obtain a uniform and clear overview of the different exciting annotation systems in the literature.
By finding the answer to the research question, we now have a better understanding of the issues that the healthcare providers may run into when utilizing these tools.
Interoperability Problem:
each of the systems examined above is based on a set of standards and formats unique to that system. This results in an issue with the integration of heterogeneous programs, and as a result, there is a communication blockage. there is no longer any exchange of data between the apps. A health professional cannot send or receive data from his colleagues. This creates a problem for both patients and health professionals because it restricts their mobility. Additionally, the patient is unable to communicate his personal data to his doctor, resulting in data loss. To circumvent this issue, harmonizing annotation systems’ models and standards is required.
Problem of Patient Integration:
because the patient is unable to access the content of the annotation systems, he can no longer communicate his ideas in a meaningful way. In addition, he finds himself in a state of uncertainty as to his understanding of the notes that have been placed in his medical file. Indeed, he does not master the scientific language and medical terminology provided by his doctor, which leads him to ignore his current state of health, his medications, and his entire treatment protocol, which can sometimes make the recovery more difficult. In this way, the annotation is unable to promote collaboration between different stakeholders. But, on the contrary, it leads to a breakdown in communication between health professionals and patients.
No Development of a Partnership Cycle:
with the integration of this cycle, the annotation will ensure sharing and communication between all stakeholders. This must be done to reach a consensus on a decision.
Problem of Deciphering the Structure of Annotation Systems:
several of the systems reviewed are open sources, which allows for the examination of their documentation and source code in order to gain a better understanding of their structure. However, decoding the structures of other systems is difficult, if not impossible, because we no longer have access to their source codes.
Hardware restrictions:
the only data entering materials are a keyboard and a mouse. Improved data entry assistance devices, such as the stylus, are required. The stylus is a tool that can make healthcare professionals’ annotation activities easier and more versatile.
5 Conclusion
Towards the end of this article, we will briefly say that we have proposed a strategy for the filtering and classification of annotation systems in the medical profession. This has allowed us to draw attention to the problems healthcare professionals may encounter when using these systems in their daily activities.
As part of our future study, we want to focus on establishing an annotation modeling standard that allows both healthcare professionals and patients to annotate electronic medical records.
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
