Detecting situations of importance with Stream Reasoning on live health IoT data

Tracking #: 2914-4128

Mathieu Bourgais
Franco Giustozzi
Laurent Vercouter

Responsible editor: 
Armin Haller

Submission type: 
Full Paper
he development of Internet of Things (IoT) creates large amount of data which may be used by decision making systems in a variety of domains. In particular, in the field of health monitoring, it enables to follow the medical state of a patient hospitalized at home in real-time. An important challenge is to represent and interpret these data with a high-level model in order to have a better understanding of the overall medical state of a patient, taking into account the context of these data. This article overcomes this challenge by using Stream Reasoning techniques associated to an ontological representation of the medical context of a patient to understand her situation. This permits to combine in real time static knowledge stored in an ontology and dynamic information provided by smart sensors. To facilitate this process, constraints and situations concepts are introduced to ease the translation of expert knowledge into logical queries. The paper concludes with a discussion on the coverage of the proposed ontology and an experimental analysis of real body temperature data to illustrate how situations may be detected.
Full PDF Version: 

Major Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Zhangcheng Qiang submitted on 12/Oct/2021
Minor Revision
Review Comment:

While deep learning technologies have been used in many out-of-hospital health monitoring scenarios, they are suffering from the pain of lack of training data. Collecting data from patients is time and resource consuming, and it may also have some ethical issues. This paper provides a novel stream reasoning based approach to overcome the lack of training data, and it is really appreciated that the authors are taking an empirical approach to the problem.
The paper is well-motivated, well written and well designed. Firstly, the paper clearly identifies the current research gaps on live health IoT data: lack of data interoperability, context consideration and training data. Then, this work proposes an ontology to represent the patient's medical information, activities, events and the sensors observing particular properties of the patient. The paper also illustrates constraints and situations concepts to interpret the values measured by sensors in regard to the patient's static context. The evaluation of the ontology is based on experimental analysis of real body temperature. I suggest the following improvements:
1. Section 3.4: Consider the subtitle "ontology validation" instead of "ontology evaluation". Ideally, ontology evaluation for real-world applications focuses more on completeness and expressiveness. OOPS! (OntOlogy Pitfall Scanner!) is a very good tool to detect the ontology pitfalls, but it is designed for validating the structure, architecture and design of the ontology.
2. Section 5.1: Figure 3 is a good example of the ontological representation of EMR. However, one specific example may not be enough to evidence the coverage of the ontology. It may need a quantitive analysis to make it more convincing. For example, "We experiment with the ontology on XXX number of EMR, and it covers an average XX% of the concepts."
3. Section 5.2: It could be better to clarify constraints, context and situation. Ideally, the situation refers to a high level of context and is inferred from the aggregation (fusion) of multiple pieces of context. For example, in Table 1 and Table 2, C1-C5 refer to the temperature context, while C6-C8 refer to the time context. In this case, the situation is a high-level abstraction from temperature and time context. Compared with constraint->situation, a more logical flow is constraint->context->situation.
4. Section 5.3: The expressiveness of the ontology needs a short paragraph. It could be a comparison of ontological stream reasoning with other techniques mentioned in Section 2.1. The results will be very engaging if stream reasoning shows (1) significant time reduction, (2) better performance on limited training data, and (3) successfully detect the personalisation and provide customised alert service.

Additional comments:

1. Section 3.3: The relationship (i.e., object property) of the ontology can be integrated into Figure 1, which could save some space for other sections.
2. Be careful about the use of words and punctuations. For example, on Page 4 Line 31, use "his/her" or "their" instead of "her"; On Page 1 Line 46, use ``’’ instead of "" (LaTex specific).
3. Add one short paragraph to discuss the severity of the importance. From a practical perspective, a health monitoring system should be able to distinguish the severity of the importance, such as Critical, Important, Moderate and Low, etc.

Review #2
Anonymous submitted on 29/Nov/2021
Major Revision
Review Comment:

The authors present a study about how to detect the emergency situations of patients based on data from medical devices using semantic stream processing techniques. Hence, the authors introduced an ontology for semantically annotating data from medical devices using the RDF. After that, they demonstrated how their system can detect the high temperature of a patient during night.

The quality of research and presentation of this manuscript has not reached the standard of the semantic web journal yet.
Overall, the work has to be improved:

1. The authors claim that they have been using stream reasoning techniques in their work. However, what they demonstrated is only using a continuous query. They did not explain how new knowledge can be inferred or what reasoners they have been using. As their context is to monitor real-time data, the processing time of the reasoners should be concerned.

2. The given example (in Section 5) is too trivial. In the situation given in the example, semantic annotation for the data does not give any benefit.

Otherwise, the manuscript is essentially a copy of their previous publication[1] without significant improvement. The content (text and figures) of sections 1, 2, 4, 5, and 6 remains the same with a few rewritten sentences. They have a small extension of their ontology and ontology evaluation in Section 3.4. However, the ontology evaluation section does not make sense as the tool they used in the evaluation has not become a standard yet.

1. Bourgais, Mathieu, Franco Giustozzi, and Laurent Vercouter. "Detecting Situations with Stream Reasoning on Health Data Obtained with IoT." Procedia Computer Science 192 (2021): 507-516.

Review #3
Anonymous submitted on 25/Jan/2022
Major Revision
Review Comment:

This manuscript showcases a Stream Reasoning application in the healthcare context. It is well written and appropriately organized. The goal of the research is clear and relevant. The originality is low. The same authors published a similar paper in [1] on September 2021. The significance of the results is also low. The paper presents a use case. It demonstrates that it is possible to solve the problem using Stream Reasoning, but it does not prove that it makes sense. I would expect to see a comparative study that shows advantages and disadvantages compared to a solution purely based on a stream processor engine (e.g., esper, ksqldb, flink, or Spark Structured Streaming).

The data file provided by the authors under “Long-term stable URL for resources” is well organized and contains a README file. The provided resources are published in their institution GitLab and appear to be complete for replication of experiments. I did not import the project using an IDE, but the artifacts appear complete.

As a side comment, I invite the authors to stop using c-sparql and use rsp4j [2,3] instead.

[1] Mathieu Bourgais, Franco Giustozzi, Laurent Vercouter: Detecting Situations with Stream Reasoning on Health Data Obtained with IoT. KES 2021: 507-516
[2] Riccardo Tommasini, Pieter Bonte, Femke Ongenae, Emanuele Della Valle: RSP4J: An API for RDF Stream Processing. ESWC 2021: 565-581