200
A. Henaien et al.
chronically ill and elderly patients. Our framework is build up in three keys stage:
ontology for semantic modelling and representation, semantic rules for reasoning
and machine learning techniques for learning; detailed in the following:
Semantic Representation and Ontological Modelling: The aim of this
step is to find the best practices in semantic representation for holistic remote
health monitoring system that is characterized by a large set of terminologies.
Ontology modelling is one of the best choices, and as discussed before, the combination of different standard and valid ontologies is one of the recommended
practice to build up an integrated multidisciplinary ontology.
Semantic Rules Reasoning Based Prediction: This step consists in the
definition of primary knowledge base: a prediction based set of semantic rules.
It exists two categories of rules: objectives and subjective. Objective knowledge contains medical rules defined in general medicine textbooks. Subjective
knowledge is defined about the patient profile and context such as prior medical
history, genetic diseases, personal lifestyle, etc.
Machine Learning Based Healthcare Reasoning: The outcome of this step
is the best ML algorithm able to give the efficient support to the risk assessment
system by providing the best and accurate new medical rules, detailed later in
the Algorithm 1.
3.1 Information Life Cycle
In this subsection, we explain the information life cycle in our system: from a
data, to an information, then finally a knowledge. The schema of Fig. 1 represents the different steps starting from the collection of data, passing by the
different information uses in real-time ubiquitous healthcare monitoring, finally
generating of knowledge. We have two main types of data sources: received data
from smart devices and entered data by users (medical staff basically). All the
data is collected and prepared to be analysed. The first step of the data preparation consists on highlighting the outliers and missing values: any abnormal value
could be an alert. Then, in data selection, only contextual and health attributes
are selected that are related to the environment or the health situation of a
patient. un-selected data will be temporary removed from the data. Different
transformations are required, viz, String to Nominal, Unify Date Format. The
data mining step is our main contribution because it is not only processed using
data mining techniques but also it is based on inferring meaning applied using
a set of rules which consists on the subjective knowledge. In a first step, the
inferring meaning is used in real-time by the system to determinate the current
health situation of the patient, instantaneous alert, healthcare risk assessment
and anomalous detection. Each applied rule is registered in the subjective knowledge. This knowledge base is able to grow in terms of number of rules. This
A. Henaien et al.
chronically ill and elderly patients. Our framework is build up in three keys stage:
ontology for semantic modelling and representation, semantic rules for reasoning
and machine learning techniques for learning; detailed in the following:
Semantic Representation and Ontological Modelling: The aim of this
step is to find the best practices in semantic representation for holistic remote
health monitoring system that is characterized by a large set of terminologies.
Ontology modelling is one of the best choices, and as discussed before, the combination of different standard and valid ontologies is one of the recommended
practice to build up an integrated multidisciplinary ontology.
Semantic Rules Reasoning Based Prediction: This step consists in the
definition of primary knowledge base: a prediction based set of semantic rules.
It exists two categories of rules: objectives and subjective. Objective knowledge contains medical rules defined in general medicine textbooks. Subjective
knowledge is defined about the patient profile and context such as prior medical
history, genetic diseases, personal lifestyle, etc.
Machine Learning Based Healthcare Reasoning: The outcome of this step
is the best ML algorithm able to give the efficient support to the risk assessment
system by providing the best and accurate new medical rules, detailed later in
the Algorithm 1.
3.1 Information Life Cycle
In this subsection, we explain the information life cycle in our system: from a
data, to an information, then finally a knowledge. The schema of Fig. 1 represents the different steps starting from the collection of data, passing by the
different information uses in real-time ubiquitous healthcare monitoring, finally
generating of knowledge. We have two main types of data sources: received data
from smart devices and entered data by users (medical staff basically). All the
data is collected and prepared to be analysed. The first step of the data preparation consists on highlighting the outliers and missing values: any abnormal value
could be an alert. Then, in data selection, only contextual and health attributes
are selected that are related to the environment or the health situation of a
patient. un-selected data will be temporary removed from the data. Different
transformations are required, viz, String to Nominal, Unify Date Format. The
data mining step is our main contribution because it is not only processed using
data mining techniques but also it is based on inferring meaning applied using
a set of rules which consists on the subjective knowledge. In a first step, the
inferring meaning is used in real-time by the system to determinate the current
health situation of the patient, instantaneous alert, healthcare risk assessment
and anomalous detection. Each applied rule is registered in the subjective knowledge. This knowledge base is able to grow in terms of number of rules. This