Stefano Bromuri

General Overview of ImageCLEF at the CLEF 2015 Labs

This paper presents an overview of the ImageCLEF 2015 evaluation campaign, an event that was organized as part of the CLEF labs 2015. ImageCLEF is an ongoing initiative that promotes the evaluation of technologies for annotation, indexing and retrieval for providing information access to databases of images in various usage scenarios and domains. In 2015, the 13th edition of ImageCLEF, four main tasks were proposed: 1 automatic concept annotation, localization and sentence description generation for general images; 2 identification, multi-label classification and separation of compound figures from biomedical literature; 3 clustering of x-rays from all over the body; and 4 prediction of missing radiological annotations in reports of liver CT images. The x-ray task was the only fully novel task this year, although the other three tasks introduced modifications to keep up relevancy of the proposed challenges. The participation was considerably positive in this edition of the lab, receiving almost twice the number of submitted working notes papers as compared to previous years.

COMMODITY12: A smart e-health environment for diabetes management

We present the development of COMMODITY12, a Personal Health System PHS to assist in the provision of continuous and personalised health services to diabetic patients, thus empowering their lifestyle regardless of their location. COMMODITY12 consists of ambient, wearable and portable devices, which acquire, monitor and communicate physiological parameters and other health-related context of an individual, such as physical activity and vital body signals. This data is interpreted by intelligent agents that use expert biomedical knowledge to derive important insights about the individuals health status, which are then presented in the form of active feedback to the patient directly from the device, or via health professionals who assist in diagnosis, treatment and life management. The emphasis of the work is on the design of the PHS in terms of its main components, their integration and deployment to address major problems of interest to both diabetic patients and doctors that treat diabetes.

Multi-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms

OBJECTIVE This research is motivated by the issue of classifying illnesses of chronically ill patients for decision support in clinical settings. Our main objective is to propose multi-label classification of multivariate time series contained in medical records of chronically ill patients, by means of quantization methods, such as bag of words (BoW), and multi-label classification algorithms. Our second objective is to compare supervised dimensionality reduction techniques to state-of-the-art multi-label classification algorithms. The hypothesis is that kernel methods and locality preserving projections make such algorithms good candidates to study multi-label medical time series. METHODS We combine BoW and supervised dimensionality reduction algorithms to perform multi-label classification on health records of chronically ill patients. The considered algorithms are compared with state-of-the-art multi-label classifiers in two real world datasets. Portavita dataset contains 525 diabetes type 2 (DT2) patients, with co-morbidities of DT2 such as hypertension, dyslipidemia, and microvascular or macrovascular issues. MIMIC II dataset contains 2635 patients affected by thyroid disease, diabetes mellitus, lipoid metabolism disease, fluid electrolyte disease, hypertensive disease, thrombosis, hypotension, chronic obstructive pulmonary disease (COPD), liver disease and kidney disease. The algorithms are evaluated using multi-label evaluation metrics such as hamming loss, one error, coverage, ranking loss, and average precision. RESULTS Non-linear dimensionality reduction approaches behave well on medical time series quantized using the BoW algorithm, with results comparable to state-of-the-art multi-label classification algorithms. Chaining the projected features has a positive impact on the performance of the algorithm with respect to pure binary relevance approaches. CONCLUSIONS The evaluation highlights the feasibility of representing medical health records using the BoW for multi-label classification tasks. The study also highlights that dimensionality reduction algorithms based on kernel methods, locality preserving projections or both are good candidates to deal with multi-label classification tasks in medical time series with many missing values and high label density.

INTERDEPENDENT ARTIFICIAL INSTITUTIONS IN AGENT ENVIRONMENTS

In this paper we present a new approach to model artificial institutions (AIs) that are situated in agent environments where heterogeneous agents reside. An AI is seen here as an entity that can evolve over time, whose rules, in terms of powers, permissions, and obligations, are perceivable as first-class entities by the agents belonging to the institution. We use a Multi-Agent Normative EnvironmenTs (MANET) meta-model for the specification of AIs that are situated in first-class agent environments. We present the concepts of MANET in a way that makes them re-usable in different application domains, and we extend our presentation with the study of AIs interdependences for the specification of the institutional part of a first-class environment. As a consequence, our framework presents institutions as first-class abstractions that can be inspected, manipulated and modified, created and destroyed by the agents populating the agent environment where the institution resides. We use an e-Energy marketplace scenario to illustrate the properties of our model.

Towards distributed agent environments for pervasive healthcare

In this paper we present a prototypical pervasive health care infrastructure, whose purpose is the continuous monitoring of pregnant women with gestational diabetes mellitus. In this infrastructure, patients are equipped with a body-area network made of sensors to control blood pressure and glucose levels, where the sensors are connected to a smart phone working as a hub to collect the data. These data is then fed to a pervasive GRID where abductive agents provide a diagnosis for the actual reading of the sensors and contacting health care professionals if necessary. We also show how, by applying the concept of agent environment, we are facilitated in defining a pervasive GRID for roaming agents that monitor continuously the health status of the patients.

Processing Diabetes Mellitus Composite Events in MAGPIE

The focus of this research is in the definition of programmable expert Personal Health Systems (PHS) to monitor patients affected by chronic diseases using agent oriented programming and mobile computing to represent the interactions happening amongst the components of the system. The paper also discusses issues of knowledge representation within the medical domain when dealing with temporal patterns concerning the physiological values of the patient. In the presented agent based PHS the doctors can personalize for each patient monitoring rules that can be defined in a graphical way. Furthermore, to achieve better scalability, the computations for monitoring the patients are distributed among their devices rather than being performed in a centralized server. The system is evaluated using data of 21 diabetic patients to detect temporal patterns according to a set of monitoring rules defined. The system’s scalability is evaluated by comparing it with a centralized approach. The evaluation concerning the detection of temporal patterns highlights the system’s ability to monitor chronic patients affected by diabetes. Regarding the scalability, the results show the fact that an approach exploiting the use of mobile computing is more scalable than a centralized approach. Therefore, more likely to satisfy the needs of next generation PHSs. PHSs are becoming an adopted technology to deal with the surge of patients affected by chronic illnesses. This paper discusses architectural choices to make an agent based PHS more scalable by using a distributed mobile computing approach. It also discusses how to model the medical knowledge in the PHS in such a way that it is modifiable at run time. The evaluation highlights the necessity of distributing the reasoning to the mobile part of the system and that modifiable rules are able to deal with the change in lifestyle of the patients affected by chronic illnesses.

An Agent Based Pervasive Healthcare System: A First Scalability Study

Gestational Diabetes Mellitus (GDM) occurs during pregnancy due to an increased resistance to insulin caused by the growth of the baby. It appears after the 24th week of pregnancy and it is treated with diet counselling and insulin treatment. In this paper we present the complete implementation of a Pervasive Healthcare System (PHS) based on intelligent agents to support continuous monitoring of pregnant women affected by GDM. Our infrastructure is composed of a mobile interface connecting to a distributed multi-agent system which in turns is connected to a patient management system. This stores the data produced during the monitoring phase and present them to the doctors in charge of the patient. Our system’s scalability is then evaluated to show the strong and weak points of our approach.

A peer to peer agent coordination framework for IHE based cross-community health record exchange

This paper presents a Peer to Peer (P2P) agent coordination framework for the exchange of Electronic Health Records (EHR) between health organisations that comply with the existing interoperability standards as proposed by the Integrating Healthcare Enterprise (IHE). Every health organisation represents a community in a P2P network and uses a set of autonomous agents and a set of distributed coordination rules to coordinate the agents in the search of specific health records. To model the interactions among communities, the framework uses the tuple centre agent communication model and semantic web technologies. In order to illustrate the scalability of our approach, we evaluate the proposed solution in distributed settings.

Multiparty Argumentation Game for Consensual Expansion Applied to Evidence Based Medicine

Evidence based medicine (EBM) requires many different sources of knowledge when dealing with complex patients. Such a discipline inherently involves the issue of conflicts arising amongst arguments coming from different sources, such as guidelines, trials and clinical studies. In this paper we consider a set of agents with their own medical argumentation which exchange medical arguments to enrich their own knowledge and suggest a set of treatments resulting from the argumentation process.

A self-healing distributed pervasive health system

In the context of pervasive healthcare systems there is a growing need of services that are constantly available to the patients accessing them. To address this issue, in this paper we present a distributed pervasive infrastructure that is capable of self-healing one or more of its parts when an external event causes a disruption of the service in the areas covered by the pervasive system. We utilise approaches from multi-agent systems MASs such as communication, coordination, planning and agent environments to create a distributed system whose emergent behaviour shows the capability to heal itself even if 50% of the system is not functioning due to external causes.