Agents and Multi-Agent Systems for Health Care

Telerehabilitation in older adults is most needed in the patient environments, rather than in formal ambulatories or hospitals. Supporting such practices brings significant advantages to patients, their family, formal and informal caregivers, clinicians, and researchers. Several techniques and technologies have been developed aiming at facilitating and enhancing the effectiveness of telerehabilitation. This paper gives a quick overview of the state of the art, investigating video-based, wearable, robotic, distributed, and gamified telerehabilitation solutions. In particular, agent-based solutions are analyzed and discussed addressing strength, limitations, and future challenges. Elaborating on functional requirements expressed by professional physiotherapists and researchers, the need for extending multi-agent systems (MAS) peculiarities at the sensing level in wearable solutions establishes new research challenges.

Employed in cyber-physical scenarios with users-sensors and sensors-sensors interactions, MAS are requested to handle timing constraints, scarcity of resources and new communication means, which are crucial for providing real-time feedback and coaching.

The increasing percentage of elderly people in the population (at least in Europe and North America) is part of a demographic change that will have an enormous impact on the society in the next few years. Thus, intelligent solutions that rely on the Internet of Things have been proposed in the literature, with the final goal to give remote support to elderly people at their home. Those solutions aim at monitoring activities and behaviors, and automatically send alarms in case of anomalies, putting in contact the end-user with her/his GP or alerting the emergency center or familiars, according to the specific needs. However, although the great deal of worldwide researches in the area of the Internet of Things and its early applications to healthcare and teleassistance, the technologies to apply it in real-world with the necessary dependability levels are far from being assessed. In this paper, we propose novel software engineering concepts that, by synthesizing existing proposals bringing in the lessons of agent-based computing and agent-oriented software engineering, can effectively support the systematic (and thus more dependable) development of Internet of Things applications.

The increasing incidence of chronic diseases is a major challenge for the healthcare sector. Personal Health Systems (PHSs) address the self-management of chronic diseases, by decentralizing the health monitoring outside hospitalized environments. Rule based agents allow bringing domain experts’ knowledge into PHSs. However, agents must meet the requirements of real monitoring scenarios, characterized by massive streams of events. Hence, with the aim to monitor the health status of diabetic patients, two logic-based agent minds for an agent-oriented PHS are presented. One agent mind is based on the standard version of jREC, a Prolog-based implementation of Cached Event Calculus, while the other is a customization of the standard jREC mind that exploits an event-indexing technique. Both of them are as well integrated into MAGPIE, a Java agent platform. The paper then compares and analyzes the performance of the proposed agent minds, by computing the time needed to trigger different type of alerts, when the number of recorded events (e.g. values of physiological parameters) increases. The results show that the customized jREC mind performs much better when a high number of events need to be checked, making its use advisable in monitoring scenarios.

In this paper we present Trauma Tracker, a project – in cooperation with the Trauma Center of a hospital in Italy – in which agent technologies are exploited to realise Personal Medical Digital Assistant Agents (PMDA) supporting a Trauma Team in trauma management operations. This project aims at exploring the fruitful integration of software personal agents with wearable/eyewear computing, based on mobile and wearable devices such as smart-glasses. The key functionality of Trauma Tracker is to keep track of relevant events occurring during the management of a trauma, for different purposes. The basic one – discussed in detail in this paper – is to have an accurate documentation of the trauma, to automate the creation (and management) of reports and to enable offline data analysis, useful for performance evaluation and to improve the work of the Trauma Team. Then, tracking is essential to conceive more involved assisting functionalities by the PMDA, from monitoring and warning generation to suggesting actions to perform—fully exploiting the hands-free interface of wearable technologies. This goes towards the idea – envisioned in the paper – of augmented physicians working in augmented hospitals, in which software personal agents are exploited along with enabling technologies from wearable and pervasive computing, augmented reality, to create novel smart environments to support individual and cooperative work of healthcare professionals.

Computer-Interpretable Guidelines have been associated with a higher integration of standard practices in the daily context of health care institutions. The Clinical Decision Support Systems that deliver these machine-interpretable recommendations usually follow a Q&A style of communication, retrieving information from the user or a clinical repository and performing reasoning upon it, based on the rules from Clinical Practice Guidelines. However, these systems are limited in the reach they are capable of achieving as they were initially conceived for use in very specific moments of the clinical process, namely in physician appointments. The purpose of this work is thus to present a system that, in addition to Q&A reasoning, is equipped with other functionalities such as the scheduling and temporal management of clinical tasks, the mapping of these tasks onto an agenda of activities to allow an easy consultation by health care professionals, and notifications that let health care professionals know of task enactment times and information collection times. In this way, the system ensures the delivery of procedures. The main components of the system, which reflect a different perspective on the delivery of CIG advice that we call guideline as a service, are disclosed, and they include a health care Personal Assistant Web Application, a health care assistant mobile application, and the integration with the private calendar services of the user.

Supporting human actors in daily living activities for improving health and wellbeing is a fundamental goal for assistive technology. The personalisation of the support provided by assistive technology in the form of digital coaching requires user models that handle potentially conflicting goals and motives. The aim of this research is to extend a motivational model implemented in an assistive technology, into a multipurpose motivational model for the human actor who is to be supported, which can be translated into a multipurpose goal model for a team of assistive agents. A team of assistive agents is outlined with supplementary goals following the human’s different properties. A method for generating multipurpose arguments relating to different motives were developed, and implemented in a human-agent dialogue system. The results are exemplified based on a use case from an earlier pilot user study of the assistive technology. Future work includes user studies to validate the model.

Prediction models are widely used in insurance companies and health services. Even when 120 million people are at risk of suffering poverty or social exclusion in the EU, this kind of models are surprisingly unusual in the field of social services. A fundamental reason for this gap is the difficulty in labeling and annotating social services data. Conditions such as social exclusion require a case-by-case debate. This paper presents a multi-agent architecture that combines semantic web technologies, exploratory data analysis techniques, and supervised machine learning methods. The architecture offers a holistic view of the main challenges involved in labeling data and generating prediction models for social services. Moreover, the proposal discusses to what extent these tasks may be automated by intelligent agents.

In this paper, we show the convenience of multi-agent systems to help computational epidemiology come to the rescue of mathematical epidemiology for its practical limits on modeling and simulation of complex epidemiological phenomena. Herein, we propose as an example, an agent-based simulation platform for schistosomiasis (commonly known as Bilharzia, which is a parasitic disease found in tropical and subtropical areas and caused by a tapeworm called schistosome or bilharzias) that we have experimented with actual data of schistosomiasis in Niamey (Niger).