Complementing Agents with Cognitive Services: A Case Study in Healthcare
- PDF / 821,223 Bytes
- 10 Pages / 595.224 x 790.955 pts Page_size
- 62 Downloads / 233 Views
MOBILE & WIRELESS HEALTH
Complementing Agents with Cognitive Services: A Case Study in Healthcare Sara Montagna1
· Stefano Mariani2 · Emiliano Gamberini3 · Alessandro Ricci1 · Franco Zambonelli2
Received: 20 May 2020 / Accepted: 16 July 2020 © The Author(s) 2020
Abstract Personal Agents (PAs) have longly been explored as assistants to support users in their daily activities. Surprisingly, few works refer to the adoption of PAs in the healthcare domain, where they can assist physicians’ activities reducing medical errors. Although literature proposes different approaches for modelling and engineering PAs, none of them discusses how they can be integrated with cognitive services in order to empower their reasoning capabilities. In this paper we present an integration model, specifically devised for healthcare applications, that enhances Belief-Desire-Intention agents reasoning with advanced cognitive capabilities. As a case study, we adopt this integrated model in the critical care path of trauma resuscitation, stepping forward to the vision of Smart Hospitals. Keywords Personal medical digital assistant · Trauma management · Cognitive services
Introduction Several clinical problems require complex and quick decision making on diagnosis and care of patients. For instance, during trauma resuscitation, physicians need to decide and act in few instants. It is indeed demonstrated that trauma is a time-dependent pathology, where actions taken during the first hour, called “the golden hour”, heavily influence patient outcome [30]. Decisions are made by integrating information on patients’ biographical data, vital signs, lab tests, and imaging. However, these data are usually not available in the same location and at the same time, since interoperability between acquisition systems is still far from reality in many world countries—especially in primary care. Moreover, literature data and medical protocols must be taken into account to take the most informed choice: consulting them This article is part of the Topical Collection on Healthcare Intelligent Multi-Agent Systems (HIMAS2020) Guest Editors: Neil Vaughan, Sara Montagna, Stefano Mariani, Eloisa Vargiu and Michael I. Schumacher Sara Montagna
[email protected] 1
Universit`a degli Studi di Bologna, Cesena, Italy
2
Universit`a degli Studi di Modena e Reggio Emilia, Reggio Emilia, Italy
3
Maurizio Bufalini Hospital, Cesena, Italy
in these fast-paced scenarios, as well as remembering all of them, is simply impractical for a human being. Pervasive computing can support physicians by acquiring patients’ data and integrating it with information accessed and analysed from literature, making them available anywhere, anytime. In particular, in this context, personal assistant agents (PAs) have been recognised as crucial components of a pervasive application [33]. Today, they commonly support users in daily activities, from simple ones such as make calls, read mails, send messages, open web pages, to more complex tasks such as schedule appointments, interact wit
Data Loading...
