HES-So introduces EREBOTS: an agent-based framework forchatbot based on Pryv.io eHealth backend
EREBOTS enable the configuration and deployment of personalized chatbots to support users in multi-topic and multi-campaign behavioral change programs with full respect to data privacy. Conversational agents coaching people fighting chronic diseases, addictions, and other health issues, leading to decreased life quality are among EREBOTS applications.
Healthcare and eHealth systems are facing the strain of a significant demand for user (patient) empowerment—implying the need for new logics, architectures, dynamics, and interfaces
Siri, Alexa and Cortana are among the best known intelligent systems that have the ability to assist humans through multimodal interactions, including text, buttons, vocal, video, and gesture-based communication. Although such virtual assistants heavily rely on vocal interactions, sometimes more discrete and asynchronous chat-like communications are still preferred. Chatbots are an example of intelligent systems relying on interactions mostly menu/text-based. Anywhere/anytime availability, immediate response, confidentiality, social acceptance, and massive scalability are among the factors contributing to the increasing and an effective adoption of chatbots in a wide range of domains, particularly for motivational such as for social network campaigns and support, customer management, eHealth and assisted-living scenarios. In the healthcare domain, chatbots leveraging on tailored support and social aspects can be of great support to foster behavioural change, monitoring of chronic health conditions and primary care to name a few.
However, most of the modern chatbots rely on state machines (implementing conversational rules) and one-fits-all approaches, neglecting personalization, data-stream privacy management, multi-topic management/interconnection, and multimodal interactions. This leads to significant limitations in inadequate personalization, lack of real-time monitoring, reporting and customization for medical personnel, lack of mechanisms to integrate communities of chatbots, limited knowledge sharing capabilities, and the impossibility of seamlessly deploying multi-domain campaigns within the same framework. These limitations are linked to the predominantly rigid architectures proposed in most existing approaches. Most chatbot solutions rely on monolithic and centralized data management strategies, making it hard to comply with privacy regulations such as GDPR, Swiss DPA. The sensitive nature of data collected through chatbot interactions makes it necessary to shift the control of personal data towards the users themselves, empowering them in the process. EREBOTS uses an instance of Pryv to persist the user’s chat history and all personal data. Employing Pryv, users gain exclusive control of their data, thus being able to revoke the consent at any point, disabling EREBOT access to it, and, if necessary, fully removing any stored piece of information.
- Multi-scenario agent-based chatbot framework: In EREBOTS, it is possible to combine several context-dependent behaviors that can be encapsulated in dedicated story lines, which can be modeled as isolated or interconnected scenarios. These behaviors are enacted by a network of user agents, doctor agents, and orchestrated through gateway agents.
- User personalization: User agents build a model of the user profile, his/her preferences, history, goals, and aggregated information. With this model, the user agents are able to tailor behaviors and provide a personalized experience.
- Healthcare personnel control and monitoring: Medical doctors and healthcare providers have the possibility of defining possible goals, configure self-assessment interactions, or customize the types of activities proposed to patients/participants. Moreover, they can monitor users’ profiles with detailed analytics describing their behaviors and aggregated trends.
- Privacy and ethics compliance: In EREBOTS, all the sensitive/personal information are solely under the control of the user, who can make any decisions concerning storage and sharing of her information. Through the Pryv.io platform integrated into EREBOTS, users may configure fine-grained access control or even entirely remove their data if they decide so.
- Multi-campaign implementation and testing: EREBOTS has been employed and tested in scenarios such as smoking cessation and balance enhancement exercises (physical rehabilitation) for older adults during social confinement (due to COVID-19 restrictions).
EREBOTS proves that assistive agents can interact with each other in the back-end:
- opening the door to knowledge sharing for campaign-related investigations
- Allowing medical personnel to access real-time aggregated and personal information of the individuals participating in a given campaign
- Enabling multimodel knowledge representation which can be enabled for simultaneous campaign executions,
- Fine-tuning data-/action-driven personalization strategies
- Allowing users to be monitored via direct feedback collection
- (Re)defining online therapies and campaigns story lines
- By using the the data schema defined as Pryv streams typically serialized in JSON and possibly exposed using semantically rich representations (e.g., HL7 FHIR—ongoing work in EREBOTS);
- Proposing (pro)active mechanisms that can be tailored to a specific case study
- Storing users’ data in a stream-based privacy-compliant system solely managed by the user.
About the eHealth unit of the Institute Information Systems HES-SO Valais-Wallis
The eHealth unit is part of the Institute of Information Systems of the University of Applied Sciences and Arts Western Switzerland (HES-SO). Based in Sierre (Valais, Switzerland), the eHealth unit undertakes applied research in close collaboration with public or private companies and institutions. It has gained solid experience with complex interdisciplinary projects related to digital health, at national and international levels. The eHealth unit has for instance invested many research efforts in the development of sensor-based mHealth applications for chronic diseases (e.g. diabetes type 1 and 2). Furthermore, the unit has developed expertise in health record data interchange and the usage of standards (HL7, FHIR), as well as the development of privacy and anonymity preserving algorithms for health data exchange (Nano-Tera.ch ISyPeM2 project). It is also working on blockchain-based healthcare data management and on a prototype of a framework for managing and sharing EMR data for cancer patient care. It is investing many efforts in personalized health support, such as for coaching in physiotherapy, or smoking cessation programs run on social networks with chatbot supports.
Pryv makes essential software for data-driven healthcare innovation. Our purpose-built middleware helps organizations manage personal data from creation to use, sharing and disposal. We accelerate time to market, cut IT development costs and speed up connectivity to all data sources. Pryv addresses the enhanced citizen’s right under GDPR and turns privacy compliance into a competitive advantage. For more information: pryv.com