HELENA: An intelligent digital assistant based on a Lifelong Health User Model

Highlights

• Definition of a lifelong health user model.

• Definition of an intelligent digital assistant, HELENA.

• Evaluation through a large user study to evaluate the model and the digital assistant.

Abstract

Digital Assistants are overgrowing in the mobile application industry and are now implemented in various commercial devices. So far, their use in the health domain is limited and often narrowed to remote monitoring of specific patient pathology. The main contribution of this paper is HELENA, a conversational agent endowed with healthcare knowledge that supports users in managing their lifelong health user model (LHUM) by providing simple services.

The proposed platform has been evaluated in a user study involving 160 participants who gave feedback on the digital assistant and the profile conceptualization. The results showed that LHUM is comprehensive and inclusive (76.25% positive feedback), and the users appreciated that all personal health data were available in one single profile (83.75% positive feedback). Furthermore, the user interaction was pleasant, functional, and efficient. Also, measurement management, data sharing, and food diary management have been broadly appreciated. The outcomes of our investigation suggest that adopting a lifelong comprehensive user profile by digital assistants is a promising research direction.

Introduction

The implementation of information and communication technology in the medical field is commonly referred to as eHealth (or digital health), which consists of using information technology for the benefit of human health (El Benny et al., 2021, Srivastava et al., 2015). Applications for monitoring patients usually adopt wearable smart sensors and devices to monitor vital parameters such as heart rate, blood pressure, blood saturation, and body temperature. These devices are often connected to the Internet or mobile platforms via Bluetooth technology (Sebestyen et al., 2014, Zhang et al., 2021). This puts the world of eHealth within reach of the end-users, who can gain a huge advantage in dealing with daily activities that affect their health.

In this user-centered vision of eHealth, digital assistants can play an important role. For instance, voice-based digital assistants, such as Siri and Alexa, are rapidly becoming adopted by consumers (Brill, Munoz, & Miller, 2019). Recent studies have shown high user satisfaction when using conversational devices and personal digital assistants in eHealth, but the perception of their limited reliability is still a problem (Abdul-Kader and Woods, 2015, Omrani et al., 2022).

It is crucial to provide reliable eHealth services based on explainable models that support decision-making. It is necessary to design systems that support the physician in making informed and timely decisions and provide an empathetic, easy-to-use, reliable interface to improve user experience and increase trust.

The contributions of this work are:

• the conceptualization of LHUM, a Lifelong Health User Model, which is a comprehensive clinical user profile fed with data coming from the interaction with the users or from other systems. LHUM could be exported in standard formats and shared among physicians treating the patient;

• the design and implementation of HELENA, a healthcare digital assistant exploiting LHUM to provide personalized services. HELENA allows users to monitor personal health status through a text-based interface (i.e., a chatbot), as well as a classic graphical interface with buttons and labels;

• the definition of a privacy-aware and transparent process for lifelong monitoring of the patient’s health status;

• an experimental session to assess user satisfaction with HELENA.