A prototype educational virtual assistant for diabetes management

The global prevalence of diabetes is escalating. Several digital health strategies have recently risen to assist in optimal diabetes management and reduce clinical, economic, and humanistic implications. This paper describes the first prototype of an Educational Virtual Assistant (EVA) intended to increase people’s engagement in diabetes management, through continuous education, interaction, and recommendations. Since the patient holds a pivotal role in his disease progression, the overall objective of EVA is to reduce the risk of critical events, by fostering them to adopt optimal diabetes management strategies and finally improving their daily quality of life. EVA was trained based on standardized educational material and implemented based on natural language processing (NLP) techniques that present an opportunity to use natural language understanding (NLU) through machine learning (ML). The assistant was integrated into a diabetes self-management application and tested within Chrodis Plus JA. Initial usability and acceptability results are presented here. Overall, this pilot study yielded a positive opinion, as well as suggestions for improvement. On-going work includes testing the first prototype with older people with T2D plus health professionals in primary care units in Greece and incorporating a ML-based context-sensitive dialogue manager, which is expected to convey a more flexible dialogue flow.

[1]  Yi Shang,et al.  Development and evaluation of a healthy coping voice interface application using the Google home for elderly patients with type 2 diabetes , 2018, 2018 15th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[2]  Dimitrios Tzovaras,et al.  MyAirCoach: Designing a mobile application for the education of patients regarding asthma disease , 2015, 2015 International Conference on Interactive Mobile Communication Technologies and Learning (IMCL).

[3]  Dimitrios Tzovaras,et al.  Applying an Intelligent Personal Agent on a Smart Home Using a Novel Dialogue Generator , 2020, AIAI.

[4]  Dimitrios Tzovaras,et al.  An mHealth System for Monitoring Medication Adherence in Obstructive Respiratory Diseases Using Content Based Audio Classification , 2018, IEEE Access.

[5]  Nick Pawlowski,et al.  Rasa: Open Source Language Understanding and Dialogue Management , 2017, ArXiv.

[6]  Manolis Tsiknakis,et al.  Employing Conversational Agents in Palliative Care: A Feasibility Study and Preliminary Assessment , 2019, 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE).

[7]  Taweesak Samanchuen,et al.  Chatbot Utilization for Medical Consultant System , 2018, 2018 3rd Technology Innovation Management and Engineering Science International Conference (TIMES-iCON).

[8]  Alexandre Escande,et al.  A Chatbot Versus Physicians to Provide Information for Patients With Breast Cancer: Blind, Randomized Controlled Noninferiority Trial , 2019, Journal of medical Internet research.

[9]  T. Kowatsch,et al.  Text-based Healthcare Chatbots Supporting Patient and Health Professional Teams: Preliminary Results of a Randomized Controlled Trial on Childhood Obesity , 2017 .

[10]  Shafquat Hussain,et al.  Extending a Conventional Chatbot Knowledge Base to External Knowledge Source and Introducing User Based Sessions for Diabetes Education , 2018, 2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA).

[11]  Amit P. Sheth,et al.  kBot: Knowledge-Enabled Personalized Chatbot for Asthma Self-Management , 2019, 2019 IEEE International Conference on Smart Computing (SMARTCOMP).

[12]  Jessica A. Chen,et al.  Conversational agents in healthcare: a systematic review , 2018, J. Am. Medical Informatics Assoc..

[13]  Oscar Díaz,et al.  Using Health Chatbots for Behavior Change: A Mapping Study , 2019, Journal of medical systems.

[14]  Rokas Navickas,et al.  Multimorbidity: What do we know? What should we do? , 2016, Journal of comorbidity.