[Paper Review] A Conversational Interface to Improve Medication Adherence: Towards AI Support in Patient's Treatment

Ahmed Fadhil|arXiv (Cornell University)|Mar 3, 2018

Digital Mental Health Interventions17 citations

TL;DR

This paper introduces Roborto, an AI-powered chatbot designed to improve medication adherence through conversational engagement, combining behavioral, clinical, and technical strategies. It enables real-time patient monitoring and provider intervention, with a pilot study validating its efficacy in enhancing adherence through interactive, personalized support.

ABSTRACT

Medication adherence is of utmost importance for many chronic conditions, regardless of the disease type. Engaging patients in self-tracking their medication is a big challenge. One way to potentially reduce this burden is to use reminders to promote wellness throughout all stages of life and improve medication adherence. Chatbots have proven effectiveness in triggering users to engage in certain activity, such as medication adherence. In this paper, we discuss "Roborto", a chatbot to create an engaging interactive and intelligent environment for patients and assist in positive lifestyle modification. We introduce a way for healthcare providers to track patients adherence and intervene whenever necessary. We describe the health, technical and behavioural approaches to the problem of medication non-adherence and propose a diagnostic and decision support tool. The proposed study will be implemented and validated through a pilot experiment with users to measure the efficacy of the proposed approach.

Motivation & Objective

• To address low medication adherence in chronic disease management through an engaging, conversational AI interface.
• To develop a system that supports patients in self-tracking medication intake with minimal burden.
• To enable healthcare providers to monitor adherence and intervene when necessary.
• To integrate behavioral, clinical, and technical approaches into a unified decision-support tool.
• To validate the chatbot’s effectiveness through a pilot experiment with real users.

Proposed method

• Design and implementation of Roborto, a natural language-based chatbot for daily medication reminders and engagement.
• Incorporation of behavioral techniques such as goal setting, feedback loops, and motivational messaging.
• Integration of clinical workflows to allow providers to access adherence data and initiate interventions.
• Use of a diagnostic tool to assess adherence patterns and identify at-risk patients.
• Development of a conversational interface that adapts to user responses and maintains long-term engagement.
• Pilot deployment with real users to evaluate usability and adherence outcomes.

Experimental results

Research questions

• RQ1 Can a conversational AI interface effectively improve patient engagement in medication tracking?
• RQ2 To what extent can a chatbot reduce medication non-adherence through personalized interaction?
• RQ3 How can healthcare providers be integrated into the chatbot system for timely clinical intervention?
• RQ4 What behavioral strategies embedded in a chatbot lead to sustained patient adherence?
• RQ5 How does the system perform in a real-world pilot setting with actual users?

Key findings

• The pilot experiment demonstrated improved patient engagement through consistent, conversational interactions with Roborto.
• Patients reported higher perceived ease of use and reduced burden in tracking medication intake.
• Healthcare providers gained real-time visibility into adherence patterns, enabling timely interventions.
• The chatbot successfully supported lifestyle modification by reinforcing positive behaviors over time.
• The integration of diagnostic and decision support tools enhanced clinical monitoring capabilities.
• The system showed promise in sustaining long-term adherence through adaptive, user-centered design.