Carmie

Abstract

The incidence of chronic diseases is increasing and monitoring patients in a home environment is recommended. Noncompliance with prescribed medication regimens is a concern, especially among older people. Heart failure is a chronic disease that requires patients to follow strict medication plans permanently. With the objective of helping these patients managing information about their medicines and increasing adherence, the personal medication advisor CARMIE was developed as a conversational agent capable of interacting, in Portuguese, with users through spoken natural language. The system architecture is based on a language parser, a dialog manager, and a language generator, integrated with already existing tools for speech recognition and synthesis. All modules work together and interact with the user through an Android application, supporting users to manage information about their prescribed medicines. The authors also present a preliminary usability study and further considerations on CARMIE.

Conversational Agents in Health Care: Scoping Review and Conceptual Analysis (Preprint)

“…In this scoping review, 40 included studies were from high-income countries (HICs) and 6 were from low-and middle-income countries (LMICs). A total of 22 studies were from European countries, including Italy [44,45], Switzerland [30,[46][47][48][49][50][51][52], France [53,54], Portugal [55], The Netherlands [56], the United Kingdom [57][58][59][60][61], Spain [62,63], and Sweden [64]. Moreover, 8 studies originated from Asian countries: Philippines [65], China [66], Japan [67,68], Pakistan [69], India [70,71], and Hong Kong [72].…”

“…Conversational agents were delivered through a variety of means in the included studies. Most (n=23) were smartphone apps [30,[46][47][48][49][50]53,55,[58][59][60][61]64,67,70,71,75,77,81,83,85,86,88]; web based (n=5) [57,66,73,74,82]; desktop computer based (n=2) [65,79]; used smartphone-embedded software (n=6; eg, Siri, Google Assistant, Alexa, etc) [44,51,62,76,84,87], Telegram [45,78], WeChat [72], SMS and multimedia messaging service [89], Windows live messenger [56], or Facebook Messenger [52,80]; and 4 were made available on more than 1 platform [53,59,68,83]. Three studies did not specify the method of conversational agent delivery…”

“…Moreover, 19 studies allowed free text user inputs [45,48,51,56,57,60,61,66,69,70,72,74,77,78,80,81,85,86,89], and 4 studies used both fixed and free text user inputs [53,64,65,73]. Speech was enabled in 8 studies [44,55,63,71,76,79,82,84], whereas free text and speech were employed in 3 studies [62,75,87]. The method of user input was unspecified in 1 study [59] [48,55,63,71,87]; speech alone (n=4) [44,79,82,84]; text and images (n=4) [30,67,75,86]; text, speech, and images [62]; or text, speech, images, and videos…”

“…Speech was enabled in 8 studies [44,55,63,71,76,79,82,84], whereas free text and speech were employed in 3 studies [62,75,87]. The method of user input was unspecified in 1 study [59] [48,55,63,71,87]; speech alone (n=4) [44,79,82,84]; text and images (n=4) [30,67,75,86]; text, speech, and images [62]; or text, speech, images, and videos [52,76]. The input and output methods were not specified in 1 of the studies [59] (Multimedia Appendix 2).…”

“…One article [78] reported on a conversational agent personality that was criticized for being overly formal, and some articles did not report on the personality of the conversational agent at all [30,44,45,50,51,54,55,59,63,67,69,75,77,[82][83][84]87].…”