{"id":8389,"date":"2019-11-19T15:43:31","date_gmt":"2019-11-19T14:43:31","guid":{"rendered":"https:\/\/www-old.kapcode.fr\/?p=8389"},"modified":"2023-01-16T11:29:14","modified_gmt":"2023-01-16T10:29:14","slug":"chatbots-sante","status":"publish","type":"post","link":"https:\/\/www.kapcode.fr\/en\/articles\/chatbots-health\/","title":{"rendered":"What place for chatbots in healthcare?"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Whether you want to book a train ticket, find out the opening hours of a store or get information about a product, it is now not uncommon to interact with a chatbot<\/strong>. The word chatbot is formed from the concatenation of the English words \"chat\" and \"bot\", short for \"robot\". A chatbot, also called a conversational agent, is a program that simulates a conversation with a human in natural language<\/strong>. In health, chatbots can have numerous uses<\/strong>for example from patient referral to medical diagnosis assistance<\/strong>.<\/p>

The origins of the Sanofi chatbot<\/h2>

At 39BIS<\/a><\/span>its e-health laboratory, Sanofi<\/a> questioned itself at the end of 2017 about the the issue of proper use of medicines and pharmacovigilance<\/strong>. Very quickly, the laboratory identified the interest of a chatbot in this field. It is in this context that the development of a conversational agent<\/strong> was launched in 2018, with the goal of provide physicians with validated information in a simple and rapid manner<\/strong> on the medical and regulatory fronts.<\/p>

To ensure the optimal development of this project, Sanofi has surrounded itself with two partners, Orange Healthcare<\/a> and Kap Code, selected on the basis of their complementarity. We will see how the partners have been able to combine their expertise<\/strong> to develop this chatbot and how they chose to share their experience.<\/p>

Specificities related to the health field<\/h2>

Orange Healthcare offers digital solutions to support healthcare players in their digital transformation. Experimenting with chatbots is not new for the company, but the development of a health chatbot<\/strong> raises specific constraints related to the sector<\/strong>. Indeed, this implies to answer particular problems in particular around confidentiality of health data and effectiveness of the use case<\/strong>. Thus, the experimentation of a chatbot in health is full of lessons and it is in this perspective that Orange Healthcare has chosen to join the adventure.<\/p>

Importance of health chatbot evaluation<\/h2>

Kap Code is a startup specialized in digital health and its applications. Resulting from the CRO Kappa Sant\u00e9<\/a>this startup has a solid track record of epidemiological and technological expertise<\/strong>. Kap Code is also an expert in detection of weak signals on social networks<\/strong> thanks to its tool Detec't<\/a> and quickly identified the importance of detecting pharmacovigilance cases in conversations as well as the centrality of the evaluation of digital tools<\/strong> in health. Kap Code naturally agreed to accompany Sanofi in the development of its chatbot<\/strong> and especially in its evaluation. The adoption of this tool is indeed correlated to the value given by the users.<\/p>

Based on their first experiments, Sanofi, Orange Healthcare and Kap Code have co-written a white paper on chatbots in healthcare.<\/strong><\/p>

After experimentation, experience sharing<\/h2>

The white paper \"Chatbots in health<\/strong> is positioned as a first experience sharing about chatbots designed for the healthcare field.<\/p>

The design of a chatbot<\/strong> is based on one of the disciplines of artificial intelligence (AI): automatic language processing (ALP)<\/strong> or natural language processing<\/em> (NLP). There are several NLP techniques but the natural language understanding<\/em> (NLU) and the natural language generation<\/em> (NLG) are the main techniques used for conversational agents. On the one hand, they are simulate the ability to understand human language<\/strong> and on the other hand to be able to generate an answer or an additional question<\/strong>.<\/p>

At the medical level, all the uses are not yet listed but some of them have been highlighted. Thus, a conversational bot can be used in the context of medical information<\/strong>of prevention<\/strong> or even of support for chronic pathologies<\/strong>.<\/p>

Whatever the use case, a chatbot in health has specificities<\/strong> which must be taken into account during its design. Thus, it is necessary to ensure the reliability of the content<\/strong> through credible and validated medical sources. In addition, since health and personal data may be disclosed, extra care must be taken to securing data<\/strong>. Moreover, if all chatbots have a personality, the health chatbots must bring credibility of the content<\/strong>. Finally, the technology used must ensure the relevance of the answers<\/strong> and this requires a special understanding of medical language. Finally, the detection of pharmacovigilance cases and the consideration of drug safety information<\/strong> are a central axis of this type of use.<\/p>

In addition to the respect of these specificities, an evaluation of the chatbot's effectiveness and relevance is essential<\/strong> to facilitate its adoption by users. However, a review of the literature showed us that only a very limited number of evaluations have been conducted on this type of tool. For example, in June-July 2018, Sanofi conducted, with the startup Kap Code, a pilot test of functionalities<\/strong> with a group of physicians, to determine the acceptability of a chatbot and its relevance<\/strong> in the health field. Thus, three essential criteria for evaluation<\/strong> effective of a chatbot in health have been highlighted: verification of the reliability of the answers, the use of the chatbot and the medical service rendered<\/strong>.<\/p>

Through research conducted on healthcare chatbots and a first feedback on the evaluation of healthcare chatbots, this white paper shows that, even if these tools still need to gain in maturity, they will be brought to integrate into the medical world<\/strong> without replacing the human dimension. Designed with respect to health ethics, chatbots can help improve the dissemination of information<\/strong> with patients and participate in the adaptation of the habitat<\/strong> in the context of home care.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t<\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\tRead the full white paper<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\tLearn more about digital transformation<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

Following the development of a healthcare chatbot, Sanofi, Orange Healthcare and Kap Code have co-written a white paper on healthcare chatbots.<\/p>","protected":false},"author":4,"featured_media":11524,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"default","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[26],"tags":[19,106,48],"class_list":["post-8389","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-transformation-digitale","tag-chatbot","tag-collaboration","tag-livre-blanc"],"_links":{"self":[{"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/posts\/8389","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/comments?post=8389"}],"version-history":[{"count":3,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/posts\/8389\/revisions"}],"predecessor-version":[{"id":14704,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/posts\/8389\/revisions\/14704"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/media\/11524"}],"wp:attachment":[{"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/media?parent=8389"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/categories?post=8389"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kapcode.fr\/en\/wp-json\/wp\/v2\/tags?post=8389"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}