Healthcare ex Machina: Are conversational agents ready for prime time in oncology?

Bibault, Jean‐Emmanuel; Chaix, Benjamin; Nectoux, Pierre; Pienkowski, Arthur; Guillemasé, Arthur; Brouard, Benoît

doi:10.1016/j.ctro.2019.04.002

Cited by 70 publications

(51 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Studies have shown that PDI has a good internal consistency, stability, and validity. PDI items can be grouped into factors that better reflect and predict PD and PTSD: negative emotions (items 1, 2, 3, 5, 6, 8, and 10) and perceived life threat and bodily arousal (items 4,7,9,11,12, and 13) (9). It has also been shown that a PDI score equal or over 14 was predicting full or partial PTSD six-weeks post-injury (10).…”

Section: Introductionmentioning

confidence: 99%

Psychological Distress during the COVID-19 pandemic in France: a national assessment of at-risk populations

Chaix

Delamon

Guillemassé

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background: More than 2.5 billion people in the world are currently in lockdowns to limit the spread of the novel coronavirus disease 2019 . Psychological Distress (PD) and Post-Traumatic Stress Disorder have been reported after traumatic events, but the specific effect of pandemics is not well known. Objectives:The aim of this study was to assess PD in France, a country where COVID-19 had such a dramatic impact that it required a country-wide lockdown. Methods:This study was a survey conducted in France between 31 March 2020 and 7 April 2020. We recruited patients in 4 groups of chatbot users followed for breast cancer, asthma, depression and migraine. We used the Psychological Distress Index (PDI), a validated scale to measure PD during traumatic events, and correlated PD risk with patients' characteristics in order to better identify the one who were the most at-risk. Results:The study included 1771 participants. 91.25% (1616) were female with a mean age of 32.8 years (SD=13,71), 7.96% (141) were male with a mean age of 28.0 years (SD=8,14). In total, 38.06% (674) of the respondents had psychological distress (PDI ≥15). An ANOVA analysis showed that sex (p=0.00132), unemployment (p=7.16x10-6) and depression (p=7.49x10-7) were significantly associated with a higher PDI score. Patients using their smartphone or computer more than one hour a day also had a higher PDI score (p=0.02588).

show abstract

Section: Introductionmentioning

confidence: 99%

Psychological Distress during the COVID-19 pandemic in France: a national assessment of at-risk populations

Chaix

Delamon

Guillemassé

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…But, the authors noted that the few published studies were mainly quasi-experimental, and rarely evaluated efficacy or safety. Bibault et al [9] made the same observation, if chatbots are shown to be effective and safe, they could be prescribed like any drug to improve patient information, monitoring, or treatment adherence. Chaix et al [2] showed that a chatbot designed to help patient with breast cancer could improve medication adherence.…”

Section: Introductionmentioning

confidence: 93%

Vik: A Chatbot to Support Patients with Chronic Diseases

Chaix¹,

Guillemassé²,

Nectoux³

et al. 2020

Health

Self Cite

View full text Add to dashboard Cite

Background: Chatbots are easy to use and simulate a human conversation through text or voice via smartphones or computers. In the field of health, chatbots can improve patient information, monitoring, or treatment adherence. Method: The objective of this article is to describe how a chatbot dedicated to disease monitoring and support of patients can interact with them and how data are exploited to be safe. Results: Wefight designed a chatbot named Vik to empower patients with cancers or chronic diseases and their relatives via personalized text messages. Natural Language Processing models were used. We built several Vik for each disease. Each Vik has its contents, its own NLP model and interacts its way with the patient. Conclusion: Conversational agents may help patients with minor health concerns without seeing a real physician. If the quality of these softwares is not thoroughly assessed, they could be dangerous. If chatbots are effective and safe, they could be prescribed like a drug to improve patient information, monitoring, or treatment adherence.

show abstract

“… 16 That said, a recent review reported that most healthcare applications of chat bots lack sufficient validation of clinical outcomes. 25 This is a crucial step that is needed for these solutions to be safely deployed. 26 Therefore, while these solutions may be useful to scale up patient support for mental health and self-management, any deployed solutions should be closely monitored for performance.…”

Section: Conversational Artificial Intelligencementioning

confidence: 99%