scholarly journals Conversational agents in healthcare: a systematic review

2018 ◽  
Vol 25 (9) ◽  
pp. 1248-1258 ◽  
Author(s):  
Liliana Laranjo ◽  
Adam G Dunn ◽  
Huong Ly Tong ◽  
Ahmet Baki Kocaballi ◽  
Jessica Chen ◽  
...  

Abstract Objective Our objective was to review the characteristics, current applications, and evaluation measures of conversational agents with unconstrained natural language input capabilities used for health-related purposes. Methods We searched PubMed, Embase, CINAHL, PsycInfo, and ACM Digital using a predefined search strategy. Studies were included if they focused on consumers or healthcare professionals; involved a conversational agent using any unconstrained natural language input; and reported evaluation measures resulting from user interaction with the system. Studies were screened by independent reviewers and Cohen’s kappa measured inter-coder agreement. Results The database search retrieved 1513 citations; 17 articles (14 different conversational agents) met the inclusion criteria. Dialogue management strategies were mostly finite-state and frame-based (6 and 7 conversational agents, respectively); agent-based strategies were present in one type of system. Two studies were randomized controlled trials (RCTs), 1 was cross-sectional, and the remaining were quasi-experimental. Half of the conversational agents supported consumers with health tasks such as self-care. The only RCT evaluating the efficacy of a conversational agent found a significant effect in reducing depression symptoms (effect size d = 0.44, p = .04). Patient safety was rarely evaluated in the included studies. Conclusions The use of conversational agents with unconstrained natural language input capabilities for health-related purposes is an emerging field of research, where the few published studies were mainly quasi-experimental, and rarely evaluated efficacy or safety. Future studies would benefit from more robust experimental designs and standardized reporting. Protocol Registration The protocol for this systematic review is registered at PROSPERO with the number CRD42017065917.

Author(s):  
Diana Pérez-Marín ◽  
Antonio Boza

Pedagogic Conversational Agents are computer applications that can interact with students in natural language. They have been used with satisfactory results on the instruction of several domains. The authors believe that they could also be useful for the instruction of Secondary Physics and Chemistry Education. Therefore, in this paper, the authors present a procedure to create an agent for that domain. First, teachers have to introduce the exercises with their correct answers. Secondly, students will be presented the exercises, and if the students know the answer, and if it is correct, more difficult exercises will be presented. Otherwise, step-by-step natural language support will be provided to guide the student towards the solution. It is the authors’ hypothesis that this innovative teaching method will be satisfactory and useful for teachers and students, and that by following the procedure more computer programmers can be encouraged to develop agents for other domains to be used by teachers and students at class.


2020 ◽  
pp. 070674372096642
Author(s):  
Aditya Nrusimha Vaidyam ◽  
Danny Linggonegoro ◽  
John Torous

Objective: The need for digital tools in mental health is clear, with insufficient access to mental health services. Conversational agents, also known as chatbots or voice assistants, are digital tools capable of holding natural language conversations. Since our last review in 2018, many new conversational agents and research have emerged, and we aimed to reassess the conversational agent landscape in this updated systematic review. Methods: A systematic literature search was conducted in January 2020 using the PubMed, Embase, PsychINFO, and Cochrane databases. Studies included were those that involved a conversational agent assessing serious mental illness: major depressive disorder, schizophrenia spectrum disorders, bipolar disorder, or anxiety disorder. Results: Of the 247 references identified from selected databases, 7 studies met inclusion criteria. Overall, there were generally positive experiences with conversational agents in regard to diagnostic quality, therapeutic efficacy, or acceptability. There continues to be, however, a lack of standard measures that allow ease of comparison of studies in this space. There were several populations that lacked representation such as the pediatric population and those with schizophrenia or bipolar disorder. While comparing 2018 to 2020 research offers useful insight into changes and growth, the high degree of heterogeneity between all studies in this space makes direct comparison challenging. Conclusions: This review revealed few but generally positive outcomes regarding conversational agents’ diagnostic quality, therapeutic efficacy, and acceptability, which may augment mental health care. Despite this increase in research activity, there continues to be a lack of standard measures for evaluating conversational agents as well as several neglected populations. We recommend that the standardization of conversational agent studies should include patient adherence and engagement, therapeutic efficacy, and clinician perspectives.


2020 ◽  
Vol 34 (10) ◽  
pp. 13710-13711
Author(s):  
Billal Belainine ◽  
Fatiha Sadat ◽  
Hakim Lounis

Chatbots or conversational agents have enjoyed great popularity in recent years. They surprisingly perform sensitive tasks in modern societies. However, despite the fact that they offer help, support, and fellowship, there is a task that is not yet mastered: dealing with complex emotions and simulating human sensations. This research aims to design an architecture for an emotional conversation agent for long-text conversations (multi-turns). This agent is intended to work in areas where the analysis of users feelings plays a leading role. This work refers to natural language understanding and response generation.


2021 ◽  
Vol 10 (2) ◽  
pp. 358-369
Author(s):  
Suhendra Agung Wibowo ◽  
Muhammad Amin ◽  
Laily Hidayati

Background: Tuberculosis can cause psychological disorders in a person. Spiritual approaches can be used to improve coping strategies to suppress stress symptoms that arise. Objective: The purpose of this study is to describe the psychospiritual conditions, stress and coping strategies that occur in patients with tuberculosis. Design: The research design uses systematic review based on PRISMA checklist. Data Sources: Using three databases; Scopus, Science Direct and EBSCO. The search was conducted from January to March 2021. The keyword “tuberculosis” OR “pulmonary TB’ OR “psychology” OR “spiritual” OR “stress” OR “coping strategy” was used in this systematic review with journal articles, 2016-2021 publication years and English as searching limitation. Review Methods: JBI Critical Appraisal Tool used to assess the quality of the articles and PRISMA checklist used as a guideline to filter articles. Results: 10 articles were obtained according to the inclusion criteria. The results of the analysis showed 7 articles using a cross sectional design, 2 quasi-experimental, and 1 qualitative study. The number of samples with a cross-sectional design ranged from 45 to 1,342, while articles with a quasi-experimental, qualitative and comparative study design had 32, 15 and 78 patients with pulmonary TB as respondents. Almost all of the psychological conditions in pulmonary TB patients experience stress and coping disorders. The results of the analysis show that spirituality can be used to improve the coping strategies used so as to suppress the stress symptoms that arise. Conclusion: Psychospiritual strategies can be used as a way to improve the coping of TB sufferers and reduce the stress they experience.


Author(s):  
Kim ◽  
Yoo

This systematic review aimed to examine the associations between health-related outcomes and the built environment (BE) characteristics of compact metropolitan cities in Korea using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. Searching the three Korean academic databases and PubMed, two independent reviewers identified 27 empirical articles published between 2011 and 2016. Data extracted for review included the study characteristics, the variables and measurement methods related to the BE and health-related outcomes, and the findings on the associations between the BE characteristics and health-related outcomes. Vote counting was used to assess the consistency of associations and the direction of associations between the BE characteristics and health-related outcomes. All of the reviewed studies used cross-sectional designs. The objective BE qualities were commonly examined. The BE characteristics associated with health-related outcomes in the reviewed articles included land use, street environment, transportation infrastructure, green and open spaces, and neighborhood facilities. Street environment, transportation infrastructure, and green and open spaces had consistent positive associations with physical health. Mixed land use and neighborhood facilities, however, had inconsistent associations with physical health. Generally, insufficient findings were reported in the association between the BE characteristics and mental and social health. The accessibility of the BE in a compact urban environment was the prominent attribute related to health promotion, health challenges, and health equity. An international comparative analysis of compact cities with different urban contexts and scale is required. Interdisciplinary urban health strategies are recommended based on the associations between the BE characteristics and health-related outcomes.


2019 ◽  
Author(s):  
Omid Fakheran ◽  
Zahra Saied-Moallemi ◽  
Abbasali Khademi

Abstract BACKGROUND The impact of diseases on psychosocial well-being or the normal function of a person has been commonly defined as health-related quality of life .High prevalence of Dental and periodontal problems during gestation period may have a negative effect on oral-health-related quality of life (OHRQoL) in pregnant and postpartum women. OBJECTIVE This systematic review aims to perform a quality assessment and to give a critical overview of the current research available on OHRQoL in pregnant and post-partum women. STUDY DESIGN A systematic search strategy was applied in PubMed, MEDLINE, Cochrane Library, Web of Science, ClinicalTrials.gov, Google Scholar and Scopus from inception until December 2018. For this systemic review all original and peer-reviewed human studies which investigated OHRQoL of women during pregnancy or post- partum period were searched. Studies were screened on title and consecutively on abstract for relevance by 2 independent investigators. Methodological quality was assessed using modified items recommended by the Newcastle–Ottawa Scale for observational studies. RESULTS In all, 8 studies regarding the assessment of OHRQoL in pregnant woman were included. All of the included studies had cross-sectional design. Meta-analysis was not possible due to heterogeneity on key aspects among the included studies. Thus, the data from the studies were evaluated qualitatively. The overall risk of bias of the included studies was low. CONCLUSION The main conclusion of this review is that the presence of signs and symptoms of dental and gingival disease negatively affects the self-perception of OHRQoL in pregnant women. The most affected domains of OHRQoL in pregnant women were related to mental and psychological discomfort followed by physical and functional problems. Considering that the available evidence is limited to cross-sectional design, longitudinal studies are needed to investigate the impacts of oral health status during pregnancy.


2021 ◽  
Vol 3 (1) ◽  
pp. 34-43
Author(s):  
Erasto Vitus Mbugi ◽  
Alfred Said Sife ◽  
Mboni Ruzegea ◽  
Grace Emmanuel Peter Msoffe ◽  
Bestina Daniel ◽  
...  

Introduction: Neem tree parts such as leaves, stem barks, and roots are known to have some medicinal values in both humans and animals. However, the evidence is scattered and vary with populations and regions. This systematic review sought to explore the effectiveness of neem as a therapeutic and prophylactic agent against malaria. Methodology: The systematic review examined the effectiveness of neem using the pre-registered review protocol and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. The Population Intervention Comparator Outcome (PICO) question was: “What is the effectiveness of neem (Azadirachta indica) when used as a therapeutic and prophylactic agent for malaria infection?” It included all cross-sectional survey studies, qualitative studies, case-control studies, randomised controlled trials, quasi-experimental studies, and cohort studies with or without comparison groups. Studies that had both children and adult patients who were diagnosed with malaria were included in the survey. Malaria patients using traditional medications other than neem as well as those who did not use neem were excluded from this study. The search for articles, screening, and synthesis were conducted using the Rayyan software. Results: Out of the total 1089 articles retrieved, only 3 fitted the inclusion criteria, 1 article could not be retrieved. A narrative synthesis was therefore done on 2 final research articles that were retrievable. The pooled evidence shows that Azadirachta indica is effective against malaria. The medicinal effects are more on symptoms and curbing development to clinical disease than ant parasitic effects. Conclusion: Neem is potential traditional medicine for malaria symptoms’ treatment, but evidence on ant parasitic effects is still not conclusive. The study recommends further primary studies to enhance the power of results to further recommend this plant for the prevention of or treatment of malaria symptoms.


10.2196/18839 ◽  
2020 ◽  
Vol 22 (7) ◽  
pp. e18839
Author(s):  
Debaleena Chattopadhyay ◽  
Tengteng Ma ◽  
Hasti Sharifi ◽  
Pamela Martyn-Nemeth

Background Virtual humans (VH) are computer-generated characters that appear humanlike and simulate face-to-face conversations using verbal and nonverbal cues. Unlike formless conversational agents, like smart speakers or chatbots, VH bring together the capabilities of both a conversational agent and an interactive avatar (computer-represented digital characters). Although their use in patient-facing systems has garnered substantial interest, it is unknown to what extent VH are effective in health applications. Objective The purpose of this review was to examine the effectiveness of VH in patient-facing systems. The design and implementation characteristics of these systems were also examined. Methods Electronic bibliographic databases were searched for peer-reviewed articles with relevant key terms. Studies were included in the systematic review if they designed or evaluated VH in patient-facing systems. Of the included studies, studies that used a randomized controlled trial to evaluate VH were included in the meta-analysis; they were then summarized using the PICOTS framework (population, intervention, comparison group, outcomes, time frame, setting). Summary effect sizes, using random-effects models, were calculated, and the risk of bias was assessed. Results Among the 8,125 unique records identified, 53 articles describing 33 unique systems, were qualitatively, systematically reviewed. Two distinct design categories emerged — simple VH and VH augmented with health sensors and trackers. Of the 53 articles, 16 (26 studies) with 44 primary and 22 secondary outcomes were included in the meta-analysis. Meta-analysis of the 44 primary outcome measures revealed a significant difference between intervention and control conditions, favoring the VH intervention (SMD = .166, 95% CI .039-.292, P=.012), but with evidence of some heterogeneity, I2=49.3%. There were more cross-sectional (k=15) than longitudinal studies (k=11). The intervention was delivered using a personal computer in most studies (k=18), followed by a tablet (k=4), mobile kiosk (k=2), head-mounted display (k=1), and a desktop computer in a community center (k=1). Conclusions We offer evidence for the efficacy of VH in patient-facing systems. Considering that studies included different population and outcome types, more focused analysis is needed in the future. Future studies also need to identify what features of virtual human interventions contribute toward their effectiveness.


2019 ◽  
Vol 35 (2) ◽  
pp. 397-408 ◽  
Author(s):  
Watinee Kunpeuk ◽  
William Spence ◽  
Sirinya Phulkerd ◽  
Rapeepong Suphanchaimat ◽  
Siriwan Pitayarangsarit

Abstract Community gardening has been widely recognized as a multicomponent approach that has affected a broad range of health and well-being outcomes. The objective of this study was to investigate the association between community gardening and nutrition and physical health among adults. A systematic review and meta-analysis were conducted. Five electronic databases were searched systematically. Quality of included studies was appraised by several quality assessment tools related to the study design of each included article. Evidence from 19 articles was included (14 cross-sectional studies, 4 quasi-experimental studies and 1 case–control study). Although the majority of included studies appeared to have moderate quality, there existed weaknesses in the methods used, including low response rate and lack of confounder controls. Due to diversity in the measurement units, only body mass index (BMI) data could be pooled to perform meta-analysis. The results suggest that gardening had a significantly positive effect on BMI reduction. Subgroup analysis showed that quasi-experimental and case–control studies produced greater pooled effect size than those of cross-sectional design. Funnel plot and Egger’s test showed no significant evidence of publication bias. As robust evidence for the effect of community gardening on BMI reduction was found, this intervention should be integrated in health promoting policy to improve population health.


2019 ◽  
pp. 107755871986070 ◽  
Author(s):  
Loretta Hsueh ◽  
Adam T. Hirsh ◽  
Gerardo Maupomé ◽  
Jesse C. Stewart

Although patient–provider language concordance has the potential to reduce health disparities for people with limited English proficiency, no previous work has synthesized this literature. Our systematic review sought to describe the characteristics of studies examining relationships between language concordance and health outcomes, summarize the nature of observed associations, and propose an evidence map and research agenda. A comprehensive search of published articles identified 38 quantitative studies for inclusion. Most studies were cross-sectional, conducted in primary care, concentrated in Western states, and focused on Spanish speakers and physician providers. Results were split between supporting a positive association versus no association of language concordance with patient behaviors, provider behaviors, interpersonal processes of care, and clinical outcomes. Several methodological limitations were identified. Based on these results, we developed an evidence map, identified knowledge gaps, and proposed a research agenda. There is a particular need for quasi-experimental longitudinal studies with well-characterized samples.


Sign in / Sign up

Export Citation Format

Share Document