scholarly journals The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review (Preprint)

2020 ◽  
Author(s):  
Madison Milne-Ives ◽  
Caroline de Cock ◽  
Ernest Lim ◽  
Melissa Harper Shehadeh ◽  
Nick de Pennington ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Health Care ◽  
Language Processing ◽  
Health Care Services ◽  
Interactive Voice Response ◽  
Future Research ◽  
Conversational Agents ◽  
Privacy And Security ◽  
Care Services

BACKGROUND The high demand for health care services and the growing capability of artificial intelligence have led to the development of conversational agents designed to support a variety of health-related activities, including behavior change, treatment support, health monitoring, training, triage, and screening support. Automation of these tasks could free clinicians to focus on more complex work and increase the accessibility to health care services for the public. An overarching assessment of the acceptability, usability, and effectiveness of these agents in health care is needed to collate the evidence so that future development can target areas for improvement and potential for sustainable adoption. OBJECTIVE This systematic review aims to assess the effectiveness and usability of conversational agents in health care and identify the elements that users like and dislike to inform future research and development of these agents. METHODS PubMed, Medline (Ovid), EMBASE (Excerpta Medica dataBASE), CINAHL (Cumulative Index to Nursing and Allied Health Literature), Web of Science, and the Association for Computing Machinery Digital Library were systematically searched for articles published since 2008 that evaluated unconstrained natural language processing conversational agents used in health care. EndNote (version X9, Clarivate Analytics) reference management software was used for initial screening, and full-text screening was conducted by 1 reviewer. Data were extracted, and the risk of bias was assessed by one reviewer and validated by another. RESULTS A total of 31 studies were selected and included a variety of conversational agents, including 14 chatbots (2 of which were voice chatbots), 6 embodied conversational agents (3 of which were interactive voice response calls, virtual patients, and speech recognition screening systems), 1 contextual question-answering agent, and 1 voice recognition triage system. Overall, the evidence reported was mostly positive or mixed. Usability and satisfaction performed well (27/30 and 26/31), and positive or mixed effectiveness was found in three-quarters of the studies (23/30). However, there were several limitations of the agents highlighted in specific qualitative feedback. CONCLUSIONS The studies generally reported positive or mixed evidence for the effectiveness, usability, and satisfactoriness of the conversational agents investigated, but qualitative user perceptions were more mixed. The quality of many of the studies was limited, and improved study design and reporting are necessary to more accurately evaluate the usefulness of the agents in health care and identify key areas for improvement. Further research should also analyze the cost-effectiveness, privacy, and security of the agents. INTERNATIONAL REGISTERED REPORT RR2-10.2196/16934

scholarly journals The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review

10.2196/20346 ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. e20346
Author(s):  
Madison Milne-Ives ◽  
Caroline de Cock ◽  
Ernest Lim ◽  
Melissa Harper Shehadeh ◽  
Nick de Pennington ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Health Care ◽  
Language Processing ◽  
Health Care Services ◽  
Interactive Voice Response ◽  
Future Research ◽  
Conversational Agents ◽  
Privacy And Security ◽  
Care Services

Background The high demand for health care services and the growing capability of artificial intelligence have led to the development of conversational agents designed to support a variety of health-related activities, including behavior change, treatment support, health monitoring, training, triage, and screening support. Automation of these tasks could free clinicians to focus on more complex work and increase the accessibility to health care services for the public. An overarching assessment of the acceptability, usability, and effectiveness of these agents in health care is needed to collate the evidence so that future development can target areas for improvement and potential for sustainable adoption. Objective This systematic review aims to assess the effectiveness and usability of conversational agents in health care and identify the elements that users like and dislike to inform future research and development of these agents. Methods PubMed, Medline (Ovid), EMBASE (Excerpta Medica dataBASE), CINAHL (Cumulative Index to Nursing and Allied Health Literature), Web of Science, and the Association for Computing Machinery Digital Library were systematically searched for articles published since 2008 that evaluated unconstrained natural language processing conversational agents used in health care. EndNote (version X9, Clarivate Analytics) reference management software was used for initial screening, and full-text screening was conducted by 1 reviewer. Data were extracted, and the risk of bias was assessed by one reviewer and validated by another. Results A total of 31 studies were selected and included a variety of conversational agents, including 14 chatbots (2 of which were voice chatbots), 6 embodied conversational agents (3 of which were interactive voice response calls, virtual patients, and speech recognition screening systems), 1 contextual question-answering agent, and 1 voice recognition triage system. Overall, the evidence reported was mostly positive or mixed. Usability and satisfaction performed well (27/30 and 26/31), and positive or mixed effectiveness was found in three-quarters of the studies (23/30). However, there were several limitations of the agents highlighted in specific qualitative feedback. Conclusions The studies generally reported positive or mixed evidence for the effectiveness, usability, and satisfactoriness of the conversational agents investigated, but qualitative user perceptions were more mixed. The quality of many of the studies was limited, and improved study design and reporting are necessary to more accurately evaluate the usefulness of the agents in health care and identify key areas for improvement. Further research should also analyze the cost-effectiveness, privacy, and security of the agents. International Registered Report Identifier (IRRID) RR2-10.2196/16934

scholarly journals Analysis of Facilitators and Barriers to the Delivery of Routine Care during the COVID-19 Global Pandemic: A Systematic Review

Healthcare ◽  
2021 ◽  
Vol 9 (5) ◽  
pp. 528
Author(s):  
Cristian Lieneck ◽  
Brooke Herzog ◽  
Raven Krips
Keyword(s):  
Systematic Review ◽  
Health Care ◽  
Health Care Services ◽  
Care Delivery ◽  
Routine Care ◽  
Future Research ◽  
Healthcare Organizations ◽  
Care Services ◽  
Global Pandemic ◽  
Facilitators And Barriers

The delivery of routine health care during the COVID-19 global pandemic continues to be challenged as public health guidelines and other local/regional/state and other policies are enforced to help prevent the spread of the virus. The objective of this systematic review is to identify the facilitators and barriers affecting the delivery of routine health care services during the pandemic to provide a framework for future research. In total, 32 articles were identified for common themes surrounding facilitators of routine care during COVID-19. Identified constructed in the literature include enhanced education initiatives for parents/patients regarding routine vaccinations, an importance of routine vaccinations as compared to the risk of COVID-19 infection, an enhanced use of telehealth resources (including diagnostic imagery) and identified patient throughput/PPE initiatives. Reviewers identified the following barriers to the delivery of routine care: conservation of medical providers and PPE for non-routine (acute) care delivery needs, specific routine care services incongruent the telehealth care delivery methods, and job-loss/food insecurity. Review results can assist healthcare organizations with process-related challenges related to current and/or future delivery of routine care and support future research initiatives as the global pandemic continues.

scholarly journals The Antecedents and Consequences of Health Care Professional–Patient Online Interactions: Systematic Review

10.2196/13940 ◽  
2019 ◽  
Vol 21 (9) ◽  
pp. e13940 ◽  
Author(s):  
Lili Shang ◽  
Meiyun Zuo ◽  
Dan Ma ◽  
Qinjun Yu
Keyword(s):  
Systematic Review ◽  
Health Care ◽  
Health Care Professionals ◽  
Health Care Services ◽  
Future Research ◽  
Online Interaction ◽  
Health Care Settings ◽  
Online Interactions ◽  
Care Services ◽  
Antecedents And Consequences

Background Online health care services effectively supplement traditional medical treatment. The development of online health care services depends on sustained interactions between health care professionals (HCPs) and patients. Therefore, it is necessary to understand the demands and gains of health care stakeholders in HCP-patient online interactions and determine an agenda for future work. Objective This study aims to present a systematic review of the antecedents and consequences of HCP-patient online interactions. It seeks to reach a better understanding of why HCPs and patients are willing to interact with each other online and what the consequences of HCP-patient online interactions are for health care stakeholders. Based on this, we intend to identify the gaps in existing studies and make recommendations for future research. Methods In accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, a systematic retrieval was carried out from the Web of Science, PubMed, and Scopus electronic databases. The search results were confined to those papers published in English between January 1, 2000 and June 30, 2018. Selected studies were then evaluated for quality; studies that did not meet quality criteria were excluded from further analysis. Findings of the reviewed studies related to our research questions were extracted and synthesized through inductive thematic analysis. Results A total of 8440 records were found after the initial search, 28 papers of which were selected for analysis. Accessibility to HCPs, self-management, and unmet needs were the main triggers for patients to participate in online interaction. For HCPs, patient education, career needs, and self-promotion were the major reasons why they took the online approach. There were several aspects of the consequences of HCP-patient online interactions on health care stakeholders. Consequences for patients included patient empowerment, health promotion, and acquisition of uncertain answers. Consequences for HCPs included social and economic returns, lack of control over their role, and gaining more appointments. HCP-patient online interactions also improved communication efficiency in offline settings and helped managers of online health care settings get a better understanding of patients’ needs. Health care stakeholders have also encountered ethical and legal issues during online interaction. Conclusions Through a systematic review, we sought out the antecedents and consequences of HCP-patient online interactions to understand the triggers for HCPs and patients to participate and the consequences of participating. Potential future research topics are the influences on the chain of online interaction, specifications and principles of privacy design within online health care settings, and roles that sociodemographic and psychological characteristics play. Longitudinal studies and the adoption of text-mining method are worth encouraging. This paper is expected to contribute to the sustained progress of online health care settings.

scholarly journals The Antecedents and Consequences of Health Care Professional–Patient Online Interactions: Systematic Review (Preprint)

2019 ◽  
Author(s):  
Lili Shang ◽  
Meiyun Zuo ◽  
Dan Ma ◽  
Qinjun Yu
Keyword(s):  
Systematic Review ◽  
Health Care ◽  
Health Care Professionals ◽  
Health Care Services ◽  
Future Research ◽  
Online Interaction ◽  
Health Care Settings ◽  
Online Interactions ◽  
Care Services ◽  
Antecedents And Consequences

BACKGROUND Online health care services effectively supplement traditional medical treatment. The development of online health care services depends on sustained interactions between health care professionals (HCPs) and patients. Therefore, it is necessary to understand the demands and gains of health care stakeholders in HCP-patient online interactions and determine an agenda for future work. OBJECTIVE This study aims to present a systematic review of the antecedents and consequences of HCP-patient online interactions. It seeks to reach a better understanding of why HCPs and patients are willing to interact with each other online and what the consequences of HCP-patient online interactions are for health care stakeholders. Based on this, we intend to identify the gaps in existing studies and make recommendations for future research. METHODS In accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, a systematic retrieval was carried out from the Web of Science, PubMed, and Scopus electronic databases. The search results were confined to those papers published in English between January 1, 2000 and June 30, 2018. Selected studies were then evaluated for quality; studies that did not meet quality criteria were excluded from further analysis. Findings of the reviewed studies related to our research questions were extracted and synthesized through inductive thematic analysis. RESULTS A total of 8440 records were found after the initial search, 28 papers of which were selected for analysis. Accessibility to HCPs, self-management, and unmet needs were the main triggers for patients to participate in online interaction. For HCPs, patient education, career needs, and self-promotion were the major reasons why they took the online approach. There were several aspects of the consequences of HCP-patient online interactions on health care stakeholders. Consequences for patients included patient empowerment, health promotion, and acquisition of uncertain answers. Consequences for HCPs included social and economic returns, lack of control over their role, and gaining more appointments. HCP-patient online interactions also improved communication efficiency in offline settings and helped managers of online health care settings get a better understanding of patients’ needs. Health care stakeholders have also encountered ethical and legal issues during online interaction. CONCLUSIONS Through a systematic review, we sought out the antecedents and consequences of HCP-patient online interactions to understand the triggers for HCPs and patients to participate and the consequences of participating. Potential future research topics are the influences on the chain of online interaction, specifications and principles of privacy design within online health care settings, and roles that sociodemographic and psychological characteristics play. Longitudinal studies and the adoption of text-mining method are worth encouraging. This paper is expected to contribute to the sustained progress of online health care settings.

scholarly journals Development of a Natural Language Processing Algorithm to Identify and Evaluate Transgender Patients in Electronic Health Record System

2019 ◽  
Vol 29 (Supp2) ◽  
pp. 441-450 ◽  
Author(s):  
Jesse M. Ehrenfeld ◽  
Keanan Gabriel Gottlieb ◽  
Lauren Brittany Beach ◽  
Shelby E. Monahan ◽  
Daniel Fabbri
Keyword(s):  
Health Care ◽  
Natural Language ◽  
Language Processing ◽  
Health Care Services ◽  
False Positive Rate ◽  
Health Condition ◽  
Record System ◽  
Care Services ◽  
Electronic Health ◽  
Hormone Use

Objective: To create a natural language pro­cessing (NLP) algorithm to identify transgen­der patients in electronic health records.Design: We developed an NLP algorithm to identify patients (keyword + billing codes). Patients were manually reviewed, and their health care services categorized by billing code.Setting: Vanderbilt University Medical CenterParticipants: 234 adult and pediatric trans­gender patientsMain Outcome Measures: Number of transgender patients correctly identified and categorization of health services utilized.Results: We identified 234 transgender pa­tients of whom 50% had a diagnosed men­tal health condition, 14% were living with HIV, and 7% had diabetes. Largely driven by hormone use, nearly half of patients attended the Endocrinology/Diabetes/Me­tabolism clinic. Many patients also attended the Psychiatry, HIV, and/or Obstetrics/Gyne­cology clinics. The false positive rate of our algorithm was 3%.Conclusions: Our novel algorithm correctly identified transgender patients and provided important insights into health care utiliza­tion among this marginalized population. Ethn Dis. 2019;29(Suppl 2): 441-450. doi:10.18865/ed.29.S2.441

Interactive voice response system (IVRS) in health care services

2003 ◽  
Vol 51 (6) ◽  
pp. 277-283 ◽  
Author(s):  
Haeok Lee ◽  
Mary Ellen Friedman ◽  
Peter Cukor ◽  
David Ahern
Keyword(s):  
Health Care ◽  
Health Care Services ◽  
Interactive Voice Response ◽  
Interactive Voice Response System ◽  
Response System ◽  
Care Services ◽  
Voice Response

A Survey on Health Care Services Using Wireless Sensor Networks

2015 ◽  
pp. 132-151
Author(s):  
Sunilkumar S. Manvi ◽  
Manjula R. B.
Keyword(s):  
Health Care ◽  
Heart Disease ◽  
Health Care Services ◽  
Health Centre ◽  
Ambient Assisted Living ◽  
Well Being ◽  
Wireless Sensor ◽  
Future Research ◽  
Care Services ◽  
The Individual

Although the present technology has aided in development of high-technology-based disease detection machines, potential medicines and devices, the well-being of the individual remains a challenge. Human beings are struggling to control diseases such as Parkinson's disease, Alzheimer's disease, asthma, hypertension, insomnia, heart disease, and diabetes due to non-availability of patient's real-time data for comprehensive study and analysis. Smart health centre environments represent the evolutionary developmental step towards intelligent health care. The Wireless Sensor Network (WSN) with pervasive and ubiquitous computing may be a solution for this predicament. WSNs are a key technology for ambient assisted living. The concept of WSN is used to measure the various health parameters like blood pressure, blood clot, allergy, ECG, cholesterol, RBCs, etc. In this chapter, the authors highlight the importance of WSNs with respect to health care services and discuss some of its challenging applications for diseases like Parkinson's, Alzheimer's, asthma, and heart disease. They delineate the challenges that researchers face in this area that may lead to future research.

scholarly journals Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

2020 ◽  
Vol 78 (4) ◽  
pp. 1547-1574
Author(s):  
Sofia de la Fuente Garcia ◽  
Craig W. Ritchie ◽  
Saturnino Luz
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Language Processing ◽  
Future Research ◽  
Original Research ◽  
Speech And Language ◽  
Eligibility Criteria ◽  
Speech And Language Processing

Background: Language is a valuable source of clinical information in Alzheimer’s disease, as it declines concurrently with neurodegeneration. Consequently, speech and language data have been extensively studied in connection with its diagnosis. Objective: Firstly, to summarize the existing findings on the use of artificial intelligence, speech, and language processing to predict cognitive decline in the context of Alzheimer’s disease. Secondly, to detail current research procedures, highlight their limitations, and suggest strategies to address them. Methods: Systematic review of original research between 2000 and 2019, registered in PROSPERO (reference CRD42018116606). An interdisciplinary search covered six databases on engineering (ACM and IEEE), psychology (PsycINFO), medicine (PubMed and Embase), and Web of Science. Bibliographies of relevant papers were screened until December 2019. Results: From 3,654 search results, 51 articles were selected against the eligibility criteria. Four tables summarize their findings: study details (aim, population, interventions, comparisons, methods, and outcomes), data details (size, type, modalities, annotation, balance, availability, and language of study), methodology (pre-processing, feature generation, machine learning, evaluation, and results), and clinical applicability (research implications, clinical potential, risk of bias, and strengths/limitations). Conclusion: Promising results are reported across nearly all 51 studies, but very few have been implemented in clinical research or practice. The main limitations of the field are poor standardization, limited comparability of results, and a degree of disconnect between study aims and clinical applications. Active attempts to close these gaps will support translation of future research into clinical practice.

Sign in / Sign up

Export Citation Format

Share Document