The Use and Promise of Conversational Agents in Digital Health

Summary Objectives: To describe the use and promise of conversational agents in digital health—including health promotion andprevention—and how they can be combined with other new technologies to provide healthcare at home. Method: A narrative review of recent advances in technologies underpinning conversational agents and their use and potential for healthcare and improving health outcomes. Results: By responding to written and spoken language, conversational agents present a versatile, natural user interface and have the potential to make their services and applications more widely accessible. Historically, conversational interfaces for health applications have focused mainly on mental health, but with an increase in affordable devices and the modernization of health services, conversational agents are becoming more widely deployed across the health system. We present our work on context-aware voice assistants capable of proactively engaging users and delivering health information and services. The proactive voice agents we deploy, allow us to conduct experience sampling in people's homes and to collect information about the contexts in which users are interacting with them. Conclusion: In this article, we describe the state-of-the-art of these and other enabling technologies for speech and conversation and discuss ongoing research efforts to develop conversational agents that “live” with patients and customize their service offerings around their needs. These agents can function as ‘digital companions’ who will send reminders about medications and appointments, proactively check in to gather self-assessments, and follow up with patients on their treatment plans. Together with an unobtrusive and continuous collection of other health data, conversational agents can provide novel and deeply personalized access to digital health care, and they will continue to become an increasingly important part of the ecosystem for future healthcare delivery.

Download Full-text

Effect of Speech Recognition on Problem Solving and Recall in Consumer Digital Health Tasks: Controlled Laboratory Experiment (Preprint)

10.2196/preprints.14827 ◽

2019 ◽

Author(s):

Jessica Chen ◽

David Lyell ◽

Liliana Laranjo ◽

Farah Magrabi

Keyword(s):

Speech Recognition ◽

Problem Solving ◽

Cognitive Load ◽

Language Processing ◽

Digital Health ◽

Task Completion ◽

Consumer Health ◽

Conversational Agents ◽

Complex Tasks ◽

Health Applications

BACKGROUND Recent advances in natural language processing and artificial intelligence have led to widespread adoption of speech recognition technologies. In consumer health applications, speech recognition is usually applied to support interactions with conversational agents for data collection, decision support, and patient monitoring. However, little is known about the use of speech recognition in consumer health applications and few studies have evaluated the efficacy of conversational agents in the hands of consumers. In other consumer-facing tools, cognitive load has been observed to be an important factor affecting the use of speech recognition technologies in tasks involving problem solving and recall. Users find it more difficult to think and speak at the same time when compared to typing, pointing, and clicking. However, the effects of speech recognition on cognitive load when performing health tasks has not yet been explored. OBJECTIVE The aim of this study was to evaluate the use of speech recognition for documentation in consumer digital health tasks involving problem solving and recall. METHODS Fifty university staff and students were recruited to undertake four documentation tasks with a simulated conversational agent in a computer laboratory. The tasks varied in complexity determined by the amount of problem solving and recall required (simple and complex) and the input modality (speech recognition vs keyboard and mouse). Cognitive load, task completion time, error rate, and usability were measured. RESULTS Compared to using a keyboard and mouse, speech recognition significantly increased the cognitive load for complex tasks (Z=–4.08, P<.001) and simple tasks (Z=–2.24, P=.03). Complex tasks took significantly longer to complete (Z=–2.52, P=.01) and speech recognition was found to be overall less usable than a keyboard and mouse (Z=–3.30, P=.001). However, there was no effect on errors. CONCLUSIONS Use of a keyboard and mouse was preferable to speech recognition for complex tasks involving problem solving and recall. Further studies using a broader variety of consumer digital health tasks of varying complexity are needed to investigate the contexts in which use of speech recognition is most appropriate. The effects of cognitive load on task performance and its significance also need to be investigated.

Download Full-text

Symposium: Advances in Heart Failure Treatment From Mechanical Cardiac Support to Heart Transplant: A Guide for Sonographers

Journal of Diagnostic Medical Sonography ◽

10.1177/8756479317697953 ◽

2017 ◽

Vol 33 (4) ◽

pp. 333-345

Author(s):

Rhonda Coleman ◽

Lou Mitchell ◽

Lenora Eberhart ◽

David E. Langholz

Keyword(s):

Heart Failure ◽

New Technologies ◽

Treatment Options ◽

Ventricular Assist ◽

Bridge To Transplant ◽

Advanced Therapies ◽

Limited Experience ◽

Treatment Plans

Advances in cardiac sonography have made it an essential tool for physicians in detection, surveillance, and treatment of patients with advanced heart failure (HF). Echocardiographic examinations are often pivotal in assisting physicians develop treatment plans. The Food and Drug Administration (FDA) approved the HeartMate II (HMII) ventricular assist device (VAD) for bridge to transplant (BTT) in 2008. Since then, there has been the addition of many devices and treatment options for these patients. Sonographers and vascular technologists can be expected to encounter increasing numbers of long-term VAD patients in facilities with limited experience with these devices. Cardiac sonographers are in a key position to assist physicians in the care of these patients such that data generated assist with the selection of advanced therapies or as part of a patient’s follow-up care. This article provides a review of these new technologies along with practical considerations for sonographers.

Download Full-text

Role reconfiguration: what ethnographic studies tell us about the implications of technological change for work and collaboration in healthcare

BMJ Leader ◽

10.1136/leader-2020-000224 ◽

2021 ◽

pp. leader-2020-000224

Author(s):

Heloise Agreli ◽

Ruthanne Huising ◽

Marina Peduzzi

Keyword(s):

Technological Change ◽

Technology Implementation ◽

Health Informatics ◽

New Technologies ◽

Digital Health ◽

New Technology ◽

Healthcare Delivery ◽

Leadership Challenges ◽

Health Occupations ◽

Ethnographic Studies

New technologies including digital health and robotics are driving the evolution of healthcare. At the same time, healthcare systems are transitioning from a multiprofessional model approach of healthcare delivery to an interprofessional model. The concurrence of these two trends may represent an opportunity for leaders in healthcare because both require renegotiation of the complex division of work and enhanced interdependency. This review examines how the introduction of new technologies alters the role boundaries of occupations and interdependencies among health occupations. Based on a scoping review of ethnographic studies of technology implementation in a variety of contexts (from primary care to operating room) and of diverse technologies (from health informatics systems to robotics), we develop the concept of role reconfiguration to capture simultaneous adjustments of multiple, interdependent roles during technological change. Ethnographic and qualitative studies provide rich, detailed accounts of what people actually do and how their work and role is changed (or not) when a new technology arrives. Through a synthesis of these studies, we develop a typology of four types of role reconfiguration: negotiation, clarification, enlargement and restriction. We discuss leadership challenges in managing role reconfiguration and formulate four leadership priorities. We suggest that leaders: redesign roles proactively, paying attention to interdependencies; offer opportunities for collective learning about new technologies; ensure that knowledge of new technologies is distributed across roles and prepare to address resistance.

Download Full-text

Comparing the Perception of Privacy for Medical Devices and Devices With Medical Functionality

International Journal of Privacy and Health Information Management ◽

10.4018/ijphim.2020010103 ◽

2020 ◽

Vol 8 (1) ◽

pp. 52-69

Author(s):

Florian Kaiser ◽

Marcus Wiens ◽

Frank Schultmann

Keyword(s):

Medical Devices ◽

Data Privacy ◽

Digital Health ◽

Healthcare Delivery ◽

Health Data ◽

Medical Product ◽

Current State ◽

Significant Difference ◽

Perceived Security ◽

Health Applications

Health data privacy is essential for the acceptance of digital health applications. Hence, privacy is a precondition for future healthcare delivery. This study compares the perception of the current state of health data privacy in officially registered and therefore regulated health applications (medical devices) according to the medical product act as well as non-regulated health applications (devices with medical functionality) in Germany. To this end, an empirical study based on a questionnaire is conducted (n=53). The results show that there are significant differences between the analysed health applications with respect to perceived data privacy. In particular, there is a significant difference of the levels of perceived security between both types of devices. Low privacy for one type of device may hamper trust in digital health applications in general as there are spill-over effects regarding the perception of data privacy. Thus, the study suggests that legal regulations for devices with medical functionality should be adapted to protect health data adequately.

Download Full-text

A Method for Machine Learning Generation of Realistic Synthetic Datasets for Validating Healthcare Applications

10.1101/2021.02.11.21250741 ◽

2021 ◽

Author(s):

Theodoros N. Arvanitis ◽

Sean White ◽

Stuart Harrison ◽

Rupert Chaplin ◽

George Despotou

Keyword(s):

New Technologies ◽

Digital Health ◽

Synthetic Dataset ◽

Statistical Characteristics ◽

Categorical Variables ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Clinical Scenarios ◽

Synthetic Datasets ◽

Health Applications

ABSTRACTBackgroundDigital health applications can improve quality and effectiveness of healthcare, by offering a number of tools to patients, professionals, and the healthcare system. Introduction of new technologies is not without risk, and digital health applications are often considered a medical device. Assuring their safe operation requires, amongst others, clinical validation, which needs large datasets to test their application in realistic clinical scenarios. Access to such datasets is challenging, due to concerns about patient privacy. Development of synthetic datasets, which will be sufficiently realistic to test digital applications, is seen as a potential alternative, enabling their deployment.ObjectiveThe aim of work was to develop a method for the generation of realistic synthetic datasets, statistically equivalent to real clinical datasets, and demonstrate that Generative Adversarial Network based approach is fit for purpose.MethodA generative adversarial network was implemented and trained, in a series of six experiments, using numerical and categorical variables from three clinically relevant datasets, including ICD-9 and laboratory codes from the MIMIC III dataset. A number of contextual steps provided the success criteria for the synthetic dataset.ResultsThe approach created a synthetic dataset that exhibits very similar statistical characteristics with the real dataset. Pairwise association of variables is very similar. A high degree of Jaccard similarity and a successful K-S test further support this.ConclusionsThe proof of concept of generating realistic synthetic datasets was successful, with the approach showing promise for further work.

Download Full-text

Effect of Speech Recognition on Problem Solving and Recall in Consumer Digital Health Tasks: Controlled Laboratory Experiment

Journal of Medical Internet Research ◽

10.2196/14827 ◽

2020 ◽

Vol 22 (6) ◽

pp. e14827

Author(s):

Jessica Chen ◽

David Lyell ◽

Liliana Laranjo ◽

Farah Magrabi

Keyword(s):

Speech Recognition ◽

Problem Solving ◽

Cognitive Load ◽

Language Processing ◽

Digital Health ◽

Task Completion ◽

Consumer Health ◽

Conversational Agents ◽

Complex Tasks ◽

Health Applications

Background Recent advances in natural language processing and artificial intelligence have led to widespread adoption of speech recognition technologies. In consumer health applications, speech recognition is usually applied to support interactions with conversational agents for data collection, decision support, and patient monitoring. However, little is known about the use of speech recognition in consumer health applications and few studies have evaluated the efficacy of conversational agents in the hands of consumers. In other consumer-facing tools, cognitive load has been observed to be an important factor affecting the use of speech recognition technologies in tasks involving problem solving and recall. Users find it more difficult to think and speak at the same time when compared to typing, pointing, and clicking. However, the effects of speech recognition on cognitive load when performing health tasks has not yet been explored. Objective The aim of this study was to evaluate the use of speech recognition for documentation in consumer digital health tasks involving problem solving and recall. Methods Fifty university staff and students were recruited to undertake four documentation tasks with a simulated conversational agent in a computer laboratory. The tasks varied in complexity determined by the amount of problem solving and recall required (simple and complex) and the input modality (speech recognition vs keyboard and mouse). Cognitive load, task completion time, error rate, and usability were measured. Results Compared to using a keyboard and mouse, speech recognition significantly increased the cognitive load for complex tasks (Z=–4.08, P<.001) and simple tasks (Z=–2.24, P=.03). Complex tasks took significantly longer to complete (Z=–2.52, P=.01) and speech recognition was found to be overall less usable than a keyboard and mouse (Z=–3.30, P=.001). However, there was no effect on errors. Conclusions Use of a keyboard and mouse was preferable to speech recognition for complex tasks involving problem solving and recall. Further studies using a broader variety of consumer digital health tasks of varying complexity are needed to investigate the contexts in which use of speech recognition is most appropriate. The effects of cognitive load on task performance and its significance also need to be investigated.

Download Full-text

Digital Health for Supporting Precision Medicine in Pediatric Endocrine Disorders: Opportunities for Improved Patient Care

Frontiers in Pediatrics ◽

10.3389/fped.2021.715705 ◽

2021 ◽

Vol 9 ◽

Author(s):

Luis Fernandez-Luque ◽

Abdullah Al Herbish ◽

Riyad Al Shammari ◽

Jesús Argente ◽

Bassam Bin-Abbas ◽

...

Keyword(s):

Precision Medicine ◽

New Technologies ◽

Digital Health ◽

Genomic Medicine ◽

Healthcare Delivery ◽

Digital Technologies ◽

Endocrine Disorders ◽

Growth Disorders ◽

Pediatric Endocrinology ◽

Obesity And Diabetes

Digitalization of healthcare delivery is rapidly fostering development of precision medicine. Multiple digital technologies, known as telehealth or eHealth tools, are guiding individualized diagnosis and treatment for patients, and can contribute significantly to the objectives of precision medicine. From a basis of “one-size-fits-all” healthcare, precision medicine provides a paradigm shift to deliver a more nuanced and personalized approach. Genomic medicine utilizing new technologies can provide precision analysis of causative mutations, with personalized understanding of mechanisms and effective therapy. Education is fundamental to the telehealth process, with artificial intelligence (AI) enhancing learning for healthcare professionals and empowering patients to contribute to their care. The Gulf Cooperation Council (GCC) region is rapidly implementing telehealth strategies at all levels and a workshop was convened to discuss aspirations of precision medicine in the context of pediatric endocrinology, including diabetes and growth disorders, with this paper based on those discussions. GCC regional investment in AI, bioinformatics and genomic medicine, is rapidly providing healthcare benefits. However, embracing precision medicine is presenting some major new design, installation and skills challenges. Genomic medicine is enabling precision and personalization of diagnosis and therapy of endocrine conditions. Digital education and communication tools in the field of endocrinology include chatbots, interactive robots and augmented reality. Obesity and diabetes are a major challenge in the GCC region and eHealth tools are increasingly being used for management of care. With regard to growth failure, digital technologies for growth hormone (GH) administration are being shown to enhance adherence and response outcomes. While technical innovations become more affordable with increasing adoption, we should be aware of sustainability, design and implementation costs, training of HCPs and prediction of overall healthcare benefits, which are essential for precision medicine to develop and for its objectives to be achieved.

Download Full-text

Empirically-based Acceptance Research on Digital Technologies in Medicine (Preprint)

10.2196/preprints.13472 ◽

2019 ◽

Author(s):

Sabur Safi ◽

Gerhard Danzer ◽

Kurt J.G. Schmailzl

Keyword(s):

Health Care ◽

Technology Acceptance ◽

New Technologies ◽

Digital Health ◽

Empirical Evaluation ◽

Digital Technologies ◽

Sociodemographic Factors ◽

Health Care Sector ◽

Health Care Applications ◽

Health Applications

BACKGROUND In recent years, the health care sector has shown increased interest in digital technologies. Digital health applications include e-health, mobile health, telemedicine, big data, and health apps. Acceptance and sustainability play a considerable, although not yet sufficiently well known, role for innovative health care applications. The acceptance of new technologies is measured by using the Technology Acceptance Model, which was applied to health care in this study. OBJECTIVE We conducted an up-to-date empirical evaluation of the spread of and experience with new digital technologies in the medical sector. METHODS The study was based on the EPatient Survey, considered one of the most comprehensive online surveys in the German-speaking region. The survey used standardized questionnaires to provide information about the prevalence, impact, and development of digital health applications in a study sample of 9621 individuals. The average age of respondents in the survey was 59.7 years. The acceptance of new technologies was analyzed further by the identification of the different health application types, evaluation of sociodemographic data, evaluation of the question items in the EPatient Survey, and discussion of the benefits of online health records. RESULTS The results of the questionnaires revealed an increasing tendency of respondents to accept digital health care. This was a representative survey, the findings of which can be applied to the whole of Germany. Nevertheless, the respondents differed clearly regarding their acceptance of digital technologies. This tendency was especially noticeable among men > 60 years old and women < 40 years old. Acceptance of digital applications differs significantly depending on sex. Although men tend to be more likely to accept technical products, women < 40 years old tend to prefer coaching and consultation applications. Acceptance must be differentiated according to sociodemographic factors and to the respective applications, which vary. The respondents were 60 years old on average, with a majority between 44 and 76 years old. It would be interesting to survey users between the ages of 25 and 45 whose willingness to use online applications can generally be rated as high. CONCLUSIONS Widespread acceptance of applications in the health care sector has great potential; however, issues and challenges among respondents must be overcome.Therefore, it is important to integrate governance to appropriately condition the spread and acceptance of health applications.

Download Full-text

Sludge minimization by disintegration at different wastewater treatment plants

Water Practice & Technology ◽

10.2166/wpt.2008.010 ◽

2008 ◽

Vol 3 (1) ◽

Author(s):

Luchien Luning ◽

Paul Roeleveld ◽

Victor W.M. Claessen

Keyword(s):

Organic Matter ◽

Wastewater Treatment ◽

Anaerobic Digestion ◽

Sewage Sludge ◽

New Technologies ◽

Wastewater Treatment Plants ◽

Treatment Plant ◽

Biological Degradation ◽

Ongoing Research ◽

Sludge Minimization

In recent years new technologies have been developed to improve the biological degradation of sewage sludge by anaerobic digestion. The paper describes the results of a demonstration of ultrasonic disintegration on the Dutch Wastewater Treatment Plant (WWTP) Land van Cuijk. The effect on the degradation of organic matter is presented, together with the effect on the dewatering characteristics. Recommendations are presented for establishing research conditions in which the effect of sludge disintegration can be determined in a more direct way that is less sensitive to changing conditions in the operation of the WWTP. These recommendations have been implemented in the ongoing research in the Netherlands supported by the National Institute for wastewater research (STOWA).

Download Full-text

Healthcare apps on smartphones available in Brazil: a preliminary classification (Preprint)

10.2196/preprints.20795 ◽

2020 ◽

Author(s):

André De Faria Pereira Neto ◽

Leticia Barbosa ◽

Rodolfo Paolucci

Keyword(s):

Health Promotion ◽

Disease Prevention ◽

Digital Health ◽

Disease Process ◽

World Health ◽

Computing Device ◽

Care Treatment ◽

Wide Range ◽

The World ◽

Health Applications

UNSTRUCTURED Billions of people in the world own a smartphone. It is a low-cost, portable computing device with countless features, among which applications stand out, which are programs or software developed to meet a specific goal. A wide range of applications available ranging from entertainment and personal organization to work and education is available currently. It is a vast and profitable market. Health applications have been a means of intervention for different areas, including chronic diseases, epidemics, and health emergencies. A recently published paper in the journal with the highest impact factor in Digital Health (“Journal of Medical Internet Research”) proposes a classification of health applications. This study performs a critical analysis of this organization and presents other sort criteria. This paper also presents and analyzes the “Meu Info Saúde” (“My Health Info”) app – a pioneering government initiative focused on primary care launched by the Oswaldo Cruz Foundation. The application classification proposal that will be presented builds on the intervention strategies in the health-disease process, namely: “Health Promotion”, “Disease Prevention” and “Care, Treatment and Rehabilitation”, as defined by official documents such as the World Health Organization and the Centers for Disease Control and Prevention. Most applications present in the sample are of private and foreign origin, free to download, but with a display of ads or the sale of products and services. The sampled applications were classified as “Health Promotion”, and some applications have also been categorized as “Disease Prevention” or “Care, Treatment or Rehabilitation” because they have multiple functionalities. The applications identified as “Health Promotion” focused only on individuals’ lifestyle and their increased autonomy and self-care management capacity. From this perspective, the apps analyzed in this paper differ from the “Meu Info-Saúde” application developed at Fiocruz.

Download Full-text