The Development and Use of Chatbots in Public Health: Scoping Review PMC

While healthcare professionals can only attend to one patient at a time, chatbots can engage and assist multiple customers simultaneously without compromising the quality of interaction or information provided. They are conversationalists that run on the rules of machine learning and development with AI technology. One study that stands out is the work of Bonnevie and colleagues [16], who describe the development of Layla, a trusted source of information in contraception and sexual health among a population at higher risk of unintended pregnancy. Layla was designed and developed through community-based participatory research, where the community that would benefit from the chatbot also had a say in its design. Layla demonstrates the potential of AI to empower community-led health interventions.

For example, in the diagnostic report, chatbots could provide links to consumer-friendly and credible information sources to help patients better understand the content of the report [42]. To further understand what caused user dropout, we examined the specific question asked by DoctorBot when a consultation was terminated and how much time users spent on answering those questions. As Table 1 demonstrates, transition questions, such as the ones prompting the user to answer the question again, often led to a termination of chatbot use. Furthermore, many uncompleted conversations occurred when users were asked to provide a detailed account of the symptoms they were experiencing.

1 according to Scopus [18], there was a rapid growth of interest in chatbots especially after the year 2016. Many chatbots were developed for industrial solutions while there is a wide range of less famous chatbots relevant to research and their applications [19]. 2, we briefly present the history of chatbots and highlight the growing interest of the research community. 6, we present the underlying chatbot architecture and the leading platforms for their development.

With regard to health concerns, individuals often have a plethora of questions, both minor and major, that need immediate clarification. A healthcare chatbot can act as a personal health specialist, offering assistance beyond just answering basic questions. In the event of a medical emergency, chatbots can instantly provide doctors with patient information such as medical history, allergies, past records, check-ups, and other important details.

AI-Powered Healthcare: How Chatbots Are Transforming Healthcare

Studies that detailed any user-centered design methodology applied to the development of the chatbot were among the minority (3/32, 9%) [16-18]. Chatbots are programmed by humans and thus, they are prone to errors and can give a wrong or misleading medical advice. Needless to say, even the smallest mistake in diagnosis can result in very serious consequences for a patient, so there is really no room for error. A chatbot can be defined as specialized software that is integrated with other systems and hence, it operates in a digital environment.

Trained on clinical data from more than 18,000 medical articles and journals, Buoy’s chatbot for medical diagnosis provides users with their likely diagnoses and accurate answers to their health questions. Machine learning applications are beginning to transform patient care as we know it. Although still in its early stages, chatbots will not only improve care delivery, but they will also lead to significant healthcare cost savings and improved patient care outcomes in the near future. In this article, we will explore how chatbots in healthcare can improve patient engagement and experience and streamline internal and external support. Athena Robinson, chief clinical officer for Woebot, says such disclosures are critical.

Author & Researcher services

Artificial intelligence (AI) is at the forefront of transforming numerous aspects of our lives by modifying the way we analyze information and improving decision-making through problem solving, reasoning, and learning. Machine learning (ML) is a subset of AI that improves its performance chatbot technology in healthcare based on the data provided to a generic algorithm from experience rather than defining rules in traditional approaches [1]. Advancements in ML have provided benefits in terms of accuracy, decision-making, quick processing, cost-effectiveness, and handling of complex data [2].

Finally, human-aided classification incorporates human computation, which provides more flexibility and robustness but lacks the speed to accommodate more requests [17]. Each completed consultation session immediately returned a diagnostic report to the user. A typical report contains the major health concerns expressed by the user and their association with possible diseases that are automatically classified by DoctorBot based on a widely adopted disease classification schema [36]. We analyzed the generated diagnostic reports to understand what health concerns or diseases people usually presented to DoctorBot and the frequency with which each disease was presented. This step was followed by a comparison with the usage of health services in hospitals. In particular, we measured the frequency of consultation on DoctorBot for each disease type and compared that with the health service usage reported by three primary hospitals in China [37].

Physical, psychological, and behavioral improvements of underserved or vulnerable populations may even be possible through chatbots, as they are so readily accessible through common messaging platforms. Health promotion use, such as lifestyle coaching, healthy eating, and smoking cessation, has been one of the most common chatbots according to our search. In addition, chatbots could help save a significant amount of health care costs and resources. Newer therapeutic innovations have come with a heavy price tag, and out-of-pocket expenses have placed a significant strain on patients’ financial well-being [23]. With chatbots implemented in cancer care, consultations for minor health concerns may be avoided, which allows clinicians to spend more time with patients who need their attention the most. For example, the workflow can be streamlined by assisting physicians in administrative tasks, such as scheduling appointments, providing medical information, or locating clinics.

A typical consultation session starts with a prompt for the user to describe their main symptom or chief complaint (Figure 1, left). ” This inquiry triggers DoctorBot to take the initiative and ask the user a series of questions related to the symptoms (eg, “How long has the cough been present?”). The chatbot may also inquire if the user is experiencing other relevant symptoms (Figure 1, middle). For example, if a user indicates that he/she has been coughing, the chatbot would consecutively ask if the user is also experiencing a sore throat, shortness of breath, and so forth. If the answer is “yes,” the chatbot then asks the user more questions about each relevant symptom.

Last but not least, the 4th top use case for AI healthcare chatbots is medication reminders. These automated chatbot medical assistants can send you timely reminders for many things, including medication schedules, instructions for dosages, and potential interactions between drugs you’re taking. AI-powered chatbots in healthcare can handle all your appointment bookings, cancellations, and rescheduling needs.

He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years. Cem’s work in Hypatos was covered by leading technology publications like TechCrunch and Business Insider. He graduated from Bogazici University as a computer engineer and holds an MBA from Columbia Business School. Chatbots collect patient information, name, birthday, contact information, current doctor, last visit to the clinic, and prescription information.

• Avoiding responsibility becomes easier when numerous individuals are involved at multiple stages, from development to clinical applications [107].
• We conclude the paper by discussing several design implications, including making the chatbots more informative, easy-to-use, and trustworthy, as well as improving the onboarding experience to enhance user engagement.
• The application of chatbot technology in the health domain, including mental health [21] and behavioral therapy [50,51], is becoming more and more common.

Through the rapid deployment of chatbots, the tech industry may gain a new kind of dominance in health care. AI technologies, especially ML, have increasingly been occupying other industries; thus, these technologies are arguably naturally adapted to the healthcare sector. In most cases, it seems that chatbots have had a positive effect in precisely the same tasks performed in other industries (e.g. customer service). Pasquale (2020, p. 57) has reminded us that AI-driven systems, including chatbots, mirror the successes and failures of clinicians. However, machines do not have the human capabilities of prudence and practical wisdom or the flexible, interpretive capacity to correct mistakes and wrong decisions.

While healthbots have a potential role in the future of healthcare, our understanding of how they should be developed for different settings and applied in practice is limited. There has been one systematic review of commercially available apps; this review focused on features and content of healthbots that supported dementia patients and their caregivers34. To our knowledge, no review has been published examining the landscape of commercially available and consumer-facing healthbots across all health domains and characterized the NLP system design of such apps. This review aims to classify the types of healthbots available on the app store (Apple iOS and Google Play app stores), their contexts of use, as well as their NLP capabilities. UK health authorities have recommended apps, such as Woebot, for those suffering from depression and anxiety (Jesus 2019).

To obtain big data, healthcare organizations need to use multiple data sources, and healthcare chatbots are actually one of them. Ensuring the privacy and security of patient data with healthcare chatbots involves strict adherence to regulations like HIPAA. Employ robust encryption and secure authentication mechanisms to safeguard data transmission.

For example, if a chatbot is designed for users residing in the United States, a lookup table for “location” should contain all 50 states and the District of Columbia. In this article, we shall focus on the NLU component and how you can use Rasa NLU to build contextual chatbots. Identifying the context of your audience also helps to build the persona of your chatbot. For instance, a Level 1 maturity chatbot only provides pre-built responses to clearly stated questions without the capacity to follow through with any deviations. AIMultiple informs hundreds of thousands of businesses (as per similarWeb) including 60% of Fortune 500 every month.

Also, she says, “it is imperative that what’s available to the public is clinically and rigorously tested,” she says. Data using Woebot, she says, has been published in peer-reviewed scientific journals. And some of its applications, including for post-partum depression and substance use disorder, are part of ongoing clinical research studies. The company continues to test its products’ effectiveness in addressing mental health conditions for things like post-partum depression, or substance use disorder. She says that rather than replacing her human health care providers, the chatbot has helped lift her spirits enough so she keeps those appointments.

While AI may not fully simulate one-on-one individual counseling, its proponents say there are plenty of other existing and future uses where it could be used to support or improve human counseling. With it, you’re able to send up to 7 messages to the Docus chatbot and even request an AI-powered second opinion with DDx, Tx, and more. I am looking for a conversational AI engagement solution for the web and other channels. Also, they will help you define the flow of every use case, including input artifacts and required third-party software integrations. Finally, contexts are strings that store the context of the object the user is referring to or talking about.

These bots are used after the patient received a treatment or a service, and their main goal is to collect user feedback and patient data. As we mentioned earlier, the collection of information is vital for the healthcare sector as it allows more personalized healthcare and, as a result, leads to more satisfied patients. Hence, these bots are really important as they help healthcare organizations evaluate their services, understand their patients better, and overall gain a better understanding of what might be improved and how.

For example, the recently published WHO Guidance on the Ethics and Governance of AI in Health [10] is a big step toward achieving these goals and developing a human rights framework around the use of AI. However, as Privacy International commented in a review of the WHO guidelines, the guidelines do not go far enough in challenging the assumption that the use of AI will inherently lead to better outcomes [60]. Chat and artificial intelligence (AI) are transforming appointment scheduling in healthcare, making it simpler and more efficient. This streamlined process results in quicker and more convenient access to care, leading to increased patient satisfaction.

Although research on the use of chatbots in public health is at an early stage, developments in technology and the exigencies of combatting COVID-19 have contributed to the huge upswing in their use, most notably in triage roles. Studies on the use of chatbots for mental health, in particular depression, also seem to show potential, with users reporting positive outcomes [33,34,41]. Impetus for the research on the therapeutic use of chatbots in mental health, while still predominantly experimental, predates the COVID-19 pandemic.

In this section, we report our analysis on the completed and uncompleted sessions, as well as on the user feedback, to present the major issues in the real-world use of DoctorBot. Funders like the Gates Foundation, the Patrick J. McGovern Foundation and Data.org, are seeking to build up this “missing middle” in AI development, especially in areas like health and education. Tekin says there’s a risk that teenagers, for example, might attempt AI-driven therapy, find it lacking, then refuse the real thing with a human being. “My worry is they will turn away from other mental health interventions saying, ‘Oh well, I already tried this and it didn’t work,’ ” she says. In any case, this AI-powered chatbot is able to analyze symptoms, find potential causes for them, and follow up with the next steps.

A Deep Dive Into Healthcare Chatbots: Benefits, Use Cases, and Challenges

A conversational bot can examine the patient’s symptoms and offer potential diagnoses. This also helps medical professionals stay updated about any changes in patient symptoms. This bodes well for patients with long-term illnesses like diabetes or heart disease symptoms. AI chatbots in the healthcare industry are great at automating everyday responsibilities in the healthcare setting.

However, in the case of chatbots, ‘the most important factor for explaining trust’ (Nordheim et al. 2019, p. 24) seems to be expertise. People can trust chatbots if they are seen as ‘experts’ (or as possessing expertise of some kind), while expertise itself requires maintaining this trust or trustworthiness. Chatbot users (patients) need to see and experience the bots as ‘providing answers reflecting knowledge, competence, and experience’ (p. 24)—all of which are important to trust. In practice, ‘chatbot expertise’ has to do with, for example, giving a correct answer (provision of accurate and relevant information). The importance of providing correct answers has been found in previous studies (Nordheim et al. 2019, p. 25), which have ‘identified the perceived ability of software agents as a strong predictor of trust’.

And the best part is that these actions do not require patients to schedule an appointment or stand in line, waiting for the doctor to respond. As for the doctors, the constant availability of bots means that doctors can better manage their time since the bots will undertake some of their responsibilities and tasks. Healthcare chatbots, acknowledging the varied linguistic environment, provide support for multiple languages. This inclusive approach enables patients from diverse linguistic backgrounds to access healthcare information and services without encountering language barriers.

In this way, a patient can conveniently schedule an appointment at any time and from anywhere (most importantly, from the comfort of their own home) while a doctor will simply receive a notification and an entry in their calendar. Integration with a hospital’s internal systems is required to run administrative tasks like appointment scheduling or prescription refill request processing. All authors contributed to the assessment of the apps, and to writing of the manuscript.

As apps could fall within one or both of the major domains and/or be included in multiple focus areas, each individual domain and focus area was assigned a numerical value. While there were 78 apps in the review, accounting for the multiple categorizations, this multi-select characterization yielded a total of 83 (55%) counts for one or more of the focus areas. Classification based on the service provided considers the sentimental proximity of the chatbot to the user, the amount of intimate interaction that takes place, and it is also dependent upon the task the chatbot is performing.

The application of chatbot technology in the health domain, including mental health [21] and behavioral therapy [50,51], is becoming more and more common. Despite the effectiveness of chatbots in delivering health care services to improve well-being, this novel technology has not been adopted at the rates predicted based on the high level of interest [25]. Due to the lack of large-scale deployment, prior work primarily examined the use of health chatbots in controlled settings rather than in a real-world context [28]. This study aimed to bridge the knowledge gap in how people use health chatbots in real-world scenarios. We focus on a single chatbot category used in the area of self-care or that precedes contact with a nurse or doctor. These chatbots are variously called dialog agents, conversational agents, interactive agents, virtual agents, virtual humans or virtual assistants (Abd-Alrazaq et al. 2020; Palanica et al. 2019).

Healthcare chatbots offer the convenience of having a doctor available at all times. With a 99.9% uptime, healthcare professionals can rely on chatbots to assist and engage with patients as needed, providing answers to their queries at any time. Healthcare chatbots can be a valuable resource for managing basic patient inquiries that are frequently asked repeatedly. By having an intelligent chatbot to answer these queries, healthcare providers can focus on more complex issues. Lastly one of the benefits of healthcare chatbots is that it provide reliable and consistent healthcare advice and treatment, reducing the chances of errors or inconsistencies.

Pasquale (2020, p. 46) pondered, ironically, that cheap mental health apps are a godsend for health systems pressed by austerity cuts, such as Britain’s National Health Service. Unfortunately, according to a study in the journal Evidence Based Mental Health, the true clinical value of most apps was ‘impossible to determine’. To develop social bots, designers leverage the abundance of human–human social media conversations that model, analyse and generate utterances through NLP modules. However, the use of therapy chatbots among vulnerable patients with mental health problems bring many sensitive ethical issues to the fore. Regulatory standards have been developed to accommodate for rapid modifications and ensure the safety and effectiveness of AI technology, including chatbots. With the growing number of AI algorithms approved by the Food and Drug Administration, they opened public consultations for setting performance targets, monitoring performance, and reviewing when performance strays from preset parameters [102].

We can think of them as intermediaries between physicians for facilitating the history taking of sensitive and intimate information before consultations. They could also be thought of as decision aids that deliver regular feedback on disease progression and treatment reactions to help clinicians better understand individual conditions. Preventative measures of cancer have become a priority worldwide, as early detection and treatment alone have not been effective in eliminating this disease [22].

The name of the entity here is “location,” and the value is “colorado.” You need to provide a lot of examples for “location” to capture the entity adequately. Furthermore, to avoid contextual inaccuracies, it is advisable to specify this training data in lower case. This will generate several files, including your training data, story data, initial models, and endpoint files, using default data. The first step is to set up the virtual environment for your chatbot; and for this, you need to install a python module.

Chatbots provide patients with a more personalized experience, making them feel more connected to their healthcare providers. Chatbots can help patients feel more comfortable and involved in their healthcare by conversationally engaging with them. When using chatbots in healthcare, it is essential to ensure that patients understand how their data will be used and are allowed to opt out if they choose. For example, chatbots can schedule appointments, answer common questions, provide medication reminders, and even offer mental health support. These chatbots also streamline internal support by giving these professionals quick access to information, such as patient history and treatment plans.

Other applications in pandemic support, global health, and education are yet to be fully explored. Health care systems have been working on implementing telemedicine programs for a number of years [69,70]. This leads to the question of why the uptake of web-based care solutions has been limited despite their salient clinical and economical potential. You can foun additiona information about ai customer service and artificial intelligence and NLP. Key barriers that delay the adoption of new solutions and practice patterns exist at many levels in the chain of health care delivery [71,72]. Patient-specific obstacles include difficulties interfacing with the technology and the lack of motivation to follow through with computer-derived advice and instructions.

And one more great thing about chatbots is that one bot can process multiple requests simultaneously, while a doctor cannot do so. The healthcare industry is constantly embracing technological advancements, as every new innovation brings significant improvements to patient care and to work processes of medical professionals. And while some innovations may be too complex or expensive to implement, there is one that is highly affordable and efficient, and it’s a healthcare chatbot. Designing chatbot functionalities for remote patient monitoring requires a balance between accuracy and timeliness. Implement features that allow the chatbot to collect and analyze health data in real-time. Leverage machine learning algorithms for adaptive interactions and continuous learning from user inputs.