Effectiveness and Safety of Using Chatbots to Improve Mental Health: Systematic Review and Meta-Analysis PMC

AI Chatbots have revolutionized the healthcare industry by offering a multitude of benefits that contribute to improving efficiency and reducing costs. These intelligent virtual assistants automate various administrative tasks, allowing health systems, hospitals, and medical professionals to focus more on providing quality care to patients. As we navigate the evolving landscape of healthcare, the integration of AI-driven chatbots marks a significant leap forward.

Still, it may not work for a doctor seeking information about drug dosages or adverse effects. If you look up articles about flu symptoms on WebMD, for instance, a chatbot may pop up with information about flu treatment and current outbreaks in your area. With the use of empathetic, friendly, and positive language, a chatbot can help reshape a patient’s thoughts and emotions stemming from negative places. Dr. Liji Thomas is an OB-GYN, who graduated from the Government Medical College, University of Calicut, Kerala, in 2001.

The effectiveness and safety outcomes of chatbots may be different when considering long-term, relative to short-term, findings; it is essential to assess long-term outcomes. Chatbots, or virtual digital companions who engage in conversational interactions, have come a long way since their inception. From their early days as simple rule-based systems to their current incarnation as sophisticated AI-powered assistants, chatbots have evolved remarkably, shaping the future of healthcare delivery. Artificial Intelligence (AI) and automation have rapidly become popular in many industries, including healthcare. One of the most fascinating applications of AI and automation in healthcare is using chatbots. Chatbots in healthcare are computer programs designed to simulate conversation with human users, providing personalized assistance and support.

This allows them to provide relevant responses tailored to the specific needs of each individual. In addition to educating patients, AI chatbots also play a crucial role in promoting preventive care. By using AI to offer personalized recommendations for healthy habits, such as exercise routines or dietary guidelines, they encourage patients to adopt healthier lifestyles. This proactive approach not only benefits of chatbots in healthcare improves patient outcomes but also reduces the burden on healthcare systems by preventing the onset of chronic diseases. This continuous monitoring allows healthcare providers to detect any deviations from normal values promptly. In case of alarming changes, the chatbot can trigger alerts to both patients and healthcare professionals, ensuring timely intervention and reducing the risk of complications.

In the conditions of across-the-board digitalization penetrating an ever-growing range of industries, healthcare facilities employ various state-of-the-art tools to take their services to a new level. AI- and NLP-powered conversational chatbots are quickly becoming a vital element of the professional IT ecosystem of medicare organizations. They present a 24/7 customer support channel that can provide prompt advice and assistance to consumers of healthcare services. Chatbots solve a multitude of tasks concerning the healthcare pipeline – from symptom assessment, appointment management, and patient onboarding to disease management, medical data access, and collecting customer feedback. Implementing advanced technologies often comes with significant costs; however, chatbot solutions offer an affordable option for healthcare organizations looking to enhance patient care without straining their budgets excessively.

During emergencies or when seeking urgent medical advice, chatbot platforms offer immediate assistance. Whether it's a minor health issue or a crisis situation, chatbots are available 24/7 to address user concerns promptly. One of the key advantages of chatbots https://chat.openai.com/ is their ability to offer reliable and up-to-date information sourced from trusted medical databases or institutions. By accessing a vast pool of medical resources, chatbots can provide users with comprehensive information on various health topics.

There is a shortage of mental health human resources, poor funding, and mental health illiteracy globally [5,6]. This lack of resources is especially evident in low-income and middle-income countries where there are 0.1 psychiatrists per 1,000,000 people [7], compared to 90 psychiatrists per 1,000,000 people in high-income countries [8]. According to the World Health Organization, mental health services reach 15% and 45% of those in need in developing and developed countries, respectively [9]. This could be a major factor contributing to the increase in suicidal behavior in recent decades [10].

Diagnostic appointment support

They will be equipped to identify symptoms early, cross-reference them with patients’ medical histories, and recommend appropriate actions, significantly improving the success rates of treatments. This proactive approach will be particularly beneficial in diseases where early detection is vital to effective treatment. To reduce selection bias, two reviewers independently selected studies, extracted data, and assessed the risk of bias in the included studies and quality of the evidence.

By engaging patients in interactive conversations, chatbots can elicit detailed responses and ensure accurate data collection. The use of chatbots in healthcare has become increasingly prevalent, particularly in addressing public health concerns, including COVID-19 pandemic during previous years. These AI-powered tools have proven to be invaluable in screening individuals for COVID-19 symptoms and providing guidance on necessary precautions. Chatbots minimize the risk of errors and omissions by ensuring that all necessary information is recorded accurately. This includes details about medical history, treatments, medications, and any other relevant data. With chatbots handling documentation tasks, physicians can focus more on patient care and treatment plans without worrying about missing critical information.

What are some real-world applications of healthcare chatbots?

However, collaborative efforts on fitting these applications to more demanding scenarios are underway. Beginning with primary healthcare services, the chatbot industry could gain experience and help develop more reliable solutions. Chatbots are integrated into a professional solution launched by a medical facility as a 24/7 available tool for customer support in the healthcare field. Relying on AI, ML, and NLP, chatbots can analyze human speech, understand the message’s intent, and search its pre-programmed response database for a relevant answer, thus providing advice and assistance to consumers of healthcare services. You can foun additiona information about ai customer service and artificial intelligence and NLP. Acropolium provides healthcare bot development services for telemedicine, mental health support, or insurance processing. Skilled in mHealth app building, our engineers can utilize pre-designed building blocks or create custom medical chatbots from the ground up.

Both studies had a high risk of bias; therefore, this finding should be interpreted with caution. To be more precise, an RCT concluded that online chat counselling significantly improved psychological distress over time [45]. The effect of using chatbots on positive and negative affect, which is an indicator of depression and anxiety, was examined in 2 studies [28,29]. The outcome in the 3 studies was measured using the Positive and Negative Affect Schedule. Meta-analysis could not be executed as only 1 study reported enough data for the analysis [28].

By leveraging the expertise of medical professionals and incorporating their knowledge into an automated system, chatbots ensure that users receive reliable advice even in the absence of human experts. These virtual assistants are trained using vast amounts of data from medical professionals, enabling them to provide accurate information and guidance to patients. Patients no longer need to wait on hold or navigate complex websites to access their medical records or test results. With just a few clicks on a chatbot platform, patients can conveniently retrieve all relevant information related to their health. This streamlined process saves time and effort for both patients and healthcare providers alike.

• Discover how a leading chatbot development company can tailor AI solutions for your healthcare needs.
• Your next step is to train your chatbot to respond to stories in a dialogue platform using Rasa core.
• Moreover, chatbots offer an efficient way for individuals to assess their risk level without overwhelming healthcare systems already under strain due to the pandemic.
• Some of these platforms, e.g., Telegram, also provide custom keyboards with predefined reply buttons to make the conversation seamless.
• The level of conversation and rapport-building at this stage for the medical professional to convince the patient could well overwhelm the saving of time and effort at the initial stages.

So in case you have a simple bot and don’t want your patients to complain about its insufficient knowledge, either invest in a smarter bot or simply add an option to connect with a medical professional for more in-depth advice. The main function of mental health chatbots is to provide immediate assistance and guidance in the form of useful tips, guided meditations, and regular well-being checks. In addition, such bots can connect a patient with a medical professional if there is an acute issue. Chat PG In this way, a patient can rest assured that they will receive guaranteed help and their issue will not be left unattended. It might be challenging for a patient to access medical consultations or services due to a number of reasons, and here is where chatbots step in and serve as virtual nurses. While not being able to fully replace a doctor, these bots, nevertheless, perform routine yet important tasks such as symptoms evaluation to help patients constantly be aware of their state.

Thus, medical diagnosis and decision-making require ‘prudence’, that is, ‘a mode of reasoning about contingent matters in order to select the best course of action’ (Hariman 2003, p. 5). For example, it may be almost impossible for a healthcare chat bot to give an accurate diagnosis based on symptoms for complex conditions. While chatbots that serve as symptom checkers could accurately generate differential diagnoses of an array of symptoms, it will take a doctor, in many cases, to investigate or query further to reach an accurate diagnosis. Similarly, conversational style for a healthcare bot for people with mental health problems such as depression or anxiety must maintain sensitivity, respect, and appropriate vocabulary.

As is the case with any custom mobile application development, the final cost will be determined by how advanced your chatbot application will end up being. For instance, implementing an AI engine with ML algorithms in a healthcare AI chatbot will put the price tag for development towards the higher end. Rasa offers a transparent system of handling and storing patient data since the software developers at Rasa do not have access to the PHI. All the tools you use on Rasa are hosted in your HIPAA-complaint on-premises system or private data cloud, which guarantees a high level of data privacy since all the data resides in your infrastructure. The NLU is the library for natural language understanding that does the intent classification and entity extraction from the user input.

They are AI-powered virtual assistants designed to automate routine administrative tasks, streamline workflows, and improve operational efficiency across healthcare facilities. They use AI algorithms to analyze symptoms reported by patients and suggest possible causes or conditions. The chatbot’s NLP capabilities analyze the user’s input to understand their intent and desired outcome. This involves identifying keywords, phrases, and context to interpret the user’s query or request. Healthcare professionals can’t reach and screen everyone who may have symptoms of the infection; therefore, leveraging AI health bots could make the screening process fast and efficient. Rasa stack provides you with an open-source framework to build highly intelligent contextual models giving you full control over the process flow.

Early research even suggests that chatbots can improve upon some doctors’ style of communication. In a recent study, licensed healthcare professionals were tasked with evaluating and comparing responses from doctors and ChatGPT to health-related inquiries on social media. ChatGPT responses outperformed doctors’ responses in terms of both quality and empathy, earning significantly higher ratings in 79 percent of the 585 evaluations.

However, more conversational bots, for example, those that strive to help with mental illnesses and conditions, cannot be constructed—at least not easily—using these thought models. This requires the same kind of plasticity from conversations as that between human beings. The division of task-oriented and social chatbots requires additional elements to show the relation among users, experts (professionals) and chatbots. Most chatbot cases—at least task-oriented chatbots—seem to be user facing, that is, they are like a ‘gateway’ between the patient and the HCP.

When they become the staple of the tech stack leveraged in creating various software solutions, these cutting-edge tools transform into state-of-the-art products capable of solving the most complex problems. In addition to answering the patient’s questions, prescriptive chatbots offer actual medical advice based on the information provided by the user. To do that, the application must employ NLP algorithms and have the latest knowledge base to draw insights. Acropolium has delivered a range of bespoke solutions and provided consulting services for the medical industry.

The SMD was used when, between studies, the outcome was assessed using different measurement tools. The global shortage of mental health workers has prompted the utilization of technological advancements, such as chatbots, to meet the needs of people with mental health conditions. Chatbots are systems that are able to converse and interact with human users using spoken, written, and visual language. While numerous studies have assessed the effectiveness and safety of using chatbots in mental health, no reviews have pooled the results of those studies. However, despite certain disadvantages of chatbots in healthcare, they add value where it really counts. They can significantly augment the efforts of healthcare professionals, offering time-saving support and contributing meaningfully in crucial areas.

Healthcare chatbot applications offer round-the-clock assistance to patients, addressing queries, providing information, and even assisting with emergency advice outside regular clinic hours. This continuous availability ensures patients can receive timely support whenever needed, improving patient experience with chatbots. According to a report by HealthITAnalytics, patients appreciate the immediate responses and 24/7 support that chatbots provide, highlighting the importance of timely communication in patient care. Due to the rapid digital leap caused by the Coronavirus pandemic in health care, there are currently no established ethical principles to evaluate healthcare chatbots. Shum et al. (2018, p. 16) defined CPS (conversation-turns per session) as ‘the average number of conversation-turns between the chatbot and the user in a conversational session’.

Physicians must also be kept in the loop about the possible uncertainties of the chatbot and its diagnoses, such that they can avoid worrying about potential inaccuracies in the outcomes and predictions of the algorithm. When you know which specialist can solve your problem, the chatbot will schedule and set up a video or voice call with the doctor, who will leverage the power of telemedicine software to provide consultation and help to the chatbot user. You can bring this universal truth home to people by raising their awareness of the causes of different disorders. Chatbots can be programmed to address relevant audiences that should be encouraged to be proactive in avoiding heart attacks, strokes, or even simple colds and flu during certain seasons.

Data were analyzed using descriptive statistics and frequencies to examine the characteristics of participant responses to survey items on health care chatbots. Preliminary analyses revealed no major differences across factors of age, gender, or years of practice. A total of 100 practicing physicians across the United States completed a Web-based, self-report survey to examine their opinions of chatbot technology in health care.

Each of these use cases demonstrates the versatility and effectiveness of healthcare chatbots in enhancing patient care, streamlining operations, and improving overall healthcare delivery. Despite their potential to provide medical advice and expedite diagnoses, concerns persist about the accuracy of responses and the need for human oversight. Instances of chatbots providing false or misleading information pose significant risks to users’ health. Engaging in open conversations about health with medical professionals can be challenging for individuals who anticipate encountering stigma or embarrassment upon revealing their symptoms and experiences of health.

This study is the first review of the literature that assessed the effectiveness and safety of chatbots in mental health. This review was developed, executed, and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement [20]. As all extracted data were continuous, the effect of each trial and the overall effect were measured using either the mean difference (MD) or the standardized mean difference (SMD). To be more precise, when the outcome was measured using the same method between studies, the MD was utilized.

The app users may engage in a live video or text consultation on the platform, bypassing hospital visits. In emergency situations, bots will immediately advise the user to see a healthcare professional for treatment. That’s why hybrid chatbots – combining artificial intelligence and human intellect – can achieve better results than standalone AI powered solutions. Now that you have understood the basic principles of conversational flow, it is time to outline a dialogue flow for your chatbot. This forms the framework on which a chatbot interacts with a user, and a framework built on these principles creates a successful chatbot experience whether you’re after chatbots for medical providers or patients. Users usually prefer chatbots over symptom checker apps as they can precisely describe how they feel to a bot in the form of a simple conversation and get reliable and real-time results.

“What doctors often need is wisdom rather than intelligence, and we are a long way away from a science of artificial wisdom.” Chatbots lack both wisdom and the flexibility to correct their errors and change their decisions. For all their apparent understanding of how a patient feels, they are machines and cannot show empathy. They also cannot assess how different people prefer to talk, whether seriously or lightly, keeping the same tone for all conversations. It is not only about live answering FAQs concerning your hospital’s onboarding procedure and guiding patients through this routine.

With standalone chatbots, businesses have been able to drive their customer support experiences, but it has been marred with flaws, quite expectedly. With the eHealth chatbot, users submit their symptoms, and the app runs them against a database of thousands of conditions that fit the mold. This is followed by the display of possible diagnoses and the steps the user should take to address the issue – just like a patient symptom tracking tool. This AI chatbot for healthcare has built-in speech recognition and natural language processing to analyze speech and text to produce relevant outputs.

With their ability to offer tailored assistance, chatbots enhance patient satisfaction and improve outcomes. They alleviate the burden on hospital staff by handling routine queries, allowing physicians and nurses to dedicate more time to critical cases. Moreover, as artificial intelligence continues to advance, chatbots are becoming increasingly intelligent, capable of addressing complex medical questions with accuracy. AI chatbots in healthcare are used for various purposes, including symptom assessment, patient triage, health education, medication management, and supporting telehealth services. For instance, a healthcare chatbot uses AI to evaluate symptoms against a vast medical database, providing patients with potential diagnoses and advice on the next steps.

What are the benefits of using chatbots in healthcare?

Given such a multitude of use cases, it’s no wonder that the future of chatbots in healthcare looks extremely bright. Whereas the healthcare chatbot market size was under $195 million only three years ago, it is expected to top $943 million by 2030, manifesting a tremendous CAGR of 19.16%. Such numbers are the best proof that the application of this technology in healthcare is experiencing a sharp spike. Of course, no algorithm can compare to the experience of a doctor that’s earned in the field or the level of care a trained nurse can provide. However, chatbot solutions for the healthcare industry can effectively complement the work of medical professionals, saving time and adding value where it really counts.

Patients love speaking to real-life doctors, and artificial intelligence is what makes chatbots sound more human. In fact, some chatbots with complex self-learning algorithms can successfully maintain in-depth, nearly human-like conversations. Neither does she miss a dose of the prescribed antibiotic – a healthcare chatbot app brings her up to speed on those details. A healthcare chatbot also sends out gentle reminders to patients for the consumption of medicines at the right time when requested by the doctor or the patient.

This bot uses AI to provide personalized consultations by analyzing the patient’s medical history and while it cannot fully replace a medical professional, it can for sure provide valuable advice and guidance. 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. One of the key advantages of using chatbots in healthcare is their ability to automate time-consuming administrative tasks. For instance, they can handle insurance verification and claims processing seamlessly, eliminating the need for hospital staff to manually navigate through complex paperwork. By streamlining these processes, chatbots save valuable time and resources for both patients and healthcare organizations.

Informative, conversational, and prescriptive healthcare chatbots can be built into messaging services like Facebook Messenger, Whatsapp, or Telegram or come as standalone apps. By using this information, a medical organization can analyze the efficiency and quality of their services and identify areas for improvement. As well, doctors can gain a better understanding of patients and create a more personalized treatment plan for them, which will ultimately result in better patient care.

They offer symptom checkers, reliable information about the virus, and guidance on necessary actions based on symptoms exhibited. One significant advantage of using chatbots in collecting patient data is the assurance of privacy and confidentiality. These intelligent systems are designed with secure data encryption protocols that safeguard sensitive patient information from unauthorized access or breaches.

Thus, new technologies require system-level assessment of their effects in the design and implementation phase. Information can be customized to the user’s needs, something that’s impossible to achieve when searching for COVID-19 data online via search engines. What’s more, the information generated by chatbots takes into account users’ locations, so they can access only information useful to them. Let’s create a contextual chatbot called E-Pharm, which will provide a user – let’s say a doctor – with drug information, drug reactions, and local pharmacy stores where drugs can be purchased. The first step is to create an NLU training file that contains various user inputs mapped with the appropriate intents and entities.

Future assistants may support more sophisticated multimodal interactions, incorporating voice, video, and image recognition for a more comprehensive understanding of user needs. At the same time, we can expect the development of advanced chatbots that understand context and emotions, leading to better interactions. The integration of predictive analytics can enhance bots’ capabilities to anticipate potential health issues based on historical data and patterns. As you can see, chatbots are on the rise and both patients and doctors recognize their value. Bonus points if chatbots are designed on the base of Artificial Intelligence, as the technology allows bots to hold more complex conversations and provide more personalized services.