Explore the vast range of titles available.

Prompt engineering is a relatively new field of research that refers to the practice of designing, refining, and implementing prompts or instructions that guide the output of large language models (LLMs) to help in various tasks. With the emergence of LLMs, the most popular one being ChatGPT that has attracted the attention of over a 100 million users in only 2 months, artificial intelligence (AI), especially generative AI, has become accessible for the masses. This is an unprecedented paradigm shift not only because of the use of AI becoming more widespread but also due to the possible implications of LLMs in health care. As more patients and medical professionals use AI-based tools, LLMs being the most popular representatives of that group, it seems inevitable to address the challenge to improve this skill. This paper summarizes the current state of research about prompt engineering and, at the same time, aims at providing practical recommendations for the wide range of health care professionals to improve their interactions with LLMs.

ChatGPT-4 is the latest release of a novel artificial intelligence (AI) chatbot able to answer freely formulated and complex questions. In the near future, ChatGPT could become the new standard for health care professionals and patients to access medical information. However, little is known about the quality of medical information provided by the AI. We aimed to assess the reliability of medical information provided by ChatGPT. Medical information provided by ChatGPT-4 on the 5 hepato-pancreatico-biliary (HPB) conditions with the highest global disease burden was measured with the Ensuring Quality Information for Patients (EQIP) tool. The EQIP tool is used to measure the quality of internet-available information and consists of 36 items that are divided into 3 subsections. In addition, 5 guideline recommendations per analyzed condition were rephrased as questions and input to ChatGPT, and agreement between the guidelines and the AI answer was measured by 2 authors independently. All queries were repeated 3 times to measure the internal consistency of ChatGPT. Five conditions were identified (gallstone disease, pancreatitis, liver cirrhosis, pancreatic cancer, and hepatocellular carcinoma). The median EQIP score across all conditions was 16 (IQR 14.5-18) for the total of 36 items. Divided by subsection, median scores for content, identification, and structure data were 10 (IQR 9.5-12.5), 1 (IQR 1-1), and 4 (IQR 4-5), respectively. Agreement between guideline recommendations and answers provided by ChatGPT was 60% (15/25). Interrater agreement as measured by the Fleiss κ was 0.78 (P<.001), indicating substantial agreement. Internal consistency of the answers provided by ChatGPT was 100%. ChatGPT provides medical information of comparable quality to available static internet information. Although currently of limited quality, large language models could become the future standard for patients and health care professionals to gather medical information.

Chatbots are intelligent conversational computer systems designed to mimic human conversation to enable automated online guidance and support. The increased benefits of chatbots led to their wide adoption by many industries in order to provide virtual assistance to customers. Chatbots utilise methods and algorithms from two Artificial Intelligence domains: Natural Language Processing and Machine Learning. However, there are many challenges and limitations in their application. In this survey we review recent advances on chatbots, where Artificial Intelligence and Natural Language processing are used. We highlight the main challenges and limitations of current work and make recommendations for future research investigation.

Chatbots have become ubiquitous in our daily lives, enabling natural language conversations with users through various modes of communication. Chatbots have the potential to play a significant role in promoting health and well-being. As the number of studies and available products related to chatbots continues to rise, there is a critical need to assess product features to enhance the design of chatbots that effectively promote health and behavioral change. This scoping review aims to provide a comprehensive assessment of the current state of health-related chatbots, including the chatbots' characteristics and features, user backgrounds, communication models, relational building capacity, personalization, interaction, responses to suicidal thoughts, and users' in-app experiences during chatbot use. Through this analysis, we seek to identify gaps in the current research, guide future directions, and enhance the design of health-focused chatbots. Following the scoping review methodology by Arksey and O'Malley and guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist, this study used a two-pronged approach to identify relevant chatbots: (1) searching the iOS and Android App Stores and (2) reviewing scientific literature through a search strategy designed by a librarian. Overall, 36 chatbots were selected based on predefined criteria from both sources. These chatbots were systematically evaluated using a comprehensive framework developed for this study, including chatbot characteristics, user backgrounds, building relational capacity, personalization, interaction models, responses to critical situations, and user experiences. Ten coauthors were responsible for downloading and testing the chatbots, coding their features, and evaluating their performance in simulated conversations. The testing of all chatbot apps was limited to their free-to-use features. This review provides an overview of the diversity of health-related chatbots, encompassing categories such as mental health support, physical activity promotion, and behavior change interventions. Chatbots use text, animations, speech, images, and emojis for communication. The findings highlight variations in conversational capabilities, including empathy, humor, and personalization. Notably, concerns regarding safety, particularly in addressing suicidal thoughts, were evident. Approximately 44% (16/36) of the chatbots effectively addressed suicidal thoughts. User experiences and behavioral outcomes demonstrated the potential of chatbots in health interventions, but evidence remains limited. This scoping review underscores the significance of chatbots in health-related applications and offers insights into their features, functionalities, and user experiences. This study contributes to advancing the understanding of chatbots' role in digital health interventions, thus paving the way for more effective and user-centric health promotion strategies. This study informs future research directions, emphasizing the need for rigorous randomized control trials, standardized evaluation metrics, and user-centered design to unlock the full potential of chatbots in enhancing health and well-being. Future research should focus on addressing limitations, exploring real-world user experiences, and implementing robust data security and privacy measures.

Communication is a core competency of medical professionals and of utmost importance for patient safety. Although medical curricula emphasize communication training, traditional formats, such as real or simulated patient interactions, can present psychological stress and are limited in repetition. The recent emergence of large language models (LLMs), such as generative pretrained transformer (GPT), offers an opportunity to overcome these restrictions. The aim of this study was to explore the feasibility of a GPT-driven chatbot to practice history taking, one of the core competencies of communication. We developed an interactive chatbot interface using GPT-3.5 and a specific prompt including a chatbot-optimized illness script and a behavioral component. Following a mixed methods approach, we invited medical students to voluntarily practice history taking. To determine whether GPT provides suitable answers as a simulated patient, the conversations were recorded and analyzed using quantitative and qualitative approaches. We analyzed the extent to which the questions and answers aligned with the provided script, as well as the medical plausibility of the answers. Finally, the students filled out the Chatbot Usability Questionnaire (CUQ). A total of 28 students practiced with our chatbot (mean age 23.4, SD 2.9 years). We recorded a total of 826 question-answer pairs (QAPs), with a median of 27.5 QAPs per conversation and 94.7% (n=782) pertaining to history taking. When questions were explicitly covered by the script (n=502, 60.3%), the GPT-provided answers were mostly based on explicit script information (n=471, 94.4%). For questions not covered by the script (n=195, 23.4%), the GPT answers used 56.4% (n=110) fictitious information. Regarding plausibility, 842 (97.9%) of 860 QAPs were rated as plausible. Of the 14 (2.1%) implausible answers, GPT provided answers rated as socially desirable, leaving role identity, ignoring script information, illogical reasoning, and calculation error. Despite these results, the CUQ revealed an overall positive user experience (77/100 points). Our data showed that LLMs, such as GPT, can provide a simulated patient experience and yield a good user experience and a majority of plausible answers. Our analysis revealed that GPT-provided answers use either explicit script information or are based on available information, which can be understood as abductive reasoning. Although rare, the GPT-based chatbot provides implausible information in some instances, with the major tendency being socially desirable instead of medically plausible information.

A plethora of weight management apps are available, but many individuals, especially those living with overweight and obesity, still struggle to achieve adequate weight loss. An emerging area in weight management is the support for one's self-regulation over momentary eating impulses. This study aims to examine the feasibility and effectiveness of a novel artificial intelligence-assisted weight management app in improving eating behaviors in a Southeast Asian cohort. A single-group pretest-posttest study was conducted. Participants completed the 1-week run-in period of a 12-week app-based weight management program called the Eating Trigger-Response Inhibition Program (eTRIP). This self-monitoring system was built upon 3 main components, namely, (1) chatbot-based check-ins on eating lapse triggers, (2) food-based computer vision image recognition (system built based on local food items), and (3) automated time-based nudges and meal stopwatch. At every mealtime, participants were prompted to take a picture of their food items, which were identified by a computer vision image recognition technology, thereby triggering a set of chatbot-initiated questions on eating triggers such as who the users were eating with. Paired 2-sided t tests were used to compare the differences in the psychobehavioral constructs before and after the 7-day program, including overeating habits, snacking habits, consideration of future consequences, self-regulation of eating behaviors, anxiety, depression, and physical activity. Qualitative feedback were analyzed by content analysis according to 4 steps, namely, decontextualization, recontextualization, categorization, and compilation. The mean age, self-reported BMI, and waist circumference of the participants were 31.25 (SD 9.98) years, 28.86 (SD 7.02) kg/m , and 92.60 (SD 18.24) cm, respectively. There were significant improvements in all the 7 psychobehavioral constructs, except for anxiety. After adjusting for multiple comparisons, statistically significant improvements were found for overeating habits (mean -0.32, SD 1.16; P<.001), snacking habits (mean -0.22, SD 1.12; P<.002), self-regulation of eating behavior (mean 0.08, SD 0.49; P=.007), depression (mean -0.12, SD 0.74; P=.007), and physical activity (mean 1288.60, SD 3055.20 metabolic equivalent task-min/day; P<.001). Forty-one participants reported skipping at least 1 meal (ie, breakfast, lunch, or dinner), summing to 578 (67.1%) of the 862 meals skipped. Of the 230 participants, 80 (34.8%) provided textual feedback that indicated satisfactory user experience with eTRIP. Four themes emerged, namely, (1) becoming more mindful of self-monitoring, (2) personalized reminders with prompts and chatbot, (3) food logging with image recognition, and (4) engaging with a simple, easy, and appealing user interface. The attrition rate was 8.4% (21/251). eTRIP is a feasible and effective weight management program to be tested in a larger population for its effectiveness and sustainability as a personalized weight management program for people with overweight and obesity. ClinicalTrials.gov NCT04833803; https://classic.clinicaltrials.gov/ct2/show/NCT04833803.

ChatGPT is a well-known large language model-based chatbot. It could be used in the medical field in many aspects. However, some physicians are still unfamiliar with ChatGPT and are concerned about its benefits and risks. We aim to evaluate the perception of physicians and medical students toward using ChatGPT in the medical field. A web-based questionnaire was sent to medical students, interns, residents, and attending staff with questions regarding their perception toward using ChatGPT in clinical practice and medical education. Participants were also asked to rate their perception of ChatGPT's generated response about knee osteoarthritis. Participants included 124 medical students, 46 interns, 37 residents, and 32 attending staff. After reading ChatGPT's response, 132 of the 239 (55.2%) participants had a positive rating about using ChatGPT for clinical practice. The proportion of positive answers was significantly lower in graduated physicians (48/115, 42%) compared with medical students (84/124, 68%; P<.001). Participants listed a lack of a patient-specific treatment plan, updated evidence, and a language barrier as ChatGPT's pitfalls. Regarding using ChatGPT for medical education, the proportion of positive responses was also significantly lower in graduate physicians (71/115, 62%) compared to medical students (103/124, 83.1%; P<.001). Participants were concerned that ChatGPT's response was too superficial, might lack scientific evidence, and might need expert verification. Medical students generally had a positive perception of using ChatGPT for guiding treatment and medical education, whereas graduated doctors were more cautious in this regard. Nonetheless, both medical students and graduated doctors positively perceived using ChatGPT for creating patient educational materials.

Background:Symptoms of depression and anxiety, suicidal ideation, and self-harm have escalated among adolescents to crisis levels during the COVID-19 pandemic. As a result, primary care providers (PCPs) are often called on to provide first-line care for these youth. Digital health interventions can extend mental health specialty care, but few are evidence based. We evaluated the feasibility of delivering an evidence-based mobile health (mHealth) app with an embedded conversational agent to deliver cognitive behavioral therapy (CBT) to symptomatic adolescents presenting in primary care settings during the pandemic.Objective:In this 12-week pilot study, we evaluated the feasibility of delivering the app-based intervention to adolescents aged 13 to 17 years with moderate depressive symptoms who were treated in a practice-based research network (PBRN) of academically affiliated primary care clinics. We also obtained preliminary estimates of app acceptability, effectiveness, and usability.Methods:This small, pilot randomized controlled trial (RCT) evaluated depressive symptom severity in adolescents randomized to the app or to a wait list control condition. The primary end point was depression severity at 4-weeks, measured by the 9-item Patient Health Questionnaire (PHQ-9). Data on acceptability, feasibility, and usability were collected from adolescents and their parent or legal guardian. Qualitative interviews were conducted with 13 PCPs from 11 PBRN clinics to identify facilitators and barriers to incorporating mental health apps in treatment planning for adolescents with depression and anxiety.Results:The pilot randomized 18 participants to the app (n=10, 56%) or to a wait list control condition (n=8, 44%); 17 participants were included in the analysis, and 1 became ineligible upon chart review due to lack of eligibility based on documented diagnosis. The overall sample was predominantly female (15/17, 88%), White (15/17, 88%), and privately insured (15/17, 88%). Mean PHQ-9 scores at 4 weeks decreased by 3.3 points in the active treatment group (representing a shift in mean depression score from moderate to mild symptom severity categories) and 2 points in the wait list control group (no shift in symptom severity category). Teen- and parent-reported usability, feasibility, and acceptability of the app was high. PCPs reported preference for introducing mHealth interventions like the one in this study early in the course of care for individuals presenting with mild or moderate symptoms.Conclusions:In this small study, we demonstrated the feasibility, acceptability, usability, and safety of using a CBT-based chatbot for adolescents presenting with moderate depressive symptoms in a network of PBRN-based primary care clinics. This pilot study could not establish effectiveness, but our results suggest that further study in a larger pediatric population is warranted. Future study inclusive of rural, socioeconomically disadvantaged, and underrepresented communities is needed to establish generalizability of effectiveness and identify implementation-related adaptations needed to promote broader uptake in pediatric primary care.Trial Registration:ClinicalTrials.gov NCT04603053; https://clinicaltrials.gov/ct2/show/NCT04603053

Conversational artificial intelligence (CAI) is emerging as a promising digital technology for mental health care. CAI apps, such as psychotherapeutic chatbots, are available in app stores, but their use raises ethical concerns. We aimed to provide a comprehensive overview of ethical considerations surrounding CAI as a therapist for individuals with mental health issues. We conducted a systematic search across PubMed, Embase, APA PsycINFO, Web of Science, Scopus, the Philosopher's Index, and ACM Digital Library databases. Our search comprised 3 elements: embodied artificial intelligence, ethics, and mental health. We defined CAI as a conversational agent that interacts with a person and uses artificial intelligence to formulate output. We included articles discussing the ethical challenges of CAI functioning in the role of a therapist for individuals with mental health issues. We added additional articles through snowball searching. We included articles in English or Dutch. All types of articles were considered except abstracts of symposia. Screening for eligibility was done by 2 independent researchers (MRM and TS or AvB). An initial charting form was created based on the expected considerations and revised and complemented during the charting process. The ethical challenges were divided into themes. When a concern occurred in more than 2 articles, we identified it as a distinct theme. We included 101 articles, of which 95% (n=96) were published in 2018 or later. Most were reviews (n=22, 21.8%) followed by commentaries (n=17, 16.8%). The following 10 themes were distinguished: (1) safety and harm (discussed in 52/101, 51.5% of articles); the most common topics within this theme were suicidality and crisis management, harmful or wrong suggestions, and the risk of dependency on CAI; (2) explicability, transparency, and trust (n=26, 25.7%), including topics such as the effects of \"black box\" algorithms on trust; (3) responsibility and accountability (n=31, 30.7%); (4) empathy and humanness (n=29, 28.7%); (5) justice (n=41, 40.6%), including themes such as health inequalities due to differences in digital literacy; (6) anthropomorphization and deception (n=24, 23.8%); (7) autonomy (n=12, 11.9%); (8) effectiveness (n=38, 37.6%); (9) privacy and confidentiality (n=62, 61.4%); and (10) concerns for health care workers' jobs (n=16, 15.8%). Other themes were discussed in 9.9% (n=10) of the identified articles. Our scoping review has comprehensively covered ethical aspects of CAI in mental health care. While certain themes remain underexplored and stakeholders' perspectives are insufficiently represented, this study highlights critical areas for further research. These include evaluating the risks and benefits of CAI in comparison to human therapists, determining its appropriate roles in therapeutic contexts and its impact on care access, and addressing accountability. Addressing these gaps can inform normative analysis and guide the development of ethical guidelines for responsible CAI use in mental health care.

Patients with cancer experience complex physical, psychosocial, and behavioral challenges that require continuous support. This need has intensified with the rising cancer burden worldwide and the limited scalability of traditional care models. In response, conversational agents (CAs) have emerged as promising digital interventions for enhancing cancer care, but evidence regarding their feasibility and effectiveness remains limited. This study aimed to evaluate the feasibility and effectiveness of CAs in supporting care for patients with cancer and to summarize the key characteristics of CA interventions to inform future design and implementation. We systematically searched PubMed, Cochrane Library, Web of Science, and Embase databases from the index date through February 3, 2025, and screened reference lists and trial registries for gray literature. Eligible studies included randomized controlled trials (RCTs) and nonrandomized interventions (NRIs) evaluating CA-delivered interventions targeting health outcomes in patients with cancer. Two reviewers independently selected studies and extracted data. Study quality was then appraised using the Cochrane Risk of Bias 2.0 tool for RCTs and the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for NRIs. Extracted data included study characteristics, CA features, and implementation outcomes, including feasibility, acceptability, and usability. Meta-analyses were conducted on physical activity, pain, anxiety, depression, psychological distress, and quality of life. Narrative synthesis was used for outcomes with inconsistent reporting across studies, including health information acquisition and treatment-related side effects. In total, 17 studies involving 1817 patients with cancer were included, with 10 (58.8%) studies being included in the meta-analysis. The meta-analysis showed significant improvements in physical activity (mean difference [MD]=1.44, 95% CI 0.36-2.52, P<.01), pain (MD=-0.91, 95% CI -1.44 to -0.38, P<.01), anxiety (SMD=-0.19, 95% CI -0.35 to -0.02, P=.02), and quality of life (SMD=0.35, 95% CI 0.03-0.67, P=.03). No significant effects were observed on depression (SMD=-0.07, 95% CI -0.42 to 0.27, P=.68) or psychological distress (SMD=-0.33, 95% CI -0.66 to 0.01, P=.06). Narrative synthesis suggested that CAs have the potential to improve patients' acquisition of health information and help manage treatment-related side effects. Notably, CAs were generally found to be safe, feasible, acceptable, and usable among patients with cancer, particularly during the initial phase of use. However, user engagement tended to decline over time, underscoring the need for strategies to sustain long-term use. This systematic review is the first comprehensive analysis to suggest that CAs are feasible, acceptable, usable, and effective interventions for patients with cancer. Nevertheless, the limited psychological benefits and suboptimal long-term user engagement indicate the need for further refinement. Future research should adopt theory-based designs and leverage emerging technologies to enhance personalization, empathy, and sustained engagement in CA interventions. Robust evidence from large-scale RCTs is needed to strengthen the evidence base. PROSPERO CRD42025645982; https://www.crd.york.ac.uk/PROSPERO/view/CRD42025645982.