UNASSIGNED: The introduction of ChatGPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out.
UNASSIGNED: This study aims to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot.
UNASSIGNED: Three texts of varying lengths were presented to ChatGPT. ChatGPT was then instructed to paraphrase the provided texts using five different prompts. In the subsequent stage of the study, the texts were divided into separate paragraphs, and ChatGPT was requested to paraphrase each paragraph individually. Lastly, in the third stage, ChatGPT was asked to paraphrase the texts it had previously generated.
UNASSIGNED: The average plagiarism rate in the texts generated by ChatGPT was 45% (SD 10%). ChatGPT exhibited a substantial reduction in plagiarism for the provided texts (mean difference -0.51, 95% CI -0.54 to -0.48; P<.001). Furthermore, when comparing the second attempt with the initial attempt, a significant decrease in the plagiarism rate was observed (mean difference -0.06, 95% CI -0.08 to -0.03; P<.001). The number of paragraphs in the texts demonstrated a noteworthy association with the percentage of plagiarism, with texts consisting of a single paragraph exhibiting the lowest plagiarism rate (P<.001).
UNASSIGNED: Although ChatGPT demonstrates a notable reduction of plagiarism within texts, the existing levels of plagiarism remain relatively high. This underscores a crucial caution for researchers when incorporating this chatbot into their work.

Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.

BACKGROUND: Building therapeutic relationships and social presence are challenging in digital services and maybe even more difficult in written services. Despite these difficulties, in-person care may not be feasible or accessible in all situations.
OBJECTIVE: This study aims to categorize crisis counselors\' efforts to build rapport in written conversations by using deidentified conversation transcripts from the text and chat arms of the National Child Abuse Hotline. Using these categories, we identify the common characteristics of successful conversations. We defined success as conversations where help-seekers reported the hotline was a good way to seek help and that they were a lot more hopeful, a lot more informed, a lot more prepared to address the situation, and experiencing less stress, as reported by help-seekers.
METHODS: The sample consisted of transcripts from 314 purposely selected conversations from of the 1153 text and chat conversations during July 2020. Hotline users answered a preconversation survey (ie, demographics) and a postconversation survey (ie, their perceptions of the conversation). We used qualitative content analysis to process the conversations.
RESULTS: Active listening skills, including asking questions, paraphrasing, reflecting feelings, and interpreting situations, were commonly used by counselors. Validation, unconditional positive regard, and evaluation-based language, such as praise and apologies, were also often used. Compared with less successful conversations, successful conversations tended to include fewer statements that attend to the emotional dynamics. There were qualitative differences in how the counselors applied these approaches. Generally, crisis counselors in positive conversations tended to be more specific and tailor their comments to the situation.
CONCLUSIONS: Building therapeutic relationships and social presence are essential to digital interventions involving mental health professionals. Prior research demonstrates that they can be challenging to develop in written conversations. Our work demonstrates characteristics associated with successful conversations that could be adopted in other written help-seeking interventions.

More clinicians and researchers are exploring uses for large language model chatbots, such as ChatGPT, for research, dissemination, and educational purposes. Therefore, it becomes increasingly relevant to consider the full potential of this tool, including the special features that are currently available through the application programming interface. One of these features is a variable called temperature, which changes the degree to which randomness is involved in the model\'s generated output. This is of particular interest to clinicians and researchers. By lowering this variable, one can generate more consistent outputs; by increasing it, one can receive more creative responses. For clinicians and researchers who are exploring these tools for a variety of tasks, the ability to tailor outputs to be less creative may be beneficial for work that demands consistency. Additionally, access to more creative text generation may enable scientific authors to describe their research in more general language and potentially connect with a broader public through social media. In this viewpoint, we present the temperature feature, discuss potential uses, and provide some examples.

BACKGROUND: In 2017, the Quebec government assigned the Association québécoise de prévention du suicide (AQPS) to develop a digital suicide prevention strategy (DSPS). The AQPS responded by creating a centralized website that provides information on suicide and mental health, identifies at-risk individuals on the internet, and offers direct crisis intervention support via chat and text.
OBJECTIVE: This study aims to evaluate the effectiveness of suicide.ca, Quebec\'s DSPS platform.
METHODS: This study used a cross-sectional descriptive design. The study population comprised internet users from Quebec, Canada, who visited the suicide.ca platform between October 2020 and October 2021. Various data sources, such as Google Analytics, Firebase Console, and Customer Relation Management data, were analyzed to document the use of the platform. To understand the profile of suicide.ca users, frequency analyses were conducted using data from the self-assessment module questionnaires, the intervention service\'s triage questionnaire, and the counselors\' intervention reports. The effectiveness of the platform\'s promotional activities on social media was assessed by examining traffic peaks. Google Analytics was used to evaluate the effectiveness of AQPS\' strategy for identifying at-risk internet users. The impact of the intervention service was evaluated through an analysis of counselors\' intervention reports and postintervention survey results.
RESULTS: The platform received traffic from a diverse range of sources, with promotional efforts on social media directly contributing to the increased traffic. The requirement of a user account posed a barrier to the use of the mobile app, and a triage question that involved personal information led to a substantial number of dropouts during the intervention service triage. AdWords campaigns and fact sheets addressing suicide risk factors played a crucial role in driving traffic to the platform. With regard to the profile of suicide.ca users, the findings revealed that the platform engaged individuals with diverse levels of suicidal risk. Notably, users of the chat service displayed a higher suicide risk than those who used the self-assessment module. Crisis chat counselors reported a positive impact on approximately half of the contacts, and overall, intervention service users expressed satisfaction with the support they received.
CONCLUSIONS: A centralized digital platform can be used to implement a DSPS, effectively reaching the general population, individuals with risk factors for suicide, and those facing suicidal issues.

BACKGROUND: Adverse events refer to incidents with potential or actual harm to patients in hospitals. These events are typically documented through patient safety event (PSE) reports, which consist of detailed narratives providing contextual information on the occurrences. Accurate classification of PSE reports is crucial for patient safety monitoring. However, this process faces challenges due to inconsistencies in classifications and the sheer volume of reports. Recent advancements in text representation, particularly contextual text representation derived from transformer-based language models, offer a promising solution for more precise PSE report classification. Integrating the machine learning (ML) classifier necessitates a balance between human expertise and artificial intelligence (AI). Central to this integration is the concept of explainability, which is crucial for building trust and ensuring effective human-AI collaboration.
OBJECTIVE: This study aims to investigate the efficacy of ML classifiers trained using contextual text representation in automatically classifying PSE reports. Furthermore, the study presents an interface that integrates the ML classifier with the explainability technique to facilitate human-AI collaboration for PSE report classification.
METHODS: This study used a data set of 861 PSE reports from a large academic hospital\'s maternity units in the Southeastern United States. Various ML classifiers were trained with both static and contextual text representations of PSE reports. The trained ML classifiers were evaluated with multiclass classification metrics and the confusion matrix. The local interpretable model-agnostic explanations (LIME) technique was used to provide the rationale for the ML classifier\'s predictions. An interface that integrates the ML classifier with the LIME technique was designed for incident reporting systems.
RESULTS: The top-performing classifier using contextual representation was able to obtain an accuracy of 75.4% (95/126) compared to an accuracy of 66.7% (84/126) by the top-performing classifier trained using static text representation. A PSE reporting interface has been designed to facilitate human-AI collaboration in PSE report classification. In this design, the ML classifier recommends the top 2 most probable event types, along with the explanations for the prediction, enabling PSE reporters and patient safety analysts to choose the most suitable one. The LIME technique showed that the classifier occasionally relies on arbitrary words for classification, emphasizing the necessity of human oversight.
CONCLUSIONS: This study demonstrates that training ML classifiers with contextual text representations can significantly enhance the accuracy of PSE report classification. The interface designed in this study lays the foundation for human-AI collaboration in the classification of PSE reports. The insights gained from this research enhance the decision-making process in PSE report classification, enabling hospitals to more efficiently identify potential risks and hazards and enabling patient safety analysts to take timely actions to prevent patient harm.

This paper details the acquisition, structure and preprocessing of the MultiCaRe Dataset, a multimodal case report dataset which contains data from 75,382 open access PubMed Central articles spanning the period from 1990 to 2023. The dataset includes 96,428 clinical cases, 135,596 images, and their corresponding labels and captions. Data extraction was performed using different APIs and packages such as Biopython, requests, Beautifulsoup, BioC API for PMC and EuropePMC RESTful API. Image labels were created based on the contents of their corresponding captions, by using Spark NLP for Healthcare and manual annotations. Images were preprocessed with OpenCV in order to remove borders and split figures containing multiple images, data were analyzed and described, and a subset was randomly selected for quality assessment. The dataset\'s structure allows for seamless integration of different types of data, making it a valuable resource for training or fine-tuning medical language, computer vision or multi-modal models.

ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers.
We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research.
We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content.
The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference -4.33; 95% CI -4.79 to -3.86; P<.001) but minimal in the 4-subheading structured format (mean difference -2.33; 95% CI -2.79 to -1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT.
Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%.

Digital health technologies are widely used for disease management, with their computing platforms, software, and sensors being used for health care. These technologies are developed to manage chronic diseases and infectious bacterial diseases, including tuberculosis (TB).
This study aims to comprehensively review the literature on the use of digital health interventions (DHIs) for enhancing TB treatment adherence and identify major strategies for their adoption.
We conducted a literature search in the PubMed, Cochrane Library, Ovid Embase, and Scopus databases for relevant studies published between January 2012 and March 2022. Studies that focused on web-based or mobile phone-based interventions, medication adherence, digital health, randomized controlled trials, digital interventions, or mobile health and ubiquitous health technology for TB treatment and related health outcomes were included.
We identified 27 relevant studies and classified them according to the intervention method, a significant difference in treatment success, and health outcomes. The following interventions were emphasized: SMS text messaging interventions (8/27, 30%), medicine reminders (6/27, 22%), and web-based direct observation therapy (9/27, 33%). Digital health technology significantly promoted disease management among individuals and health care professionals. However, only a few studies addressed 2-way communication therapies, such as interactive SMS text messaging and feedback systems.
This scoping review classified studies on DHIs for patients with TB and demonstrated their potential for the self-management of TB. DHIs are still being developed, and evidence on the impact of digital technologies on enhancing TB treatment adherence remains limited. However, it is necessary to encourage patients\' participation in TB treatment and self-management through bidirectional communication. We emphasize the importance of developing a communication system.

BACKGROUND: This research integrates a comparative analysis of the performance of human researchers and OpenAI\'s ChatGPT in systematic review tasks and describes an assessment of the application of natural language processing (NLP) models in clinical practice through a review of 5 studies.
OBJECTIVE: This study aimed to evaluate the reliability between ChatGPT and human researchers in extracting key information from clinical articles, and to investigate the practical use of NLP in clinical settings as evidenced by selected studies.
METHODS: The study design comprised a systematic review of clinical articles executed independently by human researchers and ChatGPT. The level of agreement between and within raters for parameter extraction was assessed using the Fleiss and Cohen κ statistics.
RESULTS: The comparative analysis revealed a high degree of concordance between ChatGPT and human researchers for most parameters, with less agreement for study design, clinical task, and clinical implementation. The review identified 5 significant studies that demonstrated the diverse applications of NLP in clinical settings. These studies\' findings highlight the potential of NLP to improve clinical efficiency and patient outcomes in various contexts, from enhancing allergy detection and classification to improving quality metrics in psychotherapy treatments for veterans with posttraumatic stress disorder.
CONCLUSIONS: Our findings underscore the potential of NLP models, including ChatGPT, in performing systematic reviews and other clinical tasks. Despite certain limitations, NLP models present a promising avenue for enhancing health care efficiency and accuracy. Future studies must focus on broadening the range of clinical applications and exploring the ethical considerations of implementing NLP applications in health care settings.