UNASSIGNED: Large language model (LLM)-powered services are gaining popularity in various applications due to their exceptional performance in many tasks, such as sentiment analysis and answering questions. Recently, research has been exploring their potential use in digital health contexts, particularly in the mental health domain. However, implementing LLM-enhanced conversational artificial intelligence (CAI) presents significant ethical, technical, and clinical challenges. In this viewpoint paper, we discuss 2 challenges that affect the use of LLM-enhanced CAI for individuals with mental health issues, focusing on the use case of patients with depression: the tendency to humanize LLM-enhanced CAI and their lack of contextualized robustness. Our approach is interdisciplinary, relying on considerations from philosophy, psychology, and computer science. We argue that the humanization of LLM-enhanced CAI hinges on the reflection of what it means to simulate \"human-like\" features with LLMs and what role these systems should play in interactions with humans. Further, ensuring the contextualization of the robustness of LLMs requires considering the specificities of language production in individuals with depression, as well as its evolution over time. Finally, we provide a series of recommendations to foster the responsible design and deployment of LLM-enhanced CAI for the therapeutic support of individuals with depression.

Recent breakthroughs in artificial intelligence (AI) language models have elevated the vision of using conversational AI support for mental health, with a growing body of literature indicating varying degrees of efficacy. In this paper, we ask when, in therapy, it will be easier to replace humans and, conversely, in what instances, human connection will still be more valued. We suggest that empathy lies at the heart of the answer to this question. First, we define different aspects of empathy and outline the potential empathic capabilities of humans versus AI. Next, we consider what determines when these aspects are needed most in therapy, both from the perspective of therapeutic methodology and from the perspective of patient objectives. Ultimately, our goal is to prompt further investigation and dialogue, urging both practitioners and scholars engaged in AI-mediated therapy to keep these questions and considerations in mind when investigating AI implementation in mental health.

UNASSIGNED: This Research Letter describes the increasing trend of almost-constant social media use among California adolescents and the association with serious psychological distress, focusing on the influence of familial and experiential factors.

Osteoarthritis is the most prevalent age-related degenerative joint disease and a leading cause of pain and disability in aged people. Its etiology is multifaceted, involving factors such as biomechanics, pro-inflammatory mediators, genetics, and metabolism. Beyond its evident impact on joint functionality and the erosion of patients\' quality of life, OA exhibits symbiotic relationships with various systemic diseases, giving rise to various complications. This review reveals OA\'s extensive impact, encompassing osteoporosis, sarcopenia, cardiovascular diseases, diabetes mellitus, neurological disorders, mental health, and even cancer. Shared inflammatory processes, genetic factors, and lifestyle elements link OA to these systemic conditions. Consequently, recognizing these connections and addressing them offers opportunities to enhance patient care and reduce the burden of associated diseases, emphasizing the need for a holistic approach to managing OA and its complications.

BACKGROUND: Cognitive and mood status influence both personal and social daily activities, with great impact on life quality, particularly among the elderly population.
OBJECTIVE: This cross-sectional study aimed to investigate the psycho-affective status concerning eating habits within an elderly population of the Chania area in Crete, Greece.
METHODS: Cognitive status was assessed in 101 elderly subjects through the Mini-Mental State Examination (MMSE), and mood was evaluated using the Hospital Anxiety and Depression Scale (HADS). Nutritional status was assessed using a validated food frequency questionnaire.
RESULTS: Multivariable statistical analysis, after adjustment for age, marital status, education, and comorbidity, highlighted among males a positive association of the MMSE score with vegetable consumption (RR 1.18; 95%CI 1.03‒1.34) and a negative association with potato consumption (RR 0.83; 95%CI 0.72‒0.95). Conversely, among females, no statistically significant association was observed for any food. Further, among males, a protective effect on affective status was identified for chicken meat (RR 0.45; 95%CI 0.27‒0.77), fish (RR 0.41; 95%CI 0.21‒0.82), fruit (RR 0.70; 95%CI 0.52‒0.94), cereals (RR 0.67; 95%CI 0.53‒0.87), and cheese (RR 0.78; 95%CI 0.63‒0.97) consumption. Among females, the adjusted model showed a significant detrimental effect of vegetable consumption (RR 1.33; 95%CI 1.02‒1.73).
CONCLUSIONS: A predominantly vegetable-based diet-with the notable exception of fruits and legumes-was associated with better cognitive status in males, albeit not in females. A higher intake of fruit, as well as fish, chicken meat, and cheese among males was associated with a better affective status, indicating that adequate protein supply may play a role in maintaining emotional balance.

Mental anorexia nervosa is a rare, potentially severe, chronic, and recurrent mental disorder that occurs more often in women than in men, especially during the childbearing years. The disorder is associated with an increased risk of mortality, mainly related to the physical consequences of severe malnutrition and suicide. Malnutrition of the body can cause serious hormonal and somatic problems. Despite significant hormonal disturbances that reduce fertility, a woman with anorexia can become pregnant. A new phenomenon now seen with increasing frequency is pregorexia, an eating disorder associated with pregnancy. It involves the use of dietary restrictions to avoid excessive weight gain during pregnancy. Pregnancy changes the hormonal economy mainly due to the development of the placenta, which secretes many hormones, not just sex hormones. Mental anorexia poses a significant risk to both mother and child if not diagnosed and treated properly. Treatment of anorexia involves simultaneous somatic and psychological treatment. During pregnancy, additional care should be taken to create an optimal environment for the developing foetus. Unfortunately, there is still a lack of research providing guidance in this area. Available studies are mainly case reports or reports focusing on specific clinical situations. It is worth noting that no study to date has attempted a comprehensive assessment of endocrine disruption in pregnant women with anorexia. Recognising the existing knowledge gap on endocrine disorders in pregnant women with anorexia nervosa, a systematic review of the literature was conducted.

BACKGROUND: The use of chatbots in mental health support has increased exponentially in recent years, with studies showing that they may be effective in treating mental health problems. More recently, the use of visual avatars called digital humans has been introduced. Digital humans have the capability to use facial expressions as another dimension in human-computer interactions. It is important to study the difference in emotional response and usability preferences between text-based chatbots and digital humans for interacting with mental health services.
OBJECTIVE: This study aims to explore to what extent a digital human interface and a text-only chatbot interface differed in usability when tested by healthy participants, using BETSY (Behavior, Emotion, Therapy System, and You) which uses 2 distinct interfaces: a digital human with anthropomorphic features and a text-only user interface. We also set out to explore how chatbot-generated conversations on mental health (specific to each interface) affected self-reported feelings and biometrics.
METHODS: We explored to what extent a digital human with anthropomorphic features differed from a traditional text-only chatbot regarding perception of usability through the System Usability Scale, emotional reactions through electroencephalography, and feelings of closeness. Healthy participants (n=45) were randomized to 2 groups that used a digital human with anthropomorphic features (n=25) or a text-only chatbot with no such features (n=20). The groups were compared by linear regression analysis and t tests.
RESULTS: No differences were observed between the text-only and digital human groups regarding demographic features. The mean System Usability Scale score was 75.34 (SD 10.01; range 57-90) for the text-only chatbot versus 64.80 (SD 14.14; range 40-90) for the digital human interface. Both groups scored their respective chatbot interfaces as average or above average in usability. Women were more likely to report feeling annoyed by BETSY.
CONCLUSIONS: The text-only chatbot was perceived as significantly more user-friendly than the digital human, although there were no significant differences in electroencephalography measurements. Male participants exhibited lower levels of annoyance with both interfaces, contrary to previously reported findings.

BACKGROUND: Large language models (LLMs) hold potential for mental health applications. However, their opaque alignment processes may embed biases that shape problematic perspectives. Evaluating the values embedded within LLMs that guide their decision-making have ethical importance. Schwartz\'s theory of basic values (STBV) provides a framework for quantifying cultural value orientations and has shown utility for examining values in mental health contexts, including cultural, diagnostic, and therapist-client dynamics.
OBJECTIVE: This study aimed to (1) evaluate whether the STBV can measure value-like constructs within leading LLMs and (2) determine whether LLMs exhibit distinct value-like patterns from humans and each other.
METHODS: In total, 4 LLMs (Bard, Claude 2, Generative Pretrained Transformer [GPT]-3.5, GPT-4) were anthropomorphized and instructed to complete the Portrait Values Questionnaire-Revised (PVQ-RR) to assess value-like constructs. Their responses over 10 trials were analyzed for reliability and validity. To benchmark the LLMs\' value profiles, their results were compared to published data from a diverse sample of 53,472 individuals across 49 nations who had completed the PVQ-RR. This allowed us to assess whether the LLMs diverged from established human value patterns across cultural groups. Value profiles were also compared between models via statistical tests.
RESULTS: The PVQ-RR showed good reliability and validity for quantifying value-like infrastructure within the LLMs. However, substantial divergence emerged between the LLMs\' value profiles and population data. The models lacked consensus and exhibited distinct motivational biases, reflecting opaque alignment processes. For example, all models prioritized universalism and self-direction, while de-emphasizing achievement, power, and security relative to humans. Successful discriminant analysis differentiated the 4 LLMs\' distinct value profiles. Further examination found the biased value profiles strongly predicted the LLMs\' responses when presented with mental health dilemmas requiring choosing between opposing values. This provided further validation for the models embedding distinct motivational value-like constructs that shape their decision-making.
CONCLUSIONS: This study leveraged the STBV to map the motivational value-like infrastructure underpinning leading LLMs. Although the study demonstrated the STBV can effectively characterize value-like infrastructure within LLMs, substantial divergence from human values raises ethical concerns about aligning these models with mental health applications. The biases toward certain cultural value sets pose risks if integrated without proper safeguards. For example, prioritizing universalism could promote unconditional acceptance even when clinically unwise. Furthermore, the differences between the LLMs underscore the need to standardize alignment processes to capture true cultural diversity. Thus, any responsible integration of LLMs into mental health care must account for their embedded biases and motivation mismatches to ensure equitable delivery across diverse populations. Achieving this will require transparency and refinement of alignment techniques to instill comprehensive human values.

BACKGROUND: Mentalization, which is integral to human cognitive processes, pertains to the interpretation of one\'s own and others\' mental states, including emotions, beliefs, and intentions. With the advent of artificial intelligence (AI) and the prominence of large language models in mental health applications, questions persist about their aptitude in emotional comprehension. The prior iteration of the large language model from OpenAI, ChatGPT-3.5, demonstrated an advanced capacity to interpret emotions from textual data, surpassing human benchmarks. Given the introduction of ChatGPT-4, with its enhanced visual processing capabilities, and considering Google Bard\'s existing visual functionalities, a rigorous assessment of their proficiency in visual mentalizing is warranted.
OBJECTIVE: The aim of the research was to critically evaluate the capabilities of ChatGPT-4 and Google Bard with regard to their competence in discerning visual mentalizing indicators as contrasted with their textual-based mentalizing abilities.
METHODS: The Reading the Mind in the Eyes Test developed by Baron-Cohen and colleagues was used to assess the models\' proficiency in interpreting visual emotional indicators. Simultaneously, the Levels of Emotional Awareness Scale was used to evaluate the large language models\' aptitude in textual mentalizing. Collating data from both tests provided a holistic view of the mentalizing capabilities of ChatGPT-4 and Bard.
RESULTS: ChatGPT-4, displaying a pronounced ability in emotion recognition, secured scores of 26 and 27 in 2 distinct evaluations, significantly deviating from a random response paradigm (P<.001). These scores align with established benchmarks from the broader human demographic. Notably, ChatGPT-4 exhibited consistent responses, with no discernible biases pertaining to the sex of the model or the nature of the emotion. In contrast, Google Bard\'s performance aligned with random response patterns, securing scores of 10 and 12 and rendering further detailed analysis redundant. In the domain of textual analysis, both ChatGPT and Bard surpassed established benchmarks from the general population, with their performances being remarkably congruent.
CONCLUSIONS: ChatGPT-4 proved its efficacy in the domain of visual mentalizing, aligning closely with human performance standards. Although both models displayed commendable acumen in textual emotion interpretation, Bard\'s capabilities in visual emotion interpretation necessitate further scrutiny and potential refinement. This study stresses the criticality of ethical AI development for emotional recognition, highlighting the need for inclusive data, collaboration with patients and mental health experts, and stringent governmental oversight to ensure transparency and protect patient privacy.

暂无摘要。