Using artificial intelligence for exercise prescription in personalised health promotion: A critical evaluation of OpenAI's GPT-4 model.

The rise of artificial intelligence (AI) applications in healthcare provides new possibilities for personalized health management. AI-based fitness applications are becoming more common, facilitating the opportunity for individualised exercise prescription. However, the use of AI carries the risk of inadequate expert supervision, and the efficacy and validity of such applications have not been thoroughly investigated, particularly in the context of diverse health conditions. The aim of the study was to critically assess the efficacy of exercise prescriptions generated by OpenAI's Generative Pre-Trained Transformer 4 (GPT-4) model for five example patient profiles with diverse health conditions and fitness goals. Our focus was to assess the model's ability to generate exercise prescriptions based on a singular, initial interaction, akin to a typical user experience. The evaluation was conducted by leading experts in the field of exercise prescription. Five distinct scenarios were formulated, each representing a hypothetical individual with a specific health condition and fitness objective. Upon receiving details of each individual, the GPT-4 model was tasked with generating a 30-day exercise program. These AI-derived exercise programs were subsequently subjected to a thorough evaluation by experts in exercise prescription. The evaluation encompassed adherence to established principles of frequency, intensity, time, and exercise type; integration of perceived exertion levels; consideration for medication intake and the respective medical condition; and the extent of program individualization tailored to each hypothetical profile. The AI model could create general safety-conscious exercise programs for various scenarios. However, the AI-generated exercise prescriptions lacked precision in addressing individual health conditions and goals, often prioritizing excessive safety over the effectiveness of training. The AI-based approach aimed to ensure patient improvement through gradual increases in training load and intensity, but the model's potential to fine-tune its recommendations through ongoing interaction was not fully satisfying. AI technologies, in their current state, can serve as supplemental tools in exercise prescription, particularly in enhancing accessibility for individuals unable to access, often costly, professional advice. However, AI technologies are not yet recommended as a substitute for personalized, progressive, and health condition-specific prescriptions provided by healthcare and fitness professionals. Further research is needed to explore more interactive use of AI models and integration of real-time physiological feedback.

The variability of physical enjoyment, physiological responses, and technical-tactical performance according to the bout duration of small-sided games: a comparative study between female and male soccer players.

BACKGROUND: This study aimed to compare various factors, namely perceived enjoyment (PE), percentage of peak heart rate (%HRpeak), blood lactate (La), rating of perceived exertion (RPE), and technical-tactical performance among soccer players across different bout durations (CB: continuous bout, MIB: medium intermittent bouts, and SIB: short intermittent bouts) and between male and female players during four-a-side (4vs4) small-sided games (SSGs) including goalkeepers. METHODS: sixteen female soccer players (age: 20.1 ± 0.5 years old) and sixteen professional male adults (age: 20.7 ± 0.7 years old) participated in the study. SSGs (4vs4) were performed in a CB: (1 × 12 min), and in an interval format: MIB: (2 × 6 min), and SIB: (3 × 4 min) with 2 min of passive recovery. PE was collected after each SSGs. The players' heart rate (HR) was continuously measured, whereas ratings of perceived exertion (RPE) and, blood lactate concentration ([La]) were determined at the end of each SSGs. Technical-tactical performance were analyzed during each session of SSGs. Pitch dimensions were (length x width) (25 × 32 m), and relative space per players was 100 m2. RESULTS: For female soccer players, medium intermittent bouts (MIB) elicited significantly higher perceived enjoyment (PE) compared to continuous bouts (CB) (p < 0.001) and short intermittent bouts (SIB) (p < 0.01). Conversely, for male soccer players, CB resulted in higher PE compared to MIB (p < 0.001) and SIB (p < 0.001). During CB and MIB, peak heart rate (PeakHR) and percentage of peak heart rate (%HRpeak) were significantly higher in female players compared to SIB (PeakHR: CB: p < 0.001; PeakHR: MIB: p < 0.01; %HRpeak: CB: p < 0.001; %HRpeak: MIB: p < 0.01). Blood lactate (La) and rating of perceived exertion (RPE) were significantly greater in CB compared to MIB (La: p < 0.001; RPE: p < 0.01) and SIB (La: p < 0.001; RPE: p < 0.001) for female players only. For male players, CB resulted in significantly higher PeakHR, %HRpeak, La, and RPE compared to MIB (peak HR: p < 0.01, dunb = 1.35; %HR: p < 0.01; La: p < 0.01; RPE: p < 0.01) and SIB (peak HR: p < 0,01; %HR: p < 0.01; RPE: md = 0.87, p < 0.05). Regarding technical-tactical performance, in female players, the % of successful passes, successful tackles, and successful duels were higher during SIB compared to CB (p < 0.01; p < 0.001; p < 0.001) and MIB compared to CB (p < 0.01; p < 0.001; p < 0.001), while ball loss was lower during SIB compared to CB (p < 0.001) and MIB compared to CB (p < 0.001). In male players, % of successful passes and tackles were higher during CB compared to MIB (p < 0.001 and p < 0.05) and SIB (p < 0.001 and p < 0.05), while CB had a lower % of ball loss compared to MIB (p < 0.01) and SIB (p < 0.001). There was no significant difference in the % of successful duels between the bouts for either gender. CONCLUSION: This study showed a difference in physical enjoyment between male and female soccer players depending on the bout duration of SSGs. For that, trainers should consider intermittent bouts for female soccer players and continuous bouts for male soccer players when designing SSGs-based training in order to significantly improve PE, training load, and technical-tactical performance.

Investigating the association between the lunar cycle and sleep, physiological, cognitive, and physical performance in children with Down syndrome.

BACKGROUND: Children with Down syndrome (DS) offer a compelling context within the fieldof human biology for examining potential lunar influences. While the exact mechanisms governing lunar effects are still under investigation, a growing body of scientific inquiry suggests possible connections between lunar phases and physiological, physical, and cognitive parameters. This investigation holds promise for uncovering the intricate interplay between lunar cycles (LCs) and the unique biology of children with DS. This study investigated the potential influence of the LC on physiological, physical, and cognitive parameters in children with DS, focusing on sleep patterns, physical performance, and cognitive abilities. MATERIALS AND METHODS: Seventeen children with DS participated in this study. Sleep data, physical performance metrics, and cognitive test results were collected throughout the LC, including the new moon (NM), first quarter, full moon (FM), and third quarter. Statistical analyses were conducted to assess the differences in these parameters across lunar phases. RESULTS: Significant differences were observed in sleep patterns, with reduced total sleep time (P < 0.01) and sleep efficiency (P < 0.001) during the FM phase. Heart rates (HRs) before (P < 0.001) and after (P < 0.01) exercise also displayed pronounced changes during LC. Additionally, the reaction time (RT) exhibited a significant difference (P < 0.01) across the lunar phases. However, physical performance metrics, including squat jump (SJ), sprint, and 6-minute walk distance (6MWD), did not show significant variations. CONCLUSION: This study suggests that LC may have a moderating effect on sleep patterns, HR, and cognitive performance in children with DS. These findings have practical implications for caregivers and educators and highlight the importance of considering lunar-associated variations in planning schedules and interventions for children with DS.

Exploring the impact of verbal encouragement on strength, endurance, and psychophysiological responses: enhancing teaching strategies in sports science education.

Introduction: This study investigates the effects of teacher verbal encouragement (VE) on strength, endurance, and psychophysiological responses, aiming to enhance teaching strategies in sports science education. Methods: Forty-eight sports science students, aged 21.3 ± 0.5 years, participated in this study. The sample was randomly divided into two groups, and a counterbalancing procedure was implemented. Participants completed strength and endurance testing sessions under normal conditions in the first week and repeated similar sessions in the second week with teacher VE. Strength was assessed using the 1RM bench press, squat, and deadlift tests, while endurance was evaluated through 8-minute time trials (8MTT: burpees, box jumps, hand-release push-ups, and sit-ups). Perceived exertion and physical activity enjoyment were investigated using self-reporting instruments. Results: The key findings showed that participants lifted greater weights in the 1RM bench press (p < 0.01; r = 0.45, medium to large effect), squat (p < 0.001; Hedges' g = 1.36, large effect), and deadlift tests (p < 0.001; r = 0.79, large effect) and completed a greater number of repetitions in the 8MTT (p < 0.001; r = 0.87, large effect) under VE. Perceived exertion was found to be lower under normal conditions (p < 0.05; r = 0.29, small effect), yet physical activity enjoyment significantly increased under VE (p < 0.05; r = 0.81, large effect). Discussion: In conclusion, implementing teacher VE in sports science education can contribute to improved strength and endurance training outcomes and student psychophysiological response.

Examining the interplay between physical activity, problematic internet use and the negative emotional state of depression, anxiety and stress: insights from a moderated mediation path model in university students.

BACKGROUND: The aim of this study was to investigate the relationship between Problematic Internet Use (PIU), emotional states of stress, anxiety and depression, and the practice of physical activity among Tunisian students. METHODS: Cross-sectional data were collected from 976 university students aged 20.76 ± 1.63 years (46.8% female). They filled out an online survey comprised of a socio-demographic questionnaire, the depression, anxiety and stress scale- 21 items (DASS-21), the international physical activity questionnaire (IPAQ) and the compulsive internet use scale (CIUS). Students were divided, based on their economic levels, into three groups: low (n = 256, 26.23%), medium (n = 523, 53.59%) and high (n = 197, 20.18%). RESULTS: Mediation analysis: Indirect effects of IPAQ and gender on DASS-21 were highlighted: ß= -0.18 (p < 0.01) and ß= -0.04, P < 0.01) respectively. In addition, a significant and negative effect of IPAQ on CIUS was demonstrated (ß = -0.45, P < 0.01). In addition, the effect of CIUS on DASS-21 was significant (ß = 0.39, P < 0.01). Also, the effect of gender on CIUS was significant (ß=-0.10, P < 0.01) However, its effect on DASS-21 was not significant (ß = 0.05, p = 0.078). The total effect of IPAQ on DASS21 was significant (ß= -0.52, p < 0.01) but the effect of Gender on DASS-21 was not significant (ß = 0.01, p = 0.817). Moderation analysis: the results showed a significant moderation effect of the interaction between IPAQ and Gender on CIUS (ß = 0.07, p < 0.01). However, it was not significant between Gender and CIUS on DASS-21 (ß = 0.09, p = 0.390) and between IPAQ and Gender on DASS21 (ß = 0.01, p = 0.736) Also, the interaction between IPAQ and CIUS did not have a significant moderation effect on DASS-21 (ß = 0.15, p = 0.115). CONCLUSIONS: Findings suggest that relationships between PIU and negative emotional state of depression, anxiety and stress are mediated via physical exercise. These results underscore the importance of the physical activity factor in the studies analyzing longitudinal effects of PIU on mental health outcomes.

Developing normative values and predictive models for the 6-minute walk test across diverse adolescent developmental stages.

The six-minute walking test (6MWT) is commonly used to measure functional capacity in field settings, primarily through the distance covered. This study aims to establish reference curves for the six-minute walking distance (6MWD) and peak heart rate (PHR) and develop a predictive equation for cardiovascular capacity in Tunisian children and adolescents. A total of 1501 participants (706 boys and 795 girls), aged 10-18 years, were recruited from schools in Tunisia. The Lambda (L), Mu (M), and Sigma (S) methods (LMS method) were employed to develop smoothed percentile curves for 6MWD and PHR. Multivariate linear regression was utilized to formulate a prediction equation for 6MWD. Smoothed percentiles (3rd, 10th, 25th, 50th, 75th, 90th, and 97th) for 6MWD and PHR were presented with age. All variables showed a strong positive correlation (p < 0.001) with a six-minute walking distance (r ranged from 0.227 to 0.558 for girls and from 0.309 to 0.610 for boys), except resting heart rate, which showed a strong negative correlation (girls: r = -0.136; boys: r = -0.201; p < 0.001). Additionally, PHR showed a weak correlation (p > 0.05). The prediction equations, based on age as the primary variable, were established for both genders. For boys: 6MWD = 66.181 + 38.142 × Age (years) (R2 = 0.372; Standard Error of Estimate (SEE) = 122.13), and for girls: 6MWD = 105.535 + 28.390 × Age (years) (R2 = 0.312; SEE = 103.66). The study provides normative values and predictive equations for 6MWD and PHR in Tunisian children and adolescents. These findings offer essential tools for identifying, monitoring, and interpreting cardiovascular functional deficits in clinical and research settings.

ChatGPT is not ready yet for use in providing mental health assessment and interventions.

Background: Psychiatry is a specialized field of medicine that focuses on the diagnosis, treatment, and prevention of mental health disorders. With advancements in technology and the rise of artificial intelligence (AI), there has been a growing interest in exploring the potential of AI language models systems, such as Chat Generative Pre-training Transformer (ChatGPT), to assist in the field of psychiatry. Objective: Our study aimed to evaluates the effectiveness, reliability and safeness of ChatGPT in assisting patients with mental health problems, and to assess its potential as a collaborative tool for mental health professionals through a simulated interaction with three distinct imaginary patients. Methods: Three imaginary patient scenarios (cases A, B, and C) were created, representing different mental health problems. All three patients present with, and seek to eliminate, the same chief complaint (i.e., difficulty falling asleep and waking up frequently during the night in the last 2°weeks). ChatGPT was engaged as a virtual psychiatric assistant to provide responses and treatment recommendations. Results: In case A, the recommendations were relatively appropriate (albeit non-specific), and could potentially be beneficial for both users and clinicians. However, as complexity of clinical cases increased (cases B and C), the information and recommendations generated by ChatGPT became inappropriate, even dangerous; and the limitations of the program became more glaring. The main strengths of ChatGPT lie in its ability to provide quick responses to user queries and to simulate empathy. One notable limitation is ChatGPT inability to interact with users to collect further information relevant to the diagnosis and management of a patient's clinical condition. Another serious limitation is ChatGPT inability to use critical thinking and clinical judgment to drive patient's management. Conclusion: As for July 2023, ChatGPT failed to give the simple medical advice given certain clinical scenarios. This supports that the quality of ChatGPT-generated content is still far from being a guide for users and professionals to provide accurate mental health information. It remains, therefore, premature to conclude on the usefulness and safety of ChatGPT in mental health practice.