Generative artificial intelligence (genAI) systems are progressively transforming health science education and research by assisting clinicians in diagnosis and structuring specific intervention regimens (MIR et al., 2023). Moreover, these technologies serve educators in yielding simple concept-based educational modules tailored as per student's requirements and large language models (LLMs) and analogous models display the potential for automated streamlined literature reviews, prompt generation of interpretations and conclusions, and effortless drafting of manuscripts within seconds (MIR et al., 2023;Al Kuwaiti et al., 2023;Gupta et al., 2024) thereby, offering a potentially high level of convenience and efficiency. Furthermore, many researchers contend that genAI has the potential to completely automate research processes, including drafting proposals, analyzing data, and composing concluding reports (Almansour and Alfhaid, 2024;Preiksaitis and Rose, 2023). Hence, these merits indicate a prospective future for genAI, particularly in domains that demand processing of large scale data and iterative analyses.However, despite these evident positive outcomes, concerns persist regarding the quality of AIgenerated outputs, which may include inaccuracies in text reporting that contribute to misinformation, logical inconsistencies, outdated or unverified claims, and hallucinated references, all of which undermine the academic credibility of writing (Athaluri et al., 2023;Farrelly and Baker, 2023;Sittig and Singh, 2024). In addition, a lack of transparency in datasets exacerbates ethical challenges and biases (Norori et al., 2021). In an era characterized by the expedited advancement and refinement of genAI, it is necessary to critically evaluate whether these systems encourage critical thinking and human intelligence or subtly undermine them. This raises an important question: Are we unintentionally relinquishing the cognitive abilities that have propelled scientific and clinical advancements, as healthcare professionals progressively integrate genAI into clinical and academic domains? The dilemma lies in balancing the efficiency of genAI with the preservation of essential human cognitive skills, such as critical thinking, ethical reasoning, and independent problem-solving. At its core, this dilemma focuses on how health professionals, medical trainees, and early career researchers apply outcomes produced by genAI as overreliance risk supporting passive dependence on algorithm produced outcomes in a context where time and cognitive capacity are consistently constrained. The expertise involving scientific accuracy, ethical judgment, and diagnostic reasoning are cultivated through proactive contribution by integrating knowledge in innovative and contextually relevant approaches, critically evaluating evidence, and grappling with uncertainty that genAI cannot substitute (Passerini et al., 2025;Shoja et al., 2023).The significance of the risk of cognitive complacency is emphasized globally, as industry and academia compete to implement genAI tools, and have rapidly accelerated publications related to AI, reflecting both enthusiasm and apprehension. However, medical professionals and researchers may demonstrate overdependence on genAI tools due to faster processing, thus, reducing opportunities for independent problem-solving and critical thinking (Shoja et al., 2023;Zhai et al., 2024). Additionally, in medical research where precision plays an important factor, underlying biases in data training of genAI can propagate false information (Norori et al., 2021). The inefficacy of plagiarism detection software to recognize text generated by genAI, undermines conventional ethical integrity measures as the output may be erroneously identified as genuine scholarly writing (Farrelly and Baker, 2023), though some exceptions exist (Elkhatat et al., 2023;Weber-Wulff et al., 2023). This attitude leads to a workforce adept at utilizing genAI but deficient in cognitive analytical competencies. Moreover, an evolving repository of research studies warns against excessive reliance on genAI for academic work by emphasizing that while genAI can generate complex answers to assignments, it may encourage students to trade critical thinking for speed, eroding the metacognitive skills essential to patient care and clinical reasoning (Fan et al., 2024;Eachempati et al., 2024).However, the ecosystem of scholarly communication stands at a crossroads: Will the next generation of scientists and clinicians accept findings derived from genAI uncritically, prioritizing output over insight, or will they develop the intellectual resilience necessary to critically evaluate the outcomes? In the healthcare industry, the capability to incorporate evolving evidence into public health policy, interpret subtle patient cues, and navigate cultural sensitivities is not exclusively governed by algorithms or encoded by pre-trained genAI models. This concern is particularly relevant because these higher-order cognitive functions necessitate emotional intelligence, nuances, and analytical judgment which are fundamental for fostering innovative and ethical healthcare in the future. The credibility of scientific research is defined by ethical considerations, peer evaluation, and reproducibility (Prager et al., 2018). However, negligence in critically evaluating genAI produced research risks eroding these fundamental principles. Therefore, to ensure research integrity, transparency, and mitigate overreliance on automated results, it is essential to establish and integrate genAI usage policies in academia (Athaluri et al., 2023).Prominent journals warns of a global "feedback loop" that risks reinforcing pre-existing knowledge patterns at the expense of transformative inquiry if genAI tools remain unmonitored (Kwong et al., 2024). Furthermore, a recent analysis elucidates that true intelligence is characterized by the ability to solve novel,...

Diet diversity has an important role in the prevention and treatment of anemia. Based on formative research in the community and the theory of normative social behavior, we designed an intervention to improve diet diversity among women of reproductive age. Our study, the Reduction in Anemia through Normative Innovations (RANI) Project, investigated the effect of a social norms-based intervention on diet diversity among women of reproductive age. We randomized villages in Odisha, India, into treatment or control arms, with a minimum of one village buffer between them. We assessed exposure to the intervention by frequency of self-reported images seen from the participatory learning modules, videos watched, and number of hemoglobin tests administered. We assessed diet diversity with the Food and Agriculture Organization’s Minimum Dietary Diversity for Women (MDD-W) questionnaire. We used multiple logistic regression to examine the associations between intervention and diet diversity, adjusting for covariates. Compared with baseline, diet diversity score increased in both treatment and control groups. The odds of having a diverse diet was 47% higher in the treatment group. Higher level of exposure to the RANI intervention was associated with a better diet diversity score, indicating that the intervention was effective in improving diet quality.

The COVID-19 pandemic has forced higher education institutions to shift to nearly 100% online delivery of didactic coursework nationally. Beside the stress and isolation that many students experience simply due to the physical distancing requirements imposed by the crisis, students new to learning in an online environment may feel further isolated and disengaged from the course content.

More than half of Indian women of reproductive age are anemic. Regular iron folic acid uptake can prevent and treat anemia. This study investigated the effect of interpersonal communication on improving IFA use among women of reproductive age. The Reduction in Anemia through Normative Innovations (RANI) Project is a cluster randomized trial that collected longitudinal data from control (n = 1896) and intervention (n = 1898) communities in Odisha, India at Time 1 and six months later at Time 2. Structural equation models assessed the effect of the intervention on iron folic acid use via multiple interpersonal communication pathways. Compared to the control arm, iron folic acid use significantly increased in the intervention arm. Both, general health interpersonal communication and anemia-specific interpersonal communication were augmented in the intervention communities. The impact of the intervention on iron folic acid use was mediated through anemia-specific interpersonal communication. The RANI Project increased interpersonal communication among participants, resulting in increased iron folic acid use for anemia reduction. Strategic use of targeted interpersonal communication to promote behavior change appears to be a viable strategy to increase iron folic acid use to reduce anemia.

Background: During an infodemic, timely, reliable, and accessible information is crucial to combat the proliferation of health misinformation. While message testing can provide vital information to make data-informed decisions, traditional methods tend to be time- and resource-intensive. Recognizing this need, we developed the rapid message testing at scale (RMTS) approach to allow communicators to repurpose existing social media advertising tools and understand the full spectrum of audience engagement. Objective: We had two main objectives: (1) to demonstrate the use of the RMTS approach for message testing, especially when resources and time are limited, and (2) to propose and test the efficacy of an outcome variable that measures engagement along a continuum of viewing experience. Methods: We developed 12 versions of a single video created for a vaccine confidence project in India. We manipulated video length, aspect ratio, and use of subtitles. The videos were tested across 4 demographic groups (women or men, younger or older). We assessed user engagement along a continuum of viewing experience: obtaining attention, sustaining attention, conveying the message, and inspiring action. These were measured by the percentage of video watched and clicks on the call-to-action link. Results: The video advertisements were placed on Facebook for over 4 consecutive days at the cost of US $450 and garnered a total of 3.34 million impressions. Overall, we found that the best-performing video was the shorter version in portrait aspect ratio and without subtitles. There was a significant but small association between the length of the video and users’ level of engagement at key points along the continuum of viewing experience (N=1,032,888; χ24=48,261.97; P<.001; V=.22). We found that for the longer video, those with subtitles held viewers longer after 25% video watch time than those without subtitles (n=15,597; χ21=7.33; P=.007; V=.02). While we found some significant associations between the aspect ratio, the use of subtitles, and the number of users watching the video and clicking on the call-to-action link, the effect size for those were extremely small. Conclusions: This test served as a proof of concept for the RMTS approach. We obtained rapid feedback on formal message attributes from a very large sample. The results of this test reinforce the need for platform-specific tailoring of communications. While our data showed a general preference for a short video in portrait orientation and without subtitles among our target audiences on Facebook, that may not necessarily be the case in other social media platforms such as YouTube or TikTok, where users go primarily to watch videos. RMTS testing highlights nuances that communication professionals can address instead of being limited to a “one size fits all” approach.

Generative artificial intelligence (GAI) offers increased accessibility and personalized learning, though the potential for inaccuracies, biases, and unethical use is concerning. We present a newly developed research paper assignment that required students to utilize GAI. The assignment was implemented within three online, asynchronous graduate courses for medical laboratory sciences. Student learning was assessed using a rubric, which rated students’ effective integration and evaluation of GAI-generated content against peer-reviewed research articles, thus demonstrating their critical thinking and synthesis skills, among other metrics. Overall rubric scores were high, suggesting that learning outcomes were met. After field testing, we administered a 16-item survey about GAI utilization, contribution to learning, and ethical concerns. Data ( n = 32) were analyzed, and free-response answers were thematically coded. While 93.8% of respondents found the GAI-generated content to be “very good” or “excellent,” 28.1% found inaccuracies, and 68.8% “strongly agreed” or “agreed” that GAI should be allowed to be used as a tool to complete academic assignments. Interestingly, however, only 28.1% “strongly agreed” or “agreed” that GAI may be used for assignments if not explicitly authorized by the instructor. Though GAI allowed for more efficient completion of the project and better understanding of the topic, students noted concerns about academic integrity and the lack of citations in GAI responses. The assignment can easily be modified for different learning preferences and course environments. Raising awareness among students and faculty about the ethical use and limitations of GAI is crucial in today’s evolving pedagogical landscape.