Randomised controlled trials in reproductive medicine are often subject to outcome truncation, where study outcomes are only defined in a subset of participants. Examples include birthweight (measurable only in the subgroup of participants who give birth) and miscarriage (which can only occur in participants who become pregnant). These are typically analysed by making a comparison between treatment arms within the subgroup (comparing birthweights in the subgroup who gave birth, or miscarriages in the subgroup who became pregnant). However, this approach does not represent a randomised comparison when treatment influences the probability of being observed (i.e. survival). The practical implications of this for reproductive trials are unclear. We developed a simulation platform to investigate the implications of outcome truncation for reproductive medicine trials. We used this to perform a simulation study, in which we considered the bias, Type 1 error, coverage, and precision of standard statistical analyses for truncated continuous and binary outcomes. Increasing treatment effect on the intermediate variable, strength of confounding between the intermediate and outcome variables, a
Artificial intelligence is steadily being integrated into all areas of medicine. In reproductive medicine, artificial intelligence methods can be utilized to improve the selection and prediction of sperm cells, oocytes, and embryos and to generate better predictive models for in vitro fertilization. The use of artificial intelligence in this field is justified by the suffering of persons or couples who wish to have children but are unable to conceive. However, research into the use of artificial intelligence in reproductive medicine is still in the early experimental stage and furthermore raises complex normative questions. There are ethical research challenges because evidence of the efficacy of certain pertinent systems is often lacking and because of the increased difficulty of ensuring informed consent on the part of the affected persons. Other ethically relevant issues include the potential risks for offspring and the difficulty of providing sufficient information. The opportunity to fulfill the desire to have children affects the welfare of patients and their reproductive autonomy. Ultimately, ensuring more accurate predictions and allowing physicians to devote more time to their patients will have a positive effect. Nevertheless, clinicians must be able to process patient data conscientiously. When using artificial intelligence, numerous actors are involved in making the diagnosis and deciding on the appropriate therapy, raising questions about who is ultimately responsible when mistakes occur. Questions of fairness arise with regard to resource allocation and cost reimbursement. Thus, before implementing artificial intelligence in clinical practice, it is necessary to critically examine the quantity and quality of the data used and to address issues of transparency. In the medium and long term, it would be necessary to confront the undesirable impact and social dynamics that may accompany the use of artificial intelligence in reproductive medicine.
暂无摘要（点击查看原文获取完整内容）
Ongoing discussions in Human-Computer Interaction(HCI) have examined the role of AI-based tools in health information seeking, particularly within sensitive domains such as reproductive health. We introduce "OpenBloom," a web application and an exploratory design probe that utilizes Large Language Models (LLMs) to turn reproductive health articles into question-based prompts to explore stigma around reproductive wellbeing. Through a survey study with 34 participants across their 136 interactions with OpenBloom, we explore how AI-generated question-based learning interacts with sociocultural stigma, contextual sensitivity, and reflexiveness. While current LLM outputs largely meet expectations for non-offensiveness, they default to superficial rephrasing or factual recall and lack critical reflections. We discuss implications for applying Feminist HCI, contestability, and value-sensitive AI frameworks to future LLM-mediated reproductive health technologies.
With the reversal of Roe v. Wade in 2022, many U.S. employers announced they would reimburse employees for abortion-related travel expenses. This action complements increasingly common employer policies subsidizing employee access to assisted reproductive technologies such as in-vitro fertilization and egg freezing. This article reflects on why employers offer these benefits and whether they enhance or undermine reproductive justice. From the employer's perspective, abortion and assisted reproductive technologies help women to plan childbearing around the demands of their jobs. Both are associated with delayed childbirth and reduced fertility, which lower the costs of motherhood to employers. However, firm subsidization of these services does not further reproductive justice because it reifies structures which incentivize women to delay childbirth and reduce fertility, and it reinforces economic and reproductive inequalities. We conclude by questioning whether reproductive justice is possible without transforming the economy so that it prioritizes care over profits.
Reproductive well-being education in the Global South is often challenged as many communities perceive many of its contents as misinformation, misconceptions, and language-inappropriate. Our ten-month-long ethnographic study (n=41) investigated the impact of sociocultural landscape, cultural beliefs, and healthcare infrastructure on Bangladeshi people's access to quality reproductive healthcare and set four design goals: combating misinformation, including culturally appropriate language, professionals' accountable moderation, and promoting users' democratic participation. Building on the model of `\textit{Distributive Justice,}' we designed and evaluated \textit{`Socheton,'} a culturally appropriate AI-mediated tool for reproductive well-being that includes healthcare professionals, AI-language teachers, and community members to moderate and run the activity-based platform. Our user study (n=28) revealed that only combating misinformation and language inappropriateness may still leave the community with a conservative mob culture and patronize reproductive care-seeking. This guides well-being HCI design toward being culturally appropriate in the context of reproductive justice wit
Reproductive well-being education remains widely stigmatized across diverse cultural contexts, constraining how individuals access and interpret reproductive health knowledge. We designed and evaluated OpenBloom, a stigma-sensitive, AI-mediated system that uses LLMs to transform reproductive health articles into reflective, question-based learning prompts. We employed OpenBloom as a design probe, aiming to explore the emerging challenges of reproductive well-being stigma through LLMs. Through surveys, semi-structured interviews, and focus group discussions, we examine how sociocultural stigma shapes participants' engagements with AI-generated questions and the opportunities of inquiry-based reproductive health education. Our findings identify key design considerations for stigma-sensitive LLM, including empathetic framing, inclusive language, values-based reflection, and explicit representation of marginalized identities. However, while current LLM outputs largely meet expectations for cultural sensitivity and non-offensiveness, they default to superficial rephrasing and factual recall rather than critical reflection. This guides well-being HCI design in sensitive health domains to
Reproductive well-being is shaped by intersecting cultural, religious, gendered, and political contexts, yet current technologies often reflect narrow, Western-centric assumptions. In this literature review, we synthesize findings from 147 peer-reviewed papers published between 2015 and 2025 across HCI, CSCW and social computing, ICTD, digital and public health, and AI for well-being scholarship to map the evolving reproductive well-being landscape. We identify three thematic waves that focused on early access and education, cultural sensitivity and privacy, and AI integration with policy-aware design, and highlight how technologies support or constrain diverse reproductive experiences. Our analysis reveals critical gaps in inclusivity, with persistent exclusions of men and non-binary users, migrants, and users in the Global South. Additionally, we surfaced the significant absence of literature on the role of stakeholders (e.g., husband and family members, household maids and cleaning helping hands, midwife, etc.) in the reproductive well-being space. Drawing on the findings from the literature, we propose the ReWA framework to support reproductive well-being for all agendas throug
This report presents a small language model (SLM) for Japanese clinical and medicine, named NCVC-slm-1. This 1B parameters model was trained using Japanese text classified to be of high-quality. Moreover, NCVC-slm-1 was augmented with respect to clinical and medicine content that includes the variety of diseases, drugs, and examinations. Using a carefully designed pre-processing, a specialized morphological analyzer and tokenizer, this small and light-weight model performed not only to generate text but also indicated the feasibility of understanding clinical and medicine text. In comparison to other large language models, a fine-tuning NCVC-slm-1 demonstrated the highest scores on 6 tasks of total 8 on JMED-LLM. According to this result, SLM indicated the feasibility of performing several downstream tasks in the field of clinical and medicine. Hopefully, NCVC-slm-1 will be contributed to develop and accelerate the field of clinical and medicine for a bright future.
Model Medicine is the science of understanding, diagnosing, treating, and preventing disorders in AI models, grounded in the principle that AI models -- like biological organisms -- have internal structures, dynamic processes, heritable traits, observable symptoms, classifiable conditions, and treatable states. This paper introduces Model Medicine as a research program, bridging the gap between current AI interpretability research (anatomical observation) and the systematic clinical practice that complex AI systems increasingly require. We present five contributions: (1) a discipline taxonomy organizing 15 subdisciplines across four divisions -- Basic Model Sciences, Clinical Model Sciences, Model Public Health, and Model Architectural Medicine; (2) the Four Shell Model (v3.3), a behavioral genetics framework empirically grounded in 720 agents and 24,923 decisions from the Agora-12 program, explaining how model behavior emerges from Core--Shell interaction; (3) Neural MRI (Model Resonance Imaging), a working open-source diagnostic tool mapping five medical neuroimaging modalities to AI interpretability techniques, validated through four clinical cases demonstrating imaging, compari
Social media platforms like TikTok have become a key source of health information, with studies reporting inaccuracies in posts. As Large Language Model (LLM) providers increasingly integrate LLMs into digital platforms to fact-check content (e.g., Grok and Perplexity on X and WhatsApp, respectively) and are being used by people to fact-check information, deploying these systems in critical areas such as reproductive health without rigorous evaluation can cause serious harm. We introduce RELIANCE, an expert-annotated dataset of health information on TikTok surrounding pregnancy and postpartum queries, serving as both an analysis of the reproductive health information landscape and an evaluation of LLMs' capabilities in fact-checking this content. Our dataset comprises 409 annotated sentences from 336 videos across 56 clinician-reviewed queries, annotated by three expert clinicians in Obstetrics, Gynecology, and Internal Medicine. Our findings reveal that nearly 60\% of the health information in the videos we sampled is accurate. Furthermore, LLM evaluations reveal a gap between evaluating specific claims and evaluating the entire content (15\%). We believe that our methodology, dat
Artificial intelligence (AI) has become increasingly central to precision medicine by enabling the integration and interpretation of multimodal data, yet implementation in clinical settings remains limited. This paper provides a scoping review of literature from 2019-2024 on the implementation of AI in precision medicine, identifying key barriers and enablers across data quality, clinical reliability, workflow integration, and governance. Through an ecosystem-based framework, we highlight the interdependent relationships shaping real-world translation and propose future directions to support trustworthy and sustainable implementation.
What does Artificial Intelligence (AI) have to contribute to health care? And what should we be looking out for if we are worried about its risks? In this paper we offer a survey, and initial evaluation, of hopes and fears about the applications of artificial intelligence in medicine. AI clearly has enormous potential as a research tool, in genomics and public health especially, as well as a diagnostic aid. It's also highly likely to impact on the organisational and business practices of healthcare systems in ways that are perhaps under-appreciated. Enthusiasts for AI have held out the prospect that it will free physicians up to spend more time attending to what really matters to them and their patients. We will argue that this claim depends upon implausible assumptions about the institutional and economic imperatives operating in contemporary healthcare settings. We will also highlight important concerns about privacy, surveillance, and bias in big data, as well as the risks of over trust in machines, the challenges of transparency, the deskilling of healthcare practitioners, the way AI reframes healthcare, and the implications of AI for the distribution of power in healthcare ins
The revolutionary progress in development of next-generation sequencing (NGS) technologies has made it possible to deliver accurate genomic information in a timely manner. Over the past several years, NGS has transformed biomedical and clinical research and found its application in the field of personalized medicine. Here we discuss the rise of personalized medicine and the history of NGS. We discuss current applications and uses of NGS in medicine, including infectious diseases, oncology, genomic medicine, and dermatology. We provide a brief discussion of selected studies where NGS was used to respond to wide variety of questions in biomedical research and clinical medicine. Finally, we discuss the challenges of implementing NGS into routine clinical use.
With the increasing interest in deploying Artificial Intelligence in medicine, we previously introduced HAIM (Holistic AI in Medicine), a framework that fuses multimodal data to solve downstream clinical tasks. However, HAIM uses data in a task-agnostic manner and lacks explainability. To address these limitations, we introduce xHAIM (Explainable HAIM), a novel framework leveraging Generative AI to enhance both prediction and explainability through four structured steps: (1) automatically identifying task-relevant patient data across modalities, (2) generating comprehensive patient summaries, (3) using these summaries for improved predictive modeling, and (4) providing clinical explanations by linking predictions to patient-specific medical knowledge. Evaluated on the HAIM-MIMIC-MM dataset, xHAIM improves average AUC from 79.9% to 90.3% across chest pathology and operative tasks. Importantly, xHAIM transforms AI from a black-box predictor into an explainable decision support system, enabling clinicians to interactively trace predictions back to relevant patient data, bridging AI advancements with clinical utility.
After the repeal of Roe vs. Wade in June 2022, women face long-distance travel across state lines to access abortion care. For women who also face socioeconomic hardship, travel for abortion care is a significant burden. To ease this burden, abortion access nonprofits are funding and/or supplying transportation to abortion clinics. However, due to the uneven distribution of demand and supply for abortions, these nonprofits do not have efficient logistical operations. As a result, low-income, underserved women may not have access to adequate reproductive healthcare, thus widening healthcare inequity gaps. Nonprofits may also risk not serving the needs of vulnerable women without access to adequate reproductive healthcare, and in doing so, waste resources, money, and volunteer hours. To address these challenges, we create an interactive, web-based planning tool, the Reproductive Healthcare Equity Algorithm (RHEA), to guide nonprofits in strategically allocating resources and serving demand. RHEA leverages an optimization model to determine the maximum flow and minimum transportation cost to route women across a network of counties and abortion clinics, subject to transportation suppl
This article explores the critical role of statistical analysis in precision medicine. It discusses how personalized healthcare is enhanced by statistical methods that interpret complex, multidimensional datasets, focusing on predictive modeling, machine learning algorithms, and data visualization techniques. The paper addresses challenges in data integration and interpretation, particularly with diverse data sources like electronic health records (EHRs) and genomic data. It also delves into ethical considerations such as patient privacy and data security. In addition, the paper highlights the evolution of statistical analysis in medicine, core statistical methodologies in precision medicine, and future directions in the field, emphasizing the integration of artificial intelligence (AI) and machine learning (ML).
Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI m
Augmented reality becomes popular in education gradually, which provides a contextual and adaptive learning experience. Here, we develop a Chinese herb medicine AR platform based the 3dsMax and the Unity that allows users to visualize and interact with the herb model and learn the related information. The users use their mobile camera to scan the 2D herb picture to trigger the presentation of 3D AR model and corresponding text information on the screen in real-time. The system shows good performance and has high accuracy for the identification of herbal medicine after interference test and occlusion test. Users can interact with the herb AR model by rotating, scaling, and viewing transformation, which effectively enhances learners' interest in Chinese herb medicine.
There is an abundance of digital sexual and reproductive health technologies that presents a concern regarding their potential sensitive data breaches. We analyzed 15 Internet of Things (IoT) devices with sexual and reproductive tracking services and found this ever-extending collection of data implicates many beyond the individual including partner, child, and family. Results suggest that digital sexual and reproductive health data privacy is both an individual and collective endeavor.