Hasil untuk "Public aspects of medicine"

L. Frank, T. Schmid, J. Sallis et al.

B. Meskó

When large language models (LLMs) were introduced to the public at large in late 2022 with ChatGPT (OpenAI), the interest was unprecedented, with more than 1 billion unique users within 90 days. Until the introduction of Generative Pre-trained Transformer 4 (GPT-4) in March 2023, these LLMs only contained a single mode—text. As medicine is a multimodal discipline, the potential future versions of LLMs that can handle multimodality—meaning that they could interpret and generate not only text but also images, videos, sound, and even comprehensive documents—can be conceptualized as a significant evolution in the field of artificial intelligence (AI). This paper zooms in on the new potential of generative AI, a new form of AI that also includes tools such as LLMs, through the achievement of multimodal inputs of text, images, and speech on health care’s future. We present several futuristic scenarios to illustrate the potential path forward as multimodal LLMs (M-LLMs) could represent the gateway between health care professionals and using AI for medical purposes. It is important to point out, though, that despite the unprecedented potential of generative AI in the form of M-LLMs, the human touch in medicine remains irreplaceable. AI should be seen as a tool that can augment health care professionals rather than replace them. It is also important to consider the human aspects of health care—empathy, understanding, and the doctor-patient relationship—when deploying AI.

Claire Liang, Franziska Babel, Hannah Pelikan et al.

Many of the challenges encountered in in-the-wild public deployments of robots remain undocumented despite sharing many common pitfalls. This creates a high barrier of entry and results in repetition of avoidable mistakes. To articulate the tacit knowledge in the HRI community, this paper presents a guideline in the form of a checklist to support researchers in preparing for robot deployments in public. Drawing on their own experience with public robot deployments, the research team collected essential topics to consider in public HRI research. These topics are represented as modular flip cards in a hierarchical table, structured into deployment phases and important domains. We interviewed six interdisciplinary researchers with expertise in public HRI and show how including community input refines the checklist. We further show the checklist in action in context of real public studies. Finally, we contribute the checklist as an open-source, customizable community resource that both collects joint expertise for continual evolution and is usable as a list, set of cards, and an interactive web tool.

M.A. Valencia Pacheco, R.E. Zapata Lamana, A.S. Robles Campos et al.

Elizabeth K. Farkouh, Loren L. Toussaint, Brian A. Lynch

Introduction/Objectives: Social determinants of health (SDOH) have the potential to differentially impact child developmental outcomes. This study examined whether scores on the Environmental Screening Questionnaire (ESQ), a newly developed SDOH screening tool, were associated with scores on the Brigance and Ages & Stages Questionnaires-Social-Emotional (ASQ:SE-2) child development assessments. Methods: Brigance, ASQ:SE-2, and ESQ scores from children enrolled in a Head Start Program in Northeast Iowa were collected during the 2021 to 2022 and 2022 to 2023 school years. Associations between scores in each ESQ domain and Brigance and ASQ:SE-2 scores were assessed. Results: Education-Employment and Community concerns on the ESQ were associated with reduced Brigance scores ( r  = −.21, P  < .001; r  = −.17, P  = .001). Concerns related to Housing, Child and Family Health, and Community were associated with more concerning ASQ:SE-2 scores ( r  = .14, P  = .005; r  = .18, P  < .001; r  = 0.27, P  < .001). In multivariable models controlling for sex and ethnicity, Education-Employment concerns were significant predictors of lower Brigance scores, while Child and Family Health and Community concerns were significant predictors of ASQ:SE-2 scores. Conclusions: ESQ scores in certain SDOH domains correlate significantly with child developmental outcomes. The ESQ domains of Child and Family Health and Community appear to be particularly important for appropriate child socio-emotional development. Interventions should focus on addressing critical SDOH domains to promote child resilience and counteract the non-medical factors that can interfere with child developmental outcomes.

Eli Berglas, David Musheyev, Aaron B. Lavi et al.

Summary: Background: Disease burden has been used to predict National Institutes of Health (NIH) funding but included diseases with little underlying relationship. Here we focus on cancers to create a more appropriate model to allow for more targeted scrutinization of funding allocation. Methods: An ecological study using NIH funding data (2008–2023) was performed. Inclusion of cancers was based on their presence in the NIH Research Portfolio Online Reporting Tool and the 2021 Global Burden of Disease (GBD) study. Disability-adjusted life years (DALY) were collected and to evaluate the impact of public interest, Google Trends data was used. Multivariable linear regression determined appropriate funding based on disease burden and public interest. To quantify how each cancer’s funding differed from model predictions residual values were used to calculate the percent over/under funding. Findings: Fifteen cancers met inclusion criteria. Neuroblastoma had the greatest ratio of funding to DALYs per 100,000 people (US$14,000,000) while lung cancer had the lowest (US$300,000). Stomach cancer was the most underfunded (197.9% [95% CI: 136.0%, 276.2%]) while brain cancer was the most overfunded (64.1% [95% CI: 53.8%, 72.1%]). Even at their lowest funding values in the study period brain, breast, and colorectal cancer all had greater than 40% overfunding. Contrarily, the lowest annual funding for leukemia, uterine, and stomach cancer received less than 150% of expected funding. Despite its overfunding brain cancer had an increase in DALYs in the study period. Interpretation: Modeling by disease category demonstrated disparities in funding indicating the need for reevaluation for possible funding inequities. The year-by-year approach taken in this study will drive the ability for future research to better understand NIH funding decisions. Additionally, the role of public interest in research funding needs to be further evaluated to ensure that popularity does not override disease burden, in funding decisions. Funding: No Funding.

Neus Latorre-Margalef

In April 2025, a human seasonal reassortant influenza A(H1N2) virus with a 7:1 genetic constellation was detected in Sweden in a patient seeking primary care for influenza-like illness. The neuraminidase gene of this virus was from A(H3N2) and the remaining genes from A(H1N1)pdm09. The patient recovered. No additional cases have been detected through routine surveillance. This is so far the only identified A(H1N2) reassortant among three seasonal A(H1N1)pdm09 and A(H3N2) reassortants reported in GISAID from Europe during the 2024/25 season.

Jing Chen, Wentao Zhou

With the rise of smart contracts, decentralized autonomous organizations (DAOs) have emerged in public good auctions, allowing "small" bidders to gather together and enlarge their influence in high-valued auctions. However, models and mechanisms in the existing research literature do not guarantee non-excludability, which is a main property of public goods. As such, some members of the winning DAO may be explicitly prevented from accessing the public good. This side effect leads to regrouping of small bidders within the DAO to have a larger say in the final outcome. In particular, we provide a polynomial-time algorithm to compute the best regrouping of bidders that maximizes the total bidding power of a DAO. We also prove that such a regrouping is less-excludable, better aligning the needs of the entire DAO and the nature of public goods. Next, notice that members of a DAO in public good auctions often have a positive externality among themselves. Thus we introduce a collective factor into the members' utility functions. We further extend the mechanism's allocation for each member to allow for partial access to the public good. Under the new model, we propose a mechanism that is incentive compatible in generic games and achieves higher social welfare as well as less-excludable allocations.

Alessandro Connor Crocetti, Troy Walker, Fiona Mitchell et al.

Abstract Background The commercial determinants of health is a rapidly expanding field of research; however Indigenous perspectives remain notably underrepresented. For Indigenous peoples the intersection of globalisation, colonialism and capitalism may amplify commercially-driven health inequities. This study aimed to explore the perspectives of Aboriginal leaders regarding the influence of commercial activities on Aboriginal health and wellbeing in Victoria, Australia. Methods Semi-structured interviews with 23 Aboriginal leaders from across five sectors (n = 15 urban, n = 8 rural/regional) were analysed through reflexive thematic analysis. Results Three overarching themes were identified encompassing (i) harmful commercial practices and processes, (ii) improving corporate engagement and (iii) opportunities for self-determination through business. Participants expressed concern over aggressive marketing by the gambling industry, commercial exploitation of Aboriginal culture, the privatisation of public services, and lack of oversignt of corporate social responsibility strategies. Simultaneously, Aboriginal-led businesses were viewed as opportunities for cultural connection, and financial empowerment and self-determination. Conclusion Numerous commercial entities and activities are perceived to influence Aboriginal health and wellbeing. This study highlights the need for stronger policy and regulation to mitigate harmful industry practices while incentivising the potential positive impacts of the commercial activities on Aboriginal health and wellbeing.

Kristin Pullyblank, Nicole Krupa, Melissa Scribani et al.

BackgroundTelehealth has undergone widespread implementation since 2020 and is considered an invaluable tool to improve access to healthcare, particularly in rural areas. However, telehealth's applicability may be limited for certain populations including those who live in rural, medically underserved communities. While broadband access is a recognized barrier, other important factors including age and education influence a person's ability or preference to engage with telehealth via video telehealth or a patient portal. It remains unclear the degree to which these digital technologies lead to disparities in access to care.PurposeThe purpose of this analysis is to determine if access to healthcare differs for telehealth users compared with non-users.MethodsUsing electronic health record data, we evaluated differences in “time to appointment” and “no-show rates” between telehealth users and non-users within an integrated healthcare network between August 2021 and January 2022. We limited analysis to patient visits in endocrinology or outpatient behavioral health departments. We analyzed new patients and established patients separately.ResultsTelehealth visits were associated with shorter time to appointment for new and established patients in endocrinology and established patients in behavioral health, as well as with lower no-show rates for established patients in both departments.ConclusionsThe findings suggest that those who are unwilling or unable to engage with telehealth may have more difficulty accessing timely care.

Kazuto Nakamura, Keiko Kigure, Toshio Nishimura et al.

Abstract Background The incidence of cervical intraepithelial neoplasia is increasing in Japan. Although human papillomavirus (HPV) vaccination and cancer screening are crucial in preventing cancer-related mortality, the cervical cancer screening rate in Japan was only approximately 43.6% in 2022. This study aimed to conduct an epidemiological analysis of cervical cancer by collecting data from individual patients. Methods A questionnaire survey was administered to patients who visited our hospital between January 2017 and July 2023 owing to abnormal cervical cytological findings or a cancer diagnosis. Patients answered questions regarding their history of cervical cancer screening as well as their knowledge of HPV and cervical cancer. Results During the study period, 471 patients participated in the survey, with 35 declining to participate. Patients with Stage 1b1–4b primarily sought medical attention due to self-reported symptoms (P < 0.001); however, they were less likely to have undergone cervical cancer screening (P < 0.001). Additionally, older patients were less likely to be aware of the association of HPV with cervical and other cancers. Notably, 28 of the 129 patients with stage 1b1–4b cancer underwent cervical cancer screening within 2 years. The tumor location within the endocervical canal emerged as a significant factor contributing to the difficulty for an accurate diagnosis of precancerous or cervical cancer during cervical screening. Furthermore, non- squamous cell carcinoma (SCC) histology was another possible factor. Conclusions Our findings suggest the need to widely disseminate information regarding the significance of cancer screening to increase cancer screening rates. Moreover, establishing strategies for improving the accuracy of detecting lesions during screening for non-SCC and endocervical canal tumors is crucial.

Jonathan Bright, Florence E. Enock, Saba Esnaashari et al.

Generative AI has the potential to transform how public services are delivered by enhancing productivity and reducing time spent on bureaucracy. Furthermore, unlike other types of artificial intelligence, it is a technology that has quickly become widely available for bottom-up adoption: essentially anyone can decide to make use of it in their day to day work. But to what extent is generative AI already in use in the public sector? Our survey of 938 public service professionals within the UK (covering education, health, social work and emergency services) seeks to answer this question. We find that use of generative AI systems is already widespread: 45% of respondents were aware of generative AI usage within their area of work, while 22% actively use a generative AI system. Public sector professionals were positive about both current use of the technology and its potential to enhance their efficiency and reduce bureaucratic workload in the future. For example, those working in the NHS thought that time spent on bureaucracy could drop from 50% to 30% if generative AI was properly exploited, an equivalent of one day per week (an enormous potential impact). Our survey also found a high amount of trust (61%) around generative AI outputs, and a low fear of replacement (16%). While respondents were optimistic overall, areas of concern included feeling like the UK is missing out on opportunities to use AI to improve public services (76%), and only a minority of respondents (32%) felt like there was clear guidance on generative AI usage in their workplaces. In other words, it is clear that generative AI is already transforming the public sector, but uptake is happening in a disorganised fashion without clear guidelines. The UK's public sector urgently needs to develop more systematic methods for taking advantage of the technology.

Jasmina Karabegovic

This paper introduces an explicit algorithm for computing perfect public equilibrium (PPE) payoffs in repeated games with imperfect public monitoring, public randomization, and discounting. The method adapts the established framework by Abreu, Pearce, and Stacchetti (1990) into a practical tool that balances theoretical accuracy with computational efficiency. The algorithm simplifies the complex task of identifying PPE payoff sets for any given discount factor δ. A stand-alone implementation of the algorithm can be accessed at: https://github.com/jasmina-karabegovic/IRGames.git.

Xi Chen, MingKe You, Li Wang et al.

The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. This study focused on evaluating and enhancing the clinical capabilities of LLMs in specific domains, using osteoarthritis (OA) management as a case study. A domain specific benchmark framework was developed, which evaluate LLMs across a spectrum from domain-specific knowledge to clinical applications in real-world clinical scenarios. DocOA, a specialized LLM tailored for OA management that integrates retrieval-augmented generation (RAG) and instruction prompts, was developed. The study compared the performance of GPT-3.5, GPT-4, and a specialized assistant, DocOA, using objective and human evaluations. Results showed that general LLMs like GPT-3.5 and GPT-4 were less effective in the specialized domain of OA management, particularly in providing personalized treatment recommendations. However, DocOA showed significant improvements. This study introduces a novel benchmark framework which assesses the domain-specific abilities of LLMs in multiple aspects, highlights the limitations of generalized LLMs in clinical contexts, and demonstrates the potential of tailored approaches for developing domain-specific medical LLMs.

Necdet Gurkan, Jordan W. Suchow

As the societal implications of Artificial Intelligence (AI) continue to grow, the pursuit of responsible AI necessitates public engagement in its development and governance processes. This involvement is crucial for capturing diverse perspectives and promoting equitable practices and outcomes. We applied Cultural Consensus Theory (CCT) to a nationally representative survey dataset on various aspects of AI to discern beliefs and attitudes about responsible AI in the United States. Our results offer valuable insights by identifying shared and contrasting views on responsible AI. Furthermore, these findings serve as critical reference points for developers and policymakers, enabling them to more effectively consider individual variances and group-level cultural perspectives when making significant decisions and addressing the public's concerns.

Michael Vollenweider, Manuel Schürch, Chiara Rohrer et al.

Precision medicine has the potential to tailor treatment decisions to individual patients using machine learning (ML) and artificial intelligence (AI), but it faces significant challenges due to complex biases in clinical observational data and the high-dimensional nature of biological data. This study models various types of treatment assignment biases using mutual information and investigates their impact on ML models for counterfactual prediction and biomarker identification. Unlike traditional counterfactual benchmarks that rely on fixed treatment policies, our work focuses on modeling different characteristics of the underlying observational treatment policy in distinct clinical settings. We validate our approach through experiments on toy datasets, semi-synthetic tumor cancer genome atlas (TCGA) data, and real-world biological outcomes from drug and CRISPR screens. By incorporating empirical biological mechanisms, we create a more realistic benchmark that reflects the complexities of real-world data. Our analysis reveals that different biases lead to varying model performances, with some biases, especially those unrelated to outcome mechanisms, having minimal effect on prediction accuracy. This highlights the crucial need to account for specific biases in clinical observational data in counterfactual ML model development, ultimately enhancing the personalization of treatment decisions in precision medicine.

Muthoni Ogola, John Wainaina, Naomi Muinga et al.

Clinical audits are an important intervention that enables health workers to reflect on their practice and identify and act on modifiable gaps in the care provided. To effectively audit the quality of care provided to the small and sick newborns, the clinical audit process must use a structured tool that comprehensively covers the continuum of newborn care from immediately after birth to the period of newborn unit care. The objective of the study was to co-design a newborn clinical audit tool that considered the key principles of a Human Centred Design approach. A three-step Human Centred Design approach was used that began by (1) understanding the context, the users and the available audit tools through literature, focus group discussions and a consensus meeting that was used to develop a prototype audit tool and its implementation guide, (2) the prototype audit tool was taken through several cycles of reviewing with users on real cases in a high volume newborn unit and refining it based on their feedback, and (3) the final prototype tool and the implementation guide were then tested in two high volume newborn units to determine their usability. Several cycles of evaluation and redesigning of the prototype audit tool revealed that the users preferred a comprehensive tool that catered to human factors such as reduced free text for ease of filling, length of the tool, and aesthetics. Identified facilitators and barriers influencing the newborn clinical audit in Kenyan public hospitals informed the design of an implementation guide that builds on the strengths and overcomes the barriers. We adopted a Human Centred Design approach to developing a newborn clinical audit tool and an implementation guide that we believe are comprehensive and consider the characteristics of the context of use and the user requirements.

Fatemeh Bahador, Azam Sabahi, Samaneh Jalali et al.

Background and Aim: Diabetes is one of the most common metabolic diseases in Iran and the fifth leading cause of death all over the world. Its spread around the world has created new methods in biomedical research, including artificial intelligence. The present study was carried out to review the studies conducted in the area of artificial intelligence and diabetes in Iran.  Materials and Methods: This study was carried out using a systematic review method. Valid domestic databases, including Irandoc, Magiran, Sid and Google Scholar search engine, were reviewed using the keywords of artificial intelligence and diabetes in Persian both individually and in a combined manner without time limitation until June 20, 2021. A total number of 7495 articles were retrieved, which were screened in different stages (exclusion of duplicates (1824), title and summary of the articles (5884) and full text (30) and finally 20 articles that met the criteria desired by the researchers were carefully reviewed.  Results: Among the retrieved articles, 20 articles met the inclusion criteria, of which 16 articles dealt with methods based on artificial intelligence and 4 articles dealt with the design of new systems based on artificial intelligence. Also, 10 articles examined the role of artificial intelligence in prediction, 8 articles in diagnosis, and 2 articles dealt with the control and management of diabetes. Most of the articles were related to the use of data mining methods such as artificial neural network, decision tree, etc. (16 articles). Some studies also evaluated and compared artificial intelligence methods on application, accuracy and the sensitivity of artificial intelligence in diagnosing and predicting diabetes (10 studies).  Conclusion: A systematic review of articles revealed that the use of data mining methods for diabetes management in Iran has been associated with good progress, but there is a need to design artificial intelligence systems and algorithms and more measures should be taken in the area of diabetes control and management.

Antonio J. Di Scala, Carlo Sanna

MinRank is an NP-complete problem in linear algebra whose characteristics make it attractive to build post-quantum cryptographic primitives. Several MinRank-based digital signature schemes have been proposed. In particular, two of them, MIRA and MiRitH, have been submitted to the NIST Post-Quantum Cryptography Standardization Process. In this paper, we propose a key-generation algorithm for MinRank-based schemes that reduces the size of the public key to about 50% of the size of the public key generated by the previous best (in terms of public-key size) algorithm. Precisely, the size of the public key generated by our algorithm sits in the range of 328-676 bits for security levels of 128-256 bits. We also prove that our algorithm is as secure as the previous ones.

Demircan Tas, Rohit Priyadarshi Sanatani

Sentiment analysis methods are rapidly being adopted by the field of Urban Design and Planning, for the crowdsourced evaluation of urban environments. However, most models used within this domain are able to identify positive or negative sentiment associated with a textual appraisal as a whole, without inferring information about specific urban aspects contained within it, or the sentiment associated with them. While Aspect Based Sentiment Analysis (ABSA) is becoming increasingly popular, most existing ABSA models are trained on non-urban themes such as restaurants, electronics, consumer goods and the like. This body of research develops an ABSA model capable of extracting urban aspects contained within geo-located textual urban appraisals, along with corresponding aspect sentiment classification. We annotate a dataset of 2500 crowdsourced reviews of public parks, and train a Bidirectional Encoder Representations from Transformers (BERT) model with Local Context Focus (LCF) on this data. Our model achieves significant improvement in prediction accuracy on urban reviews, for both Aspect Term Extraction (ATE) and Aspect Sentiment Classification (ASC) tasks. For demonstrative analysis, positive and negative urban aspects across Boston are spatially visualized. We hope that this model is useful for designers and planners for fine-grained urban sentiment evaluation.