Locally-deployed vs. cloud-based AI in healthcare: evaluating DeepSeek-R1:8b, DeepSeek-R1, and ChatGPT o3-mini-high for complex medical diagnostics.

BackgroundGlobally, young adults with mental health problems struggle to access appropriate and timely care, which may lead to a poorer future prognosis. Artificial intelligence (AI) is suggested to improve the quality of mental health care through increased capacities in diagnostics, monitoring, access, advanced decision-making, and digital consultations. Within mental health care, the design and application of AI solutions should elucidate the patient perspective on AI.ObjectiveThe aim was to explore the perceptions of AI in mental health care from the viewpoint of young adults with experience of seeking help for common mental health problems.MethodsThis was an interview study with 25 young adults aged between 18 and 30 years that applied a qualitative inductive design, with content analysis, to explore how AI-based technology can be used in mental health care.ResultsThree categories were derived from the analysis, representing the participants’ perceptions of how AI-based technology can be used in care for mental health problems. The first category entailed perceptions of AI-based technology as a digital companion, supporting individuals at difficult times, reminding and suggesting self-care activities, suggesting sources of information, and generally being receptive to changes in behavior or mood. The second category revolved around AI enabling more effective care and functioning as a tool, both for the patient and health care professionals (HCPs). Young adults expressed confidence in AI to improve triage, screening, identification, and diagnosis. The third category concerned risks and skepticism toward AI as a product developed by humans with limitations. Young adults voiced concerns about security and integrity, and about AI being autonomous, incapable of human empathy but with strong predictive capabilities.ConclusionsYoung adults recognize the potential of AI to serve as personalized support and its function as a digital guide and companion between mental health care consultations. It was believed that AI would function as a support in navigating the help-seeking process, ensuring that they avoid the “missing middle” service gap. They also voiced that AI will improve efficiency in health care, through monitoring, diagnostic accuracy, and reduction of the workload of HCPs, while simultaneously reducing the need for young adults to repeatedly tell their stories. Young adults express an ambivalence toward the use of AI in health care and voice risks of data integrity and bias. They consider AI to be more rational and objective than HCPs but do not want to forsake personal interaction with humans. Based on the results of this study and young adults’ perceptions of the monitoring capabilities of AI, future studies should define the boundaries regarding information collection responsibilities of the health care system versus the individuals’ responsibility for self-care.

The increasing integration of artificial intelligence (AI) in healthcare presents a host of ethical, legal, social, and political challenges involving various stakeholders. These challengesprompt various studies proposing frameworks and guidelines to tackle these issues, emphasizing distinct phases of AI development, deployment, and oversight. As a result, the notion of responsible AI has become widespread, incorporating ethical principles such as transparency, fairness, responsibility, and privacy.This paper explores the existing literature on AI use in healthcare to examine how it addresses, defines, and discusses the concept of responsibility. We conducted a scoping review of literature related to AI responsibility in healthcare, searching databases and reference lists between January 2017 and January 2022 for terms related to "responsibility" and "AI in healthcare", and their derivatives.Following screening, 136 articles were included. Data were grouped into four thematic categories: (1) the variety of terminology used to describe and address responsibility; (2) principles and concepts associated with responsibility; (3) stakeholders' responsibilities in AI clinical development, use, and deployment; and (4)recommendations for addressing responsibility concerns. The results show the lack of a clear definition of AI responsibility in healthcare and highlight the importance of ensuring responsible development and implementation of AI in healthcare. Further research is necessary to clarify this notion to contribute to developing frameworks regarding the type of responsibility (ethical/moral/professional, legal, and causal) of various stakeholders involved in the AI lifecycle.

A survey for large language models in biomedicine.

Over the past five years, medical question answering (QA) has witnessed rapid advancements, driven by the evolution of large language models (LLMs), explainability techniques, and the growing emphasis on human-centered AI in healthcare. In clinical settings, where decisions directly impact patient outcomes, the need for transparency, interpretability, and trust in AI-generated answers is not merely beneficial but essential..Traditional QA systems, although reasonably accurate, often lack explainability, thus continuing to function as black boxes. This opacity raises fundamental concerns about accountability, safety in high-stakes medical domains. We introduce ExplainMed++, a novel system designed to generate human-centered medical QA summaries with intelligible explanations. Our approach enhances the interpretability and reliability of QA outputs by fine-tuning state-of-the-art LLMs using domain-specific datasets such as MedQA. This design is influenced by cognitive models of physician decision-making and recent progress in self-rationale LLMs. This literature increasingly highlights the limitations of accuracy-centric but also provides evidence-based and clinically aligned explanations.We incorporate an explanation module that leverages retrieval-augmented generation and reflective reasoning to align model outputs with clinical reasoning patterns. This literature review synthesizes findings from 70 influential studies published between 2020 and 2025,spanning foundational work in biomedical NLP, explainable AI(XAI), highlighting key technological advances, unresolved challenges, and promising future directions in explainable medical QA. These works collectively illuminate both the promise and limitations of current methodologies, including prompt-based reasoning and counterfactual generation. ExplainMed++ contributes to this landscape by bridging the gap between model performance and clinical usability and also, advancing both the performance and the trust-worthiness of QA systems in healthcare.

In recent years, the integration of artificial intelligence (AI) in healthcare has led to numerous groundbreaking applications that have transformed various aspects of medical practice. One of the primary areas where AI has made substantial contributions is in medical imaging analysis. By leveraging machine learning algorithms, AI systems can assist radiologists in interpreting medical images with greater accuracy and efficiency. AI-driven tools can detect subtle abnormalities, aid in early disease detection, and facilitate more precise diagnosis and treatment planning. Predictive analytics is another key application of AI in healthcare, wherein algorithms analyze vast amounts of patient data to forecast potential health outcomes and identify individuals at high risk of developing certain conditions. Additionally, the rise of virtual health assistants powered by AI has revolutionized patient care delivery by providing personalized and accessible healthcare services. These virtual assistants, often in the form of chatbots or voice-enabled interfaces, can interact with patients, answer medical queries, schedule appointments, and even provide medication reminders. Overall, the various applications of AI in healthcare, including medical imaging analysis, predictive analytics, personalized medicine, and virtual health assistants, have demonstrated significant potential in improving diagnostic accuracy, optimizing treatment plans, and enhancing patient care delivery. As these technologies continue to evolve and mature, they have the potential to revolutionize healthcare delivery and contribute to better health outcomes for individuals worldwide. This research paper contributes to the ongoing discourse surrounding the integration of AI in healthcare by providing a comprehensive overview of its advancements, challenges, and ethical considerations.

Large language models (LLMs) are increasingly adopted in medical question answering (QA) scenarios. However, LLMs have been proven to generate hallucinations and nonfactual information, undermining their trustworthiness in high-stakes medical tasks. Conformal Prediction (CP) is now recognized as a robust framework within the broader domain of machine learning, offering statistically rigorous guarantees of marginal (average) coverage for prediction sets. However, the applicability of CP in medical QA remains to be explored. To address this limitation, this study proposes an enhanced CP framework for medical multiple-choice question answering (MCQA) tasks. The enhanced CP framework associates the non-conformance score with the frequency score of the correct option. The framework generates multiple outputs for the same medical query by leveraging self-consistency theory. The proposed framework calculates the frequency score of each option to address the issue of limited access to the model’s internal information. Furthermore, a risk control framework is incorporated into the enhanced CP framework to manage task-specific metrics through a monotonically decreasing loss function. The enhanced CP framework is evaluated on three popular MCQA datasets using off-the-shelf LLMs. Empirical results demonstrate that the enhanced CP framework achieves user-specified average (or marginal) error rates on the test set. Moreover, the results show that the test set’s average prediction set size (APSS) decreases as the risk level increases. It is concluded that it is a promising evaluation metric for the uncertainty of LLMs.

The rapid advancement of artificial intelligence (AI) in healthcare has revolutionized the industry, offering significant improvements in diagnostic accuracy, efficiency, and patient outcomes. However, the increasing adoption of AI systems also raises concerns about their environmental impact, particularly in the context of climate change. This review explores the intersection of climate change and AI in healthcare, examining the challenges posed by the energy consumption and carbon footprint of AI systems, as well as the potential solutions to mitigate their environmental impact. The review highlights the energy-intensive nature of AI model training and deployment, the contribution of data centers to greenhouse gas emissions, and the generation of electronic waste. To address these challenges, the development of energy-efficient AI models, the adoption of green computing practices, and the integration of renewable energy sources are discussed as potential solutions. The review also emphasizes the role of AI in optimizing healthcare workflows, reducing resource waste, and facilitating sustainable practices such as telemedicine. Furthermore, the importance of policy and governance frameworks, global initiatives, and collaborative efforts in promoting sustainable AI practices in healthcare is explored. The review concludes by outlining best practices for sustainable AI deployment, including eco-design, lifecycle assessment, responsible data management, and continuous monitoring and improvement. As the healthcare industry continues to embrace AI technologies, prioritizing sustainability and environmental responsibility is crucial to ensure that the benefits of AI are realized while actively contributing to the preservation of our planet.

Artificial intelligence (AI) in healthcare can potentially improve patient outcomes, operational efficiency, and diagnostic accuracy. However, it also raises serious ethical issues, especially in light of possible disparities in the distribution and accessibility of AI-powered healthcare resources. This study investigates how AI might affect health disparities. It bases its proposal for an equitable AI implementation framework on the justice teachings of the Catholic Church. In line with the Church's ethical commitment to social justice, the paper makes an ethical case for a responsible approach to AI in healthcare by examining the concepts of human dignity, the common good, and preferential option for the poor.

Medical question answering aims to enhance diagnostic support, improve patient education, and assist in clinical decision-making by automatically answering medical-related queries, which is an important foundation for realizing intelligent healthcare. Existing methods predominantly focus on extracting key information from a single data source, e.g., CT image, for answering. However, these methods are not enough to promote the development of intelligent healthcare, because they lack comprehensive medical diagnosis capabilities, which usually require the integration of multi-source data (e.g., laboratory tests, radiology images, pathology images, etc.) for processing. To address these limitations, our paper introduces the extended task of medical question answering, named medical diagnosis question answering MedDQA. MedDQA task aims to answer questions related to medical diagnosis based on multi-source data. Specifically, we introduce a corresponding dataset that incorporates multi-source diagnostic information from 250,917 patients in clinical data from hospital records, and utilize a large-scale model for constructing Q&A pairs. We propose a novel system based on large language models, named medical multi-agent (MMA) system, which includes a mechanism of multiple agents to handle different medical tasks. Each agent is specifically tailored to process various modalities of data and provide outputs in a uniform textual modality. Experimental results demonstrate that the MMA system's architecture significantly enhances the handling of multi-source data, thereby improving medical diagnosis, establishing a robust baseline for future research.

Qure.AI, a leading company in artificial intelligence (AI) applied to healthcare, has developed a suite of innovative solutions to revolutionize medical diagnosis and treatment. With a plethora of FDA-approved tools for clinical use, Qure.AI continually strives for innovation in integrating AI into healthcare systems. This article delves into the efficacy of Qure.AI's chest X-ray interpretation tool, "qXR,"in medicine, drawing from a comprehensive review of clinical trials conducted by various institutions. Key applications of AI in healthcare include machine learning, deep learning, and natural language processing (NLP), all of which contribute to enhanced diagnostic accuracy, efficiency, and speed. Through the analysis of vast datasets, AI algorithms assist physicians in interpreting medical data and making informed decisions, thereby improving patient care outcomes. Illustrative examples highlight AI's impact on medical imaging, particularly in the diagnosis of conditions such as breast cancer, heart failure, and pulmonary nodules. AI can significantly reduce diagnostic errors and expedite the interpretation of medical images, leading to more timely interventions and treatments. Furthermore, AI-powered predictive analytics enable early detection of diseases and facilitate personalized treatment plans, thereby reducing healthcare costs and improving patient outcomes. The efficacy of AI in healthcare is underscored by its ability to complement traditional diagnostic methods, providing physicians with valuable insights and support in clinical decision-making. As AI continues to evolve, its role in patient care and medical research is poised to expand, promising further advancements in diagnostic accuracy and treatment efficacy.

BACKGROUND Medical question answering (QA) is essential for various medical applications. While small-scale pre-training language models (PLMs) are widely adopted in open-domain QA tasks through fine-tuning with related datasets, applying this approach in the medical domain requires significant and rigorous integration of external knowledge. Knowledge-enhanced small-scale PLMs have been proposed to incorporate knowledge bases (KBs) to improve performance, as KBs contain vast amounts of factual knowledge. Large language models (LLMs) contain a vast amount of knowledge and have attracted significant research interest due to their outstanding natural language processing (NLP) capabilities. KBs and LLMs can provide external knowledge to enhance small-scale models in medical QA. OBJECTIVE KBs consist of structured factual knowledge that must be converted into sentences to align with the input format of PLMs. However, these converted sentences often lack semantic coherence, potentially causing them to deviate from the intrinsic knowledge of KBs. LLMs, on the other hand, can generate natural, semantically rich sentences, but they may also produce irrelevant or inaccurate statements. Retrieval-augmented generation (RAG) paradigm enhances LLMs by retrieving relevant information from an external database before responding. By integrating LLMs and KBs using the RAG paradigm, it is possible to generate statements that combine the factual knowledge of KBs with the semantic richness of LLMs, thereby enhancing the performance of small-scale models. In this paper, we explore a RAG fine-tuning method, RAG-mQA, that combines KBs and LLMs to improve small-scale models in medical QA. METHODS In the RAG fine-tuning scenario, we adopt medical KBs as an external database to augment the text generation of LLMs, producing statements that integrate medical domain knowledge with semantic knowledge. Specifically, KBs are used to extract medical concepts from the input text, while LLMs are tasked with generating statements based on these extracted concepts. In addition, we introduce two strategies for constructing knowledge: KB-based and LLM-based construction. In the KB-based scenario, we extract medical concepts from the input text using KBs and convert them into sentences by connecting the concepts sequentially. In the LLM-based scenario, we provide the input text to an LLM, which generates relevant statements to answer the question. For downstream QA tasks, the knowledge produced by these three strategies is inserted into the input text to fine-tune a small-scale PLM. F1 and exact match (EM) scores are employed as evaluation metrics for performance comparison. Fine-tuned PLMs without knowledge insertion serve as baselines. Experiments are conducted on two medical QA datasets: emrQA (English) and MedicalQA (Chinese). RESULTS RAG-mQA achieved the best results on both datasets. On the MedicalQA dataset, compared to the KB-based and LLM-based enhancement methods, RAG-mQA improved the F1 score by 0.59% and 2.36%, and the EM score by 2.96% and 11.18%, respectively. On the emrQA dataset, the EM score of RAG-mQA exceeded those of the KB-based and LLM-based methods by 4.65% and 7.01%, respectively. CONCLUSIONS Experimental results demonstrate that RAG fine-tuning method can improve the model performance in medical QA. RAG-mQA achieves greater improvements compared to other knowledge-enhanced methods. CLINICALTRIAL This study does not involve trial registration.

The Promise Fund and Hologic Inc. have partnered to expand access to AI-supported breast cancer screening exams in a medically underserved population. As part of this initiative, patient focus groups and patient navigator interviews were conducted to explore patient experiences and perceptions related to breast health, mammography, and artificial intelligence (AI) in healthcare. These interviews were held, virtually, between February and March 2024, and focus groups were held, in-person, on April 9-10, 2024, with participants at FoundCare and the Community Health Center. FoundCare, a federally qualified health center (FQHC), and Community Health Center, a free clinic, both collaborate with the Promise Fund in promoting access to women’s breast and cervical health screenings, diagnostic follow up and cancer care services. The in-person sessions, attended by twenty patients, and the virtual interviews, attended by six patient navigators, were designed to represent diverse linguistic, racial, and cultural backgrounds, including multiple Spanish-speaking communities from Mexico, Dominican Republic, Guatemala, Chile, and Venezuela. All patient navigators were adult women from various free clinics and FQHCs. Patient participants were adult females, all at or below 200% of the Federal Poverty Guidelines. Key themes from the discussions included: 1. Health Information Sources: Patients primarily relied on the internet, community health centers, medical visits, family, and cultural community communications for health information. Some patients expressed difficulty in keeping up with health information and emphasized the importance of direct medical consultations with providers and preventive care. Patient navigators were a critical source of information once the patient could access and be connected to that resource. Clinical health and more upstream social services, such as transportation to health appointments and family food security, were also critical needs that patient navigators were key in facilitating. 2. Mammogram Experiences: Experiences with mammograms varied, with some patients reporting pain and discomfort, particularly those with implants. Regular screenings, family history of breast cancer, and personal vigilance were common motivators for mammograms. Financial barriers, insurance issues, and the need for patient advocacy were frequently highlighted. 3. AI in Healthcare: Patients had mixed levels of awareness and understanding of AI. Many associated AI with advanced diagnostics and potential improvements in early disease detection and surgical precision. Concerns included the potential loss of personal interactions with healthcare providers, privacy issues, and the fear of job displacement. However, patients had key opinions on AI that were more favorable than anticipated. There was optimism about AI’s ability to enhance diagnostic accuracy, patient experience, provider trustworthiness, and treatment outcomes. Additionally, both patients and patient navigators preferred that physicians and AI work together. Patient navigators were even more familiar with AI. Given the critical role patient navigators hold, their knowledge may play an integral role in improving patient education and access to new technologies in the future. 4. Whole Health Experience: Patients expressed a desire for a more comfortable and supportive mammography process, greater access to care, enhanced trust between patients and providers, and comprehensive information sharing across healthcare providers. Education on breast cancer, early detection, and AI in healthcare was identified as a critical need. Conclusion: The findings underscore the importance of trustworthy, patient-centered approaches in healthcare, particularly in the integration of AI technologies. Enhancing patient education and provider transparency, improving access to preventive services, and maintaining the human element in healthcare are essential for optimizing patient outcomes and satisfaction. Citation Format: Nancy Brinker. Patient Experience and Perceptions Related to Breast Health, Mammography and Artificial Intelligence in Healthcare [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2024; 2024 Dec 10-13; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(12 Suppl):Abstract nr P3-05-11.

The use of artificial intelligence (AI) and machine learning (ML) in healthcare has the potential to revolutionize the way in which patients are diagnosed, treated, and monitored. The ability of AI and ML algorithms to process and analyse large amounts of data has led to the development of new diagnostic and treatment tools that can improve patient outcomes. However, the use of these technologies in healthcare is still in its infancy, and there is a need for further research to fully understand their potential impact. Recent studies have shown that AI can improve diagnostic accuracy in a variety of medical fields, including radiology, pathology, and dermatology (Hashmi, 2017; Schüffler, 2016). In radiology, for example, deep learning algorithms have been used to analyse medical images, such as mammograms and CT scans, with a level of accuracy that is comparable to that of human radiologists (Yang, 2018). In pathology, AI algorithms have been used to analyse medical images, such as biopsy slides, with a level of accuracy that is comparable to that of human pathologists (Thrall, 2018). Furthermore, AI and ML have the potential to improve patient outcomes by identifying high-risk patients and providing personalized treatment plans. For example, machine learning algorithms have been used to predict the risk of readmission in patients with heart failure (Murphy, 2020). This can help to identify patients who are at high risk for readmission and provide them with targeted interventions to prevent readmission. Despite the potential benefits of AI and ML in healthcare, there are also potential challenges and limitations that need to be considered. These include issues related to data privacy and security, as well as concerns about the potential impact of these technologies on healthcare workforce (Hashmi, 2017). In conclusion, the use of AI and ML in healthcare has the potential to revolutionize the way in which patients are diagnosed, treated, and monitored. However, further research is needed to fully understand the potential impact of these technologies on patient outcomes and to address potential challenges and limitations.

Diabetes mellitus is a global health concern affecting millions worldwide, with profound medical and socioeconomic implications. The increasing adoption of machine learning (ML) in healthcare has revolutionized clinical decision-making by enabling predictive diagnostics, personalized treatment plans, and efficient resource allocation. Despite their potential, many ML models are often regarded as "black boxes" due to their lack of transparency, which raises significant challenges in critical fields like healthcare, where explainability is crucial for ethical and accountable decision-making (Hassija et al., 2024).Explainable Artificial Intelligence (XAI) has emerged as a solution to address these challenges by making ML models more interpretable and fostering trust among healthcare practitioners and patients. This paper explores the integration of XAI techniques with ML models for diabetes prediction, emphasizing their potential to enhance transparency, trust, and clinical utility. We present a comparative analysis of popular XAI methods, such as SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and attention mechanisms, within the context of healthcare decision support. These techniques are evaluated based on interpretability, computational efficiency, and clinical applicability, highlighting the trade-offs between accuracy and transparency.The study underscores the critical role of interpretability in advancing trust and adoption of AI-driven solutions in healthcare, while addressing challenges such as balancing model performance with explainability. Finally, future directions for deploying explainable ML in healthcare are outlined, aiming to ensure ethical, transparent, and effective AI implementation.

Artificial intelligence (AI) has the potential to revolutionize the way medicine is learned, taught, and practiced, and medical education must prepare learners for these inevitable changes. Academic medicine has, however, been slow to embrace recent AI advances. Since its launch in November 2022, ChatGPT has emerged as a fast and user-friendly large language model that can assist health care professionals, medical educators, students, trainees, and patients. While many studies focus on the technology's capabilities, potential, and risks, there is a gap in studying the perspective of end users. The aim of this study was to gauge the experiences and perspectives of graduating medical students on ChatGPT and AI in their training and future careers. A cross-sectional web-based survey of recently graduated medical students was conducted in an international academic medical center between May 5, 2023, and June 13, 2023. Descriptive statistics were used to tabulate variable frequencies. Of 325 applicants to the residency programs, 265 completed the survey (an 81.5% response rate). The vast majority of respondents denied using ChatGPT in medical school, with 20.4% (n=54) using it to help complete written assessments and only 9.4% using the technology in their clinical work (n=25). More students planned to use it during residency, primarily for exploring new medical topics and research (n=168, 63.4%) and exam preparation (n=151, 57%). Male students were significantly more likely to believe that AI will improve diagnostic accuracy (n=47, 51.7% vs n=69, 39.7%; P=.001), reduce medical error (n=53, 58.2% vs n=71, 40.8%; P=.002), and improve patient care (n=60, 65.9% vs n=95, 54.6%; P=.007). Previous experience with AI was significantly associated with positive AI perception in terms of improving patient care, decreasing medical errors and misdiagnoses, and increasing the accuracy of diagnoses (P=.001, P<.001, P=.008, respectively). The surveyed medical students had minimal formal and informal experience with AI tools and limited perceptions of the potential uses of AI in health care but had overall positive views of ChatGPT and AI and were optimistic about the future of AI in medical education and health care. Structured curricula and formal policies and guidelines are needed to adequately prepare medical learners for the forthcoming integration of AI in medicine.