Evaluating ChatGPT-4.0’s data analytic proficiency in epidemiological studies: A comparative analysis with SAS, SPSS, and R

Journal of Global Health, Год журнала: 2024, Номер 14

Опубликована: Март 28, 2024

OpenAI's Chat Generative Pre-trained Transformer 4.0 (ChatGPT-4), an emerging artificial intelligence (AI)-based large language model (LLM), has been receiving increasing attention from the medical research community for its innovative 'Data Analyst' feature. We aimed to compare capabilities of ChatGPT-4 against traditional biostatistical software (i.e. SAS, SPSS, R) in statistically analysing epidemiological data.

Язык: Английский

---

Medical Ethics of Large Language Models in Medicine

NEJM AI, Год журнала: 2024, Номер 1(7)

Опубликована: Июнь 17, 2024

Large language models (LLMs) have shown significant promise related to their application in medical research, education, and clinical tasks. While acknowledging capabilities, we face the challenge of striking a balance between defining holding ethical boundaries driving innovation LLM technology for medicine. We herein propose framework, grounded four bioethical principles, promote responsible use LLMs. This model requires LLMs by three parties — patient, clinician, systems that govern itself suggests potential approaches mitigating risks approach allows us ethically, equitably, effectively

Язык: Английский

---

Artificial intelligence in clinical medicine: a state-of-the-art overview of systematic reviews with methodological recommendations for improved reporting

Frontiers in Digital Health, Год журнала: 2025, Номер 7

Опубликована: Март 5, 2025

Medicine has become increasingly receptive to the use of artificial intelligence (AI). This overview systematic reviews (SRs) aims categorise current evidence about it and identify methodological state art in field proposing a classification AI model (CLASMOD-AI) improve future reporting. PubMed/MEDLINE, Scopus, Cochrane library, EMBASE Epistemonikos databases were screened by four blinded reviewers all SRs that investigated tools clinical medicine included. 1923 articles found, these, 360 examined via full-text 161 met inclusion criteria. The search strategy, methodological, medical risk bias information extracted. CLASMOD-AI was based on input, model, data training, performance metric tools. A considerable increase number observed last five years. most covered oncology accounting for 13.9% SRs, with diagnosis as predominant objective 44.4% cases). assessed 49.1% included yet only 39.2% these used specific items assess metrics. highlights need improved reporting metrics, particularly regarding training models dataset quality, both are essential comprehensive quality assessment mitigating using specialized evaluation

Язык: Английский

---

Publication Trends and Hot Spots of ChatGPT’s Application in the Medicine

Journal of Medical Systems, Год журнала: 2024, Номер 48(1)

Опубликована: Май 18, 2024

Abstract This study aimed to analyze the current landscape of ChatGPT application in medical field, assessing collaboration patterns and research topic hotspots understand impact trends. By conducting a search Web Science, we collected literature related applications medicine, covering period from January 1, 2000 up 16, 2024. Bibliometric analyses were performed using CiteSpace (V6.2., Drexel University, PA, USA) Microsoft Excel (Microsoft Corp.,WA, map among countries/regions, distribution institutions authors, clustering keywords. A total 574 eligible articles included, with 97.74% published 2023. These span various disciplines, particularly Health Care Sciences Services, extensive international involving 73 countries. In terms countries/regions studied, USA, India, China led number publications. USA ot only nearly half papers but also exhibits highest collaborative capability. Regarding co-occurrence scholars, National University Singapore Harvard held significant influence cooperation network, top three authors publications being Wiwanitkit V (10 articles), Seth I (9 Klang E (7 Kleebayoon articles). Through keyword clustering, identified 9 theme clusters, which “digital health”was not largest scale had most citations. The highlights ChatGPT’s cross-disciplinary nature showcasing its growth potential, digital health clinical decision support. Future exploration should examine socio-economic cultural impacts this trend, along specific technical uses practice.

Язык: Английский

---

Ethical Considerations and Fundamental Principles of Large Language Models in Medical Education: Viewpoint

Journal of Medical Internet Research, Год журнала: 2024, Номер 26, С. e60083 - e60083

Опубликована: Июль 7, 2024

This viewpoint article first explores the ethical challenges associated with future application of large language models (LLMs) in context medical education. These include not only concerns related to development LLMs, such as artificial intelligence (AI) hallucinations, information bias, privacy and data risks, deficiencies terms transparency interpretability but also issues concerning including emotional intelligence, educational inequities, problems academic integrity, questions responsibility copyright ownership. paper then analyzes existing AI-related legal frameworks highlights their limitations regard LLMs To ensure that are integrated a responsible safe manner, authors recommend unified framework is specifically tailored for this field. should be based on 8 fundamental principles: quality control supervision mechanisms; protection; interpretability; fairness equal treatment; integrity moral norms; accountability traceability; protection respect intellectual property; promotion research innovation. The further discuss specific measures can taken implement these principles, thereby laying solid foundation comprehensive actionable framework. Such principles provide clear guidance support approach help establish balance between technological advancement safeguards, ensuring education progress without compromising fairness, justice, or patient safety establishing more equitable, safer, efficient environment

Язык: Английский

---

Ethical dimensions of generative AI: a cross-domain analysis using machine learning structural topic modeling

International Journal of Ethics and Systems, Год журнала: 2024, Номер unknown

Опубликована: Сен. 3, 2024

Purpose The purpose of this study is to comprehensively examine the ethical implications surrounding generative artificial intelligence (AI). Design/methodology/approach Leveraging a novel methodological approach, curates corpus 364 documents from Scopus spanning 2022 2024. Using term frequency-inverse document frequency (TF-IDF) and structural topic modeling (STM), it quantitatively dissects thematic essence discourse in AI across diverse domains, including education, healthcare, businesses scientific research. Findings results reveal range concerns various sectors impacted by AI. In academia, primary focus on issues authenticity intellectual property, highlighting challenges AI-generated content maintaining academic integrity. healthcare sector, emphasis shifts medical decision-making patient privacy, reflecting about reliability security advice. also uncovers significant discussions educational financial settings, demonstrating broad impact societal professional practices. Research limitations/implications This provides foundation for crafting targeted guidelines regulations AI, informed systematic analysis using STM. It highlights need dynamic governance continual monitoring AI’s evolving landscape, offering model future research policymaking fields. Originality/value introduces unique combination TF-IDF STM analyze large corpus, new insights into multiple domains.

Язык: Английский

---

The Role of Social Determinants of Health in Childhood Epilepsy

Turkish Archives of Pediatrics, Год журнала: 2025, Номер 60(1), С. 13 - 21

Опубликована: Янв. 3, 2025

Social determinants of health (SDHs) are significant and potentially modifiable drivers neurologic diseases, including childhood epilepsy. greatly influence the epidemiology, management, outcomes associated with these conditions. affect every aspect a family's journey epilepsy-from initial diagnosis to accessing effective treatments ongoing care. Despite notable advancements in understanding genetic molecular underpinnings pediatric epilepsies, there remains relative lack knowledge about nature impact SDHs on disorders. Epilepsy is symptom much more profound underlying health. Addressing broader context epilepsy can transform outcomes. This narrative review appraises some available evidence explores possible solutions.

Язык: Английский

---

Health AI poses distinct harms and potential benefits for disabled people

Nature Medicine, Год журнала: 2025, Номер 31(1), С. 12 - 13

Опубликована: Янв. 1, 2025

Язык: Английский

---

Prospects and perils of ChatGPT in diabetes

World Journal of Diabetes, Год журнала: 2025, Номер 16(3)

Опубликована: Янв. 20, 2025

ChatGPT, a popular large language model developed by OpenAI, has the potential to transform management of diabetes mellitus. It is conversational artificial intelligence trained on extensive datasets, although not specifically health-related. The development and core components ChatGPT include neural networks machine learning. Since current yet diabetes-related it limitations such as risk inaccuracies need for human supervision. Nevertheless, aid in patient engagement, medical education, clinical decision support. In management, can contribute personalized dietary guidelines, providing emotional Specifically, being tested scenarios assessment obesity, screening diabetic retinopathy, provision guidelines ketoacidosis. Ethical legal considerations are essential before be integrated into healthcare. Potential concerns relate data privacy, accuracy responses, maintenance patient-doctor relationship. Ultimately, while models hold immense revolutionize care, one needs weigh their limitations, ethical implications, integration promises future proactive, personalized, patient-centric care management.

Язык: Английский

---

Artificial intelligence in healthcare

International Journal of Clinical Medical Research, Год журнала: 2025, Номер 3(2), С. 22 - 23

Опубликована: Фев. 15, 2025

In recent years, enhanced artificial intelligence algorithms and more access to training data have enabled augment or supplant certain functions of physicians. Nonetheless, the interest diverse stakeholders in application medicine has not resulted extensive acceptance. Numerous experts indicated that a primary cause for limited adoption is lack openness surrounding algorithms, particularly black-box algorithms. Clinical medicine, evidence-based practice, depends on transparency decision-making. If there no medically explicable physician cannot adequately elucidate decision-making process, patient's trust them will diminish. To resolve concern associated with specific models, explainable arisen.

Язык: Английский

---