Large Language Models for Chatbot Health Advice Studies

JAMA Network Open, Journal Year: 2025, Volume and Issue: 8(2), P. e2457879 - e2457879

Published: Feb. 4, 2025

Importance There is much interest in the clinical integration of large language models (LLMs) health care. Many studies have assessed ability LLMs to provide advice, but quality their reporting uncertain. Objective To perform a systematic review examine variability among peer-reviewed evaluating performance generative artificial intelligence (AI)–driven chatbots for summarizing evidence and providing advice inform development Chatbot Assessment Reporting Tool (CHART). Evidence Review A search MEDLINE via Ovid, Embase Elsevier, Web Science from inception October 27, 2023, was conducted with help sciences librarian yield 7752 articles. Two reviewers screened articles by title abstract followed full-text identify primary accuracy AI-driven (chatbot studies). then performed data extraction 137 eligible studies. Findings total were included. Studies examined topics surgery (55 [40.1%]), medicine (51 [37.2%]), care (13 [9.5%]). focused on treatment (91 [66.4%]), diagnosis (60 [43.8%]), or disease prevention (29 [21.2%]). Most (136 [99.3%]) evaluated inaccessible, closed-source did not enough information version LLM under evaluation. All lacked sufficient description characteristics, including temperature, token length, fine-tuning availability, layers, other details. describe prompt engineering phase study. The date querying reported 54 (39.4%) (89 [65.0%]) used subjective means define successful chatbot, while less than one-third addressed ethical, regulatory, patient safety implications LLMs. Conclusions Relevance In this chatbot studies, heterogeneous may CHART standards. Ethical, considerations are crucial as grows

Language: Английский

---

Implications of Large Language Models for Quality and Efficiency of Neurologic Care

Neurology, Journal Year: 2024, Volume and Issue: 102(11)

Published: May 18, 2024

Large language models (LLMs) are advanced artificial intelligence (AI) systems that excel in recognizing and generating human-like language, possibly serving as valuable tools for neurology-related information tasks. Although LLMs have shown remarkable potential various areas, their performance the dynamic environment of daily clinical practice remains uncertain. This article outlines multiple limitations challenges using settings need to be addressed, including limited reasoning, variable reliability accuracy, reproducibility bias, self-serving sponsorship exacerbating health care disparities. These further compounded by practical business considerations infrastructure requirements, associated costs. To overcome these hurdles harness effectively, this includes organizations, researchers, neurologists contemplating use practice. It is essential organizations cultivate a culture welcomes AI solutions aligns them seamlessly with operations. Clear objectives plans should guide selection solutions, ensuring they meet organizational needs budget considerations. Engaging both nonclinical stakeholders can help secure necessary resources, foster trust, ensure long-term sustainability implementations. Testing, validation, training, ongoing monitoring pivotal successful integration. For neurologists, safeguarding patient data privacy paramount. Seeking guidance from institutional technology resources informed, compliant decisions, remaining vigilant against biases LLM outputs practices responsible unbiased utilization tools. In research, obtaining review board approval crucial when dealing data, even if deidentified, ethical use. Compliance established guidelines like SPIRIT-AI, MI-CLAIM, CONSORT-AI maintain consistency mitigate research. summary, integration into neurology offers immense promise while presenting formidable challenges. Awareness vital harnessing neurologic effectively enhancing quality safety. The serves navigating transformative landscape.

Language: Английский

---

Sexual health in the era of artificial intelligence: a scoping review of the literature

Sexual Medicine Reviews, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Abstract Introduction Artificial Intelligence (AI) has witnessed significant growth in the field of medicine, leveraging machine learning, artificial neuron networks, and large language models. These technologies are effective disease diagnosis, education, prevention, while raising ethical concerns potential challenges. However, their utility sexual medicine remains relatively unexplored. Objective We aim to provide a comprehensive summary status AI medicine. Methods A search was conducted using MeSH keywords, including "artificial intelligence," "sexual medicine," health," "machine learning." Two investigators screened articles for eligibility within PubMed MEDLINE databases, with conflicts resolved by third reviewer. Articles English that reported on health were included. total 69 full-text systematically analyzed based predefined inclusion criteria. Data extraction included information article characteristics, study design, assessment methods, outcomes. Results The initial yielded 905 relevant Upon assessing full texts 121 eligibility, 52 studies unrelated excluded, resulting systematic review. analysis revealed AI's accuracy preventing, diagnosing, decision-making sexually transmitted diseases. also demonstrated ability diagnose offer precise treatment plans male female dysfunction infertility, accurately predict sex from bone teeth imaging, correctly orientation relationship issues. emerged as promising modality implications future Conclusions Further research is essential unlock presents advantages such accessibility, user-friendliness, confidentiality, preferred source information. it still lags human healthcare providers terms compassion clinical expertise.

Language: Английский

---

Evaluation of validity and reliability of AI Chatbots as public sources of information on dental trauma

Dental Traumatology, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 17, 2024

This study aimed to assess the validity and reliability of AI chatbots, including Bing, ChatGPT 3.5, Google Gemini, Claude AI, in addressing frequently asked questions (FAQs) related dental trauma.

Language: Английский

---

Language discrepancies in the performance of generative artificial intelligence models: an examination of infectious disease queries in English and Arabic

BMC Infectious Diseases, Journal Year: 2024, Volume and Issue: 24(1)

Published: Aug. 8, 2024

Assessment of artificial intelligence (AI)-based models across languages is crucial to ensure equitable access and accuracy information in multilingual contexts. This study aimed compare AI model efficiency English Arabic for infectious disease queries.

Language: Английский

---

Evidence-Based Analysis of AI Chatbots in Oncology Patient Education: Implications for Trust, Perceived Realness, and Misinformation Management

Journal of Cancer Education, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 18, 2025

Abstract The rapid integration of AI-driven chatbots into oncology education represents both a transformative opportunity and critical challenge. These systems, powered by advanced language models, can deliver personalized, real-time cancer information to patients, caregivers, clinicians, bridging gaps in access availability. However, their ability convincingly mimic human-like conversation raises pressing concerns regarding misinformation, trust, overall effectiveness digital health communication. This review examines the dual-edged role AI chatbots, exploring capacity support patient alleviate clinical burdens, while highlighting risks lack or inadequate algorithmic opacity (i.e., inability see data reasoning used make decision, which hinders appropriate future action), false information, ethical dilemmas posed human-seeming entities. Strategies mitigate these include robust oversight, transparent development, alignment with evidence-based protocols. Ultimately, responsible deployment requires commitment safeguarding core values practice, human-centered care.

Language: Английский

---

Artificial intelligence and public health: prospects, hype and challenges

Public Health Research & Practice, Journal Year: 2025, Volume and Issue: 35(1)

Published: March 12, 2025

Objectives and importance of the study Applications artificial intelligence (AI) platforms technologies to healthcare have been widely promoted as offering revolutionary improvements efficiencies in clinical practice health services organisation. Practical applications AI public are now emerging receiving similar attention. This paper provides an overview issues examples research that help separate potential from hype. Methods Selective review analysis cross-section relevant literature. Results Great exists for use research. includes immediate improving education communication directly with public, well great productive generative through chatbots virtual assistants communication. also has disease surveillance science, example epidemic pandemic early warning systems, synthetic data generation, sequential decision-making uncertain conditions (reinforcement learning) risk prediction. Most published examining these other is at a fairly stage, making it difficult probable benefits undoubtedly demonstrating but identifying challenges, quality relevance information being produced by AI; access, trust technology different populations; practical application support science. There real risks current access patterns may exacerbate existing inequities orientation towards personalisation advice divert attention away underlying social economic determinants health. Conclusions Realising not only requires further experimentation careful consideration its ethical implications thoughtful regulation. will ensure advances serve best interests individuals communities worldwide don’t inequalities.

Language: Английский

---

Exploring the role of Large Language Models (LLMs) in hematology: a systematic review of applications, benefits, and limitations

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: April 28, 2024

ABSTRACT Rationale and Objectives Large Language Models (LLMs) have the potential to enhance medical training, education, diagnosis. However, since these models were not originally designed for purposes, there are concerns regarding their reliability safety in clinical settings. This review systematically assesses utility, advantages, risks of employing LLMs field hematology. Materials Methods We searched PubMed, Web Science, Scopus databases original publications on application limited search articles published English from December 01 2022 March 25, 2024, coinciding with introduction ChatGPT. To evaluate risk bias, we used adapted version Quality Assessment Diagnostic Accuracy Studies criteria (QUADAS-2). Results Eleven studies fulfilled eligibility criteria. The varied goals methods, covering diagnosis, practice. GPT-3.5 GPT-4’s demonstrated superior performance diagnostic tasks information propagation compared other like Google’s Bard (currently called Gemini). GPT-4 particularly high accuracy such as interpreting hematology cases diagnosing hemoglobinopathy, metrics 76% 88% identifying normal blood cells. study also revealed discrepancies model consistency provided references, indicating variability reliability. Conclusion While present significant opportunities advancing hematology, incorporation into practice requires careful evaluation benefits limitations.

Language: Английский

---

Transitioning from “Dr. Google” to “Dr. ChatGPT”: the advent of artificial intelligence chatbots

Translational Andrology and Urology, Journal Year: 2024, Volume and Issue: 13(6), P. 1067 - 1070

Published: June 1, 2024

Language: Английский

---

Are AI chatbots concordant with evidence-based cancer screening recommendations?

Patient Education and Counseling, Journal Year: 2025, Volume and Issue: 134, P. 108677 - 108677

Published: Jan. 21, 2025

Language: Английский

---