Asunto(s)

RESUMEN

PURPOSE: Large language model (LLM) artificial intelligences may help physicians appeal insurer denials of prescribed medical services, a task that delays patient care and contributes to burnout. We evaluated LLM performance at this task for denials of radiotherapy services. METHODS: We evaluated generative pretrained transformer 3.5 (GPT-3.5; OpenAI, San Francisco, CA), GPT-4, GPT-4 with internet search functionality (GPT-4web), and GPT-3.5ft. The latter was developed by fine-tuning GPT-3.5 via an OpenAI application programming interface with 53 examples of appeal letters written by radiation oncologists. Twenty test prompts with simulated patient histories were programmatically presented to the LLMs, and output appeal letters were scored by three blinded radiation oncologists for language representation, clinical detail inclusion, clinical reasoning validity, literature citations, and overall readiness for insurer submission. RESULTS: Interobserver agreement between radiation oncologists' scores was moderate or better for all domains (Cohen's kappa coefficients: 0.41-0.91). GPT-3.5, GPT-4, and GPT-4web wrote letters that were on average linguistically clear, summarized provided clinical histories without confabulation, reasoned appropriately, and were scored useful to expedite the insurance appeal process. GPT-4 and GPT-4web letters demonstrated superior clinical reasoning and were readier for submission than GPT-3.5 letters (P < .001). Fine-tuning increased GPT-3.5ft confabulation and compromised performance compared with other LLMs across all domains (P < .001). All LLMs, including GPT-4web, were poor at supporting clinical assertions with existing, relevant, and appropriately cited primary literature. CONCLUSION: When prompted appropriately, three commercially available LLMs drafted letters that physicians deemed would expedite appealing insurer denials of radiotherapy services. LLMs may decrease this task's clerical workload on providers. However, LLM performance worsened when fine-tuned with a task-specific, small training data set.

Asunto(s)

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

The second part of the literature review on the application of artificial intelligence (AI) methods for screening, diagnosing, monitoring, and treating glaucoma provides information on how AI methods enhance the effectiveness of glaucoma monitoring and treatment, presents technologies that use machine learning, including neural networks, to predict disease progression and determine the need for anti-glaucoma surgery. The article also discusses the methods of personalized treatment based on projection machine learning methods and outlines the problems and prospects of using AI in solving tasks related to screening, diagnosing, and treating glaucoma.

Asunto(s)

Asunto(s)

RESUMEN

Artificial intelligence (AI) models for medical imaging tasks, such as classification or segmentation, require large and diverse datasets of images. However, due to privacy and ethical issues, as well as data sharing infrastructure barriers, these datasets are scarce and difficult to assemble. Synthetic medical imaging data generated by AI from existing data could address this challenge by augmenting and anonymizing real imaging data. In addition, synthetic data enable new applications, including modality translation, contrast synthesis, and professional training for radiologists. However, the use of synthetic data also poses technical and ethical challenges. These challenges include ensuring the realism and diversity of the synthesized images while keeping data unidentifiable, evaluating the performance and generalizability of models trained on synthetic data, and high computational costs. Since existing regulations are not sufficient to guarantee the safe and ethical use of synthetic images, it becomes evident that updated laws and more rigorous oversight are needed. Regulatory bodies, physicians, and AI developers should collaborate to develop, maintain, and continually refine best practices for synthetic data. This review aims to provide an overview of the current knowledge of synthetic data in medical imaging and highlights current key challenges in the field to guide future research and development.

Asunto(s)

Asunto(s)

RESUMEN

Frozen and thawed meat plays an important role in stabilizing the meat supply chain and extending the shelf life of meat. However, traditional methods of research and development (R&D) struggle to meet rising demands for quality, nutritional value, innovation, safety, production efficiency, and sustainability. Frozen and thawed meat faces specific challenges, including quality degradation during thawing. Artificial intelligence (AI) has emerged as a promising solution to tackle these challenges in R&D of frozen and thawed meat. AI's capabilities in perception, judgment, and execution demonstrate significant potential in problem-solving and task execution. This review outlines the architecture of applying AI technology to the R&D of frozen and thawed meat, aiming to make AI better implement and deliver solutions. In comparison to traditional R&D methods, the current research progress and promising application prospects of AI in this field are comprehensively summarized, focusing on its role in addressing key challenges such as rapid optimization of thawing process. AI has already demonstrated success in areas such as product development, production optimization, risk management, and quality control for frozen and thawed meat. In the future, AI-based R&D for frozen and thawed meat will also play an important role in promoting personalization, intelligent production, and sustainable development. However, challenges remain, including the need for high-quality data, complex implementation, volatile processes, and environmental considerations. To realize the full potential of AI that can be integrated into R&D of frozen and thawed meat, further research is needed to develop more robust and reliable AI solutions, such as general AI, explainable AI, and green AI.

Asunto(s)

RESUMEN

In the past few years, advances in clinical imaging in the realm of foot and ankle have been consequential and game changing. Improvements in the hardware aspects, together with the development of computer-assisted interpretation and intervention tools, have led to a noticeable improvement in the quality of health care for foot and ankle patients. Focusing on the mainstay imaging tools, including radiographs, computed tomography scans, and ultrasound, in this review study, the authors explored the literature for reports on the new achievements in improving the quality, accuracy, accessibility, and affordability of clinical imaging in foot and ankle.

Asunto(s)

RESUMEN

BACKGROUND: Robotic-assisted radical prostatectomy (RARP) is currently a first-line treatment option for men with localized prostate cancer (PCa), at least 10 years of life expectancy, and candidate for curative treatment. We performed a scoping review to evaluate the role of artificial intelligence (AI) on RARP for PCa. METHODS: A comprehensive literature search was performed using EMBASE, PubMed, and Scopus. Only English papers were accepted. The PICOS (Patient Intervention Comparison Outcome Study type) model was used; P: adult men with PCa undergoing RARP; I: use of AI; C: none; O: preoperative planning improvement and postoperative outcomes; S: prospective and retrospective studies. RESULTS: Seventeen papers were included, dealing with prediction of positive surgical margins/extraprostatic extension, biochemical recurrence, patient's outcomes, intraoperative superimposition of magnetic resonance images to identify and locate lesions for nerve-sparing surgery, identification and labeling of surgical steps, and quality of surgery. All studies found improving outcomes in procedures employing AI. CONCLUSIONS: The integration of AI in RARP represents a transformative advancement in surgical practice, augmenting surgical precision, enhancing decision-making processes and facilitating personalized patient care. This holds immense potential to improve surgical outcomes and teaching, and mitigate complications. This should be balanced against the current costs of implementation of robotic platforms with such a technology.

Asunto(s)

RESUMEN

Artificial intelligence (AI) technology is advancing rapidly, constantly presenting its application value and broad prospects in the medical field. Especially in the early intervention of burn diseases, the new developments, applications, and challenges of AI technology have a significant impact on the clinical outcomes of burn patients. Based on this, this article reviews the concept, classification, learning style, and application of AI in the early diagnosis and treatment of burn diseases, with a focus on discussing the challenges and suggestions of the application of AI technology in the medical field, in order to provide reference and suggestions for the better application of AI in the early diagnosis and treatment of burn diseases.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

Individual health data is crucial for scientific advancements, particularly in developing Artificial Intelligence (AI); however, sharing real patient information is often restricted due to privacy concerns. A promising solution to this challenge is synthetic data generation. This technique creates entirely new datasets that mimic the statistical properties of real data, while preserving confidential patient information. In this paper, we present the workflow and different services developed in the context of Germany's National Data Infrastructure project NFDI4Health. First, two state-of-the-art AI tools (namely, VAMBN and MultiNODEs) for generating synthetic health data are outlined. Further, we introduce SYNDAT (a public web-based tool) which allows users to visualize and assess the quality and risk of synthetic data provided by desired generative models. Additionally, the utility of the proposed methods and the web-based tool is showcased using data from Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Center for Cancer Registry Data of the Robert Koch Institute (RKI).

Asunto(s)

RESUMEN

INTRODUCTION: Cardiovascular diseases are a leading cause of mortality worldwide, highlighting the urgent need for accurate and efficient diagnostic tools. Echocardiography, a non-invasive imaging technique, plays a central role in the diagnosis of heart diseases, yet the potential impact of artificial intelligence (AI) on its accuracy and speed has not yet been reviewed and summarized. This scoping review aims to address this research gap by synthesizing existing evidence on AI-assisted echocardiography's. METHODS: The study followed Arksey and O'Malley's six-stage model for scoping reviews and searched the databases PubMed, Web of Science and Livivo. Inclusion criteria encompassed studies from cardiology utilizing AI for heart diseases diagnosis in adults, published from 2018 to 2023. Data extraction focused on study characteristics, AI models employed, accuracy metrics, and diagnostic speed. RESULTS: From 1059 identified studies, nine records met the inclusion criteria, categorized into view classification, left ventricular ejection fraction (LVEF) quantification, and diseases classification. Convolutional Neural Networks (CNN) were commonly used. While 44% of studies compared AI with cardiologists, those studies indicated AI's high diagnostic accuracy, with mean accuracy ranging from 87% to 92%. Three studies assessed AI's speed, demonstrating significant time savings. DISCUSSION: The review highlights AI's potential in enhancing diagnostic accuracy and efficiency in echocardiography, particularly in regions with limited access to specialized cardiologists. However, further research is needed to assess AI's specific added value compared to cardiologists, optimize training data quality, and enable real-time image processing.

Asunto(s)

RESUMEN

INTRODUCTION: Automation bias poses a significant challenge to the effectiveness of Clinical Decision Support Systems (CDSS), potentially compromising diagnostic accuracy. Previous research highlights trust, self-confidence, and task difficulty as key determinants. With the increasing availability of AI-enabled CDSS, automation bias attains new attention. This study therefore aims to identify factors influencing automation bias in a diagnostic task. METHODS: A quantitative intervention study with participants from different backgrounds (n = 210) was conducted, employing regression analysis to analyze potential factors. Automation bias was measured as the agreement rate with wrong AI-enabled recommendations. RESULTS AND DISCUSSION: Diagnostic performance, certified wound care training, physician profession, and female gender significantly reduced false agreement rates. Higher perceived benefit of the system was significantly associated with promoting false agreement. Strategies like comprehensive diagnostic training are pivotal in the prevention of automation bias when implementing CDSS. CONCLUSION: Considering factors influencing automation bias when introducing a CDSS is critical to fully leverage the benefits of such a system. This study highlights that non-specialists, who stand to gain the most from CDSS, are also the most susceptible to automation bias, emphasizing the need for specialized training to mitigate this risk and ensure diagnostic accuracy and patient safety.

Asunto(s)

RESUMEN

Importance: Safe integration of artificial intelligence (AI) into clinical settings often requires randomized clinical trials (RCT) to compare AI efficacy with conventional care. Diabetic retinopathy (DR) screening is at the forefront of clinical AI applications, marked by the first US Food and Drug Administration (FDA) De Novo authorization for an autonomous AI for such use. Objective: To determine the generalizability of the 7 ethical research principles for clinical trials endorsed by the National Institute of Health (NIH), and identify ethical concerns unique to clinical trials of AI. Design, Setting, and Participants: This qualitative study included semistructured interviews conducted with 11 investigators engaged in the design and implementation of clinical trials of AI for DR screening from November 11, 2022, to February 20, 2023. The study was a collaboration with the ACCESS (AI for Children's Diabetic Eye Exams) trial, the first clinical trial of autonomous AI in pediatrics. Participant recruitment initially utilized purposeful sampling, and later expanded with snowball sampling. Study methodology for analysis combined a deductive approach to explore investigators' perspectives of the 7 ethical principles for clinical research endorsed by the NIH and an inductive approach to uncover the broader ethical considerations implementing clinical trials of AI within care delivery. Results: A total of 11 participants (mean [SD] age, 47.5 [12.0] years; 7 male [64%], 4 female [36%]; 3 Asian [27%], 8 White [73%]) were included, with diverse expertise in ethics, ophthalmology, translational medicine, biostatistics, and AI development. Key themes revealed several ethical challenges unique to clinical trials of AI. These themes included difficulties in measuring social value, establishing scientific validity, ensuring fair participant selection, evaluating risk-benefit ratios across various patient subgroups, and addressing the complexities inherent in the data use terms of informed consent. Conclusions and Relevance: This qualitative study identified practical ethical challenges that investigators need to consider and negotiate when conducting AI clinical trials, exemplified by the DR screening use-case. These considerations call for further guidance on where to focus empirical and normative ethical efforts to best support conduct clinical trials of AI and minimize unintended harm to trial participants.

Asunto(s)

RESUMEN

This nonrandomized clinical trial investigated the electronic health record (EHR) experiences of clinicians before and after implementation of an artificial intelligence (AI)­powered clinical documentation tool.

Asunto(s)