Generative AI is revolutionizing oncological imaging, enhancing cancer detection and diagnosis. This editorial explores its impact on expanding datasets, improving image quality, and enabling predictive oncology. We discuss ethical considerations and introduce a unique perspective on personalized cancer screening using AI-generated digital twins. This approach could optimize screening protocols, improve early detection, and tailor treatment plans. While challenges remain, generative AI in oncological imaging offers unprecedented opportunities to advance cancer care and improve patient outcomes.

暂无摘要。

How good a research scientist is ChatGPT? We systematically probed the capabilities of GPT-3.5 and GPT-4 across four central components of the scientific process: as a Research Librarian, Research Ethicist, Data Generator, and Novel Data Predictor, using psychological science as a testing field. In Study 1 (Research Librarian), unlike human researchers, GPT-3.5 and GPT-4 hallucinated, authoritatively generating fictional references 36.0% and 5.4% of the time, respectively, although GPT-4 exhibited an evolving capacity to acknowledge its fictions. In Study 2 (Research Ethicist), GPT-4 (though not GPT-3.5) proved capable of detecting violations like p-hacking in fictional research protocols, correcting 88.6% of blatantly presented issues, and 72.6% of subtly presented issues. In Study 3 (Data Generator), both models consistently replicated patterns of cultural bias previously discovered in large language corpora, indicating that ChatGPT can simulate known results, an antecedent to usefulness for both data generation and skills like hypothesis generation. Contrastingly, in Study 4 (Novel Data Predictor), neither model was successful at predicting new results absent in their training data, and neither appeared to leverage substantially new information when predicting more vs. less novel outcomes. Together, these results suggest that GPT is a flawed but rapidly improving librarian, a decent research ethicist already, capable of data generation in simple domains with known characteristics but poor at predicting novel patterns of empirical data to aid future experimentation.

The SunoCaps dataset aims to provide an innovative contribution to music data. Expert description of human-made musical pieces, from the widely used MusicCaps dataset, are used as prompts for generating complete songs for this dataset. This Automatic Music Generation is done with the state-of-the-art Suno generator of audio-based music. A subset of 64 pieces from MusicCaps is currently included, with a total of 256 generated entries. This total stems from generating four different variations for each human piece; two versions based on the original caption and two versions based on the original aspect description. As an AI-generated music dataset, SunoCaps also includes expert-based information on prompt alignment, with the main differences between prompt and final generation annotated. Furthermore, annotations describing the main discrete emotions induced by the piece. This dataset can have an array of implementations, such as creating and improving music generation validation tools, training systems for multi-layered architectures and the optimization of music emotion estimation systems.

BACKGROUND: Evaluating the accuracy and educational utility of artificial intelligence-generated medical cases, especially those produced by large language models such as ChatGPT-4 (developed by OpenAI), is crucial yet underexplored.
OBJECTIVE: This study aimed to assess the educational utility of ChatGPT-4-generated clinical vignettes and their applicability in educational settings.
METHODS: Using a convergent mixed methods design, a web-based survey was conducted from January 8 to 28, 2024, to evaluate 18 medical cases generated by ChatGPT-4 in Japanese. In the survey, 6 main question items were used to evaluate the quality of the generated clinical vignettes and their educational utility, which are information quality, information accuracy, educational usefulness, clinical match, terminology accuracy (TA), and diagnosis difficulty. Feedback was solicited from physicians specializing in general internal medicine or general medicine and experienced in medical education. Chi-square and Mann-Whitney U tests were performed to identify differences among cases, and linear regression was used to examine trends associated with physicians\' experience. Thematic analysis of qualitative feedback was performed to identify areas for improvement and confirm the educational utility of the cases.
RESULTS: Of the 73 invited participants, 71 (97%) responded. The respondents, primarily male (64/71, 90%), spanned a broad range of practice years (from 1976 to 2017) and represented diverse hospital sizes throughout Japan. The majority deemed the information quality (mean 0.77, 95% CI 0.75-0.79) and information accuracy (mean 0.68, 95% CI 0.65-0.71) to be satisfactory, with these responses being based on binary data. The average scores assigned were 3.55 (95% CI 3.49-3.60) for educational usefulness, 3.70 (95% CI 3.65-3.75) for clinical match, 3.49 (95% CI 3.44-3.55) for TA, and 2.34 (95% CI 2.28-2.40) for diagnosis difficulty, based on a 5-point Likert scale. Statistical analysis showed significant variability in content quality and relevance across the cases (P<.001 after Bonferroni correction). Participants suggested improvements in generating physical findings, using natural language, and enhancing medical TA. The thematic analysis highlighted the need for clearer documentation, clinical information consistency, content relevance, and patient-centered case presentations.
CONCLUSIONS: ChatGPT-4-generated medical cases written in Japanese possess considerable potential as resources in medical education, with recognized adequacy in quality and accuracy. Nevertheless, there is a notable need for enhancements in the precision and realism of case details. This study emphasizes ChatGPT-4\'s value as an adjunctive educational tool in the medical field, requiring expert oversight for optimal application.

UNASSIGNED: Global rates of mental health concerns are rising, and there is increasing realization that existing models of mental health care will not adequately expand to meet the demand. With the emergence of large language models (LLMs) has come great optimism regarding their promise to create novel, large-scale solutions to support mental health. Despite their nascence, LLMs have already been applied to mental health-related tasks. In this paper, we summarize the extant literature on efforts to use LLMs to provide mental health education, assessment, and intervention and highlight key opportunities for positive impact in each area. We then highlight risks associated with LLMs\' application to mental health and encourage the adoption of strategies to mitigate these risks. The urgent need for mental health support must be balanced with responsible development, testing, and deployment of mental health LLMs. It is especially critical to ensure that mental health LLMs are fine-tuned for mental health, enhance mental health equity, and adhere to ethical standards and that people, including those with lived experience with mental health concerns, are involved in all stages from development through deployment. Prioritizing these efforts will minimize potential harms to mental health and maximize the likelihood that LLMs will positively impact mental health globally.

Demographics, social determinants of health, and family history documented in the unstructured text within the electronic health records are increasingly being studied to understand how this information can be utilized with the structured data to improve healthcare outcomes. After the GPT models were released, many studies have applied GPT models to extract this information from the narrative clinical notes. Different from the existing work, our research focuses on investigating the zero-shot learning on extracting this information together by providing minimum information to the GPT model. We utilize de-identified real-world clinical notes annotated for demographics, various social determinants, and family history information. Given that the GPT model might provide text different from the text in the original data, we explore two sets of evaluation metrics, including the traditional NER evaluation metrics and semantic similarity evaluation metrics, to completely understand the performance. Our results show that the GPT-3.5 method achieved an average of 0.975 F1 on demographics extraction, 0.615 F1 on social determinants extraction, and 0.722 F1 on family history extraction. We believe these results can be further improved through model fine-tuning or few-shots learning. Through the case studies, we also identified the limitations of the GPT models, which need to be addressed in future research.

UNASSIGNED: Training data fuel and shape the development of artificial intelligence (AI) models. Intensive data requirements are a major bottleneck limiting the success of AI tools in sectors with inherently scarce data. In health care, training data are difficult to curate, triggering growing concerns that the current lack of access to health care by under-privileged social groups will translate into future bias in health care AIs. In this report, we developed an autoencoder to grow and enhance inherently scarce datasets to alleviate our dependence on big data.
UNASSIGNED: Computational study with open-source data.
UNASSIGNED: The data were obtained from 6 open-source datasets comprising patients aged 40-80 years in Singapore, China, India, and Spain.
UNASSIGNED: The reported framework generates synthetic images based on real-world patient imaging data. As a test case, we used autoencoder to expand publicly available training sets of optic disc photos, and evaluated the ability of the resultant datasets to train AI models in the detection of glaucomatous optic neuropathy.
UNASSIGNED: Area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the glaucoma detector. A higher AUC indicates better detection performance.
UNASSIGNED: Results show that enhancing datasets with synthetic images generated by autoencoder led to superior training sets that improved the performance of AI models.
UNASSIGNED: Our findings here help address the increasingly untenable data volume and quality requirements for AI model development and have implications beyond health care, toward empowering AI adoption for all similarly data-challenged fields.
UNASSIGNED: The authors have no proprietary or commercial interest in any materials discussed in this article.

Technology alters both perceptions of human intelligence and creativity and the actual processes of intelligence and creativity. Skills that were once important for human intelligence, for example, computational ones, no longer hold anywhere near the same importance they did before the age of computers. The advantage of computers is that they may lead us to focus on what we believe to be more important things than what they have replaced. In the case of penmanship, spelling, or arithmetic computation, such an argument could bear fruit. But in the case of human creativity, the loss of creative skills and attitudes may be a long-term loss to humanity. Generative AI is replicative. It can recombine and re-sort ideas, but it is not clear that it will generate the kinds of paradigm-breaking ideas the world needs right now to solve the serious problems that confront it, such as global climate change, pollution, violence, increasing income disparities, and creeping autocracy.

This paper demonstrates a new, promising method using generative artificial intelligence (AI) to augment the educational value of electronic textbooks and research papers (locally stored on user\'s machine) and maximize their potential for self-study, in a way that goes beyond the standard electronic search and indexing that is already available in all of these textbooks and files. The presented method runs fully locally on the user\'s machine, is generally affordable, and does not require high technical expertise to set up and customize with the user\'s own content.