Inability to express the confidence level and detect unseen classes has limited the clinical implementation of artificial intelligence in the real-world. We developed a foundation model with uncertainty estimation (FMUE) to detect 11 retinal conditions on optical coherence tomography (OCT). In the internal test set, FMUE achieved a higher F1 score of 96.76% than two state-of-the-art algorithms, RETFound and UIOS, and got further improvement with thresholding strategy to 98.44%. In the external test sets obtained from other OCT devices, FMUE achieved an accuracy of 88.75% and 92.73% before and after thresholding. Our model is superior to two ophthalmologists with a higher F1 score (95.17% vs. 61.93% &71.72%). Besides, our model correctly predicts high uncertainty scores for samples with ambiguous features, of non-target-category diseases, or with low-quality to prompt manual checks and prevent misdiagnosis. FMUE provides a trustworthy method for automatic retinal anomalies detection in the real-world clinical open set environment.

Natural Language Processing (NLP) is a key technique for developing Medical Artificial Intelligence (AI) systems that leverage Electronic Health Record (EHR) data to build diagnostic and prognostic models. NLP enables the conversion of unstructured clinical text into structured data that can be fed into AI algorithms. The emergence of the transformer architecture and large language models (LLMs) has led to remarkable advances in NLP for various healthcare tasks, such as entity recognition, relation extraction, sentence similarity, text summarization, and question answering. In this article, we review the major technical innovations that underpin modern NLP models and present state-of-the-art NLP applications that employ LLMs in radiation oncology research. However, these LLMs are prone to many errors such as hallucinations, biases, and ethical violations, which necessitate rigorous evaluation and validation before clinical deployment. As such, we propose a comprehensive framework for assessing the NLP models based on their purpose and clinical fit, technical performance, bias and trust, legal and ethical implications, and quality assurance, prior to implementation in clinical radiation oncology. Our article aims to provide guidance and insights for researchers and clinicians who are interested in developing and using NLP models in clinical radiation oncology.

For the last several years, artificial intelligence (AI) has represented the newest, most rapidly expanding frontier of radiology technology. Expo floors at all the major professional society meetings are full of vendors showcasing AI tools they have developed or integrated into their products, billed as efficiency and time-savings aids to help ease the workload of radiologists who are increasingly bogged down by vast amounts of data. Despite the promises and potential, however, widespread clinical implementation of AI in radiology has yet to occur. Early adopters are providing potential pathways for adoption, and vendors and clinicians continue to work together to ensure AI is actually doing what radiologists need it to do. According to numerous key opinion leaders in the fields of radiology and AI, there are a few main obstacles AI currently faces to widespread adoption.

The clinical implementation of Artificial Intelligence (AI) is the most viable means of uniting the interests of the healthcare industry's capital constituents: the patient, the payer, and the provider. AI can improve healthcare outcomes while reducing costs when used to address patient compliance, chronic care management, genome sequencing, and physician diagnostics by classifying treatment options. Its widespread clinical deployment is poised to transform the healthcare industry into one that maintains wellness instead of merely combating illness. Maximizing AI's clinical value depends on the proper execution of four interrelated steps, each of which represents emerging developments within the industry: The proper implementation of each of these steps will ensure a future in which AI substantially contributes to decreased costs of chronic care and patient non-adherence, while achieving patient objectives in accordance with contemporary physician economics. Their implementation will also provide physicians with a vital support tool for conducting remote diagnostics, treatment classifications and accelerated care management.

In August of 1980 Stanford hosted the annual Workshop on Artificial Intelligence in Medicine, and we organized a twoday tutorial program so that local physicians who were interested could learn about this emerging discipline. In addition, funding from the Henry J. Kaiser Family Foundation allowed us to support a questionnaire-based project to assess physicians' attitudes. Finally, a doctoral student in educational psychology, Randy Teach, joined the project that summer and brought with him much-needed skills in the areas of statistics, study design, and the use of computer-based statistical packages. The resulting study used the physicians who were attending the AIM tutorial as subjects, with a control group of M.D.'s drawn from the surrounding community. Chapter 34 summarizes the results and concludes with design recommendations derived from the data analysis. The reader is referred to that chapter for details; however, it is pertinent to reiterate here that a program's ability to give explanations for its reasoning was judged to be the single most important requirement for an advice-giving system in medicine. This observation accounts for our continued commitment to research on explanation, both in the ONCOCIN program (Langlotz and Shortliffe, 1983) and in current doctoral dissertations from the Heuristic Programming Project (Cooper, 1984; Kunz, 1984).