This chapter on the history of the DNA barcoding enterprise attempts to set the stage for the more scholarly contributions in this volume by addressing the following questions. How did the DNA barcoding enterprise begin? What were its goals, how did it develop, and to what degree are its goals being realized? We have taken a keen interest in the barcoding movement and its relationship to taxonomy, collections, and biodiversity informatics more broadly considered. This chapter integrates our two different perspectives on barcoding. DES was the Executive Secretary of the Consortium for the Barcode of Life from 2004 to 2017, with the mission to support the success of DNA barcoding without being directly involved in generating barcode data. RDMP viewed barcoding as an important entry into the landscape of biodiversity data, with many potential linkages to other components of that landscape. We also saw it as a critical step toward the era of international genomic research that was sure to follow. Like the Mercury Program that paved the way for lunar landings by the Apollo Program, we saw DNA barcoding as the proving grounds for the interdisciplinary and international cooperation that would be needed for success of whole-genome research.

OBJECTIVE: The conclusion section of a radiology report is crucial for summarizing the primary radiological findings in natural language and essential for communicating results to clinicians. However, creating these summaries is time-consuming, repetitive, and prone to variability and errors among different radiologists. To address these issues, we evaluated a fine-tuned Text-To-Text Transfer Transformer (T5) model for abstractive summarization to automatically generate conclusions for neuroradiology MRI reports in a low-resource language.
METHODS: We retrospectively applied our method to a dataset of 232,425 neuroradiology MRI reports in Spanish. We compared various pre-trained T5 models, including multilingual T5 and those newly adapted for Spanish. For precise evaluation, we employed BLEU, METEOR, ROUGE-L, CIDEr, and cosine similarity metrics alongside expert radiologist assessments.
RESULTS: The findings are promising, with the models specifically fine-tuned for neuroradiology MRI achieving scores of 0.46, 0.28, 0.52, 2.45, and 0.87 in the BLEU-1, METEOR, ROUGE-L, CIDEr, and cosine similarity metrics, respectively. In the radiological experts\' evaluation, they found that in 75% of the cases evaluated, the conclusions generated by the system were as good as or even better than the manually generated conclusions.
CONCLUSIONS: The methods demonstrate the potential and effectiveness of customizing state-of-the-art pre-trained models for neuroradiology, yielding automatic MRI report conclusions that nearly match expert quality. Furthermore, these results underscore the importance of designing and pre-training a dedicated language model for radiology report summarization.

Access to radiology reports and images through a patient portal offers several advantages. The purpose of this study was to characterize patient\'s interactions with their radiology results. This was a retrospective study that evaluated radiography, ultrasound, computed tomography, magnetic resonance imaging, and positron emission tomography, exams performed between July 2020 and June 2021 for patients aged 12 and older. Exam information, access logs of radiology reports and images, and patient demographics were obtained from the electronic health record and image viewing software. Descriptive statistics were computed. The study included 1,685,239 exams. A total of 54.1% of reports were viewed. MRI and PET reports were viewed with the greatest frequency (70.2% and 67.6%, respectively); 25.5% of exam images were viewed, with the greatest frequency for MRI (40.1%). Exams were shared a total of 17,095 times and downloaded 8409 times; 64% of reports were viewed for patients aged 18-39 and 34% for patients aged 80 and greater. The rate of reports viewed was greater for patients with English as their preferred language (57.1%) compared to other languages (33.3%). Among those viewed, 56.5% of reports and 48.2% of images were viewed multiple times; 72.8% of images were viewed on smartphones, 25.8% on desktop computers, and 1.4% on tablets. Patients utilize a portal to view reports and view and share images. Continued efforts are warranted to promote the use of portals and create patient-friendly imaging results to help empower patients.

Large language models (LLMs) have shown promise in accelerating radiology reporting by summarizing clinical findings into impressions. However, automatic impression generation for whole-body PET reports presents unique challenges and has received little attention. Our study aimed to evaluate whether LLMs can create clinically useful impressions for PET reporting. To this end, we fine-tuned twelve open-source language models on a corpus of 37,370 retrospective PET reports collected from our institution. All models were trained using the teacher-forcing algorithm, with the report findings and patient information as input and the original clinical impressions as reference. An extra input token encoded the reading physician\'s identity, allowing models to learn physician-specific reporting styles. To compare the performances of different models, we computed various automatic evaluation metrics and benchmarked them against physician preferences, ultimately selecting PEGASUS as the top LLM. To evaluate its clinical utility, three nuclear medicine physicians assessed the PEGASUS-generated impressions and original clinical impressions across 6 quality dimensions (3-point scales) and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. When physicians assessed LLM impressions generated in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08/5. On average, physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P = 0.41). In summary, our study demonstrated that personalized impressions generated by PEGASUS were clinically useful in most cases, highlighting its potential to expedite PET reporting by automatically drafting impressions.

The inclusion of comparison studies within radiology reports is an important, standard practice. Despite this, we identified that after-hours preliminary reports rendered by trainees within our institution often omitted reference to comparison studies for pediatric inpatient portable radiographs. We addressed this issue through a quality improvement project targeting pediatric radiographs. Key interventions included modifying the structured reports by removing default text in the comparison field, designating the comparison field as mandatory, and restructuring the report templates to remove extraneous information. We also initiated a targeted educational campaign. 392 reports before and 267 reports after intervention (total 732 reports) were evaluated to determine the number of reports lacking comparison information when comparisons were available. Following the interventions, there was a statistically significant decrease in incomplete reports from 12.5% to 6%. This project highlights the success of utilizing structured reporting to improve the quality of trainee reports.

UNASSIGNED: To determine if fine-tuned large language models (LLMs) can generate accurate, personalized impressions for whole-body PET reports.
UNASSIGNED: Twelve language models were trained on a corpus of PET reports using the teacher-forcing algorithm, with the report findings as input and the clinical impressions as reference. An extra input token encodes the reading physician\'s identity, allowing models to learn physician-specific reporting styles. Our corpus comprised 37,370 retrospective PET reports collected from our institution between 2010 and 2022. To identify the best LLM, 30 evaluation metrics were benchmarked against quality scores from two nuclear medicine (NM) physicians, with the most aligned metrics selecting the model for expert evaluation. In a subset of data, model-generated impressions and original clinical impressions were assessed by three NM physicians according to 6 quality dimensions (3-point scale) and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. Bootstrap resampling was used for statistical analysis.
UNASSIGNED: Of all evaluation metrics, domain-adapted BARTScore and PEGASUSScore showed the highest Spearman\'s ρ correlations (ρ=0.568 and 0.563) with physician preferences. Based on these metrics, the fine-tuned PEGASUS model was selected as the top LLM. When physicians reviewed PEGASUS-generated impressions in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08 out of 5. Physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P=0.41).
UNASSIGNED: Personalized impressions generated by PEGASUS were clinically useful, highlighting its potential to expedite PET reporting.

In a retrospective single-center study, the authors assessed the efficacy of an automated imaging examination assignment system for enhancing the diversity of subspecialty examinations reported by oncologic imaging fellows. The study aimed to mitigate traditional biases of manual case selection and ensure equitable exposure to various case types. Methods included evaluating the proportion of \"uncommon\" to \"common\" cases reported by fellows before and after system implementation and measuring the weekly Shannon Diversity Index to determine case distribution equity. The proportion of reported uncommon cases more than doubled from 8.6% to 17.7% in total, at the cost of a concurrent 9.0% decrease in common cases from 91.3% to 82.3%. The weekly Shannon Diversity Index per fellow increased significantly from 0.66 (95% CI: 0.65, 0.67) to 0.74 (95% CI: 0.72, 0.75; P < .001), confirming a more balanced case distribution among fellows after introduction of the automatic assignment. © RSNA, 2023 Keywords: Computer Applications, Education, Fellows, Informatics, MRI, Oncologic Imaging.

The Italian Government planned to invest €15 billion of European funds on National Health Service digitalization and primary care enhancement. The critical burden brought by the pandemic upon hospital care mean these investments could no longer be delayed, considering the extraordinary backlogs of many treatments and the ordinary gaps of fragmented long-term care, in Italy and abroad. National guidelines have been published to standardize interventions across the Italian regions, and telemedicine is frequently mentioned as a key innovation to achieve both goals. The professional resources needed to run the facilities introduced in primary care are defined with great precision, but no details are given on how digitalization and remote care technologies must be implemented in this context. Building on this policy case, this paper focuses on what contribution digitalization and telemedicine can offer to specific primary care innovations, drawing from implemented technology-driven policies which may support the effective stratification, prevention and management of chronic patient needs, including anticipatory healthcare, population health management, adjusted clinical groups, chronic care management, quality and outcomes frameworks, patient-reported outcomes and patient-reported experience. All these policies can benefit significantly from digitalization and remote care technology, provided that some risks and limitations are considered by design.

The past decade has seen a number of impressive developments in predictive chemistry and reaction informatics driven by machine learning applications to computer-aided synthesis planning. While many of these developments have been made even with relatively small, bespoke data sets, in order to advance the role of AI in the field at scale, there must be significant improvements in the reporting of reaction data. Currently, the majority of publicly available data is reported in an unstructured format and heavily imbalanced toward high-yielding reactions, which influences the types of models that can be successfully trained. In this Perspective, we analyze several data curation and sharing initiatives that have seen success in chemistry and molecular biology. We discuss several factors that have contributed to their success and how we can take lessons from these case studies and apply them to reaction data. Finally, we spotlight the Open Reaction Database and summarize key actions the community can take toward making reaction data more findable, accessible, interoperable, and reusable (FAIR), including the use of mandates from funding agencies and publishers.

Nursing and informatics share a common strength in their use of structured representations of domains, specifically the underlying notion of \'things\' (ie, concepts, constructs, or named entities) and the relationships among those things. Accurate representation of nursing knowledge in machine-interpretable formats is a necessary next step for leveraging contemporary technologies. Expressing validated nursing theories in ontologies, and in particular formal ontologies, would serve not only nursing, but also investigators from other domains, clinical information system developers, and the users of advanced technologies such as artificial intelligence that seek to learn from the real-world data and evidence generated by nurses and others. Such efforts will enable sharing knowledge and conceptualizations about phenomena across the domains of nursing and generating, testing, revising, and providing theoretically-based perspectives when leveraging contemporary technologies. Nursing is well situated for this work, leveraging intentional and focused collaborations among nurse informaticists, scientists, and theorists.