Yearbook of medical informatics最新文献

Objective: To summarize significant research contributions published in 2023 in the field of clinical decision support (CDS) systems and to select the best papers for the Decision Support section of the International Medical Informatics Association (IMIA) Yearbook 2024.

Methods: We refreshed a previous search query for identifying CDS research using Medical Subject Headings (MeSH) terms and related keywords. The query was executed in PubMed in January 2024. Two reviewers reviewed the search results in three stages: title-based triaging, followed by abstract screening, and then full text review. The resulting articles were sent for external review to identity best paper candidates.

Results: We retrieved 1948 articles related to CDS, of which four articles were selected as candidates for best papers. The general themes of the final three best papers were (1) improving transfer or discharge timeliness for children in pediatric intensive care units (ICUs), (2) improving acute kidney injury outcomes using medication-targeted interventions, (3) evaluating the safety of medication-related CDS in outpatient settings, and (4) demonstrating potential use cases for CDS in spaceflight missions.

Conclusion: Our synopsis highlighted the application of CDS in environments ranging from primary care to pediatric ICUs, and even spaceflight, addressing conditions such as acute kidney injury and bronchiolitis. Ongoing evaluation of the safety and effectiveness of these systems continues to be a central focus of CDS implementation efforts.

Objectives: Despite the surge in development of artificial intelligence (AI) algorithms to support clinical decision-making, few of these algorithms are used in practice. We reviewed recent literature on clinical deployment of AI-based clinical decision support systems (AI-CDSS), and assessed the maturity of AI-CDSS implementation research. We also aimed to compare and contrast implementation of rule-based CDSS with implementation of AI-CDSS, and to give recommendations for future research in this area.

Methods: We searched PubMed and Scopus for publications in 2022 and 2023 that focused on AI and/or CDSS, health care, and implementation research, and extracted: clinical setting; clinical task; translational research phase; study design; participants; implementation theory, model or framework used; and key findings.

Results: We selected and described a total of 31 recent papers addressing implementation of AI-CDSS in clinical practice, categorised into four groups: (i) Implementation theories, frameworks, and models (4 papers); (ii) Stakeholder perspectives (22 papers); (iii) Implementation feasibility (three papers); and (iv) Technical infrastructure (2 papers). Stakeholders saw potential benefits of AI-CDSS, but emphasized the need for a strong evidence base and indicated that systems should fit into clinical workflows. There were clear similarities with rule-based CDSS, but also differences with respect to trust and transparency, knowledge, intellectual property, and regulation.

Conclusions: The field of AI-CDSS implementation research is still in its infancy. It can be strengthened by grounding studies in established theories, models and frameworks from implementation science, focusing on the perspectives of stakeholder groups other than healthcare professionals, conducting more real-world implementation feasibility studies, and through development of reusable technical infrastructure that facilitates rapid deployment of AI-CDSS in clinical practice.

The importance of virtual care has been highlighted by the recent pandemic which emphasized the need for effectively providing care remotely. In addition, the development of a range of emerging technologies to support virtual care has accelerated this trend. Technologies may vary in complexity from low (e.g., technologies that can be used easily by patients) to high (e.g., use of sophisticated software and hardware to support virtual care). In this article virtual care is first defined, followed by a discussion of a range of virtual care technologies. A framework is then described that can be used to consider and reason about virtual care in terms of both technology complexity as well as patient complexity. Examples of virtual care that can be considered using the framework are provided. It is argued that achieving an appropriate fit between the level of complexity of the technology involved and patient context will lead to improved care and ultimately precision virtual care. Implications of the approach presented are explored.

Objective: In this synopsis, the editors of the Clinical Information Systems (CIS) section of the IMIA Yearbook of Medical Informatics overview recent research and propose a selection of best papers published in 2023 in the CIS field.

Methods: The CIS section editors utilize a systematic approach to collect relevant articles and determine the best papers for the section. Last year, they refined the query to include the topic of telemedicine. Through a multi-stage systematic selection process, the editors reduced the initial pool to 15 candidate papers. Each of these papers underwent at least six independent reviews, culminating in a selection meeting with the IMIA Yearbook editorial board, where the three best papers for the CIS section were chosen.

Results: The query was carried out in January 2024 retrieving 4,784 unique papers from PubMed and Web of Science, spanning 1,401 journals. The top journals included "Telemedicine Journal and e-Health" and "Journal of Medical Internet Research". Publications predominantly originated from the United States and United Kingdom. Significant contributions included advancements in predictive analytics, such as scalable models for diagnosis prediction and patient readmission, integration of digital twin technology, and improvements in data interoperability and security. The analysis underscores the continued focus on leveraging electronic health record data and the importance of patient-centered technologies in CIS.

Conclusions: These findings highlight the ongoing evolution and potential of CIS technologies in enhancing patient care, emphasizing the importance of integrating innovative solutions and patient-centered approaches in the field.

Objectives: Large language models (LLMs) are revolutionizing the natural language pro-cessing (NLP) landscape within healthcare, prompting the need to synthesize the latest ad-vancements and their diverse medical applications. We attempt to summarize the current state of research in this rapidly evolving space.

Methods: We conducted a review of the most recent studies on biomedical NLP facilitated by LLMs, sourcing literature from PubMed, the Association for Computational Linguistics Anthology, IEEE Explore, and Google Scholar (the latter particularly for preprints). Given the ongoing exponential growth in LLM-related publications, our survey was inherently selective. We attempted to abstract key findings in terms of (i) LLMs customized for medical texts, and (ii) the type of medical text being leveraged by LLMs, namely medical literature, electronic health records (EHRs), and social media. In addition to technical details, we touch upon topics such as privacy, bias, interpretability, and equitability.

Results: We observed that while general-purpose LLMs (e.g., GPT-4) are most popular, there is a growing trend in training or customizing open-source LLMs for specific biomedi-cal texts and tasks. Several promising open-source LLMs are currently available, and appli-cations involving EHRs and biomedical literature are more prominent relative to noisier data sources such as social media. For supervised classification and named entity recogni-tion tasks, traditional (encoder only) transformer-based models still outperform new-age LLMs, and the latter are typically suited for few-shot settings and generative tasks such as summarization. There is still a paucity of research on evaluation, bias, privacy, reproduci-bility, and equitability of LLMs.

Conclusions: LLMs have the potential to transform NLP tasks within the broader medical domain. While technical progress continues, biomedical application focused research must prioritize aspects not necessarily related to performance such as task-oriented evaluation, bias, and equitable use.

Objective: To identify and summarize the top bioinformatics and translational informatics (BTI) papers published in 2023, focusing on the area of precision prevention.

Methods: We conducted a literature search to identify the top papers published in 2023 in the field of BTI. Candidate papers from the search were reviewed by the section co-editors and a panel of external reviewers to select the top three papers for this year.

Results: Our literature search returned a total of 550 candidate papers, from which we identified our top 10 papers for external review. The papers were evaluated based on their novelty, significance, and quality. After rigorous review, three papers were selected as the top BTI papers for 2023. These papers showcased innovative approaches in leveraging machine learning models, integrating multi-omics data, and developing new experimental techniques. Highlights include advancements in single-cell genomics, dynamic surveillance systems, and multimodal data integration.

Conclusions: We found several trends in the ten candidate BTI papers, including the refinement of machine learning models, the expansion of diverse biological datasets, and the development of scalable experimental techniques. These trends reflect the growing importance of bioinformatics and translational informatics as a cornerstone for improving predictive and preventative healthcare measures.

Objectives: To introduce the 2024 International Medical Informatics Association (IMIA) Year-book by the editors.

Methods: The editorial provides an introduction and overview to the 2024 IMIA Yearbook with the special theme, "Digital Health for Precision in Prevention". The special topic, the survey papers and some of the best papers selected this year by section editors are introduced. Changes in the Yearbook editorial board are also described.

Results: IMIA Yearbook 2024 provides many perspectives on the popular topic called "Digital Health for Precision in Prevention". The theme expresses the aim to provide the right intervention at the right time, adapted to the needs of each individual. Many sections presented original work on this year's theme, and all sections described notable contributions from 2023 in the various medical informatics specialties covered by the Yearbook.

Conclusions: The theme of "Digital Health for Precision in Prevention" is very important now when the rapid and extensive variety of digital tools grow exponentially.

Objectives: Alzheimer's Disease (AD) is one of the most common neurodegenerative diseases, resulting in progressive cognitive decline, and so accurate and timely AD diagnosis is of critical importance. To this end, various medical technologies and computer-aided diagnosis (CAD), ranging from biosensors and raw signals to medical imaging, have been used to provide information about the state of AD. In this survey, we aim to provide a review on CAD systems for automated AD detection, focusing on different data types: namely, signals and sensors, medical imaging, and electronic medical records (EMR).

Methods: We explored the literature on automated AD detection from 2022-2023. Specifically, we focused on various data resources and reviewed several preprocessing and learning methodologies applied to each data type, as well as evaluation metrics for model performance evaluation. Further, we focused on challenges, future perspectives, and recommendations regarding automated AD diagnosis.

Results: Compared to other modalities, medical imaging was the most common data type. The prominent modality was Magnetic Resonance Imaging (MRI). In contrast, studies based on EMR data type were marginal because EMR is mostly used for AD prediction rather than detection. Several challenges were identified: data scarcity and bias, imbalanced datasets, missing information, anonymization, lack of standardization, and explainability.

Conclusion: Despite recent developments in automated AD detection, improving the trustworthiness and performance of these models, and combining different data types will improve usability and reliability of CAD tools for early AD detection in the clinical practice.

Objectives: To summarize the recent literature and research and present a selection of the best papers published online and in print in 2023 related to health information exchange (HIE).

Methods: Using Covidence as a screening and analysis tool, a systematic review of the literature was independently conducted by the two section editors. Seven studies emerged as suitable for final IMIA Yearbook consideration.

Results: Among the papers reviewed, three major themes emerged: clinical services utilization, continuity of care, and public and population health. These themes represent an increased breadth and depth of HIE application.

Conclusions: Review of the literature suggested more studies with the use of data from HIEs, perhaps suggesting increased trust in data accuracy, adequacy, and completeness. The section editors noted the increase in papers from diverse countries describing applications of HIEs suggesting more widespread implementation of HIEs worldwide. As health data standards are developed and adopted globally, this could set the stage for increased international health data exchange. The larger corpus of 2023 literature reviewed resulted in conversations by the section editors on the changing landscape of the expanding, maturing, and innovative use cases for HIEs and HIE data. This landscape bears continued watching in 2024.

Objectives: To summarize recent public health informatics and precision epidemiology developments impacting the healthcare ecosystem. The influence of new technologies and precision approaches in surveillance and management of chronic diseases is high-lighted as areas of clinical practice where digital informatics can markedly improve pop-ulation health.

Methods: In this narrative review, we summarized the main themes from research and practice to define disease prevention and public health trends. Publications on public health informatics and precision epidemiology were searched using Google Scholar us-ing the following keywords: "digital informatics", "precision in prevention", "precision epi-demiology", "public health surveillance", "clinicogenomics" and combinations thereof. In addition, we introduced the principles of a clinicogenomics registry as a case study to empower underrepresented communities and to reduce health disparities.

Results: Technology applications such as telehealth and digital information tools fre-quently intertwine with public health informatics and precision epidemiology in efforts to identify and target individuals and populations at risk of disease. There is an urgent need for more investigations and evaluation of the validity and utility of digital platforms, including artificial intelligence (AI) and predictive analytics to advance precision preven-tion and epidemiology. The major precision-based opportunities identified included: (1) the utilization of digital tools, (2) a public health strategic framework, (3) tele-health/telemonitoring tools, (4) digital twins to simulate and optimize care models, (5) clinicogenomics registries, (6) biomarker analyses and omics panels, and (7) mobile health.

Conclusions: Successful implementation of precision prevention and epidemiology ini-tiatives requires development of a researcher and practitioner workforce that is well-versed in informatics and public health. The positive impact of precision healthcare ap-proaches depends on solutions and technologies that connect digital patient information with wearable devices, mobile apps, telehealth, and digital analytics using AI. The vital components required to successfully integrate public health informatics, precision pre-vention and epidemiology are people, data, and tool systems, albeit within legal and ethical constraints. Together, these applications can significantly improve actionability of public health surveillance and societal trends in the preservation of health and disease prevention.