Journal Article User interfaces remain an important area of study Get access Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI School of Nursing, Department of Biomedical Informatics, and Data Science Institute, Columbia University, New York, NY, United States Corresponding author: Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI, School of Nursing, Department of Biomedical Informatics, and Data Science Institute, Columbia University, 630 W. 168th Street, New York, NY 10032 (sbh22@cumc.columbia.edu) https://orcid.org/0000-0001-6202-6001 Search for other works by this author on: Oxford Academic PubMed Google Scholar Journal of the American Medical Informatics Association, Volume 31, Issue 1, January 2024, Pages 13–14, https://doi.org/10.1093/jamia/ocad246 Published: 22 December 2023 Article history Editorial decision: 04 December 2023 Received: 04 December 2023 Accepted: 04 December 2023 Published: 22 December 2023

In this editorial, the first 4 Editors-in-Chief of the Journal of the American Medical Informatics Association (JAMIA) reflect on its history and future.The origins and characterization of each Editor's era represent the "lived experience" of each Editor rather than a comparison of common metrics over time.We also qualitatively assess JAMIA's progress in meeting its original vision and goals, and posit considerations for its future.Table 1 summarizes key JAMIA-related events.

Journal Article Standards in action: historical and current perspectives Get access Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI School of Nursing, Department of Biomedical Informatics and Data Science Institute, Columbia University, New York, NY 10032, United States Corresponding author: Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI, School of Nursing, Department of Biomedical Informatics and Data Science Institute, Columbia University, 630 W. 168th Street, New York, NY 10032 (sbh22@cumc.columbia.edu) https://orcid.org/0000-0001-6202-6001 Search for other works by this author on: Oxford Academic PubMed Google Scholar Journal of the American Medical Informatics Association, Volume 30, Issue 12, December 2023, Pages 1885–1886, https://doi.org/10.1093/jamia/ocad210 Published: 17 November 2023 Article history Editorial decision: 09 October 2023 Received: 09 October 2023 Accepted: 09 October 2023 Published: 17 November 2023

Over 200 health journals call on the United Nations, political leaders, and health professionals to recognise that climate change and biodiversity loss are one indivisible crisis and must be tackled together to preserve health and avoid catastrophe. This overall environmental crisis is now so severe as to be a global health emergency. The world is currently responding to the climate crisis and the nature crisis as if they were separate challenges. This is a dangerous mistake. The 28 th Conference of the Parties (COP) on climate change is about to be held in Dubai while the 16 th COP on biodiversity is due to be held in Turkey in 2024. The research communities that provide the evidence for the two COPs are unfortunately largely separate, but they were brought together for a workshop in 2020 when they concluded that: "Only by considering climate and biodiversity as parts of the same complex problem. . .can solutions be developed that avoid maladaptation and maximize the beneficial outcomes". 1 As the health world has recognised with the development of the concept of planetary health, the natural world is made up of one overall interdependent system. Damage to one subsystem can create feedback that damages another-for example, drought, wildfires, floods and the other effects of rising global temperatures destroy plant life, and lead to soil erosion and so inhibit carbon storage, which means more global warming. 2 Climate change is set to overtake deforestation and other landuse change as the primary driver of nature loss. 3 Nature has a remarkable power to restore. For example, deforested land can revert to forest through natural regeneration, and marine phytoplankton, which act as natural carbon stores, turn over one billion tonnes of photosynthesising biomass every eight days. 4 Indigenous land and sea management has a particularly important role to play in regeneration and continuing care. 5 Restoring one subsystem can help another-for example, replenishing soil could help remove greenhouse gases from the atmosphere on a vast scale. 6 But actions that may benefit one subsystem can harm another-for example, planting forests with one type of tree can remove carbon dioxide from the air but can damage the biodiversity that is fundamental to healthy ecosystems. 7 † This Comment is being published simultaneously in multiple journals.

While there are currently approaches to handle unstructured clinical data, such as manual abstraction and structured proxy variables, these methods may be time-consuming, not scalable, and imprecise. This article aims to determine whether selective prediction, which gives a model the option to abstain from generating a prediction, can improve the accuracy and efficiency of unstructured clinical data abstraction. We trained selective classifiers (logistic regression, random forest, support vector machine) to extract 5 variables from clinical notes: depression (n = 1563), glioblastoma (GBM, n = 659), rectal adenocarcinoma (DRA, n = 601), and abdominoperineal resection (APR, n = 601) and low anterior resection (LAR, n = 601) of adenocarcinoma. We varied the cost of false positives (FP), false negatives (FN), and abstained notes and measured total misclassification cost. The depression selective classifiers abstained on anywhere from 0% to 97% of notes, and the change in total misclassification cost ranged from -58% to 9%. Selective classifiers abstained on 5%-43% of notes across the GBM and colorectal cancer models. The GBM selective classifier abstained on 43% of notes, which led to improvements in sensitivity (0.94 to 0.96), specificity (0.79 to 0.96), PPV (0.89 to 0.98), and NPV (0.88 to 0.91) when compared to a non-selective classifier and when compared to structured proxy variables. We showed that selective classifiers outperformed both non-selective classifiers and structured proxy variables for extracting data from unstructured clinical notes. Selective prediction should be considered when abstaining is preferable to making an incorrect prediction.

To apply deep neural networks (DNNs) to longitudinal EHR data in order to predict suicide attempt risk among veterans. Local explainability techniques were used to provide explanations for each prediction with the goal of ultimately improving outreach and intervention efforts. The DNNs fused demographic information with diagnostic, prescription, and procedure codes. Models were trained and tested on EHR data of approximately 500000 US veterans: all veterans with recorded suicide attempts from April 1, 2005, through January 1, 2016, each paired with 5 veterans of the same age who did not attempt suicide. Shapley Additive Explanation (SHAP) values were calculated to provide explanations of DNN predictions. The DNNs outperformed logistic and linear regression models in predicting suicide attempts. After adjusting for the sampling technique, the convolutional neural network (CNN) model achieved a positive predictive value (PPV) of 0.54 for suicide attempts within 12 months by veterans in the top 0.1% risk tier. Explainability methods identified meaningful subgroups of high-risk veterans as well as key determinants of suicide attempt risk at both the group and individual level. The deep learning methods employed in the present study have the potential to significantly enhance existing suicide risk models for veterans. These methods can also provide important clues to explore the relative value of long-term and short-term intervention strategies. Furthermore, the explainability methods utilized here could also be used to communicate to clinicians the key features which increase specific veterans' risk for attempting suicide.

Identifying sets of rare diseases with shared aspects of etiology and pathophysiology may enable drug repurposing. Toward that aim, we utilized an integrative knowledge graph to construct clusters of rare diseases. Data on 3242 rare diseases were extracted from the National Center for Advancing Translational Science Genetic and Rare Diseases Information center internal data resources. The rare disease data enriched with additional biomedical data, including gene and phenotype ontologies, biological pathway data, and small molecule-target activity data, to create a knowledge graph (KG). Node embeddings were trained and clustered. We validated the disease clusters through semantic similarity and feature enrichment analysis. Thirty-seven disease clusters were created with a mean size of 87 diseases. We validate the clusters quantitatively via semantic similarity based on the Orphanet Rare Disease Ontology. In addition, the clusters were analyzed for enrichment of associated genes, revealing that the enriched genes within clusters are highly related. We demonstrate that node embeddings are an effective method for clustering diseases within a heterogenous KG. Semantically similar diseases and relevant enriched genes have been uncovered within the clusters. Connections between disease clusters and drugs are enumerated for follow-up efforts. We lay out a method for clustering rare diseases using graph node embeddings. We develop an easy-to-maintain pipeline that can be updated when new data on rare diseases emerges. The embeddings themselves can be paired with other representation learning methods for other data types, such as drugs, to address other predictive modeling problems.

Journal Article The relationship between biomedical and health informatics and society: is it time for a social contract? Get access Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI School of Nursing, Department of Biomedical Informatics, Data Science Institute, Columbia University, New York, NY, United States Corresponding author: Suzanne Bakken, PhD, RN, FAAN, FACMI, FIAHSI, School of Nursing, Department of Biomedical Informatics, Data Science Institute, Columbia University, 630 W. 168th Street, New York, NY 10032 (sbh22@cumc.columbia.edu) https://orcid.org/0000-0001-6202-6001 Search for other works by this author on: Oxford Academic PubMed Google Scholar Journal of the American Medical Informatics Association, Volume 30, Issue 10, October 2023, Pages 1591–1592, https://doi.org/10.1093/jamia/ocad169 Published: 25 September 2023 Article history Editorial decision: 11 August 2023 Received: 11 August 2023 Published: 25 September 2023

Electronic health records (EHRs) user interfaces (UI) designed for data entry can potentially impact the quality of patient information captured in the EHRs. This review identified and synthesized the literature evidence about the relationship of UI features in EHRs on data quality (DQ). We performed an integrative review of research studies by conducting a structured search in 5 databases completed on October 10, 2022. We applied Whittemore & Knafl's methodology to identify literature, extract, and synthesize information, iteratively. We adapted Kmet et al appraisal tool for the quality assessment of the evidence. The research protocol was registered with PROSPERO (CRD42020203998). Eleven studies met the inclusion criteria. The relationship between 1 or more UI features and 1 or more DQ indicators was examined. UI features were classified into 4 categories: 3 types of data capture aids, and other methods of DQ assessment at the UI. The Weiskopf et al measures were used to assess DQ: completeness (n = 10), correctness (n = 10), and currency (n = 3). UI features such as mandatory fields, templates, and contextual autocomplete improved completeness or correctness or both. Measures of currency were scarce. The paucity of studies on UI features and DQ underscored the limited knowledge in this important area. The UI features examined had both positive and negative effects on DQ. Standardization of data entry and further development of automated algorithmic aids, including adaptive UIs, have great promise for improving DQ. Further research is essential to ensure data captured in our electronic systems are high quality and valid for use in clinical decision-making and other secondary analyses.

Outcomes are important clinical study information. Despite progress in automated extraction of PICO (Population, Intervention, Comparison, and Outcome) entities from PubMed, rarely are these entities encoded by standard terminology to achieve semantic interoperability. This study aims to evaluate the suitability of the Unified Medical Language System (UMLS) and SNOMED-CT in encoding outcome concepts in randomized controlled trial (RCT) abstracts. We iteratively developed and validated an outcome annotation guideline and manually annotated clinically significant outcome entities in the Results and Conclusions sections of 500 randomly selected RCT abstracts on PubMed. The extracted outcomes were fully, partially, or not mapped to the UMLS via MetaMap based on established heuristics. Manual UMLS browser search was performed for select unmapped outcome entities to further differentiate between UMLS and MetaMap errors. Only 44% of 2617 outcome concepts were fully covered in the UMLS, among which 67% were complex concepts that required the combination of 2 or more UMLS concepts to represent them. SNOMED-CT was present as a source in 61% of the fully mapped outcomes. Domains such as Metabolism and Nutrition, and Infections and Infectious Diseases need expanded outcome concept coverage in the UMLS and MetaMap. Future work is warranted to similarly assess the terminology coverage for P, I, C entities. Computational representation of clinical outcomes is important for clinical evidence extraction and appraisal and yet faces challenges from the inherent complexity and lack of coverage of these concepts in UMLS and SNOMED-CT, as demonstrated in this study.