Search

Drug repositioning has been based largely on genomic signatures of drugs and diseases. One challenge in these efforts lies in connecting the molecular signatures of drugs into clinical responses, including therapeutic and side effects, to the repurpose of drugs. We addressed this challenge by evaluating drug-drug relationships using a phenotypic and molecular-based approach that integrates therapeutic indications, side effects, and gene expression profiles induced by each drug. Using cosine similarity, relationships between 445 drugs were evaluated based on high-dimensional spaces consisting of phenotypic terms of drugs and genomic signatures, respectively. One hundred fifty-one of 445 drugs comprising 450 drug pairs displayed significant similarities in both phenotypic and genomic signatures ( P value < 0.05). We also found that similar gene expressions of drugs do indeed yield similar clinical phenotypes. We generated similarity matrixes of drugs using the expression profiles they induce in a cell line and phenotypic effects. [ABSTRACT FROM AUTHOR]

The advances of genomics, sequencing, and high throughput technologies have led to the creation of large volumes of diverse datasets for drug discovery. Analyzing these datasets to better understand disease and discover new drugs is becoming more common. Recent open data initiatives in basic and clinical research have dramatically increased the types of data available to the public. The past few years have witnessed successful use of big data in many sectors across the whole drug discovery pipeline. In this review, we will highlight the state of the art in leveraging big data to identify new targets, drug indications, and drug response biomarkers in this era of precision medicine. [ABSTRACT FROM AUTHOR]

A central premise in systems pharmacology is that structurally similar compounds have similar cellular responses; however, this principle often does not hold. One of the most widely used measures of cellular response is gene expression. By integrating gene expression data from Library of Integrated Network-based Cellular Signatures (LINCS) with chemical structure and bioactivity data from PubChem, we performed a large-scale correlation analysis of chemical structures and gene expression profiles of over 11,000 compounds taking into account confounding factors such as biological conditions (e.g., cell line, dose) and bioactivities. We found that structurally similar compounds do indeed yield similar gene expression profiles. There is an ∼20% chance that two structurally similar compounds (Tanimoto Coefficient ≥ 0.85) share significantly similar gene expression profiles. Regardless of structural similarity, two compounds tend to share similar gene expression profiles in a cell line when they are administrated at a higher dose or when the cell line is sensitive to both compounds. [ABSTRACT FROM AUTHOR]

Genome-wide association studies (GWAS) have revealed novel genes and pathways involved in lung disease, many of which are potential targets for therapy. However, despite numerous successes, a large proportion of the genetic variance in disease risk remains unexplained, and the function of the associated genetic variations identified by GWAS and the mechanisms by which they alter individual risk for disease or pathogenesis are still largely unknown. The National Heart, Lung, and Blood Institute (NHLBI) convened a 2-day workshop to address these shortcomings and to make recommendations for future research areas that will move the scientific community beyond gene discovery. Topics of individual sessions ranged from data integration and systems genetics to functional validation of genetic variations in humans and model systems. There was broad consensus among the participants for five high-priority areas for future research, including the following: (1) integrated approaches to characterize the function of genetic variations, (2) studies on the role of environment and mechanisms of transcriptional and post-transcriptional regulation, (3) development of model systems to study gene function in complex biological systems, (4) comparative phenomic studies across lung diseases, and (5) training in and applications of bioinformatic approaches for comprehensive mining of existing data sets. Last, it was agreed that future research on lung diseases should integrate approaches across "-omic" technologies and to include ethnically/racially diverse populations in human studies of lung disease whenever possible. [ABSTRACT FROM AUTHOR]

Objective: We investigated the common-disease relevant information obtained from sequencing compared with that reported from genotyping arrays.Materials and Methods: Using 187 publicly available individual human genomes, we constructed genomic disease risk summaries based on 55 common diseases with reported gene-disease associations in the research literature using two different risk models, one based on the product of likelihood ratios and the other on the allelic variant with the maximum associated disease risk. We also constructed risk profiles based on the single nucleotide polymorphisms (SNPs) of these individuals that could be measured or imputed from two common genotyping array platforms.Results: We show that the model risk predictions derived from sequencing differ substantially from those obtained from the SNPs measured on commercially available genotyping arrays for several different non-monogenic diseases, although high density genotyping arrays give identical results for many diseases.Conclusions: Our approach may be used to compare the ability of different platforms to probe known genetic risks disease by disease. [ABSTRACT FROM AUTHOR]

Antibodies to human leukocyte antigens (HLAs) are a risk factor for acute renal allograft rejection and loss. The role of non-HLAs and their significance to allograft rejection have gained recent attention. Here, we applied protein microarray technology, with the capacity to simultaneously identify 5056 potential antigen targets, to assess non-HLA antibody formation in 15 pediatric renal transplant recipients during allograft rejection. Comparison of the pre- and post-transplant serum identified de novo antibodies to 229 non-HLA targets, 36 of which were present in multiple patients at allograft rejection. On the basis of its reactivity, protein kinase Czeta (PKCzeta) was selected for confirmatory testing and clinical study. Immunohistochemical analysis found PKCzeta both within the renal tissue and infiltrating lymphocytes at rejection. Patients who had an elevated anti-PKCzeta titer developed rejection, which was significantly more likely to result in graft loss. The absence of C4d deposition in patients with high anti-PKCzeta titers suggests that it is a marker of severe allograft injury rather than itself being pathogenic. Presumably, critical renal injury and inflammation associated with this rejection subtype lead to the immunological exposure of PKCzeta with resultant antibody formation. Prospective assessment of serum anti-PKCzeta levels at allograft rejection will be needed to confirm these results. [ABSTRACT FROM AUTHOR]

Inflammatory skin disease is characterized by a pathologic interplay between skin cells and immunocytes and can result in disfiguring cutaneous lesions and systemic inflammation. Immunosuppression is commonly used to target the inflammatory component; however, these drugs are often expensive and associated with side effects. To identify previously unidentified targets, we carried out a nonbiased informatics screen to identify drug compounds with an inverse transcriptional signature to keratinocyte inflammatory signals. Using psoriasis, a prototypic inflammatory skin disease, as a model, we used pharmacologic, transcriptomic, and proteomic characterization to find that benzamil, the benzyl derivative of the US Food and Drug Administration-approved diuretic amiloride, effectively reversed keratinocyte-driven inflammatory signaling. Through three independent mouse models of skin inflammation (Rac1 G12V transgenic mice, topical imiquimod, and human skin xenografts from patients with psoriasis), we found that benzamil disrupted pathogenic interactions between the small GTPase Rac1 and its adaptor NCK1. This reduced STAT3 and NF-κB signaling and downstream cytokine production in keratinocytes. Genetic knockdown of sodium channels or pharmacological inhibition by benzamil prevented excess Rac1-NCK1 binding and limited proinflammatory signaling pathway activation in patient-derived keratinocytes without systemic immunosuppression. Both systemic and topical applications of benzamil were efficacious, suggesting that it may be a potential therapeutic avenue for treating skin inflammation.

Objective: We aimed to investigate the impact of social circumstances on cancer therapy selection using natural language processing to derive insights from social worker documentation., Materials and Methods: We developed and employed a Bidirectional Encoder Representations from Transformers (BERT) based approach, using a hierarchical multi-step BERT model (BERT-MS), to predict the prescription of targeted cancer therapy to patients based solely on documentation by clinical social workers. Our corpus included free-text clinical social work notes, combined with medication prescription information, for all patients treated for breast cancer at UCSF between 2012 and 2021. We conducted a feature importance analysis to identify the specific social circumstances that impact cancer therapy regimen., Results: Using only social work notes, we consistently predicted the administration of targeted therapies, suggesting systematic differences in treatment selection exist due to non-clinical factors. The findings were confirmed by several language models, with GatorTron achieving the best performance with an area under the receiver operating characteristic curve (AUROC) of 0.721 and a Macro F1 score of 0.616. The UCSF BERT-MS model, capable of leveraging multiple pieces of notes, surpassed the UCSF-BERT model in both AUROC and Macro-F1. Our feature importance analysis identified several clinically intuitive social determinants of health that potentially contribute to disparities in treatment., Discussion: Leveraging social work notes can be instrumental in identifying disparities in clinical decision-making. Hypotheses generated in an automated way could be used to guide patient-specific quality improvement interventions. Further validation with diverse clinical outcomes and prospective studies is essential., Conclusions: Our findings indicate that significant disparities exist among breast cancer patients receiving different types of therapies based on social determinants of health. Social work reports play a crucial role in understanding these disparities in clinical decision-making., Competing Interests: A.J.B. is a co-founder and consultant to Personalis and NuMedii; consultant to Mango Tree Corporation, and in the recent past, Samsung, 10x Genomics, Helix, Pathway Genomics, and Verinata (Illumina); has served on paid advisory panels or boards for Geisinger Health, Regenstrief Institute, Gerson Lehman Group, AlphaSights, Covance, Novartis, Genentech, and Merck, and Roche; is a shareholder in Personalis and NuMedii; is a minor shareholder in Apple, Meta (Facebook), Alphabet (Google), Microsoft, Amazon, Snap, 10x Genomics, Illumina, Regeneron, Sanofi, Pfizer, Royalty Pharma, Moderna, Sutro, Doximity, BioNtech, Invitae, Pacific Biosciences, Editas Medicine, Nuna Health, Assay Depot, and Vet24seven, and several other non-health related companies and mutual funds; and has received honoraria and travel reimbursement for invited talks from Johnson and Johnson, Roche, Genentech, Pfizer, Merck, Lilly, Takeda, Varian, Mars, Siemens, Optum, Abbott, Celgene, AstraZeneca, AbbVie, Westat, and many academic institutions, medical or disease-specific foundations and associations, and health systems. A.J.B. receives royalty payments through Stanford University, for several patents and other disclosures licensed to NuMedii and Personalis. A.J.B.’s research has been funded by NIH, Peraton (as the prime on an NIH contract), Genentech, Johnson and Johnson, FDA, Robert Wood Johnson Foundation, Leon Lowenstein Foundation, Intervalien Foundation, Priscilla Chan and Mark Zuckerberg, the Barbara and Gerson Bakar Foundation, and in the recent past, the March of Dimes, Juvenile Diabetes Research Foundation, California Governor’s Office of Planning and Research, California Institute for Regenerative Medicine, L’Oreal, and Progenity. None of these entities had any bearing on the design of this study or the writing of the manuscript., (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association.)

The release of GPT-4 and other large language models (LLMs) has the potential to transform healthcare. However, existing research evaluating LLM performance on real-world clinical notes is limited. Here, we conduct a highly-powered study to determine whether LLMs can provide clinical recommendations for three tasks (admission status, radiological investigation(s) request status, and antibiotic prescription status) using clinical notes from the Emergency Department. We randomly selected 10,000 Emergency Department visits to evaluate the accuracy of zero-shot, GPT-3.5-turbo- and GPT-4-turbo-generated clinical recommendations across four different prompting strategies. We found that both GPT-4-turbo and GPT-3.5-turbo performed poorly compared to a resident physician, with accuracy scores 8% and 24%, respectively, lower than physician on average. Both LLMs tended to be overly cautious in its recommendations, with high sensitivity at the cost of specificity. Our findings demonstrate that, while early evaluations of the clinical use of LLMs are promising, LLM performance must be significantly improved before their deployment as decision support systems for clinical recommendations and other complex tasks., (© 2024. The Author(s).)

Objective: Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations., Materials and Methods: We curated a dataset of 769 breast cancer pathology reports, manually labeled with 12 categories, to compare zero-shot classification capability of the following LLMs: GPT-4, GPT-3.5, Starling, and ClinicalCamel, with task-specific supervised classification performance of 3 models: random forests, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model., Results: Across all 12 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, LSTM-Att (average macro F1-score of 0.86 vs 0.75), with advantage on tasks with high label imbalance. Other LLMs demonstrated poor performance. Frequent GPT-4 error categories included incorrect inferences from multiple samples and from history, and complex task design, and several LSTM-Att errors were related to poor generalization to the test set., Discussion: On tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of data labeling. However, if the use of LLMs is prohibitive, the use of simpler models with large annotated datasets can provide comparable results., Conclusions: GPT-4 demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in clinical studies., (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association.)

Background: Exosome therapy shows potential for cardiac repair after injury. However, intrinsic challenges such as short half-life and lack of clear targets hinder the clinical feasibility. Here, we report a noninvasive and repeatable method for exosome delivery through inhalation after myocardial infarction (MI), which we called stem cell-derived exosome nebulization therapy (SCENT)., Methods: Stem cell-derived exosomes were characterized for size distribution and surface markers. C57BL/6 mice with MI model received exosome inhalation treatment through a nebulizer for 7 consecutive days. Echocardiographies were performed to monitor cardiac function after SCENT, and histological analysis helped with the investigation of myocardial repair. Single-cell RNA sequencing of the whole heart was performed to explore the mechanism of action by SCENT. Last, the feasibility, efficacy, and general safety of SCENT were demonstrated in a swine model of MI, facilitated by 3-dimensional cardiac magnetic resonance imaging., Results: Recruitment of exosomes to the ischemic heart after SCENT was detected by ex vivo IVIS imaging and fluorescence microscopy. In a mouse model of MI, SCENT ameliorated cardiac repair by improving left ventricular function, reducing fibrotic tissue, and promoting cardiomyocyte proliferation. Mechanistic studies using single-cell RNA sequencing of mouse heart after SCENT revealed a downregulation of Cd36 in endothelial cells (ECs). In an EC- Cd36 fl/- conditional knockout mouse model, the inhibition of CD36, a fatty acid transporter in ECs, led to a compensatory increase in glucose utilization in the heart and higher ATP generation, which enhanced cardiac contractility. In pigs, cardiac magnetic resonance imaging showed an enhanced ejection fraction (Δ=11.66±5.12%) and fractional shortening (Δ=5.72±2.29%) at day 28 after MI by SCENT treatment compared with controls, along with reduced infarct size and thickened ventricular wall., Conclusions: In both rodent and swine models, our data proved the feasibility, efficacy, and general safety of SCENT treatment against acute MI injury, laying the groundwork for clinical investigation. Moreover, the EC- Cd36 fl/- mouse model provides the first in vivo evidence showing that conditional EC-CD36 knockout can ameliorate cardiac injury. Our study introduces a noninvasive treatment option for heart disease and identifies new potential therapeutic targets., Competing Interests: Dr Li is currently an employee of Xsome Biotech Inc. Dr Cheng is a cofounder and equity holder of Xsome Biotech Inc. The remaining authors report no conflicts.

Computational data-centric research techniques play a prevalent and multi-disciplinary role in life science research. In the past, scientists in wet labs generated the data, and computational researchers focused on creating tools for the analysis of those data. Computational researchers are now becoming more independent and taking leadership roles within biomedical projects, leveraging the increased availability of public data. We are now able to generate vast amounts of data, and the challenge has shifted from data generation to data analysis. Here we discuss the pitfalls, challenges, and opportunities facing the field of data-centric research in biology. We discuss the evolving perception of computational data-driven research and its rise as an independent domain in biomedical research while also addressing the significant collaborative opportunities that arise from integrating computational research with experimental and translational biology. Additionally, we discuss the future of data-centric research and its applications across various areas of the biomedical field., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2024 Elsevier Inc. All rights reserved.)

Importance: The ways in which we access, acquire, and use data in clinical trials have evolved very little over time, resulting in a fragmented and inefficient system that limits the amount and quality of evidence that can be generated., Observations: Clinical trial design has advanced steadily over several decades. Yet the infrastructure for clinical trial data collection remains expensive and labor intensive and limits the amount of evidence that can be collected to inform whether and how interventions work for different patient populations. Meanwhile, there is increasing demand for evidence from randomized clinical trials to inform regulatory decisions, payment decisions, and clinical care. Although substantial public and industry investment in advancing electronic health record interoperability, data standardization, and the technology systems used for data capture have resulted in significant progress on various aspects of data generation, there is now a need to combine the results of these efforts and apply them more directly to the clinical trial data infrastructure., Conclusions and Relevance: We describe a vision for a modernized infrastructure that is centered around 2 related concepts. First, allowing the collection and rigorous evaluation of multiple data sources and types and, second, enabling the possibility to reuse health data for multiple purposes. We address the need for multidisciplinary collaboration and suggest ways to measure progress toward this goal.

Artificial intelligence (AI) has the potential to transform every facet of cardiovascular practice and research. The exponential rise in technology powered by AI is defining new frontiers in cardiovascular care, with innovations that span novel diagnostic modalities, new digital native biomarkers of disease, and high-performing tools evaluating care quality and prognosticating clinical outcomes. These digital innovations promise expanded access to cardiovascular screening and monitoring, especially among those without access to high-quality, specialized care historically. Moreover, AI is propelling biological and clinical discoveries that will make future cardiovascular care more personalized, precise, and effective. The review brings together these diverse AI innovations, highlighting developments in multimodal cardiovascular AI across clinical practice and biomedical discovery, and envisioning this new future backed by contemporary science and emerging discoveries. Finally, we define the critical path and the safeguards essential to realizing this AI-enabled future that helps achieve optimal cardiovascular health and outcomes for all., Competing Interests: Funding Support and Author Disclosures This work was supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health (under awards R01HL167858 and K23HL153775 to Dr Khera, F32HL170592 to Dr Oikonomou, R01HL155915 and R01HL167050 to Dr Nadkarni, R01HL158626 to Dr Wiens, and UM1 TR004407 to Dr Topol). Dr Khera is an Associate Editor of JAMA; receives research support, through Yale, from the Blavatnik Foundation, Bristol Myers Squibb, Novo Nordisk, and BridgeBio; is a coinventor of U.S. Provisional Patent Applications 63/177,117, 63/428,569, 63/346,610, 63/484,426, 63/508,315, 63/580,137, 63/606,203, 63/562,335; and is a co-founder of Ensight-AI, Inc and Evidence2Health, LLC. Dr Oikonomou is an academic cofounder of Evidence2Health LLC; has been a consultant for Caristo Diagnostics, Ltd and Ensight-AI, Inc; is a co-inventor in patent applications (US17/720,068, 63/619,241, 63/177,117, 63/580,137, 63/606,203, 63/562,335, WO2018078395A1, WO2020058713A1); and has received royalty fees from technology licensed through the University of Oxford. Dr Nadkarni is an academic cofounder of Renalytix, Pensieve, and Data2Wisdom; has patents licensed to Heart Test Laboratories; and acts as a consultant to Renalytix, Pensieve, and Heart Test Laboratories. Dr Butte is a cofounder and consultant to Personalis and NuMedii; has served as a consultant or advisor to National Institutes of Health, JAMA, Mango Tree Corporation, Samsung, Geisinger Health, Washington University in Saint Louis, University of Utah, and in the recent past, 10x Genomics, Helix, Pathway Genomics, and Verinata (Illumina); has served on paid advisory panels or boards for Regenstrief Institute, Gerson Lehman Group, AlphaSights, Covance, Novartis, Genentech, Merck, and Roche; is a shareholder in Personalis and NuMedii; is a minor shareholder in Apple, Meta (Facebook), Alphabet (Google), Microsoft, Amazon, NVIDIA, AMD, Snap, 10x Genomics, Doximity, Regeneron, Sanofi, Pfizer, Royalty Pharma, Moderna, BioNtech, Invitae, Pacific Biosciences, Editas Medicine, Eli Lilly, Nuna Health, Assay Depot (Scientist.com), Vet24seven, Snowflake, Sophia Genetics, and several other nonhealth-related companies and mutual funds; has received honoraria and travel reimbursement for invited talks from Johnson and Johnson, Roche, Genentech, Pfizer, Merck, Lilly, Takeda, Varian, Mars, Siemens, Optum, Abbott, Celgene, AstraZeneca, AbbVie, Westat, Applied Research Works, Acentrus, ALDA, and many academic institutions, medical- or disease-specific foundations and associations, and health systems; has received royalty payments through Stanford University, for several patents and other disclosures licensed to NuMedii and Personalis; and his research has been funded by the National Institutes of Health, U.S. Food and Drug Administration, Peraton (as the prime on an National Institutes of Health contract), Priscilla Chan and Mark Zuckerberg, the Barbara and Gerson Bakar Foundation, Genentech, Johnson and Johnson, Chan Zuckerberg Science, Robert Wood Johnson Foundation, Leon Lowenstein Foundation, Intervalien Foundation, and in the past, the March of Dimes, Juvenile Diabetes Research Foundation, California Governor’s Office of Planning and Research, California Institute for Regenerative Medicine, L’Oreal, and Progenity (none of these entities had any role in the design, planning, or execution of the study, or interpretation of the findings). Dr Topol is on the scientific advisory board of Tempus, Abridge, and Pheno.ai. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose., (Copyright © 2024 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

Rheumatoid arthritis (RA) management leans toward achieving remission or low disease activity. In this study, we conducted single-cell RNA sequencing (scRNA-Seq) of peripheral blood mononuclear cells (PBMCs) from 36 individuals (18 patients with RA and 18 matched controls, accounting for age, sex, race, and ethnicity), to identify disease-relevant cell subsets and cell type-specific signatures associated with disease activity. Our analysis revealed 18 distinct PBMC subsets, including an IFN-induced transmembrane 3-overexpressing (IFITM3-overexpressing) IFN-activated monocyte subset. We observed an increase in CD4+ T effector memory cells in patients with moderate-high disease activity (DAS28-CRP ≥ 3.2) and a decrease in nonclassical monocytes in patients with low disease activity or remission (DAS28-CRP < 3.2). Pseudobulk analysis by cell type identified 168 differentially expressed genes between RA and matched controls, with a downregulation of proinflammatory genes in the γδ T cell subset, alteration of genes associated with RA predisposition in the IFN-activated subset, and nonclassical monocytes. Additionally, we identified a gene signature associated with moderate-high disease activity, characterized by upregulation of proinflammatory genes such as TNF, JUN, EGR1, IFIT2, MAFB, and G0S2 and downregulation of genes including HLA-DQB1, HLA-DRB5, and TNFSF13B. Notably, cell-cell communication analysis revealed an upregulation of signaling pathways, including VISTA, in both moderate-high and remission-low disease activity contexts. Our findings provide valuable insights into the systemic cellular and molecular mechanisms underlying RA disease activity.

With the rapid growth of interest in and use of large language models (LLMs) across various industries, we are facing some crucial and profound ethical concerns, especially in the medical field. The unique technical architecture and purported emergent abilities of LLMs differentiate them substantially from other artificial intelligence (AI) models and natural language processing techniques used, necessitating a nuanced understanding of LLM ethics. In this Viewpoint, we highlight ethical concerns stemming from the perspectives of users, developers, and regulators, notably focusing on data privacy and rights of use, data provenance, intellectual property contamination, and broad applications and plasticity of LLMs. A comprehensive framework and mitigating strategies will be imperative for the responsible integration of LLMs into medical practice, ensuring alignment with ethical principles and safeguarding against potential societal risks., Competing Interests: Declaration of interests DSWT holds patents on a deep-learning system for the detection of retinal diseases. AJB is a cofounder and consultant for Personalis and NuMedii; is a consultant to Mango Tree Corporation; has previously been a consultant for Samsung, 10x Genomics, Helix, Pathway Genomics, and Verinata (Illumina); has served on paid advisory panels or boards for Geisinger Health, Regenstrief Institute, Gerson Lehman Group, AlphaSights, Covance, Novartis, Genentech, and Merck, and Roche; is a shareholder in Personalis and NuMedii; is a minor shareholder in Apple, Meta (Facebook), Alphabet (Google), Microsoft, Amazon, Snap, 10x Genomics, Illumina, Regeneron, Sanofi, Pfizer, Royalty Pharma, Moderna, Sutro, Doximity, BioNtech, Invitae, Pacific Biosciences, Editas Medicine, Nuna Health, Assay Depot, and Vet24seven, and several other non-health related companies and mutual funds; has received honoraria and travel reimbursement for invited talks from Johnson and Johnson, Roche, Genentech, Pfizer, Merck, Lilly, Takeda, Varian, Mars, Siemens, Optum, Abbott, Celgene, AstraZeneca, AbbVie, Westat, and many academic institutions, medical-specific or disease-specific foundations and associations, and health systems; receives royalty payments through Stanford University for several patents and other disclosures licensed to NuMedii and Personalis; has done research funded by NIH, Peraton (as the prime on an NIH contract), Genentech, Johnson and Johnson, FDA, Robert Wood Johnson Foundation, Leon Lowenstein Foundation, Intervalien Foundation, Priscilla Chan and Mark Zuckerberg, and the Barbara and Gerson Bakar Foundation; and has previously done research funded by the March of Dimes, Juvenile Diabetes Research Foundation, California Governor's Office of Planning and Research, California Institute for Regenerative Medicine, L’Oreal, and Progenity. NL is a scientific advisor to TIIM SG. NHS is a cofounder of Prealize Health (a predictive analytics company) and Atropos Health (an on-demand evidence generation company); receives funding from the Gordon and Betty Moore Foundation for developing virtual model deployments; and is a member of working groups of the Coalition for Health AI (CHAI), a consensus-building organisation providing guidelines for the responsible use of artificial intelligence in health care. JS, through his involvement with the Murdoch Children's Research Institute, receives funding from the Victorian State Government through the Operational Infrastructure Support (OIS) programme. JCLO is supported by grants from the National Medical Research Council Singapore (MOH-CIAINV21nov-001) and AI Singapore OTTIC (AISG2-TC-2022-006). All other authors declare no competing interests., (Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

Outpatient clinical notes are a rich source of information regarding drug safety. However, data in these notes are currently underutilized for pharmacovigilance due to methodological limitations in text mining. Large language models (LLMs) like Bidirectional Encoder Representations from Transformers (BERT) have shown progress in a range of natural language processing tasks but have not yet been evaluated on adverse event (AE) detection. We adapted a new clinical LLM, University of California - San Francisco (UCSF)-BERT, to identify serious AEs (SAEs) occurring after treatment with a non-steroid immunosuppressant for inflammatory bowel disease (IBD). We compared this model to other language models that have previously been applied to AE detection. We annotated 928 outpatient IBD notes corresponding to 928 individual patients with IBD for all SAE-associated hospitalizations occurring after treatment with a non-steroid immunosuppressant. These notes contained 703 SAEs in total, the most common of which was failure of intended efficacy. Out of eight candidate models, UCSF-BERT achieved the highest numerical performance on identifying drug-SAE pairs from this corpus (accuracy 88-92%, macro F1 61-68%), with 5-10% greater accuracy than previously published models. UCSF-BERT was significantly superior at identifying hospitalization events emergent to medication use (P < 0.01). LLMs like UCSF-BERT achieve numerically superior accuracy on the challenging task of SAE detection from clinical notes compared with prior methods. Future work is needed to adapt this methodology to improve model performance and evaluation using multicenter data and newer architectures like Generative pre-trained transformer (GPT). Our findings support the potential value of using large language models to enhance pharmacovigilance., (© 2024 The Authors. Clinical Pharmacology & Therapeutics © 2024 American Society for Clinical Pharmacology and Therapeutics.)

Objectives: Vedolizumab (VDZ) and ustekinumab (UST) are second-line treatments in pediatric patients with ulcerative colitis (UC) refractory to antitumor necrosis factor (anti-TNF) therapy. Pediatric studies comparing the effectiveness of these medications are lacking. Using a registry from ImproveCareNow (ICN), a global research network in pediatric inflammatory bowel disease, we compared the effectiveness of UST and VDZ in anti-TNF refractory UC., Methods: We performed a propensity-score weighted regression analysis to compare corticosteroid-free clinical remission (CFCR) at 6 months from starting second-line therapy. Sensitivity analyses tested the robustness of our findings to different ways of handling missing outcome data. Secondary analyses evaluated alternative proxies of response and infection risk., Results: Our cohort included 262 patients on VDZ and 74 patients on UST. At baseline, the two groups differed on their mean pediatric UC activity index (PUCAI) (p = 0.03) but were otherwise similar. At Month 6, 28.3% of patients on VDZ and 25.8% of those on UST achieved CFCR (p = 0.76). Our primary model showed no difference in CFCR (odds ratio: 0.81; 95% confidence interval [CI]: 0.41-1.59) (p = 0.54). The time to biologic discontinuation was similar in both groups (hazard ratio: 1.26; 95% CI: 0.76-2.08) (p = 0.36), with the reference group being VDZ, and we found no differences in clinical response, growth parameters, hospitalizations, surgeries, infections, or malignancy risk. Sensitivity analyses supported these findings of similar effectiveness., Conclusions: UST and VDZ are similarly effective for inducing clinical remission in anti-TNF refractory UC in pediatric patients. Providers should consider safety, tolerability, cost, and comorbidities when deciding between these therapies., (© 2024 European Society for Pediatric Gastroenterology, Hepatology, and Nutrition and North American Society for Pediatric Gastroenterology, Hepatology, and Nutrition.)

Importance: The introduction of large language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4; OpenAI), has generated significant interest in health care, yet studies evaluating their performance in a clinical setting are lacking. Determination of clinical acuity, a measure of a patient's illness severity and level of required medical attention, is one of the foundational elements of medical reasoning in emergency medicine., Objective: To determine whether an LLM can accurately assess clinical acuity in the emergency department (ED)., Design, Setting, and Participants: This cross-sectional study identified all adult ED visits from January 1, 2012, to January 17, 2023, at the University of California, San Francisco, with a documented Emergency Severity Index (ESI) acuity level (immediate, emergent, urgent, less urgent, or nonurgent) and with a corresponding ED physician note. A sample of 10 000 pairs of ED visits with nonequivalent ESI scores, balanced for each of the 10 possible pairs of 5 ESI scores, was selected at random., Exposure: The potential of the LLM to classify acuity levels of patients in the ED based on the ESI across 10 000 patient pairs. Using deidentified clinical text, the LLM was queried to identify the patient with a higher-acuity presentation within each pair based on the patients' clinical history. An earlier LLM was queried to allow comparison with this model., Main Outcomes and Measures: Accuracy score was calculated to evaluate the performance of both LLMs across the 10 000-pair sample. A 500-pair subsample was manually classified by a physician reviewer to compare performance between the LLMs and human classification., Results: From a total of 251 401 adult ED visits, a balanced sample of 10 000 patient pairs was created wherein each pair comprised patients with disparate ESI acuity scores. Across this sample, the LLM correctly inferred the patient with higher acuity for 8940 of 10 000 pairs (accuracy, 0.89 [95% CI, 0.89-0.90]). Performance of the comparator LLM (accuracy, 0.84 [95% CI, 0.83-0.84]) was below that of its successor. Among the 500-pair subsample that was also manually classified, LLM performance (accuracy, 0.88 [95% CI, 0.86-0.91]) was comparable with that of the physician reviewer (accuracy, 0.86 [95% CI, 0.83-0.89])., Conclusions and Relevance: In this cross-sectional study of 10 000 pairs of ED visits, the LLM accurately identified the patient with higher acuity when given pairs of presenting histories extracted from patients' first ED documentation. These findings suggest that the integration of an LLM into ED workflows could enhance triage processes while maintaining triage quality and warrants further investigation.

Detecting epistatic drivers of human phenotypes is a considerable challenge. Traditional approaches use regression to sequentially test multiplicative interaction terms involving pairs of genetic variants. For higher-order interactions and genome-wide large-scale data, this strategy is computationally intractable. Moreover, multiplicative terms used in regression modeling may not capture the form of biological interactions. Building on the Predictability, Computability, Stability (PCS) framework, we introduce the epiTree pipeline to extract higher-order interactions from genomic data using tree-based models. The epiTree pipeline first selects a set of variants derived from tissue-specific estimates of gene expression. Next, it uses iterative random forests (iRF) to search training data for candidate Boolean interactions (pairwise and higher-order). We derive significance tests for interactions, based on a stabilized likelihood ratio test, by simulating Boolean tree-structured null (no epistasis) and alternative (epistasis) distributions on hold-out test data. Finally, our pipeline computes PCS epistasis p-values that probabilisticly quantify improvement in prediction accuracy via bootstrap sampling on the test set. We validate the epiTree pipeline in two case studies using data from the UK Biobank: predicting red hair and multiple sclerosis (MS). In the case of predicting red hair, epiTree recovers known epistatic interactions surrounding MC1R and novel interactions, representing non-linearities not captured by logistic regression models. In the case of predicting MS, a more complex phenotype than red hair, epiTree rankings prioritize novel interactions surrounding HLA-DRB1, a variant previously associated with MS in several populations. Taken together, these results highlight the potential for epiTree rankings to help reduce the design space for follow up experiments., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Behr et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Electronic health records (EHRs) provide meaningful knowledge of drug-related adverse events (AEs) that are not captured in standard drug development and postmarketing surveillance. Using variables obtained from EHR data in the University of California San Francisco de-identified Clinical Data Warehouse, we aimed to evaluate the potential of machine learning to predict two hematological AEs, thrombocytopenia and anemia, in a cohort of patients treated with linezolid for 3 or more days. Features for model input were extracted at linezolid initiation (index), and outcomes were characterized from index to 14 days post-treatment. Random forest classification (RFC) was used for AE prediction, and reduced feature models were evaluated using cumulative importance (cImp) for feature selection. Grade 3+ thrombocytopenia and anemia occurred in 31% of 2,171 and 56% of 2,170 evaluable patients, respectively. Of the total 53 features, as few as 7 contributed at least 50% cImp, resulting in prediction accuracies of 70% or higher and area under the receiver operating characteristic curves of 0.886 for grade 3+ thrombocytopenia and 0.759 for grade 3+ anemia. Sensitivity analyses in strictly defined patient subgroups revealed similarly high predictive performance in full and reduced feature models. A logistic regression model with the same 50% cImp features showed similar predictive performance as RFC and good concordance with RFC probability predictions after isotonic calibration, adding interpretability. Collectively, this work demonstrates potential for machine learning prediction of AE risk in real-world patients using few variables regularly available in EHRs, which may aid in clinical decision making and/or monitoring., (© 2024 The Authors. Clinical Pharmacology & Therapeutics published by Wiley Periodicals LLC on behalf of American Society for Clinical Pharmacology and Therapeutics.)

Background: The Mayo endoscopic subscore (MES) is an important quantitative measure of disease activity in ulcerative colitis. Colonoscopy reports in routine clinical care usually characterize ulcerative colitis disease activity using free text description, limiting their utility for clinical research and quality improvement. We sought to develop algorithms to classify colonoscopy reports according to their MES., Methods: We annotated 500 colonoscopy reports from 2 health systems. We trained and evaluated 4 classes of algorithms. Our primary outcome was accuracy in identifying scorable reports (binary) and assigning an MES (ordinal). Secondary outcomes included learning efficiency, generalizability, and fairness., Results: Automated machine learning models achieved 98% and 97% accuracy on the binary and ordinal prediction tasks, outperforming other models. Binary models trained on the University of California, San Francisco data alone maintained accuracy (96%) on validation data from Zuckerberg San Francisco General. When using 80% of the training data, models remained accurate for the binary task (97% [n = 320]) but lost accuracy on the ordinal task (67% [n = 194]). We found no evidence of bias by gender (P = .65) or area deprivation index (P = .80)., Conclusions: We derived a highly accurate pair of models capable of classifying reports by their MES and recognizing when to abstain from prediction. Our models were generalizable on outside institution validation. There was no evidence of algorithmic bias. Our methods have the potential to enable retrospective studies of treatment effectiveness, prospective identification of patients meeting study criteria, and quality improvement efforts in inflammatory bowel diseases., (© The Author(s) 2024. Published by Oxford University Press on behalf of Crohn’s & Colitis Foundation. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)