Evaluating site-of-care-related racial disparities in kidney graft failure using a novel federated learning framework

OBJECTIVES

Racial disparities in kidney transplant access and posttransplant outcomes exist between non-Hispanic Black (NHB) and non-Hispanic White (NHW) patients in the United States, with the site of care being a key contributor. Using multi-site data to examine the effect of site of care on racial disparities, the key challenge is the dilemma in sharing patient-level data due to regulations for protecting patients' privacy.

MATERIALS AND METHODS

We developed a federated learning framework, named dGEM-disparity (decentralized algorithm for Generalized linear mixed Effect Model for disparity quantification). Consisting of 2 modules, dGEM-disparity first provides accurately estimated common effects and calibrated hospital-specific effects by requiring only aggregated data from each center and then adopts a counterfactual modeling approach to assess whether the graft failure rates differ if NHB patients had been admitted at transplant centers in the same distribution as NHW patients were admitted.

RESULTS

Utilizing United States Renal Data System data from 39 043 adult patients across 73 transplant centers over 10 years, we found that if NHB patients had followed the distribution of NHW patients in admissions, there would be 38 fewer deaths or graft failures per 10 000 NHB patients (95% CI, 35-40) within 1 year of receiving a kidney transplant on average.

DISCUSSION

The proposed framework facilitates efficient collaborations in clinical research networks. Additionally, the framework, by using counterfactual modeling to calculate the event rate, allows us to investigate contributions to racial disparities that may occur at the level of site of care.

CONCLUSIONS

Our framework is broadly applicable to other decentralized datasets and disparities research related to differential access to care. Ultimately, our proposed framework will advance equity in human health by identifying and addressing hospital-level racial disparities.

Challenges of COVID-19 Case Forecasting in the US, 2020-2021

During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub (https://covid19forecasthub.org). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1-4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

Radiomics-based distinction of small (≤2 cm) hepatocellular carcinoma and precancerous lesions based on unenhanced MRI

AIM

To assess the feasibility of a radiomics model based on unenhanced magnetic resonance imaging (MRI) to differentiate small hepatocellular carcinoma (S-HCC) (≤2 cm) and pre-hepatocellular carcinoma (Pre-HCC).

MATERIALS AND METHODS

One hundred and fourteen histopathologically confirmed 114 hepatic nodules were analysed retrospectively. All patients had undergone MRI before surgery using a 3 T MRI system. Each nodule was segmented on unenhanced MRI sequences (T1-weighted imaging [T1] and T2WI with fat-suppression [FS-T2]). Radiomics features were extracted and the optimal features were selected using the least absolute shrinkage and selection operator (LASSO). The support vector machine (SVM) was used to establish the radiomics model. One abdominal radiologist performed the conventional qualitative analysis for classification of S-HCC and Pre-HCC. The diagnostic performances of the radiomics and radiologist models were evaluated using receiver operating characteristic (ROC) analysis.

RESULT

Radiomics features (n=1,223) were extracted from each sequence and the optimal features were selected from T1, FS-T2, and T1+FS-T2 to construct the radiomics models. The radiomics model based on T1+FS-T2 showed the best performance among the three models, with areas under the ROC curves (AUCs) of 0.95 (95 % confidence interval [CI], 0.875-0.986) and 0.942 (95 % CI, 0.775-0.985), accuracies of 86 % and 88.5 %, sensitivities of 94.12 % and 100 %, and specificities of 85.48 % and 85.19 %, respectively. The radiomics model on FS-T2 showed better performance on a single sequence than that of the T1-based model. The diagnostic performance for the radiomic model was significantly higher than that for the radiologist (AUC = 0.518, p<0.05).

CONCLUSION

This study suggested that a radiomics model based on unenhanced MRI may serve as a feasible and non-invasive tool to classify S-HCC and Pre-HCC.

Model tuning or prompt Tuning? a study of large language models for clinical concept and relation extraction

OBJECTIVE

To develop soft prompt-based learning architecture for large language models (LLMs), examine prompt-tuning using frozen/unfrozen LLMs, and assess their abilities in transfer learning and few-shot learning.

METHODS

We developed a soft prompt-based learning architecture and compared 4 strategies including (1) fine-tuning without prompts; (2) hard-prompting with unfrozen LLMs; (3) soft-prompting with unfrozen LLMs; and (4) soft-prompting with frozen LLMs. We evaluated GatorTron, a clinical LLM with up to 8.9 billion parameters, and compared GatorTron with 4 existing transformer models for clinical concept and relation extraction on 2 benchmark datasets for adverse drug events and social determinants of health (SDoH). We evaluated the few-shot learning ability and generalizability for cross-institution applications.

RESULTS AND CONCLUSION

When LLMs are unfrozen, GatorTron-3.9B with soft prompting achieves the best strict F1-scores of 0.9118 and 0.8604 for concept extraction, outperforming the traditional fine-tuning and hard prompt-based models by 0.6 ∼ 3.1 % and 1.2 ∼ 2.9 %, respectively; GatorTron-345 M with soft prompting achieves the best F1-scores of 0.8332 and 0.7488 for end-to-end relation extraction, outperforming other two models by 0.2 ∼ 2 % and 0.6 ∼ 11.7 %, respectively. When LLMs are frozen, small LLMs have a big gap to be competitive with unfrozen models; scaling LLMs up to billions of parameters makes frozen LLMs competitive with unfrozen models. Soft prompting with a frozen GatorTron-8.9B model achieved the best performance for cross-institution evaluation. We demonstrate that (1) machines can learn soft prompts better than hard prompts composed by human, (2) frozen LLMs have good few-shot learning ability and generalizability for cross-institution applications, (3) frozen LLMs reduce computing cost to 2.5 ∼ 6 % of previous methods using unfrozen LLMs, and (4) frozen LLMs require large models (e.g., over several billions of parameters) for good performance.

Identifying social determinants of health from clinical narratives: A study of performance, documentation ratio, and potential bias

OBJECTIVE

To develop a natural language processing (NLP) package to extract social determinants of health (SDoH) from clinical narratives, examine the bias among race and gender groups, test the generalizability of extracting SDoH for different disease groups, and examine population-level extraction ratio.

METHODS

We developed SDoH corpora using clinical notes identified at the University of Florida (UF) Health. We systematically compared 7 transformer-based large language models (LLMs) and developed an open-source package - SODA (i.e., SOcial DeterminAnts) to facilitate SDoH extraction from clinical narratives. We examined the performance and potential bias of SODA for different race and gender groups, tested the generalizability of SODA using two disease domains including cancer and opioid use, and explored strategies for improvement. We applied SODA to extract 19 categories of SDoH from the breast (n = 7,971), lung (n = 11,804), and colorectal cancer (n = 6,240) cohorts to assess patient-level extraction ratio and examine the differences among race and gender groups.

RESULTS

We developed an SDoH corpus using 629 clinical notes of cancer patients with annotations of 13,193 SDoH concepts/attributes from 19 categories of SDoH, and another cross-disease validation corpus using 200 notes from opioid use patients with 4,342 SDoH concepts/attributes. We compared 7 transformer models and the GatorTron model achieved the best mean average strict/lenient F1 scores of 0.9122 and 0.9367 for SDoH concept extraction and 0.9584 and 0.9593 for linking attributes to SDoH concepts. There is a small performance gap (∼4%) between Males and Females, but a large performance gap (>16 %) among race groups. The performance dropped when we applied the cancer SDoH model to the opioid cohort; fine-tuning using a smaller opioid SDoH corpus improved the performance. The extraction ratio varied in the three cancer cohorts, in which 10 SDoH could be extracted from over 70 % of cancer patients, but 9 SDoH could be extracted from less than 70 % of cancer patients. Individuals from the White and Black groups have a higher extraction ratio than other minority race groups.

CONCLUSIONS

Our SODA package achieved good performance in extracting 19 categories of SDoH from clinical narratives. The SODA package with pre-trained transformer models is available at https://github.com/uf-hobi-informatics-lab/SODA_Docker.

A Single-cell and Spatial RNA-seq Database for Alzheimer's Disease (ssREAD)

Alzheimer's Disease (AD) pathology has been increasingly explored through single-cell and single-nucleus RNA-sequencing (scRNA-seq & snRNA-seq) and spatial transcriptomics (ST). However, the surge in data demands a comprehensive, user-friendly repository. Addressing this, we introduce a single-cell and spatial RNA-seq database for Alzheimer's disease (ssREAD). It offers a broader spectrum of AD-related datasets, an optimized analytical pipeline, and improved usability. The database encompasses 1,053 samples (277 integrated datasets) from 67 AD-related scRNA-seq & snRNA-seq studies, totaling 7,332,202 cells. Additionally, it archives 381 ST datasets from 18 human and mouse brain studies. Each dataset is annotated with details such as species, gender, brain region, disease/control status, age, and AD Braak stages. ssREAD also provides an analysis suite for cell clustering, identification of differentially expressed and spatially variable genes, cell-type-specific marker genes and regulons, and spot deconvolution for integrative analysis. ssREAD is freely available at https://bmblx.bmi.osumc.edu/ssread/.

Gra-CRC-miRTar: The pre-trained nucleotide-to-graph neural networks to identify potential miRNA targets in colorectal cancer

Colorectal cancer (CRC) is the third most diagnosed cancer and the second deadliest cancer worldwide representing a major public health problem. In recent years, increasing evidence has shown that microRNA (miRNA) can control the expression of targeted human messenger RNA (mRNA) by reducing their abundance or translation, acting as oncogenes or tumor suppressors in various cancers, including CRC. Due to the significant up-regulation of oncogenic miRNAs in CRC, elucidating the underlying mechanism and identifying dysregulated miRNA targets may provide a basis for improving current therapeutic interventions. In this paper, we proposed Gra-CRC-miRTar, a pre-trained nucleotide-to-graph neural network framework, for identifying potential miRNA targets in CRC. Different from previous studies, we constructed two pre-trained models to encode RNA sequences and transformed them into de Bruijn graphs. We employed different graph neural networks to learn the latent representations. The embeddings generated from de Bruijn graphs were then fed into a Multilayer Perceptron (MLP) to perform the prediction tasks. Our extensive experiments show that Gra-CRC-miRTar achieves better performance than other deep learning algorithms and existing predictors. In addition, our analyses also successfully revealed 172 out of 201 functional interactions through experimentally validated miRNA-mRNA pairs in CRC. Collectively, our effort provides an accurate and efficient framework to identify potential miRNA targets in CRC, which can also be used to reveal miRNA target interactions in other malignancies, facilitating the development of novel therapeutics.

Generative large language models are all-purpose text analytics engines: text-to-text learning is all your need

OBJECTIVE

To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning.

METHODS

We formulated 7 key clinical NLP tasks as text-to-text learning and solved them using one unified generative clinical LLM, GatorTronGPT, developed using GPT-3 architecture and trained with up to 20 billion parameters. We adopted soft prompts (ie, trainable vectors) with frozen LLM, where the LLM parameters were not updated (ie, frozen) and only the vectors of soft prompts were updated, known as prompt tuning. We added additional soft prompts as a prefix to the input layer, which were optimized during the prompt tuning. We evaluated the proposed method using 7 clinical NLP tasks and compared them with previous task-specific solutions based on Transformer models.

RESULTS AND CONCLUSION

The proposed approach achieved state-of-the-art performance for 5 out of 7 major clinical NLP tasks using one unified generative LLM. Our approach outperformed previous task-specific transformer models by ∼3% for concept extraction and 7% for relation extraction applied to social determinants of health, 3.4% for clinical concept normalization, 3.4%-10% for clinical abbreviation disambiguation, and 5.5%-9% for natural language inference. Our approach also outperformed a previously developed prompt-based machine reading comprehension (MRC) model, GatorTron-MRC, for clinical concept and relation extraction. The proposed approach can deliver the "one model for all" promise from training to deployment using a unified generative LLM.

A novel hybrid modelling framework for GPP estimation: Integrating a multispectral surface reflectance based Vcmax25 simulator into the process-based model

Terrestrial gross primary productivity (GPP) is the key element in the carbon cycle process. Accurate GPP estimation hinges on the maximum carboxylation rate (Vcmax,025). The high uncertainty in deriving ecosystem-level Vcmax,025 has long hampered efforts toward the performance of the GPP model. Recently studies suggest the strong relationship between spectral reflectance and Vcmax,025. We proposed the multispectral surface reflectance-driven Vcmax,025 simulator using the fully connected deep neural network and built the hybrid modelling framework for GPP estimation by integrating the data-driven Vcmax,025 simulator in the process-based model. The performance of hybrid GPP model was evaluated at 95 flux sites. The result shows that the multispectral surface reflectance-driven Vcmax,025 simulator acquires the satisfactory estimation, with correlation coefficient (R), root mean square error (RMSE) and median absolute percentage error (MdAPE) ranging from 0.34 to 0.80, 14 to 43 μmol m-2 s-1 and 21 % to 66 % across different land cover types, respectively. The hybrid framework generates good GPP estimates with R, RMSE and MdAPE varying from 0.76 to 0.89, 1.79 to 6.16 μmol m-2 s-1 and 27 % to 90 %, respectively. Compared with EVI-driven method, the multispectral surface reflectance significantly improves the Vcmax,025 and GPP estimates, with MdAPE declining by 0.6 %-18 % and 1 % to 21 %, respectively. The Shapley value analysis reveals that red (620-670 nm), near-infrared (841-876 nm) and shortwave infrared (1628-1652 nm and 2105-2155 nm) are the key bands for Vcmax,025 estimation. This study highlights the potential of multispectral surface reflectance for quantifying ecosystem-level Vcmax,025. The new hybrid framework fully extracts the information of all available spectral bands using deep learning to reduce parameter uncertainty while maintains the description of photosynthetic process to ensure its physical reasonability. It can serve as a powerful tool for accurate global GPP estimation.

Effect of Eligibility Criteria on Patients' Survival and Serious Adverse Events in Colorectal Cancer Drug Trials

This study investigates the impact of clinical trial eligibility criteria on patient survival and serious adverse events (SAEs) in colorectal cancer (CRC) drug trials using real-world data. We utilized the OneFlorida+ network's data repository, conducting a retrospective analysis of CRC patients receiving FDA-approved first-line metastatic treatments. Propensity score matching created balanced case-control groups, which were evaluated using survival analysis and machine learning algorithms to assess the effects of eligibility criteria. Our study included 68,375 patients, with matched case-control groups comprising 1,126 patients each. Survival analysis revealed ethnicity and race, along with specific medical history (eligibility criteria), as significant survival outcome predictors. Machine learning models, particularly the XgBoost regressor, were employed to analyze SAEs, indicating that age and study groups were notable factors in SAEs occurrence. The study's findings highlight the importance of considering patient demographics and medical history in CRC trial designs.

Confidence score: a data-driven measure for inclusive systematic reviews considering unpublished preprints

OBJECTIVES

COVID-19, since its emergence in December 2019, has globally impacted research. Over 360 000 COVID-19-related manuscripts have been published on PubMed and preprint servers like medRxiv and bioRxiv, with preprints comprising about 15% of all manuscripts. Yet, the role and impact of preprints on COVID-19 research and evidence synthesis remain uncertain.

MATERIALS AND METHODS

We propose a novel data-driven method for assigning weights to individual preprints in systematic reviews and meta-analyses. This weight termed the "confidence score" is obtained using the survival cure model, also known as the survival mixture model, which takes into account the time elapsed between posting and publication of a preprint, as well as metadata such as the number of first 2-week citations, sample size, and study type.

RESULTS

Using 146 preprints on COVID-19 therapeutics posted from the beginning of the pandemic through April 30, 2021, we validated the confidence scores, showing an area under the curve of 0.95 (95% CI, 0.92-0.98). Through a use case on the effectiveness of hydroxychloroquine, we demonstrated how these scores can be incorporated practically into meta-analyses to properly weigh preprints.

DISCUSSION

It is important to note that our method does not aim to replace existing measures of study quality but rather serves as a supplementary measure that overcomes some limitations of current approaches.

CONCLUSION

Our proposed confidence score has the potential to improve systematic reviews of evidence related to COVID-19 and other clinical conditions by providing a data-driven approach to including unpublished manuscripts.

An Interpretable Population Graph Network to Identify Rapid Progression of Alzheimer's Disease Using UK Biobank

Alzheimer's disease (AD) manifests with varying progression rates across individuals, necessitating the understanding of their intricate patterns of cognition decline that could contribute to effective strategies for risk monitoring. In this study, we propose an innovative interpretable population graph network framework for identifying rapid progressors of AD by utilizing patient information from electronic health-related records in the UK Biobank. To achieve this, we first created a patient similarity graph, in which each AD patient is represented as a node; and an edge is established by patient clinical characteristics distance. We used graph neural networks (GNNs) to predict rapid progressors of AD and created a GNN Explainer with SHAP analysis for interpretability. The proposed model demonstrates superior predictive performance over the existing benchmark approaches. We also revealed several clinical features significantly associated with the prediction, which can be used to aid in effective interventions for the progression of AD patients.

The Burden of Cancer and Pre-cancerous Conditions Among Transgender Individuals in a Large Healthcare Network

The current study aimed to examine the prevalence of and risk factors for cancer and pre-cancerous conditions, comparing transgender and cisgender individuals, using 2012-2023 electronic health record data from a large healthcare system. We identified 2,745 transgender individuals using a previously validated computable phenotype and 54,900 matched cisgender individuals. We calculated the prevalence of cancer and pre-cancer related to human papillomavirus (HPV), human immunodeficiency virus (HIV), tobacco, alcohol, lung, breast, colorectum, and built multivariable logistic models to examine the association between gender identity and the presence of cancer or pre-cancer. Results indicated similar odds of developing cancer across gender identities, but transgender individuals exhibited significantly higher risks for pre-cancerous conditions, including alcohol-related, breast, and colorectal pre-cancers compared to cisgender women, and HPV-related, tobacco-related, alcohol-related, and colorectal pre-cancers compared to cisgender men. These findings underscore the need for tailored interventions and policies addressing cancer health disparities affecting the transgender population.

Machine Learning Prediction of Autism Spectrum Disorder Through Linking Mothers' and Children's Electronic Health Record Data

Autism spectrum disorder (ASD) is a neurodevelopmental disorder typically diagnosed in children. Early detection of ASD, particularly in girls who are often diagnosed late, can aid long-term development for children. We aimed to develop machine learning models for predicting ASD diagnosis in children, both boys and girls, using child-mother linked electronic health records (EHRs) data from a large clinical research network. Model features were children and mothers' risk factors in EHRs, including maternal health factors. We tested XGBoost and logistic regression with Random Oversampling (ROS) and Random Undersampling (RUS) to address imbalanced data. Logistic regression with RUS considering a three-year observation window for children's risk factors achieved the best performance for predicting ASD among the overall study population (AUROC = 0.798), boys (AUROC = 0.786), and girls (AUROC = 0.791). We calculated SHAP values to quantify the impacts of important clinical and sociodemographic risk factors.

Assessing the Seasonality of Lab Tests Among Patients with Alzheimer's Disease and Related Dementias in OneFlorida Data Trust

About 1 in 9 older adults over 65 has Alzheimer's disease (AD), many of whom also have multiple other chronic conditions such as hypertension and diabetes, necessitating careful monitoring through laboratory tests. Understanding the patterns of laboratory tests in this population aids our understanding and management of these chronic conditions along with AD. In this study, we used an unimodal cosinor model to assess the seasonality of lab tests using electronic health record (EHR) data from 34,303 AD patients from the OneFlorida+ Clinical Research Consortium. We observed significant seasonal fluctuations-higher in winter in lab tests such as glucose, neutrophils per 100 white blood cells (WBC), and WBC. Notably, certain leukocyte types like eosinophils, lymphocytes, and monocytes are elevated during summer, likely reflecting seasonal respiratory diseases and allergens. Seasonality is more pronounced in older patients and varies by gender. Our findings suggest that recognizing these patterns and adjusting reference intervals for seasonality would allow healthcare providers to enhance diagnostic precision, tailor care, and potentially improve patient outcomes.

OCTOPUS: Disk-based, Multiplatform, Mobile-friendly Metagenomics Classifier

Portable genomic sequencers such as Oxford Nanopore's MinION enable real-time applications in both clinical and environmental health, e.g., detection of bacterial outbreaks. However, there is a bottleneck in the downstream analytics when bioinformatics pipelines are unavailable, e.g., when cloud processing is unreachable due to absence of Internet connection, or only low-end computing devices can be carried on site. For instance, metagenomics classifiers usually require a large amount of memory or specific operating systems/libraries. In this work, we present a platform-friendly software for portable metagenomic analysis of Nanopore data, the Oligomer-based Classifier of Taxonomic Operational and Pan-genome Units via Singletons (OCTOPUS). OCTOPUS is written in Java, reimplements several features of the popular Kraken2 and KrakenUniq software, with original components for improving metagenomics classification on incomplete/sampled reference databases (e.g., selection of bacteria of public health priority), making it ideal for running on smartphones or tablets. We indexed both OCTOPUS and Kraken2 on a bacterial database with ~4,000 reference genomes, then simulated a positive (bacterial genomes from the same species, but different genomes) and two negative (viral, mammalian) Nanopore test sets. On the bacterial test set OCTOPUS yielded sensitivity and precision comparable to Kraken2 (94.4% and 99.8% versus 94.5% and 99.1%, respectively). On non-bacterial sequences (mammals and viral), OCTOPUS dramatically decreased (4- to 16-fold) the false positive rate when compared to Kraken2 (2.1% and 0.7% versus 8.2% and 11.2%, respectively). We also developed customized databases including viruses, and the World Health Organization's set of bacteria of concern for drug resistance, tested with real Nanopore data on an Android smartphone. OCTOPUS is publicly available at https://github.com/DataIntellSystLab/OCTOPUS and https://github.com/Ruiz-HCI-Lab/OctopusMobile.

Oxymatrine protects articular chondrocytes from IL-1β-induced damage through autophagy activation via AKT/mTOR signaling pathway inhibition

BACKGROUND

Osteoarthritis (OA) is a common degenerative joint disease characterized by persistent articular cartilage degeneration and synovitis. Oxymatrine (OMT) is a quinzolazine alkaloid extracted from the traditional Chinese medicine, matrine, and possesses anti-inflammatory properties that may help regulate the pathogenesis of OA; however, its mechanism has not been elucidated. This study aimed to investigate the effects of OMT on interleukin-1β (IL-1β)-induced damage and the potential mechanisms of action.

METHODS

Chondrocytes were isolated from Sprague-Dawley rats. Toluidine blue and Collagen II immunofluorescence staining were used to determine the purity of the chondrocytes. Thereafter, the chondrocytes were subjected to IL-1β stimulation, both in the presence and absence of OMT, or the autophagy inhibitor 3-methyladenine (3-MA). Cell viability was assessed using the MTT assay and SYTOX Green staining. Additionally, flow cytometry was used to determine cell apoptosis rate and reactive oxygen species (ROS) levels. The protein levels of AKT, mTOR, LC3, P62, matrix metalloproteinase-13, and collagen II were quantitatively analyzed using western blotting. Immunofluorescence was used to assess LC3 expression.

RESULTS

OMT alleviated IL-1β-induced damage in chondrocytes, by increasing the survival rate, reducing the apoptosis rates of chondrocytes, and preventing the degradation of the cartilage matrix. In addition, OMT decreased the ROS levels and inhibited the AKT/mTOR signaling pathway while promoting autophagy in IL-1β treated chondrocytes. However, the effectiveness of OMT in improving chondrocyte viability under IL-1β treatment was limited when autophagy was inhibited by 3-MA.

CONCLUSIONS

OMT decreases oxidative stress and inhibits the AKT/mTOR signaling pathway to enhance autophagy, thus inhibiting IL-1β-induced damage. Therefore, OMT may be a novel and effective therapeutic agent for the clinical treatment of OA.

Detection of Personal and Family History of Suicidal Thoughts and Behaviors using Deep Learning and Natural Language Processing: A Multi-Site Study

Objective

Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with future suicide events. These are often captured in narrative clinical notes in electronic health records (EHRs). Collaboratively, Weill Cornell Medicine (WCM), Northwestern Medicine (NM), and the University of Florida (UF) developed and validated deep learning (DL)-based natural language processing (NLP) tools to detect PSH and FSH from such notes. The tool's performance was further benchmarked against a method relying exclusively on ICD-9/10 diagnosis codes.

Materials and Methods

We developed DL-based NLP tools utilizing pre-trained transformer models Bio_ClinicalBERT and GatorTron, and compared them with expert-informed, rule-based methods. The tools were initially developed and validated using manually annotated clinical notes at WCM. Their portability and performance were further evaluated using clinical notes at NM and UF.

Results

The DL tools outperformed the rule-based NLP tool in identifying PSH and FHS. For detecting PSH, the rule-based system obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based NLP tool's F1-score was 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. For the gold standard corpora across the three sites, only 2.2% (WCM), 9.3% (NM), and 7.8% (UF) of patients reported to have an ICD-9/10 diagnosis code for suicidal thoughts and behaviors prior to the clinical notes report date. The best performing GatorTron DL tool identified 93.0% (WCM), 80.4% (NM), and 89.0% (UF) of patients with documented PSH, and 85.0%(WCM), 89.5%(NM), and 100%(UF) of patients with documented FSH in their notes.

Discussion

While PSH and FSH are significant risk factors for future suicide events, little effort has been made previously to identify individuals with these history. To address this, we developed a transformer based DL method and compared with conventional rule-based NLP approach. The varying effectiveness of the rule-based tools across sites suggests a need for improvement in its dictionary-based approach. In contrast, the performances of the DL tools were higher and comparable across sites. Furthermore, DL tools were fine-tuned using only small number of annotated notes at each site, underscores its greater adaptability to local documentation practices and lexical variations.

Conclusion

Variations in local documentation practices across health care systems pose challenges to rule-based NLP tools. In contrast, the developed DL tools can effectively extract PSH and FSH information from unstructured clinical notes. These tools will provide clinicians with crucial information for assessing and treating patients at elevated risk for suicide who are rarely been diagnosed.

Corticosteroids for infectious critical illness: A multicenter target trial emulation stratified by predicted organ dysfunction trajectory

Corticosteroids decrease the duration of organ dysfunction in a range of infectious critical illnesses, but their risk and benefit are not fully defined using this construct. This retrospective multicenter study aimed to evaluate the association between usage of corticosteroids and mortality of patients with infectious critical illness by emulating a target trial framework. The study employed a novel stratification method with predictive machine learning (ML) subphenotyping based on organ dysfunction trajectory. Our analysis revealed that corticosteroids' effectiveness varied depending on the stratification method. The ML-based approach identified four distinct subphenotypes, two of which had a large enough sample size in our patient cohorts for further evaluation: "Rapidly Improving" (RI) and "Rapidly Worsening," (RW) which showed divergent responses to corticosteroid treatment. Specifically, the RW group either benefited or were not harmed from corticosteroids, whereas the RI group appeared to derive harm. In the development cohort, which comprised of a combination of patients from the eICU and MIMIC-IV datasets, hazard ratio estimates for the primary outcome, 28-day mortality, in the RW group was 1.05 (95% CI: 0.96 - 1.04) whereas for the RW group, it was 1.40 (95% CI: 1.28 - 1.54). For the validation cohort, which comprised of patients from the Critical carE Database for Advanced Research, estimates for 28-day mortality for the RW and RI groups were 1.24 (95% CI: 1.05 - 1.46) and 1.34 (95% CI: 1.14 - 1.59), respectively. For secondary outcomes, the RW group had a shorter time to ICU discharge and time to cessation of mechanical ventilation with corticosteroid treatment, where the RI group again demonstrated harm. The findings support matching treatment strategies to empirically observed pathobiology and offer a more nuanced understanding of corticosteroid utility. Our results have implications for the design and interpretation of both observational studies and randomized controlled trials (RCTs), suggesting the need for stratification methods that account for the differential response to standard of care.

A scoping review of fair machine learning techniques when using real-world data

OBJECTIVE

The integration of artificial intelligence (AI) and machine learning (ML) in health care to aid clinical decisions is widespread. However, as AI and ML take important roles in health care, there are concerns about AI and ML associated fairness and bias. That is, an AI tool may have a disparate impact, with its benefits and drawbacks unevenly distributed across societal strata and subpopulations, potentially exacerbating existing health inequities. Thus, the objectives of this scoping review were to summarize existing literature and identify gaps in the topic of tackling algorithmic bias and optimizing fairness in AI/ML models using real-world data (RWD) in health care domains.

METHODS

We conducted a thorough review of techniques for assessing and optimizing AI/ML model fairness in health care when using RWD in health care domains. The focus lies on appraising different quantification metrics for accessing fairness, publicly accessible datasets for ML fairness research, and bias mitigation approaches.

RESULTS

We identified 11 papers that are focused on optimizing model fairness in health care applications. The current research on mitigating bias issues in RWD is limited, both in terms of disease variety and health care applications, as well as the accessibility of public datasets for ML fairness research. Existing studies often indicate positive outcomes when using pre-processing techniques to address algorithmic bias. There remain unresolved questions within the field that require further research, which includes pinpointing the root causes of bias in ML models, broadening fairness research in AI/ML with the use of RWD and exploring its implications in healthcare settings, and evaluating and addressing bias in multi-modal data.

CONCLUSION

This paper provides useful reference material and insights to researchers regarding AI/ML fairness in real-world health care data and reveals the gaps in the field. Fair AI/ML in health care is a burgeoning field that requires a heightened research focus to cover diverse applications and different types of RWD.

A Robust Biomimetic Superhydrophobic Coating with Superior Mechanical Durability and Chemical Stability for Inner Pipeline Protection

Durable superhydrophobic anti-erosion/anticorrosion coatings are highly demanded across various applications. However, achieving coatings with exceptional superhydrophobicity, mechanical strength, and corrosion resistance remains a grand challenge. Herein, a robust microstructure coating, inspired by the cylindrical structures situated on the surface of conch shell, for mitigating erosion and corrosion damages in gas transportation pipelines is reported. Specifically, citric acid monohydrate as a pore-forming agent is leveraged to create a porous structure between layers, effectively buffering the impact on the surface. As a result, the coating demonstrates remarkable wear resistance and water repellency. Importantly, even after abrasion by sandpaper and an erosion loop test, the resulting superhydrophobic surfaces retain the water repellency. The design strategy offers a promising route to manufacturing multifunctional materials with desired features and structural complexities, thereby enabling effective self-cleaning and antifouling abilities in harsh operating environments for an array of applications, including self-cleaning windows, antifouling coatings for medical devices, and anti-erosion/anticorrosion protection, among other areas.

Quaternary ammonium-tethered hyperbranched polyurea nanoassembly synergized with antibiotics for enhanced antimicrobial efficacy

The effective transportation of antibiotics to bacteria embedded within a biofilm consisting of a dense matrix of extracellular polymeric substances is still a challenge in the treatment of bacterial biofilm associated infections. Here, we developed an antibiotic nanocarrier constructed from quaternary ammonium-tethered hyperbranched polyureas (HPUs-QA), which showed high loading capacity for a model antibiotic, rifampicin, and high efficacy in the transportation of rifampicin to biofilms. The rifampicin-loaded HPUs-QA nanoassembly (HPUs-Rif/QA) demonstrated a synergistic antimicrobial effect in killing planktonic bacteria and eradicating the corresponding biofilms. Compared to the treatment of bacteria-infected chronic wounds by either HPUs-QA or rifampicin alone, HPUs-Rif/QA showed superior efficacy in promoting wound healing by more effectively inhibiting bacteria colonization. This study highlights the potential of the HPUs-QA nanoassembly in synergistic action with antibiotics for the treatment of biofilm associated infections.

Feasibility of Identifying Factors Related to Alzheimer's Disease and Related Dementia in Real-World Data

A comprehensive view of factors associated with AD/ADRD will significantly aid in studies to develop new treatments for AD/ADRD and identify high-risk populations and patients for prevention efforts. In our study, we summarized the risk factors for AD/ADRD by reviewing existing meta-analyses and review articles on risk and preventive factors for AD/ADRD. In total, we extracted 477 risk factors in 10 categories from 537 studies. We constructed an interactive knowledge map to disseminate our study results. Most of the risk factors are accessible from structured Electronic Health Records (EHRs), and clinical narratives show promise as information sources. However, evaluating genomic risk factors using RWD remains a challenge, as genetic testing for AD/ADRD is still not a common practice and is poorly documented in both structured and unstructured EHRs. Considering the constantly evolving research on AD/ADRD risk factors, literature mining via NLP methods offers a solution to automatically update our knowledge map.

Develop and Validate a Computable Phenotype for the Identification of Alzheimer's Disease Patients Using Electronic Health Record Data

INTRODUCTION

Alzheimer's Disease (AD) are often misclassified in electronic health records (EHRs) when relying solely on diagnostic codes. This study aims to develop a more accurate, computable phenotype (CP) for identifying AD patients by using both structured and unstructured EHR data.

METHODS

We used EHRs from the University of Florida Health (UF Health) system and created rule-based CPs iteratively through manual chart reviews. The CPs were then validated using data from the University of Texas Health Science Center at Houston (UT Health) and the University of Minnesota (UMN).

RESULTS

Our best-performing CP is " patient has at least 2 AD diagnoses and AD-related keywords " with an F1-score of 0.817 at UF, and 0.961 and 0.623 at UT Health and UMN, respectively.

DISCUSSION

We developed and validated rule-based CPs for AD identification with good performance, crucial for studies that aim to use real-world data like EHRs.

Dynamic Prognosis Prediction for Patients on DAPT After Drug-Eluting Stent Implantation: Model Development and Validation

BACKGROUND

The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management.

METHODS AND RESULTS

We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI-DAPT model. The AI-DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%-92%] for ischemia and 84% [95% CI, 82%-87%] for bleeding predictions.

CONCLUSIONS

Our AI-DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.

Genetic Testing for Cancer Risk and Perceived Importance of Genetic Information Among US Population by Race and Ethnicity: a Cross-sectional Study

BACKGROUND

Genetic testing can help determine the risk of many cancers and guide cancer prevention and treatment plans. Despite increasing concern about disparities in precision cancer medicine, public knowledge and cancer genetic testing by race and ethnicity have not been well investigated.

METHODS

We analyzed data from the 2020 Health Information National Trends Survey in 2022. Self-reported cancer genetic testing (e.g., Lynch syndrome, BRCA1/2) knowledge and utilization were compared by race and ethnicity. Perceived importance of genetic information for cancer care (prevention, detection, and treatment) was also examined in relation to the uptake of cancer genetic testing. Multivariable logistic regression models were employed to examine factors associated with knowledge and genetic testing to calculate predicted probability of undergoing genetic testing by race and ethnicity.

RESULTS

Of 3551 study participants, 37.8% reported having heard of genetic testing for cancer risk and 3.9% stated that they underwent cancer genetic testing. Being non-Hispanic Black (OR=0.47, 95% CI=0.30-0.75) or Hispanic (OR=0.56, CI=0.35-0.90) was associated with lower odds of genetic testing knowledge. Although Hispanic or non-Hispanic Black respondents were more likely to perceive higher importance of genetic information versus non-Hispanic Whites, they had a lower predicted probability of cancer genetic testing.

CONCLUSION

Non-Hispanic Black and Hispanic adults had lower knowledge and were less likely to undergo cancer genetic testing than non-Hispanic Whites. Further research is needed on sources of genetic testing information for racial and ethnic minorities and the barriers to accessing genetic testing to inform the development of effective cancer risk genetic testing promotion.

Heterogeneous treatment effects of metformin on risk of dementia in patients with type 2 diabetes: A longitudinal observational study

INTRODUCTION

Little is known about the heterogeneous treatment effects of metformin on dementia risk in people with type 2 diabetes (T2D).

METHODS

Participants (≥ 50 years) with T2D and normal cognition at baseline were identified from the National Alzheimer's Coordinating Center database (2005-2021). We applied a doubly robust learning approach to estimate risk differences (RD) with a 95% confidence interval (CI) for dementia risk between metformin use and no use in the overall population and subgroups identified through a decision tree model.

RESULTS

Among 1393 participants, 104 developed dementia over a 4-year median follow-up. Metformin was significantly associated with a lower risk of dementia in the overall population (RD, -3.2%; 95% CI, -6.2% to -0.2%). We identified four subgroups with varied risks for dementia, defined by neuropsychiatric disorders, non-steroidal anti-inflammatory drugs, and antidepressant use.

DISCUSSION

Metformin use was significantly associated with a lower risk of dementia in individuals with T2D, with significant variability among subgroups.

Real-World Effectiveness of BNT162b2 Against Infection and Severe Diseases in Children and Adolescents

BACKGROUND

The efficacy of the BNT162b2 vaccine in pediatrics was assessed by randomized trials before the Omicron variant's emergence. The long-term durability of vaccine protection in this population during the Omicron period remains limited.

OBJECTIVE

To assess the effectiveness of BNT162b2 in preventing infection and severe diseases with various strains of the SARS-CoV-2 virus in previously uninfected children and adolescents.

DESIGN

Comparative effectiveness research accounting for underreported vaccination in 3 study cohorts: adolescents (12 to 20 years) during the Delta phase and children (5 to 11 years) and adolescents (12 to 20 years) during the Omicron phase.

SETTING

A national collaboration of pediatric health systems (PEDSnet).

PARTICIPANTS

77 392 adolescents (45 007 vaccinated) during the Delta phase and 111 539 children (50 398 vaccinated) and 56 080 adolescents (21 180 vaccinated) during the Omicron phase.

INTERVENTION

First dose of the BNT162b2 vaccine versus no receipt of COVID-19 vaccine.

MEASUREMENTS

Outcomes of interest include documented infection, COVID-19 illness severity, admission to an intensive care unit (ICU), and cardiac complications. The effectiveness was reported as (1-relative risk)*100, with confounders balanced via propensity score stratification.

RESULTS

During the Delta period, the estimated effectiveness of the BNT162b2 vaccine was 98.4% (95% CI, 98.1% to 98.7%) against documented infection among adolescents, with no statistically significant waning after receipt of the first dose. An analysis of cardiac complications did not suggest a statistically significant difference between vaccinated and unvaccinated groups. During the Omicron period, the effectiveness against documented infection among children was estimated to be 74.3% (CI, 72.2% to 76.2%). Higher levels of effectiveness were seen against moderate or severe COVID-19 (75.5% [CI, 69.0% to 81.0%]) and ICU admission with COVID-19 (84.9% [CI, 64.8% to 93.5%]). Among adolescents, the effectiveness against documented Omicron infection was 85.5% (CI, 83.8% to 87.1%), with 84.8% (CI, 77.3% to 89.9%) against moderate or severe COVID-19, and 91.5% (CI, 69.5% to 97.6%) against ICU admission with COVID-19. The effectiveness of the BNT162b2 vaccine against the Omicron variant declined 4 months after the first dose and then stabilized. The analysis showed a lower risk for cardiac complications in the vaccinated group during the Omicron variant period.

LIMITATION

Observational study design and potentially undocumented infection.

CONCLUSION

This study suggests that BNT162b2 was effective for various COVID-19-related outcomes in children and adolescents during the Delta and Omicron periods, and there is some evidence of waning effectiveness over time.

PRIMARY FUNDING SOURCE

National Institutes of Health.

Geographic variation and racial disparities in adoption of newer glucose-lowering drugs with cardiovascular benefits among US Medicare beneficiaries with type 2 diabetes

BACKGROUND

Prior studies have shown disparities in the uptake of cardioprotective newer glucose-lowering drugs (GLDs), including sodium-glucose cotranwsporter-2 inhibitors (SGLT2i) and glucagon-like peptide-1 receptor agonists (GLP1a). This study aimed to characterize geographic variation in the initiation of newer GLDs and the geographic variation in the disparities in initiating these medications.

METHODS

Using 2017-2018 claims data from a 15% random nationwide sample of Medicare Part D beneficiaries, we identified individuals diagnosed with type 2 diabetes (T2D), who had ≥1 GLD prescriptions, and did not use SGLT2i or GLP1a in the year prior to the index date,1/1/2018. Patients were followed up for a year. The cohort was spatiotemporally linked to Dartmouth hospital-referral regions (HRRs), with each patient assigned to 1 of 306 HRRs. We performed multivariable Poisson regression to estimate adjusted initiation rates, and multivariable logistic regression to assess racial disparities in each HRR.

RESULTS

Among 795,469 individuals with T2D included in the analyses, the mean (SD) age was 73 (10) y, 53.3% were women, 12.2% were non-Hispanic Black, and 7.2% initiated a newer GLD in the follow-up year. In the adjusted model including clinical factors, compared to non-Hispanic White patients, non-Hispanic Black (initiation rate ratio, IRR [95% CI]: 0.66 [0.64-0.68]), American Indian/Alaska Native (0.74 [0.66-0.82]), Hispanic (0.85 [0.82-0.87]), and Asian/Pacific islander (0.94 [0.89-0.98]) patients were less likely to initiate newer GLDs. Significant geographic variation was observed across HRRs, with an initiation rate spanning 2.7%-13.6%.

CONCLUSIONS

This study uncovered substantial geographic variation and the racial disparities in initiating newer GLDs.

Real-World Effectiveness of Lung Cancer Screening Using Deep Learning-Based Counterfactual Prediction

The benefits and harms of lung cancer screening (LCS) for patients in the real-world clinical setting have been argued. Recently, discriminative prediction modeling of lung cancer with stratified risk factors has been developed to investigate the real-world effectiveness of LCS from observational data. However, most of these studies were conducted at the population level that only measured the difference in the average outcome between groups. In this study, we built counterfactual prediction models for lung cancer risk and mortality and examined for individual patients whether LCS as a hypothetical intervention reduces lung cancer risk and subsequent mortality. We investigated traditional and deep learning (DL)-based causal methods that provide individualized treatment effect (ITE) at the patient level and evaluated them with a cohort from the OneFlorida+ Clinical Research Consortium. We further discussed and demonstrated that the ITE estimation model can be used to personalize clinical decision support for a broader population.

Morphological Profiling for Drug Discovery in the Era of Deep Learning

Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high-throughput. These efforts have facilitated understanding of compound mechanism-of-action (MOA), drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering- and deep learning-based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.

A Computable Phenotype for the Identification of Sexual and Gender Minorities in Electronic Health Records

Sexual gender minorities, including lesbian, gay, and bisexual (LGB) individuals face unique challenges due to discrimination, stigma, and marginalization, which negatively impact their well-being. Electronic health record (EHR) systems present an opportunity for LGB research, but accurately identifying LGB individuals in EHRs is challenging. Our study developed and validated a rule-based computable phenotype (CP) to identify LGB individuals and their subgroups using both structured data and unstructured clinical narratives from a large integrated health system. Validating against a sample of 537 chart-reviewed patients, our three best performing CP algorithms balancing different performance metrics, each achieved sensitivity of 1.000, PPV of 0.982, and F1-score of 0.875 in identifying LGB individuals, respectively. Applying the three best-performing CPs, our study also found that the LGB population is younger and experiences a disproportionate burden of adverse health outcomes, particularly mental health distress.

Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer's Disease Using Electronic Health Records

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

Identifying demographic and home features influencing older adults' home functioning by using machine learning models

OBJECTIVES

This study aimed to identify demographic and housing features associated with functional difficulties experienced by older adults in their homes.

PARTICIPANTS

Individuals aged ≥ 65 years who completed American Housing Survey (AHS) questionnaires. We selected one random person per household and excluded participants with missing data for the 12 AHS functional challenge items.

METHODS

Multiple machine learning models were compared to identify the best-performing model, which was then used to analyze the impact of demographic and housing features on older adults' functional difficulties at home.

RESULTS

The random forest model was selected for its preferred predictive performance (accuracy: 85.8%, sensitivity: 94.4%, specificity: 60.2%, precision: 87.6%, and negative predictive value: 78.2%). The top five variables that significantly influenced the model were: 1) walking disability, 2) presence or use of a cane or walker, 3) presence or use of handrails or grab bars in the bathroom, 4) go-outside-home disability, and 5) self-care disability. These variables had a stronger impact on the model than the householder's health and age.

CONCLUSION

Home modifications and environmental adaptations may be critical in enhancing functional abilities and independence among older adults. These findings could inform the development of interventions that promote safe and accessible living environments for older adults, thereby improving their quality of life.

Patient-Provider Discussion About Lung Cancer Screening by Race and Ethnicity: Implications for Equitable Uptake of Lung Cancer Screening

BACKGROUND

Physician-patient discussions regarding lung cancer screening (LCS) are uncommon and its racial and ethnic disparities are under-investigated. We examined the racial and ethnic disparities in the trends and frequency of LCS discussion among the LCS-eligible United States (US) population.

METHODS

We analyzed data from the Health Information National Trends Survey from 2014 to 2020. LCS-eligible individuals were defined as adults aged 55 to 80 years old who have a current or former smoking history. We estimated the trends and frequency of LCS discussions and adjusted the probability of having an LCS discussion by racial and ethnic groups.

RESULTS

Among 2136 LCS-eligible participants (representing 22.7 million US adults), 12.9% (95% CI, 10.9%-15%) reported discussing LCS with their providers in the past year. The frequency of LCS discussion was lowest among non-Hispanic White participants (12.3%, 95% CI, 9.9%-14.7%) compared to other racial and ethnic groups (14.1% in Hispanic to 15.3% in non-Hispanic Black). A significant increase over time was only observed among non-Hispanic Black participants (10.1% in 2014 to 22.1% in 2020; P = .05) and non-Hispanic Whites (8.5% in 2014 to 14% in 2020; P = .02). In adjusted analyses, non-Hispanic Black participants (14.6%, 95% CI, 12.3%-16.7%) had a significantly higher probability of LCS discussion than non-Hispanic Whites (12.1%, 95% CI, 11.4%-12.7%).

CONCLUSION

Patient-provider LCS discussion was uncommon in the LCS-eligible US population. Non-Hispanic Black individuals were more likely to have LCS discussions than other racial and ethnic groups. There is a need for more research to clarify the discordance between LCS discussions and the actual screening uptake in this population.

Quantifying Health Outcome Disparity in Invasive Methicillin-Resistant Staphylococcus aureus Infection using Fairness Algorithms on Real-World Data

This study quantifies health outcome disparities in invasive Methicillin-Resistant Staphylococcus aureus (MRSA) infections by leveraging a novel artificial intelligence (AI) fairness algorithm, the Fairness-Aware Causal paThs (FACTS) decomposition, and applying it to real-world electronic health record (EHR) data. We spatiotemporally linked 9 years of EHRs from a large healthcare provider in Florida, USA, with contextual social determinants of health (SDoH). We first created a causal structure graph connecting SDoH with individual clinical measurements before/upon diagnosis of invasive MRSA infection, treatments, side effects, and outcomes; then, we applied FACTS to quantify outcome potential disparities of different causal pathways including SDoH, clinical and demographic variables. We found moderate disparity with respect to demographics and SDoH, and all the top ranked pathways that led to outcome disparities in age, gender, race, and income, included comorbidity. Prior kidney impairment, vancomycin use, and timing were associated with racial disparity, while income, rurality, and available healthcare facilities contributed to gender disparity. From an intervention standpoint, our results highlight the necessity of devising policies that consider both clinical factors and SDoH. In conclusion, this work demonstrates a practical utility of fairness AI methods in public health settings.

Predicting preterm birth using explainable machine learning in a prospective cohort of nulliparous and multiparous pregnant women

Preterm birth (PTB) presents a complex challenge in pregnancy, often leading to significant perinatal and long-term morbidities. "While machine learning (ML) algorithms have shown promise in PTB prediction, the lack of interpretability in existing models hinders their clinical utility. This study aimed to predict PTB in a pregnant population using ML models, identify the key risk factors associated with PTB through the SHapley Additive exPlanations (SHAP) algorithm, and provide comprehensive explanations for these predictions to assist clinicians in providing appropriate care. This study analyzed a dataset of 3509 pregnant women in the United Arab Emirates and selected 35 risk factors associated with PTB based on the existing medical and artificial intelligence literature. Six ML algorithms were tested, wherein the XGBoost model exhibited the best performance, with an area under the operator receiving curves of 0.735 and 0.723 for parous and nulliparous women, respectively. The SHAP feature attribution framework was employed to identify the most significant risk factors linked to PTB. Additionally, individual patient analysis was performed using the SHAP and the local interpretable model-agnostic explanation algorithms (LIME). The overall incidence of PTB was 11.23% (11 and 12.1% in parous and nulliparous women, respectively). The main risk factors associated with PTB in parous women are previous PTB, previous cesarean section, preeclampsia during pregnancy, and maternal age. In nulliparous women, body mass index at delivery, maternal age, and the presence of amniotic infection were the most relevant risk factors. The trained ML prediction model developed in this study holds promise as a valuable screening tool for predicting PTB within this specific population. Furthermore, SHAP and LIME analyses can assist clinicians in understanding the individualized impact of each risk factor on their patients and provide appropriate care to reduce morbidity and mortality related to PTB.

Developing a computable phenotype for glioblastoma

BACKGROUND

Glioblastoma (GBM) is the most common malignant brain tumor, and thus it is important to be able to identify patients with this diagnosis for population studies. However, this can be challenging as diagnostic codes are non-specific. The aim of this study was to create a computable phenotype (CP) for GBM from structured and unstructured data to identify patients with this condition in a large electronic health record (EHR).

METHODS

We used the UF Health Integrated Data Repository, a centralized clinical data warehouse that stores clinical and research data from various sources within the UF Health system, including the EHR system. We performed multiple iterations to refine the GBM-relevant diagnosis codes, procedure codes, medication codes, and keywords through manual chart review of patient data. We then evaluated the performances of various possible proposed CPs constructed from the relevant codes and keywords.

RESULTS

We underwent six rounds of manual chart reviews to refine the CP elements. The final CP algorithm for identifying GBM patients was selected based on the best F1-score. Overall, the CP rule "if the patient had at least 1 relevant diagnosis code and at least 1 relevant keyword" demonstrated the highest F1-score using both structured and unstructured data. Thus, it was selected as the best-performing CP rule.

CONCLUSIONS

We developed a CP algorithm for identifying patients with GBM using both structured and unstructured EHR data from a large tertiary care center. The final algorithm achieved an F1-score of 0.817, indicating a high performance which minimizes possible biases from misclassification errors.

The role of health system penetration rate in estimating the prevalence of type 1 diabetes in children and adolescents using electronic health records

OBJECTIVE

Having sufficient population coverage from the electronic health records (EHRs)-connected health system is essential for building a comprehensive EHR-based diabetes surveillance system. This study aimed to establish an EHR-based type 1 diabetes (T1D) surveillance system for children and adolescents across racial and ethnic groups by identifying the minimum population coverage from EHR-connected health systems to accurately estimate T1D prevalence.

MATERIALS AND METHODS

We conducted a retrospective, cross-sectional analysis involving children and adolescents <20 years old identified from the OneFlorida+ Clinical Research Network (2018-2020). T1D cases were identified using a previously validated computable phenotyping algorithm. The T1D prevalence for each ZIP Code Tabulation Area (ZCTA, 5 digits), defined as the number of T1D cases divided by the total number of residents in the corresponding ZCTA, was calculated. Population coverage for each ZCTA was measured using observed health system penetration rates (HSPR), which was calculated as the ratio of residents in the corresponding ZTCA and captured by OneFlorida+ to the overall population in the same ZCTA reported by the Census. We used a recursive partitioning algorithm to identify the minimum required observed HSPR to estimate T1D prevalence and compare our estimate with the reported T1D prevalence from the SEARCH study.

RESULTS

Observed HSPRs of 55%, 55%, and 60% were identified as the minimum thresholds for the non-Hispanic White, non-Hispanic Black, and Hispanic populations. The estimated T1D prevalence for non-Hispanic White and non-Hispanic Black were 2.87 and 2.29 per 1000 youth, which are comparable to the reference study's estimation. The estimated prevalence of T1D for Hispanics (2.76 per 1000 youth) was higher than the reference study's estimation (1.48-1.64 per 1000 youth). The standardized T1D prevalence in the overall Florida population was 2.81 per 1000 youth in 2019.

CONCLUSION

Our study provides a method to estimate T1D prevalence in children and adolescents using EHRs and reports the estimated HSPRs and prevalence of T1D for different race and ethnicity groups to facilitate EHR-based diabetes surveillance.

High-throughput target trial emulation for Alzheimer's disease drug repurposing with real-world data

Target trial emulation is the process of mimicking target randomized trials using real-world data, where effective confounding control for unbiased treatment effect estimation remains a main challenge. Although various approaches have been proposed for this challenge, a systematic evaluation is still lacking. Here we emulated trials for thousands of medications from two large-scale real-world data warehouses, covering over 10 years of clinical records for over 170 million patients, aiming to identify new indications of approved drugs for Alzheimer's disease. We assessed different propensity score models under the inverse probability of treatment weighting framework and suggested a model selection strategy for improved baseline covariate balancing. We also found that the deep learning-based propensity score model did not necessarily outperform logistic regression-based methods in covariate balancing. Finally, we highlighted five top-ranked drugs (pantoprazole, gabapentin, atorvastatin, fluticasone, and omeprazole) originally intended for other indications with potential benefits for Alzheimer's patients.

A Fair Individualized Polysocial Risk Score for Identifying Increased Social Risk in Type 2 Diabetes

Background

Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications. It is crucial to implement effective social risk management strategies at the point of care.

Objective

To develop an electronic health records (EHR)-based machine learning (ML) analytical pipeline to address unmet social needs associated with hospitalization risk in patients with T2D.

Methods

We identified real-world patients with T2D from the EHR data from University of Florida (UF) Health Integrated Data Repository (IDR), incorporating both contextual SDoH (e.g., neighborhood deprivation) and individual-level SDoH (e.g., housing instability). The 2015-2020 data were used for training and validation and 2021-2022 data for independent testing. We developed a machine learning analytic pipeline, namely individualized polysocial risk score (iPsRS), to identify high social risk associated with hospitalizations in T2D patients, along with explainable AI (XAI) and fairness optimization.

Results

The study cohort included 10,192 real-world patients with T2D, with a mean age of 59 years and 58% female. Of the cohort, 50% were non-Hispanic White, 39% were non-Hispanic Black, 6% were Hispanic, and 5% were other races/ethnicities. Our iPsRS, including both contextual and individual-level SDoH as input factors, achieved a C statistic of 0.72 in predicting 1-year hospitalization after fairness optimization across racial and ethnic groups. The iPsRS showed excellent utility for capturing individuals at high hospitalization risk because of SDoH, that is, the actual 1-year hospitalization rate in the top 5% of iPsRS was 28.1%, ~13 times as high as the bottom decile (2.2% for 1-year hospitalization rate).

Conclusion

Our ML pipeline iPsRS can fairly and accurately screen for patients who have increased social risk leading to hospitalization in real word patients with T2D.

Unraveling Racial Disparities in Supportive Care Medication Use among End-of-Life Pancreatic Cancer Patients: Focus on Pain Management and Psychiatric Therapies

BACKGROUND

Supportive care medication use differences may contribute to racial disparities observed in health-related quality of life in patients with pancreatic cancer.

METHODS

In this observation study using the Surveillance, Epidemiology, and End Results-Medicare linked database, we sought to examine supportive care medication use disparities in patients with pancreatic cancer from 2005 to 2017 by race and ethnicity.

RESULTS

Among 74,309 patients included in the final analysis, racial and ethnic disparities in the use of supportive care medications were identified. After adjustment for confounding factors and compared with non-Hispanic Whites, minorities had significantly less use of opioids [Black: adjusted OR (aOR), 0.84; 95% confidence interval (CI), 0.79-0.88; Asian: aOR, 0.84; 95% CI, 0.79-0.90), and skeletomuscular relaxants (Black: aOR, 0.90; 95% CI, 0.82-0.99; Hispanic: aOR, 0.82; 95% CI, 0.74-0.91; Asian: aOR, 0.59; 95% CI, 0.51-0.68), and increased use of non-opioid analgesics (Hispanic: aOR, 1.16; 95% CI, 1.01-1.14; Asian: aOR, 1.37; 95% CI, 1.26-1.49). Racial and ethnic minorities had less use of antidepressants (Black: aOR, 0.56; 95% CI, 0.53-0.59; Hispanic: aOR, 0.77; 95% CI, 0.73-0.82; Asian: aOR, 0.47; 95% CI, 0.44-0.51), anxiolytics (Black: aOR, 0.78; 95% CI, 0.74-0.82; Hispanic: aOR, 0.66; 95% CI, 0.62-0.71; Asian: aOR, 0.52; 95% CI, 0.48-0.57), and antipsychotics (Hispanic: aOR, 0.90; 95% CI, 0.82-0.99; Asian: aOR, 0.84; 95% CI, 0.74-0.95).

CONCLUSIONS

Racial and ethnic disparities in the use of supportive care medications among patients with pancreatic cancer were observed, with the differences unexplained by sociodemographic factors.

IMPACT

Future studies should identify strategies to promote equitable use of supportive care medications among racial minorities and explore factors that may influence their use in these populations.

Numerical analysis of dispersion characteristics of underwater gas-oil two-phase leakage process

Fatigue failure, third-party destruction and internal corrosion may easily trigger gas and oil leakage during the operation of submarine multiphase pipelines. In order to analyze the underwater gas-oil plume development and migration law, a 3D model based on coupled Eulerian-Lagrangian numerical approach is proposed. The model is validated by laboratory experiment and the dynamic dispersion process of gas-oil plume in a large scale shallow sea environmental is further explored. Influencing factors such as leak location, leak size and water depth, flow pattern are investigated. The simulated results show that leak location affects the gas-oil plume migration behaviors by influencing the leakage amount. Water depth significantly affects gas-oil migration and the separation of gas plume and oil plume is gradually apparent as water depth increases. This study fills in the gap of ignoring the influence of flow pattern previously and is expected to help build more accurate emergency response guidelines.

Immune tolerance induced in the anterior chamber ameliorates corneal transplant rejection

The relevance of regulatory T cells (Tregs) in induction of tolerance against corneal allografts has been well established. However, whether Tregs can be induced in the anterior chamber and suppress local alloimmune response after corneal transplantation is largely unknown. In the current study we report that not only can alloantigen specific Tregs be generated in the anterior chamber during corneal transplantation, they also play important roles in suppressing allograft rejection. Allograft rejected mice exhibit reduced Treg induction in the anterior chamber and the ability of aqueous humor and corneal endothelial cells from allograft rejected mice to induce Tregs is compromised. Further analysis revealed that the expression of immune-tolerance-related molecules is significantly decreased. Finally, we demonstrate that increasing Treg cells specifically in the anterior chamber can effectively suppress allograft rejection and exhibits better efficacy in promoting corneal allograft survival than systemic administration of Treg cells. Our current study may provide new ideas for the prevention and treatment of corneal transplant rejection.

A study of generative large language model for medical research and healthcare

There are enormous enthusiasm and concerns in applying large language models (LLMs) to healthcare. Yet current assumptions are based on general-purpose LLMs such as ChatGPT, which are not developed for medical use. This study develops a generative clinical LLM, GatorTronGPT, using 277 billion words of text including (1) 82 billion words of clinical text from 126 clinical departments and approximately 2 million patients at the University of Florida Health and (2) 195 billion words of diverse general English text. We train GatorTronGPT using a GPT-3 architecture with up to 20 billion parameters and evaluate its utility for biomedical natural language processing (NLP) and healthcare text generation. GatorTronGPT improves biomedical natural language processing. We apply GatorTronGPT to generate 20 billion words of synthetic text. Synthetic NLP models trained using synthetic text generated by GatorTronGPT outperform models trained using real-world clinical text. Physicians' Turing test using 1 (worst) to 9 (best) scale shows that there are no significant differences in linguistic readability (p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that physicians cannot differentiate them (p < 0.001). This study provides insights into the opportunities and challenges of LLMs for medical research and healthcare.

Real-world Effectiveness of BNT162b2 Against Infection and Severe Diseases in Children and Adolescents

Background

The efficacy of the BNT162b2 vaccine in pediatrics was assessed by randomized trials before the Omicron variant's emergence. The long-term durability of vaccine protection in this population during the Omicron period remains limited.

Objective

To assess the effectiveness of BNT162b2 in preventing infection and severe diseases with various strains of the SARS-CoV-2 virus in previously uninfected children and adolescents.

Design

Comparative effectiveness research accounting for underreported vaccination in three study cohorts: adolescents (12 to 20 years) during the Delta phase, children (5 to 11 years) and adolescents (12 to 20 years) during the Omicron phase.

Setting

A national collaboration of pediatric health systems (PEDSnet).

Participants

77,392 adolescents (45,007 vaccinated) in the Delta phase, 111,539 children (50,398 vaccinated) and 56,080 adolescents (21,180 vaccinated) in the Omicron period.

Exposures

First dose of the BNT162b2 vaccine vs. no receipt of COVID-19 vaccine.

Measurements

Outcomes of interest include documented infection, COVID-19 illness severity, admission to an intensive care unit (ICU), and cardiac complications. The effectiveness was reported as (1-relative risk)*100% with confounders balanced via propensity score stratification.

Results

During the Delta period, the estimated effectiveness of BNT162b2 vaccine was 98.4% (95% CI, 98.1 to 98.7) against documented infection among adolescents, with no significant waning after receipt of the first dose. An analysis of cardiac complications did not find an increased risk after vaccination. During the Omicron period, the effectiveness against documented infection among children was estimated to be 74.3% (95% CI, 72.2 to 76.2). Higher levels of effectiveness were observed against moderate or severe COVID-19 (75.5%, 95% CI, 69.0 to 81.0) and ICU admission with COVID-19 (84.9%, 95% CI, 64.8 to 93.5). Among adolescents, the effectiveness against documented Omicron infection was 85.5% (95% CI, 83.8 to 87.1), with 84.8% (95% CI, 77.3 to 89.9) against moderate or severe COVID-19, and 91.5% (95% CI, 69.5 to 97.6)) against ICU admission with COVID-19. The effectiveness of the BNT162b2 vaccine against the Omicron variant declined after 4 months following the first dose and then stabilized. The analysis revealed a lower risk of cardiac complications in the vaccinated group during the Omicron variant period.

Limitations

Observational study design and potentially undocumented infection.

Conclusions

Our study suggests that BNT162b2 was effective for various COVID-19-related outcomes in children and adolescents during the Delta and Omicron periods, and there is some evidence of waning effectiveness over time.

Primary Funding Source

National Institutes of Health.

N6-methyladenosine in 7SK small nuclear RNA underlies RNA polymerase II transcription regulation

N6-methyladenosine (m6A) modifications play crucial roles in RNA metabolism. How m6A regulates RNA polymerase II (RNA Pol II) transcription remains unclear. We find that 7SK small nuclear RNA (snRNA), a regulator of RNA Pol II promoter-proximal pausing, is highly m6A-modified in non-small cell lung cancer (NSCLC) cells. In A549 cells, we identified eight m6A sites on 7SK and discovered methyltransferase-like 3 (METTL3) and alkB homolog 5 (ALKBH5) as the responsible writer and eraser. When the m6A-7SK is specifically erased by a dCasRx-ALKBH5 fusion protein, A549 cell growth is attenuated due to reduction of RNA Pol II transcription. Mechanistically, removal of m6A leads to 7SK structural rearrangements that facilitate sequestration of the positive transcription elongation factor b (P-TEFb) complex, which results in reduction of serine 2 phosphorylation (Ser2P) in the RNA Pol II C-terminal domain and accumulation of RNA Pol II in the promoter-proximal region. Taken together, we uncover that m6A modifications of a non-coding RNA regulate RNA Pol II transcription and NSCLC tumorigenesis.

Evaluating the perceptions of pesticide use, safety, and regulation and identifying common pesticide-related topics on Twitter

Synthetic pesticides are important agricultural tools that increase crop yield and help feed the world's growing population. These products are also highly regulated to balance benefits and potential environmental and human risks. Public perception of pesticide use, safety, and regulation is an important topic necessitating discussion across a variety of stakeholders from lay consumers to regulatory agencies since attitudes toward this subject could differ markedly. Individuals and organizations can perceive the same message(s) about pesticides differently due to prior differences in technical knowledge, perceptions, attitudes, and individual or group circumstances. Social media platforms, like Twitter, include both individuals and organizations and function as a townhall where each group promotes their topics of interest, shares their perspectives, and engages in both well-informed and misinformed discussions. We analyzed public Twitter posts about pesticides by user group, time, and location to understand their communication behaviors, including their sentiments and discussion topics, using machine learning-based text analysis methods. We extracted tweets related to pesticides between 2013 and 2021 based on relevant keywords developed through a "snowball" sampling process. Each tweet was grouped into individual versus organizational groups, then further categorized into media, government, industry, academia, and three types of nongovernmental organizations. We compared topic distributions within and between those groups using topic modeling and then applied sentiment analysis to understand the public's attitudes toward pesticide safety and regulation. Individual accounts expressed concerns about health and environmental risks, while industry and government accounts focused on agricultural usage and regulations. Public perceptions are heavily skewed toward negative sentiments, although this varies geographically. Our findings can help managers and decision-makers understand public sentiments, priorities, and perceptions and provide insights into public discourse on pesticides. Integr Environ Assess Manag 2023;19:1581-1599. © 2023 The Authors. Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).

Meta-analysis of Association between Newer Glucose-Lowering Drugs and Risk of Parkinson's Disease

Background

The association between newer classes of glucose-lowering drugs (GLDs) and the risk of Parkinson's disease (PD) remains unclear.

Objective

The aim was to examine the effect of newer GLDs on the risk of PD through a meta-analysis of randomized outcome trials.

Methods

The methods included randomized placebo-controlled outcome trials that reported PD events associated with three newer classes of GLDs (ie, dipeptidyl peptidase-4 inhibitors, glucagon-like peptide-1 receptor agonists, and sodium-glucose co-transporter-2 inhibitors) in participants with or without type 2 diabetes. The pooled odds ratio (OR) and 95% confidence interval (CI) were estimated using Peto's method.

Results

The study included 24 trials involving 33 PD cases among 185,305 participants during a median follow-up of 2.2 years. Newer GLDs were significantly associated with a lower PD risk (OR: 0.50; 95% CI: 0.25-0.98) than placebo.

Conclusion

Newer GLDs may possibly be associated with a decreased risk of PD; however, larger datasets are required to confirm or refute this notion.