Investigation of commonly used aortic aneurysm growth rate metrics: Comparing their suitability for clinical and research applications.

An aneurysm is a pathological widening of a blood vessel. Aneurysms of the aorta are often asymptomatic until they rupture, killing approximately 10,000 Americans per year. Fortunately, rupture can be prevented through early detection and surgical repair. However, surgical risk outweighs rupture risk for small aortic aneurysms, necessitating a policy of surveillance. Understanding the growth rate of aneurysms is essential for determining appropriate surveillance windows. Further, identifying risk factors for fast growth can help identify potential interventions. However, studies in the literature have applied many different methods for defining the growth rate of abdominal aortic aneurysms. It is unclear which of these methods is most accurate and clinically meaningful, and whether these heterogeneous methodologies may have contributed to the varied results reported in the literature. To help future researchers best plan their studies and to help clinicians interpret existing studies, we compared five different models of aneurysmal growth rate. We examined their noise tolerance, temporal bias, predictive accuracy, and statistical power to detect risk factors. We found that hierarchical mixed effects models were more noise tolerant than traditional, unpooled models. We also found that linear models were sensitive to temporal bias, assigning lower growth rates to aneurysms that were detected earlier in their course. Our exponential mixed model was noise-tolerant, resistant to temporal bias, and detected the greatest number of clinical risk factors. We conclude that exponential mixed models may be optimal for large studies. Because our results suggest that choice of method can materially impact a study's findings, we recommend that future studies clearly state the method used and demonstrate its appropriateness.

PI3Kß controls immune evasion in PTEN-deficient breast tumours.

Loss of the PTEN tumour suppressor is one of the most common oncogenic drivers across all cancer types1. PTEN is the major negative regulator of PI3K signalling. The PI3Kß isoform has been shown to play an important role in PTEN-deficient tumours, but the mechanisms underlying the importance of PI3Kß activity remain elusive. Here, using a syngeneic genetically engineered mouse model of invasive breast cancer driven by ablation of both Pten and Trp53 (which encodes p53), we show that genetic inactivation of PI3Kß led to a robust anti-tumour immune response that abrogated tumour growth in syngeneic immunocompetent mice, but not in immunodeficient mice. Mechanistically, PI3Kß inactivation in the PTEN-null setting led to reduced STAT3 signalling and increased the expression of immune stimulatory molecules, thereby promoting anti-tumour immune responses. Pharmacological PI3Kß inhibition also elicited anti-tumour immunity and synergized with immunotherapy to inhibit tumour growth. Mice with complete responses to the combined treatment displayed immune memory and rejected tumours upon re-challenge. Our findings demonstrate a molecular mechanism linking PTEN loss and STAT3 activation in cancer and suggest that PI3Kß controls immune escape in PTEN-null tumours, providing a rationale for combining PI3Kß inhibitors with immunotherapy for the treatment of PTEN-deficient breast cancer.

An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction.

Opioid overdose (OD) has become a leading cause of accidental death in the United States, and overdose deaths reached a record high during the COVID-19 pandemic. Combating the opioid crisis requires targeting high-need populations by identifying individuals at risk of OD. While deep learning emerges as a powerful method for building predictive models using large scale electronic health records (EHR), it is challenged by the complex intrinsic relationships among EHR data. Further, its utility is limited by the lack of clinically meaningful explainability, which is necessary for making informed clinical or policy decisions using such models. In this paper, we present LIGHTED, an integrated deep learning model combining long short term memory (LSTM) and graph neural networks (GNN) to predict patients' OD risk. The LIGHTED model can incorporate the temporal effects of disease progression and the knowledge learned from interactions among clinical features. We evaluated the model using Cerner's Health Facts database with over 5 million patients. Our experiments demonstrated that the model outperforms traditional machine learning methods and other deep learning models. We also proposed a novel interpretability method by exploiting embeddings provided by GNNs to cluster patients and EHR features respectively, and conducted qualitative feature cluster analysis for clinical interpretations. Our study shows that LIGHTED can take advantage of longitudinal EHR data and the intrinsic graph structure of EHRs among patients to provide effective and interpretable OD risk predictions that may potentially improve clinical decision support.

Where Opioid Overdose Patients Live Far From Treatment: Geospatial Analysis of Underserved Populations in New York State.

BACKGROUND: Opioid addiction and overdose have a large burden of disease and mortality in New York State (NYS). The medication naloxone can reverse an overdose, and buprenorphine can treat opioid use disorder. Efforts to increase the accessibility of both medications include a naloxone standing order and a waiver program for prescribing buprenorphine outside a licensed drug treatment program. However, only a slim majority of NYS pharmacies are listed as participating in the naloxone standing order, and less than 7% of prescribers in NYS have a buprenorphine waiver. Therefore, there is a significant opportunity to increase access. OBJECTIVE: Identifying the geographic regions of NYS that are farthest from resources can help target interventions to improve access to naloxone and buprenorphine. To maximize the efficiency of such efforts, we also sought to determine where these underserved regions overlap with the largest numbers of actual patients who have experienced opioid overdose. METHODS: We used address data to assess the spatial distribution of naloxone pharmacies and buprenorphine prescribers. Using the home addresses of patients who had an opioid overdose, we identified geographic locations of resource deficits. We report findings at the high spatial granularity of census tracts, with some neighboring census tracts merged to preserve privacy. RESULTS: We identified several hot spots, where many patients live far from the nearest resource of each type. The highest density of patients in areas far from naloxone pharmacies was found in eastern Broome county. For areas far from buprenorphine prescribers, we identified subregions of Oswego county and Wayne county as having a high number of potentially underserved patients. CONCLUSIONS: Although NYS is home to thousands of naloxone pharmacies and potential buprenorphine prescribers, access is not uniform. Spatial analysis revealed census tract areas that are far from resources, yet contain the residences of many patients who have experienced opioid overdose. Our findings have implications for public health decision support in NYS. Our methods for privacy can also be applied to other spatial supply-demand problems involving sensitive data.

A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction.

Deep-learning-based clinical decision support using structured electronic health records (EHR) has been an active research area for predicting risks of mortality and diseases. Meanwhile, large amounts of narrative clinical notes provide complementary information, but are often not integrated into predictive models. In this paper, we provide a novel multimodal transformer to fuse clinical notes and structured EHR data for better prediction of in-hospital mortality. To improve interpretability, we propose an integrated gradients (IG) method to select important words in clinical notes and discover the critical structured EHR features with Shapley values. These important words and clinical features are visualized to assist with interpretation of the prediction outcomes. We also investigate the significance of domain adaptive pretraining and task adaptive fine-tuning on the Clinical BERT, which is used to learn the representations of clinical notes. Experiments demonstrated that our model outperforms other methods (AUCPR: 0.538, AUCROC: 0.877, F1:0.490).

Identifying risk of opioid use disorder for patients taking opioid medications with deep learning.

OBJECTIVE: The United States is experiencing an opioid epidemic. In recent years, there were more than 10 million opioid misusers aged 12 years or older annually. Identifying patients at high risk of opioid use disorder (OUD) can help to make early clinical interventions to reduce the risk of OUD. Our goal is to develop and evaluate models to predict OUD for patients on opioid medications using electronic health records and deep learning methods. The resulting models help us to better understand OUD, providing new insights on the opioid epidemic. Further, these models provide a foundation for clinical tools to predict OUD before it occurs, permitting early interventions. METHODS: Electronic health records of patients who have been prescribed with medications containing active opioid ingredients were extracted from Cerner's Health Facts database for encounters between January 1, 2008, and December 31, 2017. Long short-term memory models were applied to predict OUD risk based on five recent prior encounters before the target encounter and compared with logistic regression, random forest, decision tree, and dense neural network. Prediction performance was assessed using F1 score, precision, recall, and area under the receiver-operating characteristic curve. RESULTS: The long short-term memory (LSTM) model provided promising prediction results which outperformed other methods, with an F1 score of 0.8023 (about 0.016 higher than dense neural network (DNN)) and an area under the receiver-operating characteristic curve (AUROC) of 0.9369 (about 0.145 higher than DNN). CONCLUSIONS: LSTM-based sequential deep learning models can accurately predict OUD using a patient's history of electronic health records, with minimal prior domain knowledge. This tool has the potential to improve clinical decision support for early intervention and prevention to combat the opioid epidemic.

Association of Opioid Use Disorder With 2016 Presidential Voting Patterns: Cross-sectional Study in New York State at Census Tract Level.

BACKGROUND: Opioid overdose-related deaths have increased dramatically in recent years. Combating the opioid epidemic requires better understanding of the epidemiology of opioid poisoning (OP) and opioid use disorder (OUD). OBJECTIVE: We aimed to discover geospatial patterns in nonmedical opioid use and its correlations with demographic features related to despair and economic hardship, most notably the US presidential voting patterns in 2016 at census tract level in New York State. METHODS: This cross-sectional analysis used data from New York Statewide Planning and Research Cooperative System claims data and the presidential voting results of 2016 in New York State from the Harvard Election Data Archive. We included 63,958 patients who had at least one OUD diagnosis between 2010 and 2016 and 36,004 patients with at least one OP diagnosis between 2012 and 2016. Geospatial mappings were created to compare areas of New York in OUD rates and presidential voting patterns. A multiple regression model examines the extent that certain factors explain OUD rate variation. RESULTS: Several areas shared similar patterns of OUD rates and Republican vote: census tracts in western New York, central New York, and Suffolk County. The correlation between OUD rates and the Republican vote was .38 (P<.001). The regression model with census tract level of demographic and socioeconomic factors explains 30% of the variance in OUD rates, with disability and Republican vote as the most significant predictors. CONCLUSIONS: At the census tract level, OUD rates were positively correlated with Republican support in the 2016 presidential election, disability, unemployment, and unmarried status. Socioeconomic and demographic despair-related features explain a large portion of the association between the Republican vote and OUD. Together, these findings underscore the importance of socioeconomic interventions in combating the opioid epidemic.

Detecting Miscoded Diabetes Diagnosis Codes in Electronic Health Records for Quality Improvement: Temporal Deep Learning Approach.

BACKGROUND: Diabetes affects more than 30 million patients across the United States. With such a large disease burden, even a small error in classification can be significant. Currently billing codes, assigned at the time of a medical encounter, are the "gold standard" reflecting the actual diseases present in an individual, and thus in aggregate reflect disease prevalence in the population. These codes are generated by highly trained coders and by health care providers but are not always accurate. OBJECTIVE: This work provides a scalable deep learning methodology to more accurately classify individuals with diabetes across multiple health care systems. METHODS: We leveraged a long short-term memory-dense neural network (LSTM-DNN) model to identify patients with or without diabetes using data from 5 acute care facilities with 187,187 patients and 275,407 encounters, incorporating data elements including laboratory test results, diagnostic/procedure codes, medications, demographic data, and admission information. Furthermore, a blinded physician panel reviewed discordant cases, providing an estimate of the total impact on the population. RESULTS: When predicting the documented diagnosis of diabetes, our model achieved an 84% F1 score, 96% area under the curve-receiver operating characteristic curve, and 91% average precision on a heterogeneous data set from 5 distinct health facilities. However, in 81% of cases where the model disagreed with the documented phenotype, a blinded physician panel agreed with the model. Taken together, this suggests that 4.3% of our studied population have either missing or improper diabetes diagnosis. CONCLUSIONS: This study demonstrates that deep learning methods can improve clinical phenotyping even when patient data are noisy, sparse, and heterogeneous.

Allele-Specific Chromatin Recruitment and Therapeutic Vulnerabilities of ESR1 Activating Mutations.

Estrogen receptor α (ER) ligand-binding domain (LBD) mutations are found in a substantial number of endocrine treatment-resistant metastatic ER-positive (ER+) breast cancers. We investigated the chromatin recruitment, transcriptional network, and genetic vulnerabilities in breast cancer models harboring the clinically relevant ER mutations. These mutants exhibit both ligand-independent functions that mimic estradiol-bound wild-type ER as well as allele-specific neomorphic properties that promote a pro-metastatic phenotype. Analysis of the genome-wide ER binding sites identified mutant ER unique recruitment mediating the allele-specific transcriptional program. Genetic screens identified genes that are essential for the ligand-independent growth driven by the mutants. These studies provide insights into the mechanism of endocrine therapy resistance engendered by ER mutations and potential therapeutic targets.

MAP3K4 Controls the Chromatin Modifier HDAC6 during Trophoblast Stem Cell Epithelial-to-Mesenchymal Transition.

The first epithelial-to-mesenchymal transition (EMT) occurs in trophoblast stem (TS) cells during implantation. Inactivation of the serine/threonine kinase MAP3K4 in TS cells (TSKI4 cells) induces an intermediate state of EMT, where cells retain stemness, lose epithelial markers, and gain mesenchymal characteristics. Investigation of relationships among MAP3K4 activity, stemness, and EMT in TS cells may reveal key regulators of EMT. Here, we show that MAP3K4 activity controls EMT through the ubiquitination and degradation of HDAC6. Loss of MAP3K4 activity in TSKI4 cells results in elevated HDAC6 expression and the deacetylation of cytoplasmic and nuclear targets. In the nucleus, HDAC6 deacetylates the promoters of tight junction genes, promoting the dissolution of tight junctions. Importantly, HDAC6 knockdown in TSKI4 cells restores epithelial features, including cell-cell adhesion and barrier formation. These data define a role for HDAC6 in regulating gene expression during transitions between epithelial and mesenchymal phenotypes.