ROR2 Regulates Cellular Plasticity in Pancreatic Neoplasia and Adenocarcinoma.

Cellular plasticity is a hallmark of pancreatic ductal adenocarcinoma (PDAC) starting from the conversion of normal cells into precancerous lesions, to the progression of carcinoma subtypes associated with aggressiveness and therapeutic response. We discovered that normal acinar cell differentiation, maintained by the transcription factor Pdx1, suppresses a broad gastric cell identity that is maintained in metaplasia, neoplasia, and the classical subtype of PDAC in mouse and human. We have identified the receptor tyrosine kinase Ror2 as marker of a gastric metaplasia-like identity in pancreas neoplasms. Ablation of Ror2 in a mouse model of pancreatic tumorigenesis promoted a switch to a gastric pit cell identity that largely persisted through progression to the classical subtype of PDAC. In both human and mouse pancreatic cancer, ROR2 activity continued to antagonize the gastric pit cell identity, strongly promoting an epithelial to mesenchymal transition, conferring resistance to KRAS inhibition, and vulnerability to AKT inhibition.

Bidirectional modulation of negative emotional states by parallel genetically-distinct basolateral amygdala pathways to ventral striatum subregions.

Distinct basolateral amygdala (BLA) cell populations influence emotional responses in manners thought important for anxiety and anxiety disorders. The BLA contains numerous cell types which can broadcast information into structures that may elicit changes in emotional states and behaviors. BLA excitatory neurons can be divided into two main classes, one of which expresses Ppp1r1b (encoding protein phosphatase 1 regulatory inhibitor subunit 1B) which is downstream of the genes encoding the D1 and D2 dopamine receptors (drd1 and drd2 respectively). The role of drd1+ or drd2+ BLA neurons in learned and unlearned emotional responses is unknown. Here, we identified that the drd1+ and drd2+ BLA neuron populations form two parallel pathways for communication with the ventral striatum. These neurons arise from the basal nucleus of the BLA, innervate the entire space of the ventral striatum, and are capable of exciting ventral striatum neurons. Further, through three separate behavioral assays, we found that the drd1+ and drd2+ parallel pathways bidirectionally influence both learned and unlearned emotional states when they are activated or suppressed, and do so depending upon where they synapse in the ventral striatum - with unique contributions of drd1+ and drd2+ circuitry on negative emotional states. Overall, these results contribute to a model whereby parallel, genetically-distinct BLA to ventral striatum circuits inform emotional states in a projection-specific manner.

Spatial datasets of 30-year (1991-2020) average monthly total precipitation and minimum/maximum temperature for Canada and the United States.

Thin plate smoothing spline models, covering Canada and the continental United States, were developed using ANUSPLIN for 30-year (1991-2020) monthly mean maximum and minimum temperature and precipitation. These models employed monthly weather station values from the North American dataset published by National Oceanic and Atmospheric Administration's (NOAA's) National Centers for Environmental Information (NCEI). Maximum temperature mean absolute errors (MAEs) ranged between 0.54 °C and 0.64 °C (approaching measurement error), while minimum temperature MAEs were slightly higher, varying from 0.87 °C to 1.0 °C. On average, thirty-year precipitation estimates were accurate to within approximately 10 % of total precipitation levels, ranging from 9.0 % in the summer to 12.2 % in the winter. Error rates were higher in Canada compared to estimates in the United States, consistent with a less dense station network in Canada relative to the United States. Precipitation estimates in Canada exhibited MAEs representing 14.7 % of mean total precipitation compared to 9.7 % in the United States. The datasets exhibited minimal bias overall; 0.004 °C for maximum temperature, 0.01 °C for minimum temperature, and 0.5 % for precipitation. Winter months showed a greater dry bias (0.8 % of total winter precipitation) compared to other seasons (-0.4 % of precipitation). These 30-year gridded datasets are available at ∼2 km resolution.

Mixed Valence {Ni2+Ni1+} Clusters as Models of Acetyl Coenzyme A Synthase Intermediates.

Acetyl coenzyme A synthase (ACS) catalyzes the formation and deconstruction of the key biological metabolite, acetyl coenzyme A (acetyl-CoA). The active site of ACS features a {NiNi} cluster bridged to a [Fe4S4]n+ cubane known as the A-cluster. The mechanism by which the A-cluster functions is debated, with few model complexes able to replicate the oxidation states, coordination features, or reactivity proposed in the catalytic cycle. In this work, we isolate the first bimetallic models of two hypothesized intermediates on the paramagnetic pathway of the ACS function. The heteroligated {Ni2+Ni1+} cluster, [K(12-crown-4)2][1], effectively replicates the coordination number and oxidation state of the proposed "Ared" state of the A-cluster. Addition of carbon monoxide to [1]- allows for isolation of a dinuclear {Ni2+Ni1+(CO)} complex, [K(12-crown-2)n][2] (n = 1-2), which bears similarity to the "ANiFeC" enzyme intermediate. Structural and electronic properties of each cluster are elucidated by X-ray diffraction, nuclear magnetic resonance, cyclic voltammetry, and UV/vis and electron paramagnetic resonance spectroscopies, which are supplemented by density functional theory (DFT) calculations. Calculations indicate that the pseudo-T-shaped geometry of the three-coordinate nickel in [1]- is more stable than the Y-conformation by 22 kcal mol-1, and that binding of CO to Ni1+ is barrierless and exergonic by 6 kcal mol-1. UV/vis absorption spectroscopy on [2]- in conjunction with time-dependent DFT calculations indicates that the square-planar nickel site is involved in electron transfer to the CO π*-orbital. Further, we demonstrate that [2]- promotes thioester synthesis in a reaction analogous to the production of acetyl coenzyme A by ACS.

Patterns of genetic diversity and gene flow associated with an aridity gradient in populations of common mole-rats, Cryptomys hottentotus hottentotus.

Genetic adaptation is the change of a population towards a phenotype that best fits the present ecological conditions in which it inhabits. As environmental conditions change, allele frequencies shift, resulting in different populations of the same species possessing genetic variation and divergent phenotypes. Cooperatively breeding common mole-rats (Cryptomys hottentotus hottentotus) inhabit environments along an aridity gradient in South Africa, which provides an opportunity for local genetic adaptations to occur. Using one mitochondrial gene (cytochrome b) and 3,540 SNP loci across the whole genome, we determined the phylogenetic relationship, population structure and genetic diversity of five populations of C. h. hottentotus located along an aridity gradient. Mitochondrial data identified population-specific clades that were less distinct in the two mesic populations, potentially indicating historical or recent gene flow, or the retention of ancestral haplotypes. Arid and semi-arid populations formed a distinct cluster from the non-arid populations. Genetic diversity and gene flow were higher in arid-dwelling individuals, suggesting greater connectivity and interactions between colonies in arid regions in comparison to mesic ones. Using an Aridity Index, we determined that isolation by environment, rather than isolation by geographical distance, best explains the genetic distance between the populations. Further analyses using target loci may determine if there are differing underlying genetic adaptations among populations of C. h. hottentotus. These analyses could help unravel population differences in response to environmental factors within a sub-species of bathyergid mole-rat and determine the adaptive capacity of this small non-migratory subterranean rodent species in response to aridification in the face of climate change.

Retrieval Analysis of Titanium Nitride Coatings for Orthopaedic Implants.

BACKGROUND: The first generation of titanium nitride (TiN) coatings for orthopaedic implants was clinically introduced in the 1990s because of their promising biocompatibility, wear resistance, and corrosion resistance. This study evaluated the in vivo performance of early TiN-coated knee and hip implants, focusing on the bearing surfaces and mechanisms of in vivo damage. METHODS: There were thirteen TiN-coated implants (5 knee and 8 hip) retrieved from 8 patients as part of a multi-institutional implant retrieval program. The average implantation time was 4.25 years for knees and 17.5 years for hips. Implant revisions occurred for various reasons, including PE wear, loosening, pain, infection, and instability. Components were examined using a semiquantitative scoring method, and surface roughness measurements were performed using white-light interferometry (WLI). Surface morphology, chemistry, and particle characterization were also assessed using scanning electron microscopy. RESULTS: For hips, mild corrosion was found on femoral head tapers, along with severe scratching on certain femoral heads. Knee implants exhibited low burnishing and scratching for both mechanisms. Roughness measurements (Sa) were 37.3 nm (Interquartile Range, IQR = 22.0 to 62.4) for hips and 85.3 nm (IQR = 66.3 to 110) for knees. The observed scratch depth in both hip and knee implants due to 3rd body particles ranged from 0.3 to 1.3 µm. The coating coverage remained intact in the majority of the implants, with two cases of small, localized cohesive chipping and substrate exposure. CONCLUSIONS: The results of this study confirm the potential in vivo durability of early TiN coatings and will be useful in benchmarking wear tests for modern TiN-coated orthopaedic implants.

Risk of Traumatic Brain Injury in Deployment and Nondeployment Settings Among Members of the Millennium Cohort Study.

OBJECTIVE: To describe and quantify the prevalence and risk of deployment and nondeployment service-related traumatic brain injury (TBI) among participants of the Millennium Cohort Study. SETTING: Survey data. PARTICIPANTS: 28 759 Millennium Cohort Study participants who were active duty, Reserves, or National Guard at the time of the survey. DESIGN: Cross-sectional secondary data analysis. MAIN MEASURES: Estimates of prevalence and rates of TBI were calculated. Multivariable Poisson regression estimated rate ratios of TBI overall and stratified by deployment and nondeployment settings. RESULTS: The rate of TBI over the 362 535 person-years (PY) was 2.95 p/100 PY. the nondeployment rate was 2.15 p/100 PY, with a significantly higher rate (11.38 p/100 PY) in deployment settings. Bullets/blasts were the most common TBI mechanisms in deployed settings, while sports/physical training and military training were common in nondeployed settings. CONCLUSIONS: The risk of TBI as well as its mechanism varies by deployment and nondeployment, suggesting that targeted prevention strategies are needed to reduce the risk for TBI among military personnel based on their deployment status.

Suppressing phagocyte activation by overexpressing the phosphatidylserine lipase ABHD12 preserves sarmopathic nerves.

Programmed axon degeneration (AxD) is a key feature of many neurodegenerative diseases. In healthy axons, the axon survival factor NMNAT2 inhibits SARM1, the central executioner of AxD, preventing it from initiating the rapid local NAD+ depletion and metabolic catastrophe that precipitates axon destruction. Because these components of the AxD pathway act within neurons, it was also assumed that the timetable of AxD was set strictly by a cell-intrinsic mechanism independent of neuron-extrinsic processes later activated by axon fragmentation. However, using a rare human disease model of neuropathy caused by hypomorphic NMNAT2 mutations and chronic SARM1 activation (sarmopathy), we demonstrated that neuronal SARM1 can initiate macrophage-mediated axon elimination long before stressed-but-viable axons would otherwise succumb to cell-intrinsic metabolic failure. Investigating potential SARM1-dependent signals that mediate macrophage recognition and/or engulfment of stressed-but-viable axons, we found that chronic SARM1 activation triggers axonal blebbing and dysregulation of phosphatidylserine (PS), a potent phagocyte immunomodulatory molecule. Neuronal expression of the phosphatidylserine lipase ABDH12 suppresses nerve macrophage activation, preserves motor axon integrity, and rescues motor function in this chronic sarmopathy model. We conclude that PS dysregulation is an early SARM1-dependent axonal stress signal, and that blockade of phagocytic recognition and engulfment of stressed-but-viable axons could be an attractive therapeutic target for management of neurological disorders involving SARM1 activation.

A Multicenter Training and Interrater Reliability Study of the BASED Score for Infantile Epileptic Spasms Syndrome.

PURPOSE: The best possible outcomes in infantile epileptic spasms syndrome require electroclinical remission; however, determining electrographic remission is not straightforward. Although the determination of hypsarrhythmia has inadequate interrater reliability (IRR), the Burden of AmplitudeS and Epileptiform Discharges (BASED) score has shown promise for the reliable interictal assessment of infantile epileptic spasms syndrome. Our aim was to develop a BASED training program and assess the IRR among learners. We hypothesized moderate or better IRR for the final BASED score and the presence or absence of epileptic encephalopathy (+/-EE). METHODS: Using a web-based application, 31 learners assessed 12 unmarked EEGs (length 1-6 hours) from children with infantile epileptic spasms syndrome. RESULTS: For all readers, the IRR was good for the final BASED score (intraclass correlation coefficient 0.86) and +/-EE (Marginal Multirater Kappa 0.63). For all readers, the IRR was fair to good for all individual BASED score elements. CONCLUSIONS: These findings support the use of our training program to quickly learn the BASED scoring method. The BASED score may be a valuable clinical and research tool. Given that the IRR for the determination of epileptic encephalopathy is not perfect, clinical acumen remains paramount. Additional experience with the BASED scoring technique among learners and advances in collaborative EEG evaluation platforms may improve IRR.

Does a Hip Muscle Activation Home Exercise Program Change Movement Patterns on the Forward Step-Down Test?

CONTEXT: Poor knee biomechanics contribute to knee joint injuries. Neuromuscular control over knee position is partially derived from the hip. It is unknown whether isolated activation training of the gluteal muscles improves lower-extremity frontal plane mechanics. This study examined if a home-based hip muscle activation program improves performance on the Forward Step-Down Test as well as increases surface electromyography (sEMG) activation of the gluteal muscles. DESIGN: The study utilized a single-group repeated-measures design. METHODS: Thirty-five participants (24 females, mean age = 23.17 [SD 1.36] years) completed an 8-week hip muscle activation program. The Forward Step-Down Test score and sEMG of gluteus maximus and medius were assessed preintervention and postintervention. RESULTS: Forward Step-Down Test scores improved significantly from preintervention (Mdn = 3.5) to postintervention (Mdn = 3.0, T = 109, P = .010, r = .31.), but this result did not meet clinical significance. sEMG analysis revealed a significant increase in mean gluteus maximus activation (P = .028, d = 1.19). No significant dose-response relationship existed between compliance and the Forward Step-Down Test scores or sEMG results. CONCLUSIONS: A home-based hip activation program increases gluteus maximus activation without clinically significant changes in frontal plane movement quality. Future studies may find clinical relevance by adding motor learning to the activation training program to improve functional muscle use.

Cancer linguistics and the politics of decolonizing health communication in Coastal Tanzania: Reflections from an anthropological investigation.

The role of language in maintaining asymmetries of power in global public health and biomedicine has become a central part of the broader movement to "decolonize Global Health." While considering how language engenders inequalities in Global Health, hinders interventions, and inhibits medical care, this article contends that colonially derived theorizations of what language is undergirding top-down health communication efforts labeled as "decolonial" can thwart efforts to make biomedical care and public health clearer in postcolonies. We do this through outlining predicaments found in a linguistic anthropological exploration of cancer terminology in Coastal Tanzania. In the small town of Bagamoyo, saratani-the official translation for cancer in Tanzania created by the government in the 1980s as part of a larger effort of decolonial state-building-is dominantly understood as a different or unequivocal disease than kansa-the English-adapted name. As the dissemination of the term saratani into a linguistic arena where colonially derived word kansa is dominantly registered as the biological disease "cancer," this linguistic disjuncture between saratani and kansa has not only created a plethora of problems for oncological care in Bagamoyo, but also illuminates the perils of creating more just health communication in an unequal global political economy. Through showing how binary conceptualizations of language as "colonial" and "local" can reproduce incommunicability-the rendering of racialized subjects as fundamentally unintelligible in hegemonic regimes-we contend that the afterlives of this past effort to decolonize medical language has important lessons for the present of "decolonizing Global Health." Moving beyond static conceptualizations of language, we argue for a fluid "translanguaging" perspective of medical linguistics that facilitates the dismantlement of incommunicability and the global ordering that creates it.

A Chemoproteomic Approach to Monitor Native Iron-Sulfur Cluster Binding.

Iron-sulfur (Fe-S) clusters are essential redox-active metallocofactors participating in electron transfer, radical chemistry, primary metabolism, and gene regulation. Successful trafficking and incorporation of Fe-S clusters into target proteins are critical to proper cellular function. While biophysical studies of isolated Fe-S proteins provide insight into the structure and function of these inorganic cofactors, few strategies currently exist to directly interrogate Fe-S cluster binding within a cellular environment. Here, we describe a chemoproteomic platform to report on Fe-S cluster incorporation and occupancy directly within a native proteome, enabling the characterization of Fe-S biogenesis pathways and the identification of undiscovered Fe-S proteins.

PP2A-B55 phosphatase counteracts Ki-67-dependent chromosome individualization during mitosis.

Cell cycle progression is regulated by the orderly balance between kinase and phosphatase activities. PP2A phosphatase holoenzymes containing the B55 family of regulatory B subunits function as major CDK1-counteracting phosphatases during mitotic exit in mammals. However, the identification of the specific mitotic roles of these PP2A-B55 complexes has been hindered by the existence of multiple B55 isoforms. Here, through the generation of loss-of-function genetic mouse models for the two ubiquitous B55 isoforms (B55α and B55δ), we report that PP2A-B55α and PP2A-B55δ complexes display overlapping roles in controlling the dynamics of proper chromosome individualization and clustering during mitosis. In the absence of PP2A-B55 activity, mitotic cells display increased chromosome individualization in the presence of enhanced phosphorylation and perichromosomal loading of Ki-67. These data provide experimental evidence for a regulatory mechanism by which the balance between kinase and PP2A-B55 phosphatase activity controls the Ki-67-mediated spatial organization of the mass of chromosomes during mitosis.

Comparison of Infinium MethylationEPIC v2.0 to v1.0 for human population epigenetics: considerations for addressing EPIC version differences in DNA methylation-based tools.

Background: The recently launched DNA methylation profiling platform, Illumina MethylationEPIC BeadChip Infinium microarray v2.0 (EPICv2), is highly correlated with measurements obtained from its predecessor MethylationEPIC BeadChip Infinium microarray v1.0 (EPICv1). However, the concordance between the two versions in the context of DNA methylation-based tools, including cell type deconvolution algorithms, epigenetic clocks, and inflammation and lifestyle biomarkers has not yet been investigated. Findings: We profiled DNA methylation on both EPIC versions using matched venous blood samples from individuals spanning early to late adulthood across three cohorts. On combining the DNA methylomes of the cohorts, we observed that samples primarily clustered by the EPIC version they were measured on. Within each cohort, when we calculated cell type proportions, epigenetic age acceleration (EAA), rate of aging estimates, and biomarker scores for the matched samples on each version, we noted significant differences between EPICv1 and EPICv2 in the majority of these estimates. These differences were not significant, however, when estimates were adjusted for EPIC version or when EAAs were calculated separately for each EPIC version. Conclusions: Our findings indicate that EPIC version differences predominantly explain DNA methylation variation and influence estimates of DNA methylation-based tools, and therefore we recommend caution when combining cohorts run on different versions. We demonstrate the importance of calculating DNA methylation-based estimates separately for each EPIC version or accounting for EPIC version either as a covariate in statistical models or by using version correction algorithms.

Solving Advanced Task-Specific Problems in Measurement Sciences with Generative AI.

The Generative Pre-Trained Transformer known as ChatGPT-4 has undergone extensive pretraining on a diverse data set, enabling it to generate coherent and contextually relevant text based on the input it receives. This capability allows it to perform tasks from answering questions and has attracted significant interest in material sciences, synthetic chemistry, and drug discovery. In this work, we posed four advanced task-specific problems to ChatGPT, which were recently published in leading journals for topics in analytical chemistry, spectroscopy, bioimage super-resolution, and electrochemistry. ChatGPT-4 successfully implemented the four ideas after assigning the "persona" to the AI and posing targeted questions. We show two cases where "unguided" ChatGPT could complete the assignments with minimal human direction. The construction of a microwave spectrum from a free induction curve and super-resolution of bioimages was accomplished using this approach. Two other specific tasks, correcting a complex baseline with morphological operations of set theory and estimating the diffusion current, required additional input, e.g., equations and specific directions from the user. In each case, the MATLAB code was eventually generated by ChatGPT-4 even when the original authors did not provide any code themselves. We show that a validation test must be implemented to detect and correct mistakes made by ChatGPT-4, followed by feedback correction. These approaches will pave the way for open and transparent science and eliminate the black boxes in measurement science when it comes to advanced data processing.

Motor vehicle collision (MVC) emergency department (ED) visits and hospitalisations in Ontario during the COVID-19 pandemic.

BACKGROUND: The COVID-19 pandemic policy response dramatically changed local transportation patterns. This project investigated the impact of COVID-19 policies on motor vehicle collision (MVC)-related emergency department (ED) visits and hospitalisations in Ontario. METHODS: Data were collected on MVC-related ED visits and hospitalisations in Ontario between March 2016 and December 2022. Using an interrupted time series design, negative binomial regression models were fitted to the pre-pandemic data, including monthly indicator variables for seasonality and accounting for autocorrelation. Extrapolations simulated expected outcome trajectories during the pandemic, which were compared with actual observed outcome counts using the overall per cent change and mean monthly difference. Data were modelled separately for vehicle occupants, pedestrians and cyclists (MVC and non-MVC injuries). RESULTS: There was a 31.5% decrease in observed ED visits (95% CI -35.4 to -27.3) and a 6.0% decrease in hospitalisations (95% CI -13.2 to 1.6) among vehicle occupants, relative to expected counts during the pandemic. Results were similar for pedestrians. Among cyclist MVCs, there was an increase in ED visits (12.8%, 95% CI -8.2 to 39.4) and hospitalisations (46.0%, 95% CI 11.6 to 93.6). Among non-MVC cyclists, there was also an increase in ED visits (47.0%, 95% CI 12.5 to 86.8) and hospitalisations (50.1%, 95% CI 8.2 to 101.2). CONCLUSIONS: We observed fewer vehicle occupant and pedestrian collision injuries than expected during the pandemic. By contrast, we observed more cycling injuries than expected, especially in cycling injuries not involving motor vehicles. These observations may be attributable to changes in transportation patterns during the pandemic and increased uptake of recreational cycling.

Considering the Impact of High School Sexual Education on Past Sexual Victimization and Rape Myth Acceptance in a College Sample.

Sexual victimization is a serious public health crisis affecting college students, with high rates reported among both women and men. Sexual consent education is crucial as it defines sexual assault and is linked to reduced risk of victimization. Rape myths and stereotyped beliefs shifting blame to survivors are established risk factors for sexual violence. Comprehensive sexual education can mitigate these attitudes, fostering a supportive environment for survivors. However, most high school students in the United States receive abstinence-based or abstinence-plus education, which uses unstandardized protocols and often lacks information about sexual consent. The following study explores the influence of high school sexual education on past sexual victimization and rape myth acceptance in college students. Six hundred sixty-four undergraduate students participated in an online survey through a university participant pool. Results show that those who received comprehensive sexual education were more likely to understand sexual consent and were less likely to endorse past sexual victimization. In contrast, students without comprehensive sexual education reported lower satisfaction with their sexual education and greater acceptance of rape myths. Despite limitations in the study's sample and reliance on self-reporting, this research highlights the importance of implementing comprehensive sexual education, including consent education, in high schools. Policymakers and educators must recognize the influence of comprehensive sexual education in promoting healthy relationships and combating sexual assault. As a significant public health concern, incorporating standardized sexual consent education into high school curricula can equip students with the knowledge and skills to make informed decisions about their sexual health and relationships. Future research should explore diverse populations and the mediating role of related factors that may further influence these relationships. These efforts will contribute to fostering a safer environment within educational institutions and combating sexual assault.

A real-time prognostic model for venous thromboembolic events among hospitalized adults.

Background: Hospital-acquired venous thromboembolism (HA-VTE) is a leading cause of morbidity and mortality among hospitalized adults. Guidelines recommend use of a risk-prediction model to estimate HA-VTE risk for individual patients. Extant models do not perform well for broad patient populations and are not conducive to automation in clinical practice. Objectives: To develop an automated, real-time prognostic model for venous thromboembolism during hospitalization among all adult inpatients using readily available data from the electronic health record. Methods: The derivation cohort included inpatient hospitalizations ("encounters") for patients ≥16 years old at Vanderbilt University Medical Center between 2018 and 2020 (n = 132,330). HA-VTE events were identified using International Classification of Diseases, 10th Revision, codes. The prognostic model was developed using least absolute shrinkage and selection operator regression. Temporal external validation was performed in a validation cohort of encounters between 2021 and 2022 (n = 62,546). Prediction performance was assessed by discrimination accuracy (C statistic) and calibration (integrated calibration index). Results: There were 1187 HA-VTEs in the derivation cohort (9.0 per 1000 encounters) and 864 in the validation cohort (13.8 per 1000 encounters). The prognostic model included 25 variables, with placement of a central line among the most important predictors. Prediction performance of the model was excellent (C statistic, 0.891; 95% CI, 0.882-0.900; integrated calibration index, 0.001). The model performed similarly well across subgroups of patients defined by age, sex, race, and type of admission. Conclusion: This fully automated prognostic model uses readily available data from the electronic health record, exhibits superior prediction performance compared with existing models, and generates granular risk stratification in the form of a predicted probability of HA-VTE for each patient.