Design and Evaluation of a Longitudinal Method to Measure Physician Burnout in the Clinical Workflow

Burnout, a condition characterized by emotional exhaustion, listlessness, and an inability to cope, is demonstrably more prevalent among healthcare providers than other occupations.  Burnout is fundamentally a longitudinal problem, but traditional instruments for measurement such as the Maslach Burnout Inventory (MBI) and the Professional Fulfillment Index (PFI) are time-consuming, expensive, and complex to administer, making it prohibitive to collect repeated measures to capture burnout feedback with weekly, monthly or even yearly frequency. A Single-Item Burnout Measure (SIBM) has been previously validated to highly correlate to the emotional exhaustion dimension of the MBI, and thus can serve as a proxy measure…

Analysis and Dissemination of School-based Immunization Data to Improve Public Health Outcomes in Missouri

In Missouri, immunization is required for both public and private school students against common vaccine-preventable diseases (VPDs) including polio, pertussis, varicella, measles, mumps, and rubella; however, parents may forego vaccination for their child by claiming medical or religious exemptions. Like many states across the US, Missouri is experiencing increasing vaccine exemption rates. However, health officials lack adequate and reliable means of accessing local vaccination data to inform health priorities and interventions. A partnership between the University of Missouri and the Missouri Department of Health and Human Services (DHSS) was formed to 1) better understand temporal and geographic variation in vaccine…

Regulation of gene expression by DNA methylation with cytotoxic T lymphocytes evaluation in consensus molecular subtypes of colorectal cancer

Background: Low cytotoxic T lymphocyte (CTLs) infiltration in colorectal cancer (CRC) tumors is a challenge to treatment with immune checkpoint inhibitors. Consensus molecular subtypes (CMS) classify patients based on tumor attributes, and CMS1 patients include the majority of patients with high CTL infiltration and “inflamed” tumors. Epigenetic modification plays a critical role in gene expression and therapy resistance. Therefore, in this study we compared DNA methylation, gene expression, and CTL infiltration of CMS1 patients to other CMS groups to determine targets for improving immunotherapy in CRC. Furthermore, we used transcriptome of 91,103 unsorted scRNAseq to validate bulk RNA finding. Results…

Leveraging Unsupervised Machine Learning To Find Trends In The Textual Warnings Generated Using Multi-Modality Time Series Sensor Data

With technology and the internet of things (IoT), smart health care is no longer a dream. The devices that wouldn’t usually be generally expected to have an internet connection can communicate with the network independent of human action, and this is referred to as the internet of things. These devices, in our case, are the sensors placed in the elderly assisted living facility Tiger Place. Sensors include the ballistocardiogram (bed sensor) and motion sensors placed in the living room, bathroom, kitchen, etc. These sensors help in measuring nine major features, which defines the per-day activities of each elderly resident in the…

Information Extraction Framework for Facilitating the Assessment of the Quality of Radiology Interpretations

Assessing the quality of imaging interpretations requires that the results of radiological interpretations be compared with those of subsequent surgical-pathology results, when available. The manual process is inherently slow, tedious and expensive, and unless systematic errors occur in the interpretations, discrepancies are unlikely to be detected. Classical computational methods using Natural Language Processing entail using a corpus of annotated documents for model development and evaluation. However, developing such a corpus is also very expensive and time consuming, and the output is usually not portable between medical institutions. To alleviate these issues we are proposing a statistical learning method for textual…

Abnormal liver function and adverse health outcomes in COVID-19: A multicenter, retrospective analysis of 14,872 patients from the Cerner Real-World DataTM de-identified COVID-19 cohort

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has been associated with liver impairment and abnormalities in liver function tests.  However, associations between hepatic impairment and patient health outcomes have not been well-studied in large cohorts.  In this US-based, multicenter retrospective cohort study, we analyze the impact of abnormalities in liver function tests at admission on mortality and adverse health outcomes in patients with laboratory-confirmed COVID-19 infection.  Propensity score analysis and a full matching algorithm were used to minimize dissimilarity in covariates thought to impact outcomes of interest and to isolate the effect of liver abnormalities on patient…

Methods for Measuring Geodiversity in Large Overhead Imagery Datasets

This research introduces some of the first geo-computational methods to address a key gap in the artificial intelligence (AI) and big data literature as it relates to the geosciences and remote sensing: the lack of understanding of the global feature representativeness of labels in large remotely-sensed imagery (RSI) datasets. Issues of data fairness, heterogeneity and equitability – often related directly to geographic and demographic under-sampling – have recently come to the fore in multidisciplinary discussions of the ethics of AI. The risks of perpetuating data and models with unknown biases are particularly heightened in the air-and space-born RSI domain, given…

The Genescape Allele Catalog Development for Precise Identification of Causative SNPs

Next-generation sequencing (NGS) has become more popular in the modern-day. Large amounts of next-generation resequencing data have been generated and are available online for various organisms including soybeans. However, current genome-wide association study (GWAS) prediction tools simply identify the most significant SNP based on Manhattan plots and still have some limitations in pinpointing the exact causative SNPs using the SNP array or NGS datasets. Therefore, we are developing a Genescape catalog, a new bioinformatics approach to integrate all potential alleles for all genes in soybean genome using the genomic variations and phenotypic information from a large subset of cultivated and…

Evaluating the effectiveness of transfer-learning with DeepVariant

Genomic data has become ubiquitous for bioinformaticians; however, successfully inferring biological meaning depends upon the sensitive prediction of differences between genomes. The most popular method to infer short sequence variants is the Genome Analysis Toolkit (GATK). While GATK provides rigorous guidelines, the methods require knowledge-intensive refinement as software and sequencing technologies advance. A recent advancement from Google Health Genomics called DeepVariant uses a deep neural network to call variants in human whole-genome sequence (WGS) data. In comparison to GATKv4, after training, the human genome DeepVariant model achieved a significant drop in Mendelian Inheritance Errors (MIE). MIE variants are not passed…