Evaluating the predictive ability of natural language processing in identifying tertiary/quaternary cases in prioritization workflows for interhospital transfer.

Objectives: Tertiary and quaternary (TQ) care refers to complex cases requiring highly specialized health services. Our study aimed to compare the ability of a natural language processing (NLP) model to an existing human workflow in predictively identifying TQ cases for transfer requests to an academic health center. Materials and methods: Data on interhospital transfers were queried from the electronic health record for the 6-month period from July 1, 2020 to December 31, 2020. The NLP model was allowed to generate predictions on the same cases as the human predictive workflow during the study period. These predictions were then retrospectively compared to the true TQ outcomes. Results: There were 1895 transfer cases labeled by both the human predictive workflow and the NLP model, all of which had retrospective confirmation of the true TQ label. The NLP model receiver operating characteristic curve had an area under the curve of 0.91. Using a model probability threshold of ≥0.3 to be considered TQ positive, accuracy was 81.5% for the NLP model versus 80.3% for the human predictions (P = .198) while sensitivity was 83.6% versus 67.7% (P<.001). Discussion: The NLP model was as accurate as the human workflow but significantly more sensitive. This translated to 15.9% more TQ cases identified by the NLP model. Conclusion: Integrating an NLP model into existing workflows as automated decision support could translate to more TQ cases identified at the onset of the transfer process.

E-scooter related injuries: Using natural language processing to rapidly search 36 million medical notes.

BACKGROUND: Shareable e-scooters have become popular, but injuries to riders and bystanders have not been well characterized. The goal of this study was to describe e-scooter injuries and estimate the rate of injury per e-scooter trip. METHODS AND FINDINGS: Retrospective review of patients presenting to 180 clinics and 2 hospitals in greater Los Angeles between January 1, 2014 and May 14, 2020. Injuries were identified using a natural language processing (NLP) algorithm not previously used to identify injuries, tallied, and described along with required healthcare resources. We combine these tallies with municipal data on scooter use to report a monthly utilization-corrected rate of e-scooter injuries. We searched 36 million clinical notes. Our NLP algorithm correctly classified 92% of notes in the testing set compared with the gold standard of investigator review. In total, we identified 1,354 people injured by e-scooters; 30% were seen in more than one clinical setting (e.g., emergency department and a follow-up outpatient visit), 29% required advanced imaging, 6% required inpatient admission, and 2 died. We estimate 115 injuries per million e-scooter trips were treated in our health system. CONCLUSIONS: Our observed e-scooter injury rate is likely an underestimate, but is similar to that previously reported for motorcycles. However, the comparative severity of injuries is unknown. Our methodology may prove useful to study other clinical conditions not identifiable by existing diagnostic systems.

Artificial Intelligence-based Analytics for Diagnosis of Small Bowel Enteropathies and Black Box Feature Detection.

OBJECTIVES: Striking histopathological overlap between distinct but related conditions poses a disease diagnostic challenge. There is a major clinical need to develop computational methods enabling clinicians to translate heterogeneous biomedical images into accurate and quantitative diagnostics. This need is particularly salient with small bowel enteropathies; environmental enteropathy (EE) and celiac disease (CD). We built upon our preliminary analysis by developing an artificial intelligence (AI)-based image analysis platform utilizing deep learning convolutional neural networks (CNNs) for these enteropathies. METHODS: Data for the secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using CNNs including one with multizoom architecture. Gradient-weighted class activation mappings (Grad-CAMs) were used to visualize the models' decision-making process for classifying each disease. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAMs to confirm structural preservation and biomedical relevance, respectively. RESULTS: Four hundred and sixty-one high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0-121.5) months with a roughly equal sex distribution; 77 males (51.3%). ResNet50 and shallow CNN demonstrated 98% and 96% case-detection accuracy, respectively, which increased to 98.3% with an ensemble. Grad-CAMs demonstrated models' ability to learn different microscopic morphological features for EE, CD, and controls. CONCLUSIONS: Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features and emulating human pathologist decision-making process. Grad-CAMs illuminated the otherwise "black box" of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.

HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach.

Image classification is central to the big data revolution in medicine. Improved information processing methods for diagnosis and classification of digital medical images have shown to be successful via deep learning approaches. As this field is explored, there are limitations to the performance of traditional supervised classifiers. This paper outlines an approach that is different from the current medical image classification tasks that view the issue as multi-class classification. We performed a hierarchical classification using our Hierarchical Medical Image classification (HMIC) approach. HMIC uses stacks of deep learning models to give particular comprehension at each level of the clinical picture hierarchy. For testing our performance, we use biopsy of the small bowel images that contain three categories in the parent level (Celiac Disease, Environmental Enteropathy, and histologically normal controls). For the child level, Celiac Disease Severity is classified into 4 classes (I, IIIa, IIIb, and IIIC).

Diagnosis of Celiac Disease and Environmental Enteropathy on Biopsy Images Using Color Balancing on Convolutional Neural Networks.

Celiac Disease (CD) and Environmental Enteropathy (EE) are common causes of malnutrition and adversely impact normal childhood development. CD is an autoimmune disorder that is prevalent worldwide and is caused by an increased sensitivity to gluten. Gluten exposure destructs the small intestinal epithelial barrier, resulting in nutrient mal-absorption and childhood under-nutrition. EE also results in barrier dysfunction but is thought to be caused by an increased vulnerability to infections. EE has been implicated as the predominant cause of under-nutrition, oral vaccine failure, and impaired cognitive development in low-and-middle-income countries. Both conditions require a tissue biopsy for diagnosis, and a major challenge of interpreting clinical biopsy images to differentiate between these gastrointestinal diseases is striking histopathologic overlap between them. In the current study, we propose a convolutional neural network (CNN) to classify duodenal biopsy images from subjects with CD, EE, and healthy controls. We evaluated the performance of our proposed model using a large cohort containing 1000 biopsy images. Our evaluations show that the proposed model achieves an area under ROC of 0.99, 1.00, and 0.97 for CD, EE, and healthy controls, respectively. These results demonstrate the discriminative power of the proposed model in duodenal biopsies classification.

CeliacNet: Celiac Disease Severity Diagnosis on Duodenal Histopathological Images Using Deep Residual Networks.

Celiac Disease (CD) is a chronic autoimmune disease that affects the small intestine in genetically predisposed children and adults. Gluten exposure triggers an inflammatory cascade which leads to compromised intestinal barrier function. If this enteropathy is unrecognized, this can lead to anemia, decreased bone density, and, in longstanding cases, intestinal cancer. The prevalence of the disorder is 1% in the United States. An intestinal (duodenal) biopsy is considered the "gold standard" for diagnosis. The mild CD might go unnoticed due to non-specific clinical symptoms or mild histologic features. In our current work, we trained a model based on deep residual networks to diagnose CD severity using a histological scoring system called the modified Marsh score. The proposed model was evaluated using an independent set of 120 whole slide images from 15 CD patients and achieved an AUC greater than 0.96 in all classes. These results demonstrate the diagnostic power of the proposed model for CD severity classification using histological images.

Identification of Imminent Suicide Risk Among Young Adults using Text Messages.

Suicide is the second leading cause of death among young adults but the challenges of preventing suicide are significant because the signs often seem invisible. Research has shown that clinicians are not able to reliably predict when someone is at greatest risk. In this paper, we describe the design, collection, and analysis of text messages from individuals with a history of suicidal thoughts and behaviors to build a model to identify periods of suicidality (i.e., suicidal ideation and non-fatal suicide attempts). By reconstructing the timeline of recent suicidal behaviors through a retrospective clinical interview, this study utilizes a prospective research design to understand if text communications can predict periods of suicidality versus depression. Identifying subtle clues in communication indicating when someone is at heightened risk of a suicide attempt may allow for more effective prevention of suicide.

RNA2DNAlign: nucleotide resolution allele asymmetries through quantitative assessment of RNA and DNA paired sequencing data.

We introduce RNA2DNAlign, a computational framework for quantitative assessment of allele counts across paired RNA and DNA sequencing datasets. RNA2DNAlign is based on quantitation of the relative abundance of variant and reference read counts, followed by binomial tests for genotype and allelic status at SNV positions between compatible sequences. RNA2DNAlign detects positions with differential allele distribution, suggesting asymmetries due to regulatory/structural events. Based on the type of asymmetry, RNA2DNAlign outlines positions likely to be implicated in RNA editing, allele-specific expression or loss, somatic mutagenesis or loss-of-heterozygosity (the first three also in a tumor-specific setting). We applied RNA2DNAlign on 360 matching normal and tumor exomes and transcriptomes from 90 breast cancer patients from TCGA. Under high-confidence settings, RNA2DNAlign identified 2038 distinct SNV sites associated with one of the aforementioned asymetries, the majority of which have not been linked to functionality before. The performance assessment shows very high specificity and sensitivity, due to the corroboration of signals across multiple matching datasets. RNA2DNAlign is freely available from http://github.com/HorvathLab/NGS as a self-contained binary package for 64-bit Linux systems.

SNPlice: variants that modulate Intron retention from RNA-sequencing data.

RATIONALE: The growing recognition of the importance of splicing, together with rapidly accumulating RNA-sequencing data, demand robust high-throughput approaches, which efficiently analyze experimentally derived whole-transcriptome splice profiles. RESULTS: We have developed a computational approach, called SNPlice, for identifying cis-acting, splice-modulating variants from RNA-seq datasets. SNPlice mines RNA-seq datasets to find reads that span single-nucleotide variant (SNV) loci and nearby splice junctions, assessing the co-occurrence of variants and molecules that remain unspliced at nearby exon-intron boundaries. Hence, SNPlice highlights variants preferentially occurring on intron-containing molecules, possibly resulting from altered splicing. To illustrate co-occurrence of variant nucleotide and exon-intron boundary, allele-specific sequencing was used. SNPlice results are generally consistent with splice-prediction tools, but also indicate splice-modulating elements missed by other algorithms. SNPlice can be applied to identify variants that correlate with unexpected splicing events, and to measure the splice-modulating potential of canonical splice-site SNVs. AVAILABILITY AND IMPLEMENTATION: SNPlice is freely available for download from https://code.google.com/p/snplice/ as a self-contained binary package for 64-bit Linux computers and as python source-code. CONTACT: pmudvari@gwu.edu or horvatha@gwu.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Extraction of Molecular Features through Exome to Transcriptome Alignment.

Integrative Next Generation Sequencing (NGS) DNA and RNA analyses have very recently become feasible, and the published to date studies have discovered critical disease implicated pathways, and diagnostic and therapeutic targets. A growing number of exomes, genomes and transcriptomes from the same individual are quickly accumulating, providing unique venues for mechanistic and regulatory features analysis, and, at the same time, requiring new exploration strategies. In this study, we have integrated variation and expression information of four NGS datasets from the same individual: normal and tumor breast exomes and transcriptomes. Focusing on SNPcentered variant allelic prevalence, we illustrate analytical algorithms that can be applied to extract or validate potential regulatory elements, such as expression or growth advantage, imprinting, loss of heterozygosity (LOH), somatic changes, and RNA editing. In addition, we point to some critical elements that might bias the output and recommend alternative measures to maximize the confidence of findings. The need for such strategies is especially recognized within the growing appreciation of the concept of systems biology: integrative exploration of genome and transcriptome features reveal mechanistic and regulatory insights that reach far beyond linear addition of the individual datasets.