Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models.

OBJECTIVE: The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. MATERIALS AND METHODS: Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. RESULTS: Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. DISCUSSION: The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. CONCLUSIONS: Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations.

Development and external validation of multimodal postoperative acute kidney injury risk machine learning models.

Objectives: To develop and externally validate machine learning models using structured and unstructured electronic health record data to predict postoperative acute kidney injury (AKI) across inpatient settings. Materials and Methods: Data for adult postoperative admissions to the Loyola University Medical Center (2009-2017) were used for model development and admissions to the University of Wisconsin-Madison (2009-2020) were used for validation. Structured features included demographics, vital signs, laboratory results, and nurse-documented scores. Unstructured text from clinical notes were converted into concept unique identifiers (CUIs) using the clinical Text Analysis and Knowledge Extraction System. The primary outcome was the development of Kidney Disease Improvement Global Outcomes stage 2 AKI within 7 days after leaving the operating room. We derived unimodal extreme gradient boosting machines (XGBoost) and elastic net logistic regression (GLMNET) models using structured-only data and multimodal models combining structured data with CUI features. Model comparison was performed using the receiver operating characteristic curve (AUROC), with Delong's test for statistical differences. Results: The study cohort included 138 389 adult patient admissions (mean [SD] age 58 [16] years; 11 506 [8%] African-American; and 70 826 [51%] female) across the 2 sites. Of those, 2959 (2.1%) developed stage 2 AKI or higher. Across all data types, XGBoost outperformed GLMNET (mean AUROC 0.81 [95% confidence interval (CI), 0.80-0.82] vs 0.78 [95% CI, 0.77-0.79]). The multimodal XGBoost model incorporating CUIs parameterized as term frequency-inverse document frequency (TF-IDF) showed the highest discrimination performance (AUROC 0.82 [95% CI, 0.81-0.83]) over unimodal models (AUROC 0.79 [95% CI, 0.78-0.80]). Discussion: A multimodality approach with structured data and TF-IDF weighting of CUIs increased model performance over structured data-only models. Conclusion: These findings highlight the predictive power of CUIs when merged with structured data for clinical prediction models, which may improve the detection of postoperative AKI.

DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing.

The meaningful use of electronic health records (EHR) continues to progress in the digital era with clinical decision support systems augmented by artificial intelligence. A priority in improving provider experience is to overcome information overload and reduce the cognitive burden so fewer medical errors and cognitive biases are introduced during patient care. One major type of medical error is diagnostic error due to systematic or predictable errors in judgement that rely on heuristics. The potential for clinical natural language processing (cNLP) to model diagnostic reasoning in humans with forward reasoning from data to diagnosis and potentially reduce cognitive burden and medical error has not been investigated. Existing tasks to advance the science in cNLP have largely focused on information extraction and named entity recognition through classification tasks. We introduce a novel suite of tasks coined as Diagnostic Reasoning Benchmarks, Dr.Bench, as a new benchmark for developing and evaluating cNLP models with clinical diagnostic reasoning ability. The suite includes six tasks from ten publicly available datasets addressing clinical text understanding, medical knowledge reasoning, and diagnosis generation. DR.BENCH is the first clinical suite of tasks designed to be a natural language generation framework to evaluate pre-trained language models for diagnostic reasoning. The goal of DR. BENCH is to advance the science in cNLP to support downstream applications in computerized diagnostic decision support and improve the efficiency and accuracy of healthcare providers during patient care. We fine-tune and evaluate the state-of-the-art generative models on DR.BENCH. Experiments show that with domain adaptation pre-training on medical knowledge, the model demonstrated opportunities for improvement when evaluated in DR. BENCH. We share DR. BENCH as a publicly available GitLab repository with a systematic approach to load and evaluate models for the cNLP community. We also discuss the carbon footprint produced during the experiments and encourage future work on DR.BENCH to report the carbon footprint.

Identifying infected patients using semi-supervised and transfer learning.

OBJECTIVES: Early identification of infection improves outcomes, but developing models for early identification requires determining infection status with manual chart review, limiting sample size. Therefore, we aimed to compare semi-supervised and transfer learning algorithms with algorithms based solely on manual chart review for identifying infection in hospitalized patients. MATERIALS AND METHODS: This multicenter retrospective study of admissions to 6 hospitals included "gold-standard" labels of infection from manual chart review and "silver-standard" labels from nonchart-reviewed patients using the Sepsis-3 infection criteria based on antibiotic and culture orders. "Gold-standard" labeled admissions were randomly allocated to training (70%) and testing (30%) datasets. Using patient characteristics, vital signs, and laboratory data from the first 24 hours of admission, we derived deep learning and non-deep learning models using transfer learning and semi-supervised methods. Performance was compared in the gold-standard test set using discrimination and calibration metrics. RESULTS: The study comprised 432 965 admissions, of which 2724 underwent chart review. In the test set, deep learning and non-deep learning approaches had similar discrimination (area under the receiver operating characteristic curve of 0.82). Semi-supervised and transfer learning approaches did not improve discrimination over models fit using only silver- or gold-standard data. Transfer learning had the best calibration (unreliability index P value: .997, Brier score: 0.173), followed by self-learning gradient boosted machine (P value: .67, Brier score: 0.170). DISCUSSION: Deep learning and non-deep learning models performed similarly for identifying infection, as did models developed using Sepsis-3 and manual chart review labels. CONCLUSION: In a multicenter study of almost 3000 chart-reviewed patients, semi-supervised and transfer learning models showed similar performance for model discrimination as baseline XGBoost, while transfer learning improved calibration.

Correction: Identifying COVID-19 Outbreaks From Contact-Tracing Interview Forms for Public Health Departments: Development of a Natural Language Processing Pipeline.

[This corrects the article DOI: 10.2196/36119.].

Identifying COVID-19 Outbreaks From Contact-Tracing Interview Forms for Public Health Departments: Development of a Natural Language Processing Pipeline.

BACKGROUND: In Wisconsin, COVID-19 case interview forms contain free-text fields that need to be mined to identify potential outbreaks for targeted policy making. We developed an automated pipeline to ingest the free text into a pretrained neural language model to identify businesses and facilities as outbreaks. OBJECTIVE: We aimed to examine the precision and recall of our natural language processing pipeline against existing outbreaks and potentially new clusters. METHODS: Data on cases of COVID-19 were extracted from the Wisconsin Electronic Disease Surveillance System (WEDSS) for Dane County between July 1, 2020, and June 30, 2021. Features from the case interview forms were fed into a Bidirectional Encoder Representations from Transformers (BERT) model that was fine-tuned for named entity recognition (NER). We also developed a novel location-mapping tool to provide addresses for relevant NER. Precision and recall were measured against manually verified outbreaks and valid addresses in WEDSS. RESULTS: There were 46,798 cases of COVID-19, with 4,183,273 total BERT tokens and 15,051 unique tokens. The recall and precision of the NER tool were 0.67 (95% CI 0.66-0.68) and 0.55 (95% CI 0.54-0.57), respectively. For the location-mapping tool, the recall and precision were 0.93 (95% CI 0.92-0.95) and 0.93 (95% CI 0.92-0.95), respectively. Across monthly intervals, the NER tool identified more potential clusters than were verified in WEDSS. CONCLUSIONS: We developed a novel pipeline of tools that identified existing outbreaks and novel clusters with associated addresses. Our pipeline ingests data from a statewide database and may be deployed to assist local health departments for targeted interventions.

MHC genotyping from rhesus macaque exome sequences.

Indian rhesus macaque major histocompatibility complex (MHC) variation can influence the outcomes of transplantation and infectious disease studies. Frequently, rhesus macaques are MHC genotyped to identify variants that could account for unexpected results. Since the MHC is only one region in the genome where variation could impact experimental outcomes, strategies for simultaneously profiling variation in the macaque MHC and the remainder of the protein coding genome would be useful. Here we determine MHC class I and class II genotypes using target-capture probes enriched for MHC sequences, a method we term macaque exome sequence (MES) genotyping. For a cohort of 27 Indian rhesus macaques, we describe two methods for obtaining MHC genotypes from MES data and demonstrate that the MHC class I and class II genotyping results obtained with these methods are 98.1% and 98.7% concordant, respectively, with expected MHC genotypes. In contrast, conventional MHC genotyping results obtained by deep sequencing of short multiplex PCR amplicons were only 92.6% concordant with expectations for this cohort.

The Functional and Molecular Effects of Doxycycline Treatment on Borrelia burgdorferi Phenotype.

Recent studies have shown that Borrelia burgdorferi can form antibiotic-tolerant persisters in the presence of microbiostatic drugs such as doxycycline. Precisely how this occurs is yet unknown. Our goal was to examine gene transcription by B. burgdorferi following doxycycline treatment in an effort to identify both persister-associated genes and possible targets for antimicrobial intervention. To do so, we performed next-generation RNA sequencing on doxycycline-treated spirochetes and treated spirochetes following regrowth, comparing them to untreated B. burgdorferi. A number of genes were perturbed and most of those which were statistically significant were down-regulated in the treated versus the untreated or treated/re-grown. Genes upregulated in the treated B. burgdorferi included a number of Erp genes and rplU, a 50S ribosomal protein. Among those genes associated with post-treatment regrowth were bba74 (Oms28), bba03, several peptide ABC transporters, ospA, ospB, ospC, dbpA and bba62. Studies are underway to determine if these same genes are perturbed in B. burgdorferi treated with doxycycline in a host environment.

Intramuscular vaccination of guinea pigs with the live-attenuated human herpes simplex vaccine VC2 stimulates a transcriptional profile of vaginal Th17 and regulatory Tr1 responses.

Herpes simplex virus is a common causative agent of oral and genital diseases. Novel vaccines and therapeutics are needed to combat herpes infections especially after the failure of subunit vaccines in human clinical trials. We have shown that the live-attenuated HSV-1 VC2 vaccine strain is unable to establish latency in vaccinated animals and produces a robust immune response capable of completely protecting mice against lethal vaginal HSV-1 or HSV-2 infections. The guinea pig represents the best small animal model of genital HSV-2 disease. Reported here, twenty-one female Hartley guinea pigs received intramuscular injection with either the VC2 vaccine, or equal volume of conditioned tissue culture media. Animals received 2 booster vaccinations at 21 day intervals following the initial vaccination. After vaccination, animals were challenged with the highly virulent HSV-2 (G) strain. Histologically, VC2 vaccinated animals had little to no apparent inflammation/disease following challenge. Unvaccinated animals developed moderate to severe erosive and ulcerative vaginitis. Quantitative reverse-transcriptase PCR analysis in VC2 vaccinated and challenged animals identified transcriptional signatures of Th17 and regulatory Tr1 cells associated with the inflammatory response primed by VC2 vaccination. Treatment of cultured human vaginal epithelial cells (VK2 cells) with a combination of IL-17A and IL-22 resulted in the significant induction of beta-defensin 3 expression. Further, treatment of VK2 cells with IL-17A, IL-22, IL-36 or beta-defensin 3 resulted in diminished HSV-2 replication. Overall, these results suggest that intramuscular vaccination with the live-attenuated vaccine VC2 primes a mucosal immune response predisposing the adaptive expression of transcripts associated with a Th17 response to challenge and these responses contribute to antiviral immunity.

Differential growth of Mycobacterium leprae strains (SNP genotypes) in armadillos.

Leprosy (Hansen's Disease) has occurred throughout human history, and persists today at a low prevalence in most populations. Caused by Mycobacterium leprae, the infection primarily involves the skin, mucosa and peripheral nerves. The susceptible host range for Mycobacterium leprae is quite narrow. Besides humans, nine banded armadillos (Dasypus novemcinctus) and red squirrels (Sciurus vulgaris) are the only other natural hosts for M. leprae, but only armadillos recapitulate the disease as seen in humans. Armadillos across the Southern United States harbor a single predominant genotypic strain (SNP Type-3I) of M. leprae, which is also implicated in the zoonotic transmission of leprosy. We investigated, whether the zoonotic strain (3I) has any notable growth advantages in armadillos over another genetically distant strain-type (SNP Type-4P) of M. leprae, and if M. leprae strains manifest any notably different pathology among armadillos. We co-infected armadillos (n = 6) with 2 × 109 highly viable M. leprae of both strains and assessed the relative growth and dissemination of each strain in the animals. We also analyzed 12 additional armadillos, 6 each individually infected with the same quantity of either strain. The infections were allowed to fulminate and the clinical manifestations of the disease were noted. Animals were humanely sacrificed at the terminal stage of infection and the number of bacilli per gram of liver, spleen and lymph node tissue were enumerated by Q-PCR assay. The growth of M. leprae strain 4P was significantly higher (P < 0.05) than 3I when each strain was propagated individually in armadillos. Significantly (P < 0.0001) higher growth of the 4P strain also was confirmed among animals co-infected with both 3I and 4P strain types using whole genome sequencing. Interestingly, the zoonotic strain does not exhibit any growth advantage in these non-human hosts, but the varied proliferation of the two M. leprae strains within armadillos suggest there are notable pathological variations between M. leprae strain-types.

Sequencing-relative to hybridization-based transcriptomics approaches better define Mycobacterium tuberculosis stress-response regulons.

Mycobacterium tuberculosis (Mtb) infections cause tuberculosis (TB), an infectious disease which causes ∼1.5 million deaths annually. The ability of this pathogen to evade, escape and encounter immune surveillance is fueled by its adaptability. Thus, Mtb induces a transition in its transcriptome in response to environmental changes. Global transcriptome profiling has been key to our understanding of how Mtb responds to the different stress conditions it faces during its life cycle. While this was initially achieved using microarray technology, RNAseq is now widely employed. It is important to understand the correlation between the large amount of microarray based transcriptome data, which continues to shape our understanding of Mtb stress networks, and newer data being generated using RNAseq. We assessed how well the two platforms correlate using three well-defined stress conditions: diamide, hypoxia, and re-aeration. The data used here was generated by different individuals over time using distinct samples, providing a stringent test of platform correlation. While correlation between microarrays and sequencing was high upon diamide treatment, which causes a rapid reprogramming of the transcriptome, RNAseq allowed a better definition of the hypoxic response, characterized by subtle changes in the magnitude of gene-expression. RNAseq also allows for the best cross-platform reproducibility.

Herpes Simplex Virus 1 UL37 Protein Tyrosine Residues Conserved among All Alphaherpesviruses Are Required for Interactions with Glycoprotein K, Cytoplasmic Virion Envelopment, and Infectious Virus Production.

The herpes simplex virus 1 (HSV-1) UL37 protein functions in virion envelopment at trans-Golgi membranes, as well as in retrograde and anterograde transport of virion capsids. Recently, we reported that UL37 interacts with glycoprotein K (gK) and its interacting partner protein UL20 (N. Jambunathan, D. Chouljenko, P. Desai, A. S. Charles, R. Subramanian, V. N. Chouljenko, and K. G. Kousoulas, J Virol 88:5927-5935, 2014, http://dx.doi.org/10.1128/JVI.00278-14), facilitating cytoplasmic virion envelopment. Alignment of UL37 homologs encoded by alphaherpesviruses revealed the presence of highly conserved residues in the central portion of the UL37 protein. A cadre of nine UL37 site-specific mutations were produced and tested for their ability to inhibit virion envelopment and infectious virus production. Complementation analysis revealed that replacement of tyrosines 474 and 480 with alanine failed to complement the UL37-null virus, while all other mutated UL37 genes complemented the virus efficiently. The recombinant virus DC474-480 constructed with tyrosines 474, 476, 477, and 480 mutated to alanine residues produced a gK-null-like phenotype characterized by the production of very small plaques and accumulation of capsids in the cytoplasm of infected cells. Recombinant viruses having either tyrosine 476 or 477 replaced with alanine produced a wild-type phenotype. Immunoprecipitation assays revealed that replacement of all four tyrosines with alanines substantially reduced the ability of gK to interact with UL37. Alignment of HSV UL37 with the human cytomegalovirus and Epstein-Barr virus UL37 homologs revealed that Y480 was conserved only for alphaherpesviruses. Collectively, these results suggest that the UL37 conserved tyrosine 480 residue plays a crucial role in interactions with gK to facilitate cytoplasmic virion envelopment and infectious virus production. IMPORTANCE: The HSV-1 UL37 protein is conserved among all herpesviruses, functions in both retrograde and anterograde transport of virion capsids, and plays critical roles in cytoplasmic virion envelopment by interacting with gK. We show here that UL37 tyrosine residues conserved among all alphaherpesviruses serve critical roles in cytoplasmic virion envelopment and interactions with gK.

Immunomodulatory effects of tick saliva on dermal cells exposed to Borrelia burgdorferi, the agent of Lyme disease.

BACKGROUND: The prolonged feeding process of ixodid ticks, in combination with bacterial transmission, should lead to a robust inflammatory response at the blood-feeding site. Yet, factors present in tick saliva may down-regulate such responses, which may be beneficial to spirochete transmission. The primary goal of this study was to test the hypothesis that tick saliva, in the context of Borrelia burgdorferi, can have widespread effects on the production of immune mediators in skin. METHODS: A cross-section of tick feeding on skin was examined histologically. Human THP-1 cells stimulated with B. burgdorferi and grown in the presence or absence of tick saliva were examined by human DNA microarray, cytokine bead array, sandwich ELISA, and qRT-PCR. Similar experiments were also conducted using dermal fibroblasts. RESULTS: Tick feeding on skin showed dermal infiltration of histiocytes and granulocytes at the bite location. Changes in monocytic transcript levels during co-culture with B. burgdorferi and saliva indicated that tick saliva had a suppressive effect on the expression of certain pro-inflammatory mediators, such as IL-8 (CXCL8) and TLR2, but had a stimulatory effect on specific molecules such as the Interleukin 10 receptor, alpha subunit (IL-10RA), a known mediator of the immunosuppressive signal of IL-10. Stimulated cell culture supernatants were analyzed via antigen-capture ELISA and cytokine bead array for inflammatory mediator production. Treatment of monocytes with saliva significantly reduced the expression of several key mediators including IL-6, IL-8 and TNF-alpha. Tick saliva had an opposite effect on dermal fibroblasts. Rather than inhibiting, saliva enhanced production of pro-inflammatory mediators, including IL-8 and IL-6 from these sentinel skin cells. CONCLUSIONS: The effects of ixodid tick saliva on resident skin cells is cell type-dependent. The response to both tick and pathogen at the site of feeding favors pathogen transmission, but may not be wholly suppressed by tick saliva.

Cigarette Smoke Extract-Exposed Methicillin-Resistant Staphylococcus aureus Regulates Leukocyte Function for Pulmonary Persistence.

Cigarette smoke (CS) predisposes exposed individuals to respiratory infections not only by suppressing immune response but also by enhancing the virulence of pathogenic bacteria. As per our observations, in methicillin-resistant Staphylococcus aureus strain USA300, CS extract (CSE) potentiates biofilm formation via the down-regulation of quorum-sensing regulon accessory gene regulator. Because accessory gene regulator is a global regulator of the staphylococcal virulome, in the present study we sought to identify the effects of CS exposure on staphylococcal gene expression using RNAseq. Comparative analysis of RNAseq profiles revealed the up-regulation of important virulence genes encoding surface adhesins (fibronectin- and fibrinogen-binding proteins A and B and clumping factor B) and proteins involved in immune evasion, such as staphylocoagulase, staphylococcal protein A, and nuclease. In concurrence with the RNAseq data, we observed: (1) significant up-regulation of the ability of CSE-exposed USA300 to evade phagocytosis by macrophages and neutrophils, a known function of staphylococcal protein A; and (2) twofold higher (P < 0.001) number of CSE-exposed USA300 escaping neutrophil extracellular trap-mediated killing by neutrophils as a result of CS-mediated induction of nuclease. Importantly, in three different mouse strains, C57BL6/J, Balb/C, and A/J, we observed significantly higher pulmonary bacterial burden in animals infected with CSE-exposed USA300 as compared with medium-exposed control USA300. Taken together, these observations indicate that bioactive chemicals in CS induce hypervirulence by augmenting the ability of USA300 to evade bactericidal functions of leukocytes, such as phagocytosis and neutrophil extracellular trap-mediated killing.

Persister Development by Borrelia burgdorferi Populations In Vitro.

Doxycycline is an antibiotic commonly used to treat Lyme disease and other bacterial infections. The MIC and minimum bactericidal concentration (MBC) for Borrelia burgdorferi have been investigated by different groups but were experimentally established in this study as a function of input cell density. We demonstrated that B. burgdorferi treated in the stationary phase has a higher probability of regrowth following removal of antibiotic. In addition, we determined experimentally and mathematically that the spirochetes which persist posttreatment do not have a longer lag phase but exhibit a lower growth rate than untreated spirochetes. Finally, we found that treating the spirochetes by pulse-dosing did not eliminate growth or reduce the persister population in vitro. From these data, we propose that B. burgdorferi persister development is stochastic and driven by slowed growth.

Septic arthritis due to moraxella osloensis in a rhesus macaque (Macaca mulatta).

A 5.5-y-old Chinese-origin female rhesus macaque (Macaca mulatta) presented for bilateral hindlimb lameness. The primate had been group-reared in an SPF breeding colony and was seronegative for Macacine herpesvirus 1, SIV, simian retrovirus type D, and simian T-lymphotropic virus. The macaque's previous medical history included multiple occasions of swelling in the left tarsus, and trauma to the right arm and bilateral hands. In addition, the macaque had experienced osteomyelitis of the left distal tibia and rupture of the right cranial cruciate ligament that had been surgically repaired. Abnormal physical examination findings on presentation included a thin body condition, mild dehydration, and bilaterally swollen stifles that were warm to the touch, with the right stifle more severely affected. Mild instability in the left stifle was noted, and decreased range of motion and muscle atrophy were present bilaterally. Hematologic findings included marked neutrophilia and lymphopenia and moderate anemia. Arthrocentesis and culture of joint fluid revealed Moraxella-like organisms. Treatment with enrofloxacin was initiated empirically and subsequently switched to cephalexin, which over time alleviated the joint swelling and inflammation. Definitive diagnosis of Moraxella osloensis septic arthritis was made through isolation of the organism and sequencing of the 16S rDNA region. To our knowledge, this report is the first description of Moraxella osloensis septic arthritis in a rhesus macaque.

Conducting research on sensitive topics with adolescents: ethical and developmental considerations.

Promotion of adolescent health requires well-designed scientific studies that determine the prevalence of the problem of interest, identify risk and resilience factors, and evaluate methods for prevention and intervention. Many adolescent-related health problems are typically considered sensitive by society (e.g., sexual and substance use behaviors), thus further complicating the research process. Using the principles of the Belmont Report as its framework, this paper draws on developmental theories to discuss ethical issues specific to the conduct of research with adolescents. Our ability to use developmentally sensitive research practices will be enhanced by further understanding of issues associated with risk and benefit assessment by the adolescent, their parents, and institutional review boards, and by delineating ways to ensure that adolescent participants are adequately protected and have a developmentally affirming experience.