Search

We aimed to develop a data-driven machine learning model for predicting critical deterioration events from routinely collected EHR data in hospitalized children.This retrospective cohort study included all pediatric inpatients hospitalized on a medical or surgical ward between 2014-2018 at a quaternary children's hospital.We developed a large data-driven approach and evaluated three machine learning models to predict pediatric critical deterioration events. We evaluated the models using a nested, stratified 10-fold cross-validation. The evaluation metrics included C-statistic, sensitivity, and positive predictive value. We also compared the machine learning models with patients identified as high-risk Watchers by bedside clinicians.The study included 57,233 inpatient admissions from 34,976 unique patients. 3,943 variables were identified from the EHR data. The XGBoost model performed best (C-statistic=0.951, CI: 0.946 ∼ 0.956).Our data-driven machine learning models accurately predicted patient deterioration. Future sociotechnical analysis will inform deployment within the clinical setting.

Human cervical cancer is the fourth most common carcinoma in women in the world. The JAK/STAT3 signaling pathways crucially regulate cell growth and apoptosis. It is a significant target signaling pathway for the development of novel antitumor medicine. This study intended to explore whether lycorine could prevent HT-3 proliferation and induce apoptosis by targeting the JAK/STAT3 signaling cascade. The HT-3 cells were treated with various lycorine dosages and we analyzed cell growth, lipid peroxidation, antioxidants, mitochondrial membrane potential (ΔΨm), DNA damage, apoptosis markers by different in vitro methodologies. Our results revealed that lycorine substantially reserved cell growth via decreased antioxidants, augmented reactive oxygen species (ROS) generation which leads to loss of ΔΨm, increased nuclear crumbling and chromatin condensation, thus resulting in representative increased apoptotic cell death. Furthermore, we analyzed that the molecular mechanical action of lycorine considerably repressed JAK1/STAT3 transactional activation and decrease its downstream molecules Bcl-2, and enhances the expressional activity of Bax, cytochrome c, caspase 3 and 9 in HT-3 cells. Finally, the fact that N-acetylcysteine inhibits lycorine-induced ROS-mediated apoptosis was confirmed in HT-3 cells. Thus, the results indicate that lycorine efficiently enhances apoptosis and inhibits HT-3 cell proliferation. These outcomes collectively proposed that lycorine could be a beneficial chemotherapeutic agent for treating and managing human cervical carcinoma.

To develop and evaluate a high-dimensional, data-driven model to identify patients at high risk of clinical deterioration from routinely collected electronic health record (EHR) data.In this single-center, retrospective cohort study, 488 patients with single-ventricle and shunt-dependent congenital heart disease6 months old were admitted to the cardiac intensive care unit before stage 2 palliation between 2014 and 2019. Using machine-learning techniques, we developed the Intensive care Warning Index (I-WIN), which systematically assessed 1028 regularly collected EHR variables (vital signs, medications, laboratory tests, and diagnoses) to identify patients in the cardiac intensive care unit at elevated risk of clinical deterioration. An ensemble of 5 extreme gradient boosting models was developed and validated on 203 cases (130 emergent endotracheal intubations, 34 cardiac arrests requiring cardiopulmonary resuscitation, 10 extracorporeal membrane oxygenation cannulations, and 29 cardiac arrests requiring cardiopulmonary resuscitation onto extracorporeal membrane oxygenation) and 378 control periods from 446 patients.At 4 hours before deterioration, the model achieved an area under the receiver operating characteristic curve of 0.92 (95% confidence interval, 0.84-0.98), 0.881 sensitivity, 0.776 positive predictive value, 0.862 specificity, and 0.571 Brier skill score. Performance remained high at 8 hours before deterioration with 0.815 (0.688-0.921) area under the receiver operating characteristic curve.I-WIN accurately predicted deterioration events in critically-ill infants with high-risk congenital heart disease up to 8 hours before deterioration, potentially allowing clinicians to target interventions. We propose a paradigm shift from conventional expert consensus-based selection of risk factors to a data-driven, machine-learning methodology for risk prediction. With the increased availability of data capture in EHRs, I-WIN can be extended to broader applications in data-rich environments in critical care.

BACKGROUND The aim of the present work was to evaluate FOXA2 expression in ovarian cancer and to use integrated bioinformatics analysis to correlate it with patient prognosis. MATERIAL AND METHODS FOXA2 expression was evaluated in multiple cancers in The Cancer Genome Atlas database. A protein-protein interaction (PPI) network relevant to FOXA2 was constructed using the Search Tool for Retrieval of Interacting Genes/Proteins (STRIN). Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses were performed of FOXA2 and relevant genes. Correlations between overall survival (OS), disease-free survival, and FOXA2 expression were evaluated. An immunohistochemical assay (IHC) was used to test for FOXA2 protein expression in 79 ovarian cancer specimens. RESULTS FOXA2 mRNA was upregulated in colorectal, stomach, liver, and endometrial cancers. In the PPI network, 21 protein nodes and 533 edges were constructed with a local clustering coefficient of 0.698, which indicated significant PPI enrichment (P

BACKGROUND This study investigated the effect of occupational stress and circadian clock gene polymorphism on sleep disorder of oil workers in Xinjiang, China. MATERIAL AND METHODS We enrolled 2300 Xinjiang oil workers who had been working for at least 1 year. The Chinese revised version of the Occupational Stress Questionnaire (OSI-R), the Pittsburgh Sleep Quality Index (PSQI), and General Survey Questionnaire were used. A total of 308 subjects were selected for stress hormone measurements and gene polymorphism analysis of the circadian clock genes CLOCK, PER2, and PER3. RESULTS The occupational stress scores were influenced by sex, smoking, marital status, age, and work type. Different work shift groups and different professional title groups had statistically significant sleep disorder incidences (P

Nursing is a high-risk occupation with high exposure to stress. The physical and mental health of nurses is directly related to the quality of medical services. Therefore, the sleep quality of nurses should not be ignored. In this study, the method of cluster random sampling was adopted from May to September 2019, and a questionnaire survey was conducted among 521 surgical nurses from five affiliated hospitals of Xinjiang Medical University. The relationship between mental health and sleep quality was analyzed, and 20% of the participants with sleep disorders were randomly selected. The sleep disorders used 1 : 1 matching, finally providing a sample with 60 cases and 60 controls for measurement of the CLOCK gene (rs1801260, rs6850524), to analyze the effect of the interaction between mental health and the CLOCK gene on sleep. The mental health and sleep quality of the surgical nurses were evaluated using the Symptom Checklist 90 (SCL-90) and Pittsburgh Sleep Quality Index (PSQI). The study found that surgical nurses had poor sleep, and there were differences associated with age, years working, frequency of night shifts, and incidence of sleep disorders under marital status (p < 0.05). The PSQI scores of the positive psychological symptoms were higher than those of the negative psychological symptoms. The rank sum test was used to compare the sleep quality scores of different genotypes in CLOCK rs1801260 and rs6850524; the results indicated that the PSQI scores were different among different genotypes at the rs1801260 and rs6850524 loci. The logistic regression results suggested that CLOCK gene rs1801260 (TC) and positive psychological symptoms were influential factors for sleep disorders, and the interaction of positive psychological symptoms∗rs1801260 (TT) was a risk factor for sleep disorders (OR = 10.833, 95% CI: 2.987–39.288). The sleep quality of nurses is not only affected by demographic characteristics but also affected by mental health status and the CLOCK gene.

Social determinants of health (SDOH) are non-medical factors that can profoundly impact patient health outcomes. However, SDOH are rarely available in structured electronic health record (EHR) data such as diagnosis codes, and more commonly found in unstructured narrative clinical notes. Hence, identifying social context from unstructured EHR data has become increasingly important. Yet, previous work on using natural language processing to automate extraction of SDOH from text (a) usually focuses on an ad hoc selection of SDOH, and (b) does not use the latest advances in deep learning. Our objective was to advance automatic extraction of SDOH from clinical text by (a) systematically creating a set of SDOH based on standard biomedical and psychiatric ontologies, and (b) training state-of-the-art deep neural networks to extract mentions of these SDOH from clinical notes.A retrospective cohort study.Data were extracted from the Medical Information Mart for Intensive Care (MIMIC-III) database. The corpus comprised 3,504 social related sentences from 2,670 clinical notes.We developed a framework for automated classification of multiple SDOH categories. Our dataset comprised narrative clinical notes under the "Social Work" category in the MIMIC-III Clinical Database. Using standard terminologies, SNOMED-CT and DSM-IV, we systematically curated a set of 13 SDOH categories and created annotation guidelines for these. After manually annotating the 3,504 sentences, we developed and tested three deep neural network (DNN) architectures - convolutional neural network (CNN), long short-term memory (LSTM) network, and the Bidirectional Encoder Representations from Transformers (BERT) - for automated detection of eight SDOH categories. We also compared these DNNs to three baselines models: (1) cTAKES, as well as (2) L2-regularized logistic regression and (3) random forests on bags-of-words. Model evaluation metrics included micro- and macro- F1, and area under the receiver operating characteristic curve (AUC).All three DNN models accurately classified all SDOH categories (minimum micro-F1 = 0.632, minimum macro-AUC = 0.854). Compared to the CNN and LSTM, BERT performed best in most key metrics (micro-F1 = 0.690, macro-AUC = 0.907). The BERT model most effectively identified the "occupational" category (F1 = 0.774, AUC = 0.965) and least effectively identified the "non-SDOH" category (F = 0.491, AUC = 0.788). BERT outperformed cTAKES in distinguishing social vs non-social sentences (BERT F1 = 0.87 vs. cTAKES F1 = 0.06), and outperformed logistic regression (micro-F1 = 0.649, macro-AUC = 0.696) and random forest (micro-F1 = 0.502, macro-AUC = 0.523) trained on bag-of-words.Our study framework with DNN models demonstrated improved performance for efficiently identifying a systematic range of SDOH categories from clinical notes in the EHR. Improved identification of patient SDOH may further improve healthcare outcomes.

Owing to the transformation of the biomedical model of health, more and more professionals pay close attention to the occupational social psychological factors, such as occupational stress. Due to the socioeconomic impact of occupational stress and the petroleum workers stationed in the unique environment in Xinjiang, a cross-sectional study was carried out between May and December 2016 to investigate the relationship between occupational stress and demographic characteristics. A total of 1480 workers were selected. Occupational stress was evaluated with the Occupational Stress Inventory-Revised Edition. The findings of the present study revealed that the values of the Occupational Roles Questionnaire results (t = 9.266, P

The authors systematically reviewed peer-reviewed studies done with LENA (Language ENvironment Analysis) technology, guided by three research questions: (a) What types of studies have been conducted, and with which populations, since the launch of LENA technology? (b) What challenges related to use of LENA technology were identified? (c) What are the implications for practice and future research using LENA technology? Electronic databases, the LENA Research Foundation website, and bibliographies of already-included studies were searched; 38 studies were identified. The authors selected studies on the basis of purpose, design, participant characteristics, application of LENA technology, and results. They found that LENA technology was used with a range of populations to yield a variety of information. Though challenges and limitations are associated with LENA technology, great potential exists for further research and a resultant increase in evidence-based understanding of early language development and interventions on its behalf.

In response to the challenges set forth by the CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing, we describe a framework to automatically classify initial psychiatric evaluation records to one of four positive valence system severities: absent, mild, moderate, or severe. We used a dataset provided by the event organizers to develop a framework comprised of natural language processing (NLP) modules and 3 predictive models (two decision tree models and one Bayesian network model) used in the competition. We also developed two additional predictive models for comparison purpose. To evaluate our framework, we employed a blind test dataset provided by the 2016 CEGS N-GRID. The predictive scores, measured by the macro averaged-inverse normalized mean absolute error score, from the two decision trees and Naive Bayes models were 82.56%, 82.18%, and 80.56%, respectively. The proposed framework in this paper can potentially be applied to other predictive tasks for processing initial psychiatric evaluation records, such as predicting 30-day psychiatric readmissions.

Objectives This study evaluates the accuracy and transferability of Bayesian case detection systems (BCD) that use clinical notes from emergency department (ED) to detect influenza cases. Methods A BCD uses natural language processing (NLP) to infer the presence or absence of clinical findings from ED notes, which are fed into a Bayesain network classifier (BN) to infer patients’ diagnoses. We developed BCDs at the University of Pittsburgh Medical Center (BCDUPMC) and Intermountain Healthcare in Utah (BCDIH). At each site, we manually built a rule-based NLP and trained a Bayesain network classifier from over 40,000 ED encounters between Jan. 2008 and May. 2010 using feature selection, machine learning, and expert debiasing approach. Transferability of a BCD in this study may be impacted by seven factors: development (source) institution, development parser, application (target) institution, application parser, NLP transfer, BN transfer, and classification task. We employed an ANOVA analysis to study their impacts on BCD performance. Results Both BCDs discriminated well between influenza and non-influenza on local test cases (AUCs > 0.92). When tested for transferability using the other institution’s cases, BCDUPMC discriminations declined minimally (AUC decreased from 0.95 to 0.94, p

To investigate the modulating effect on lipid and gene expressions of CPT I A caused by berberine (Ber) in experimental hyperlipidemia rats.Male SD rats were randomly divided into 5 groups according to the blood lipid values: normal group, hyperlipidemia group, 300 mg x kg(-1) x d(-1) Ber-treated group, 60 mg x kg(-1) x d(-1) Ber-treated group, and 7.2 mg x kg(-1) x d(-1) lovastatin-treated group. Normal group were fed with base diet and other groups were fed with high fat and cholesterol diet. 12 weeks after drugs were given the TC, TG, LDL-C, and HDL-C from rat blood samples were tested by automatic biochemistry analyzer. Gene expressions of CPT I A and PPARalpha were evaluated by RT-PCR and Western blot, respectively.It was shown that Ber significantly decreased TC and LDL-C, but increased HDL-C in dose-dependent manner, elevated expressions of CPT I A mRNA and protein without influence on PPARalpha expression. Similar effects from lovastatin on lipidemia were observed except the Ber effect on CPT I A gene expression.Ber has modulating effect on the lipid metabolism, the mechanism of which may be by promoting the CPT I A gene expression.