A machine learning screening model for identifying the risk of high-frequency hearing impairment in a general population.

BACKGROUND: Hearing impairment (HI) has become a major public health issue in China. Currently, due to the limitations of primary health care, the gold standard for HI diagnosis (pure-tone hearing test) is not suitable for large-scale use in community settings. Therefore, the purpose of this study was to develop a cost-effective HI screening model for the general population using machine learning (ML) methods and data gathered from community-based scenarios, aiming to help improve the hearing-related health outcomes of community residents. METHODS: This study recruited 3371 community residents from 7 health centres in Zhejiang, China. Sixty-eight indicators derived from questionnaire surveys and routine haematological tests were delivered and used for modelling. Seven commonly used ML models (the naive Bayes (NB), K-nearest neighbours (KNN), support vector machine (SVM), random forest (RF), eXtreme Gradient Boosting (XGBoost), boosting, and least absolute shrinkage and selection operator (LASSO regression)) were adopted and compared to develop the final high-frequency hearing impairment (HFHI) screening model for community residents. The model was constructed with a nomogram to obtain the risk score of the probability of individuals suffering from HFHI. According to the risk score, the population was divided into three risk stratifications (low, medium and high) and the risk factor characteristics of each dimension under different risk stratifications were identified. RESULTS: Among all the algorithms used, the LASSO-based model achieved the best performance on the validation set by attaining an area under the curve (AUC) of 0.868 (95% confidence interval (CI): 0.847-0.889) and reaching precision, specificity and F-score values all greater than 80%. Five demographic indicators, 7 disease-related features, 5 behavioural factors, 2 environmental exposures, 2 hearing cognitive factors, and 13 blood test indicators were identified in the final screening model. A total of 91.42% (1235/1129) of the subjects in the high-risk group were confirmed to have HI by audiometry, which was 3.99 times greater than that in the low-risk group (22.91%, 301/1314). The high-risk population was mainly characterized as older, low-income and low-educated males, especially those with multiple chronic conditions, noise exposure, poor lifestyle, abnormal blood indices (e.g., red cell distribution width (RDW) and platelet distribution width (PDW)) and liver function indicators (e.g., triglyceride (TG), indirect bilirubin (IBIL), aspartate aminotransferase (AST) and low-density lipoprotein (LDL)). An HFHI nomogram was further generated to improve the operability of the screening model for community applications. CONCLUSIONS: The HFHI risk screening model developed based on ML algorithms can more accurately identify residents with HFHI by categorizing them into the high-risk groups, which can further help to identify modifiable and immutable risk factors for residents at high risk of HI and promote their personalized HI prevention or intervention.

Online public concern about allergic rhinitis and its association with COVID-19 and air quality in China: an informative epidemiological study using Baidu index.

BACKGROUND: Allergic rhinitis is a common health concern that affects quality of life. This study aims to examine the online search trends of allergic rhinitis in China before and after the COVID-19 epidemic and to explore the association between the daily air quality and online search volumes of allergic rhinitis in Beijing. METHODS: We extracted the online search data of allergic rhinitis-related keywords from the Baidu index database from January 23, 2017 to June 23, 2022. We analyzed and compared the temporal distribution of online search behaviors across different themes of allergic rhinitis before and after the COVID-19 pandemic in mainland China, using the Baidu search index (BSI). We also obtained the air quality index (AQI) data in Beijing and assessed its correlation with daily BSIs of allergic rhinitis. RESULTS: The online search for allergic rhinitis in China showed significant seasonal variations, with two peaks each year in spring from March to May and autumn from August and October. The BSI of total allergic rhinitis-related searches increased gradually from 2017 to 2019, reaching a peak in April 2019, and declined after the COVID-19 pandemic, especially in the first half of 2020. The BSI for all allergic rhinitis themes was significantly lower after the COVID-19 pandemic than before (all p values < 0.05). The results also revealed that, in Beijing, there was a significant negative association between daily BSI and AQI for each allergic rhinitis theme during the original variant strain epidemic period and a significant positive correlation during the Omicron variant period. CONCLUSION: Both air quality and the interventions used for COVID-19 pandemic, including national and local quarantines and mask wearing behaviors, may have affected the incidence and public concern about allergic rhinitis in China. The online search trends can serve as a valuable tool for tracking real-time public concerns about allergic rhinitis. By complementing traditional disease monitoring systems of health departments, these search trends can also offer insights into the patterns of disease outbreaks. Additionally, they can provide references and suggestions regarding the public's knowledge demands related to allergic rhinitis, which can further be instrumental in developing targeted strategies to enhance population-based disease education on allergic diseases.

A Kano model-based demand analysis and perceived barriers of pulmonary rehabilitation interventions for patients with chronic obstructive pulmonary disease in China.

BACKGROUND: Pulmonary rehabilitation (PR) has been recognized to be an effective therapy for chronic obstructive pulmonary disease (COPD). However, in China, the application of PR interventions is still less promoted. Therefore, this cross-sectional study aimed to understand COPD patients' intention to receive PR, capture the potential personal, social and environmental barriers preventing their willingness of receiving PR, and eventually identify demanding PR services with the highest priority from patients' point of view. METHODS: In total 237 COPD patients were recruited from 8 health care facilities in Zhejiang, China. A self-designed questionnaire was applied to investigate patients' intention to participate in PR and potentially associated factors, including personal dimension such as personal awareness, demographic factors, COPD status and health-related literacy/behaviors, as well as social policies and perceived environmental barriers. The demand questionnaire of PR interventions based on the Kano model was further adopted. RESULTS: Among the 237 COPD patients, 75.1% of COPD patients were willing to participate in PR interventions, while only 62.9% of the investigated patients had heard of PR interventions. Over 90% of patients believed that the cost of PR services and the ratio of medical insurance reimbursement were potential obstacles hindering them from accepting PR services. The multiple linear regression analysis indicated that the PR skills of medical staff, knowledge promotion and public education levels of PR in the community, patients' transportation concerns and degree of support from family and friends were significantly associated with willingness of participation in PR interventions. By using the Kano model, the top 9 most-requisite PR services (i.e., one-dimensional qualities) were identified from patients' point of view, which are mainly diet guidance, education interventions, psychological interventions and lower limb exercise interventions. Subgroup analysis also revealed that patients' demographics, such as breathlessness level, age, education and income levels, could influence their choice of priorities for PR services, especially services related to exercise interventions, respiratory muscle training, oxygen therapy and expectoration. CONCLUSIONS: This study suggested that PR-related knowledge education among patients and their family, as well as providing basic package of PR services with the most-requisite PR items to COPD patients, were considerable approaches to promote PR attendance in the future.

Two-layer accumulated quantized compression for communication-efficient federated learning: TLAQC.

Federated learning enables multiple nodes to perform local computations and collaborate to complete machine learning tasks without centralizing private data of nodes. However, the frequent model gradients upload/download operations required by the framework result in high communication costs, which have become the main bottleneck for federated learning as deep models scale up, hindering its performance. In this paper, we propose a two-layer accumulated quantized compression algorithm (TLAQC) that effectively reduces the communication cost of federated learning. TLAQC achieves this by reducing both the cost of individual communication and the number of global communication rounds. TLAQC introduces a revised quantization method called RQSGD, which employs zero-value correction to mitigate ineffective quantization phenomena and minimize average quantization errors. Additionally, TLAQC reduces the frequency of gradient information uploads through an adaptive threshold and parameter self-inspection mechanism, further reducing communication costs. It also accumulates quantization errors and retained weight deltas to compensate for gradient knowledge loss. Through quantization correction and two-layer accumulation, TLAQC significantly reduces precision loss caused by communication compression. Experimental results demonstrate that RQSGD achieves an incidence of ineffective quantization as low as 0.003% and reduces the average quantization error to 1.6 × [Formula: see text]. Compared to full-precision FedAVG, TLAQC compresses uploaded traffic to only 6.73% while increasing accuracy by 1.25%.

Did the COVID-19 pandemic impact urticaria information-seeking behavior in China? A retrospective longitudinal study.

Purpose: To investigate information-seeking behavior related to urticaria before and during the COVID-19 pandemic in China. Methods: Search query data for terms related to urticaria were retrieved using Baidu Index database from October 23, 2017 to April 23, 2022, and daily COVID-19 vaccination doses data were obtained from the website of the Chinese Center for Disease Control and Prevention. Among the 23 eligible urticaria search terms, four urticaria themes were generated as classification, symptom, etiology, and treatment of urticarial, respectively. Baidu Search Index (BSI) value for each term were extracted to analyze and compare the spatial and temporal distribution of online search behavior for urticaria before and after the COVID-19 pandemic, and to also explore the correlation between search query and daily COVID-19 vaccination doses. Results: The classification of urticaria accounted for nearly half of the urticaria queries on the internet. Regular seasonal patterns of BSI were observed in urticaria-related online search, by attaining its highest level in spring and summer and lowest level in winter. The BSIs of all urticaria themes significantly increased after the COVID-19 pandemic than that before the pandemic (all P<0.05). Xizang, Qinghai and Ningxia are the most active geographical areas for increased urticaria-searching activities after the COVID-19 pandemic. There was also a significant positive correlation between daily BSIs and daily COVID-19 vaccination doses in each urticaria theme. Cross-correlation analysis found that the search of symptom, etiology, and treatment attained their strongest correlation with daily COVID-19 vaccination doses at 11-27 days before the injection of vaccine, imply vaccination hesitation related to concerns of urticaria. Conclusions: This study used the internet as a proxy to provide evidence of public search interest and spatiotemporal characteristics of urticaria, and revealed that the search behavior of urticaria have increased significantly after the COVID-19 pandemic and COVID-19 vaccination. It is anticipated that the findings about such increase in search behavior, as well as the behavior of urticaria-related vaccine-hesitancy, will help guide public health education and policy regulation.

Visualizing the knowledge domains and research trends of childhood asthma: A scientometric analysis with CiteSpace.

Background: Asthma is one of the most common chronic diseases in children globally. In recent decades, advances have been made in understanding the mechanism, diagnosis, treatment and management for childhood asthma, but few studies have explored its knowledge structure and future interests comprehensively. Objective: This scientometric study aims to understand the research status and emerging trends of childhood asthma. Methods: CiteSpace (version 5.8.R3) was used to demonstrate national and institutional collaborations in childhood asthma, analyze research subjects and journal distribution, review research keywords and their clusters, as well as detect research bursts. Results: A total of 14,340 publications related to childhood asthma were extracted from Web of Science (core database) during January 2011 to December 2021. The results showed that academic activities of childhood asthma had increased steadily in the last decade. Most of the research was conducted by developed countries while China, as a developing country, was also actively engaged in this field. In addition to subjects of allergy and immunology, both public health aspects and ecological environmental impacts on the disease were emphasized recently in this research field. Keywords clustering analysis indicated that research on asthma management and atopy was constantly updated and became the two major research focuses recently, as a significant shift in research hotspots from etiology and diagnosis to atopic march and asthma management was identified. Subgroup analysis for childhood asthma management and atopy suggested that caregiver- or physician-based education and interventions were emerging directions for asthma management, and that asthma should be carefully studied in the context of atopy, together with other allergic diseases. Conclusions: This study presented a comprehensive and systematic overview of the research status of childhood asthma, provided clues to future research directions, and highlighted two significant research trends of asthma management and atopy in this field.

Progressive Metabolic Abnormalities Associated with the Development of Neonatal Bronchopulmonary Dysplasia.

Objective: To assess the longitudinal metabolic patterns during the evolution of bronchopulmonary dysplasia (BPD) development. Methods: A case-control dataset of preterm infants (<32-week gestation) was obtained from a multicenter database, including 355 BPD cases and 395 controls. A total of 72 amino acid (AA) and acylcarnitine (AC) variables, along with infants' calorie intake and growth outcomes, were measured on day of life 1, 7, 28, and 42. Logistic regression, clustering methods, and random forest statistical modeling were utilized to identify metabolic variables significantly associated with BPD development and to investigate their longitudinal patterns that are associated with BPD development. Results: A panel of 27 metabolic variables were observed to be longitudinally associated with BPD development. The involved metabolites increased from 1 predominant different AC by day 7 to 19 associated AA and AC compounds by day 28 and 16 metabolic features by day 42. Citrulline, alanine, glutamate, tyrosine, propionylcarnitine, free carnitine, acetylcarnitine, hydroxybutyrylcarnitine, and most median-chain ACs (C5:C10) were the most associated metabolites down-regulated in BPD babies over the early days of life, whereas phenylalanine, methionine, and hydroxypalmitoylcarnitine were observed to be up-regulated in BPD babies. Most calorie intake and growth outcomes revealed similar longitudinal patterns between BPD cases and controls over the first 6 weeks of life, after gestational adjustment. When combining with birth weight, the derived metabolic-based discriminative model observed some differences between those with and without BPD development, with c-statistics of 0.869 and 0.841 at day 7 and 28 of life on the test data. Conclusions: The metabolic panel we describe identified some metabolic differences in the blood associated with BPD pathogenesis. Further work is needed to determine whether these compounds could facilitate the monitoring and/or investigation of early-life metabolic status in the lung and other tissues for the prevention and management of BPD.

ALDH2, ADCY3 and BCMO1 polymorphisms and lifestyle-induced traits are jointly associated with CAD risk in Chinese Han people.

BACKGROUNDS: To investigate associations of genetic and environmental factors with coronary artery disease (CAD), we collected medical reports, lifestyle details, and blood samples of 2113 individuals, and then used the polymerase chain reaction (PCR)-ligase detection reaction (LDR) to genotype the targeted 102 SNPs. METHODS: We adopted elastic net algorithm to build an association model that considered simultaneously genetic and lifestyle/clinical factors associated with CAD in Chinese Han population. RESULTS: In this study, we developed an all covariates-based model to explain the risk of CAD, which incorporated 8 lifestyle/clinical factors and a gene-score variable calculated from 3 significant SNPs (rs671, rs6751537 and rs11641677), attaining an area under the curve (AUC) value of 0.71. It was found that, in terms of genetic variants, the AA genotype of rs671 in the additive (adjusted odds ratio (OR) = 2.51, p = 0.008) and recessive (adjusted OR = 2.12, p = 0.021) models, the GG genotype of rs6751537 in the additive (adjusted OR = 3.36, p = 0.001) and recessive (adjusted OR = 3.47, p = 0.001) models were associated with increased risk of CAD, while GG genotype of rs11641677 in additive model (adjusted OR = 0.39, p = 0.044) was associated with decreased risk of CAD. In terms of lifestyle/clinical factors, the history of hypertension (unadjusted OR = 2.37, p < 0.001) and dyslipidemia (unadjusted OR = 1.82, p = 0.007), age (unadjusted OR = 1.07, p < 0.001) and waist circumference (unadjusted OR = 1.02, p = 0.05) would significantly increase the risk of CAD, while height (unadjusted OR = 0.97, p = 0.006) and regular intake of chicken (unadjusted OR = 0.78, p = 0.008) reduced the risk of CAD. A significantinteraction was foundbetween rs671 and dyslipidemia (the relative excess risk due to interaction (RERI) = 3.36, p = 0.05). CONCLUSION: In this study, we constructed an association model and identified a set of SNPs and lifestyle/clinical risk factors of CAD in Chinese Han population. By considering both genetic and non-genetic risk factors, the built model may provide implications for CAD pathogenesis and clues for screening tool development in Chinese Han population.

Construction and Evaluation of a High-Frequency Hearing Loss Screening Tool for Community Residents.

Early screening and detection of individuals at high risk of high-frequency hearing loss and identification of risk factors are critical to reduce the prevalence at community level. However, unlike those for individuals facing occupational auditory hazards, a limited number of hearing loss screening models have been developed for community residents. Therefore, this study used lasso regression with 10-fold cross-validation for feature selection and model construction on 38 questionnaire-based variables of 4010 subjects and applied the model to training and testing cohorts to obtain a risk score. The model achieved an area under the curve (AUC) of 0.844 in the model validation stage and individuals' risk scores were subsequently stratified into low-, medium-, and high-risk categories. A total of 92.79% (1094/1179) of subjects in the high-risk category were confirmed to have hearing loss by audiometry test, which was 3.7 times higher than that in the low-risk group (25.18%, 457/1815). Half of the key indicators were related to modifiable contexts, and they were identified as significantly associated with the incident hearing loss. These results demonstrated that the developed model would be feasible to identify residents at high risk of hearing loss via regular community-level health examinations and detecting individualized risk factors, and eventually provide precision interventions.

The value of lymphocyte-to-monocyte ratio and neutrophil-to-lymphocyte ratio in differentiating pneumonia from upper respiratory tract infection (URTI) in children: a cross-sectional study.

BACKGROUNDS: Early and accurate diagnosis of pediatric pneumonia in primary health care can reduce the chance of long-term respiratory diseases, related hospitalizations and mortality while lowering medical costs. The aim of this study was to assess the value of blood biomarkers, clinical symptoms and their combination in assisting discrimination of pneumonia from upper respiratory tract infection (URTI) in children. METHODS: Both univariate and multivariate logistic regressions were used to build the pneumonia screening model based on a retrospective cohort, comprised of 5211 children (age ≤ 18 years). The electronic health records of the patients, who had inpatient admission or outpatient visits between February 15, 2012 to September 30, 2018, were extracted from the hospital information system of Zhejiang Provincial People's Hospital, Hangzhou, Zhejiang Province, China. The children who were diagnosed with pneumonia and URTI were enrolled and their clinical features and levels of blood biomarkers were compared. Using the area under the ROC curve, both two screening models were evaluated under 80% (training) versus 20% (test) cross-validation data split for their accuracy. RESULTS: In the retrospective cohort, 2548 of 5211 children were diagnosed with the defined pneumonia. The univariate screening model reached predicted AUCs of 0.76 for lymphocyte/monocyte ratio (LMR) and 0.71 for neutrophil/lymphocyte ratio (NLR) when identified overall pneumonia from URTI, attaining the best performance among the biomarker candidates. In subgroup analysis, LMR and NLR attained AUCs of 0.80 and 0.86 to differentiate viral pneumonia from URTI, and AUCs of 0.77 and 0.71 to discriminate bacterial pneumonia from URTI respectively. After integrating LMR and NLR with three clinical symptoms of fever, cough and rhinorrhea, the multivariate screening model obtained increased predictive values, reaching validated AUCs of 0.84, 0.95 and 0.86 for distinguishing pneumonia, viral pneumonia and bacterial pneumonia from URTI respectively. CONCLUSIONS: Our study demonstrated that combining LMR and NLR with critical clinical characteristics reached promising accuracy in differentiating pneumonia from URTI, thus could be considered as a useful screening tool to assist the diagnosis of pneumonia, in particular, in community healthcare centers. Further researches could be conducted to evaluate the model's clinical utility and cost-effectiveness in primary care scenarios to facilitate pneumonia diagnosis, especially in rural settings.

Corrigendum: Estimating the Minimal Number of Repeated Examinations for Random Responsiveness With the Coma Recovery Scale-Revised as an Example.

[This corrects the article DOI: 10.3389/fnint.2021.685627.].

Estimating the Minimal Number of Repeated Examinations for Random Responsiveness With the Coma Recovery Scale-Revised as an Example.

Objective: The aim of this study was to develop a general method to estimate the minimal number of repeated examinations needed to detect patients with random responsiveness, given a limited rate of missed diagnosis. Methods: Basic statistical theory was applied to develop the method. As an application, 100 patients with disorders of consciousness (DOC) were assessed with the Coma Recovery Scale-Revised (CRS-R). DOC patients were supposed to be examined for 13 times over 20 days, while anyone who was diagnosed as a minimally conscious state (MCS) in a round would no longer be examined in the subsequent rounds. To test the validation of this method, a series of the stochastic simulation was completed by computer software under all the conditions of possible combinations of three kinds of distributions for p, five values of p, and four sizes of the sample and repeated for 100 times. Results: A series of formula was developed to estimate the probability of a positive response to a single examination given by a patient and the minimal number of successive examinations needed based on the numbers of patients detected in the first i (i =1, 2,.) rounds of repeated examinations. As applied to the DOC patients assessed with the CRS-R, with a rate of missed diagnosis < 0.0001, the estimate of the minimal number of examinations was six in traumatic brain injury patients and five in non-traumatic brain injury patients. The outcome of the simulation showed that this method performed well under various conditions possibly occurring in practice. Interpretation: The method developed in this paper holds in theory and works well in application and stochastic simulation. It could be applied to any other kind of examinations for random responsiveness, not limited to CRS-R for detecting MCS; this should be validated in further research.

Model of genetic and environmental factors associated with type 2 diabetes mellitus in a Chinese Han population.

BACKGROUND: Type 2 diabetes mellitus (T2DM) is a metabolic disorder which accounts for high morbidity and mortality due to complications like renal failure, amputations, cardiovascular disease, and cerebrovascular events. METHODS: We collected medical reports, lifestyle details, and blood samples of individuals and used the polymerase chain reaction-ligase detection reaction method to genotype the SNPs, and a visit was conducted in August 2016 to obtain the incidence of Type 2 diabetes in the 2113 eligible people. To explore which genes and environmental factors are associated with type 2 diabetes mellitus in a Chinese Han population, we used elastic net to build a model, which is to explain which variables are strongly associated with T2DM, rather than predict the occurrence of T2DM. RESULT: The genotype of the additive of rs964184, together with the history of hypertension, regular intake of meat and waist circumference, increased the risk of T2DM (adjusted OR = 2.38, p = 0.042; adjusted OR = 3.31, p < 0.001; adjusted OR = 1.05, p < 0.001). The TT genotype of the additive and recessive models of rs12654264, the CC genotype of the additive and dominant models of rs2065412, the TT genotype of the additive and dominant models of rs4149336, together with the degree of education, regular exercise, reduced the risk of T2DM (adjusted OR = 0.46, p = 0.017; adjusted OR = 0.53, p = 0.021; adjusted OR = 0.59, p = 0.021; adjusted OR = 0.57, p = 0.01; adjusted OR = 0.59, p = 0.021; adjusted OR = 0.57, p = 0.01; adjusted OR = 0.50, p = 0.007; adjusted OR = 0.80, p = 0.032) . CONCLUSION: Eventually we identified a set of SNPs and environmental factors: rs5805 in the SLC12A3, rs12654264 in the HMGCR, rs2065412 and rs414936 in the ABCA1, rs96418 in the ZPR1 gene, waistline, degree of education, exercise frequency, hypertension, and the intake of meat. Although there was no interaction between these variables, people with two risk factors had a higher risk of T2DM than those only having one factor. These results provide the theoretical basis for gene and other risk factors screening to prevent T2DM.

Liver Enzyme Elevation in Coronavirus Disease 2019: A Multicenter, Retrospective, Cross-Sectional Study.

INTRODUCTION: Elevated liver enzyme levels are observed in patients with coronavirus disease 2019 (COVID-19); however, these features have not been characterized. METHODS: Hospitalized patients with COVID-19 in Zhejiang Province, China, from January 17 to February 12, 2020, were enrolled. Liver enzyme level elevation was defined as alanine aminotransferase level >35 U/L for men and 25 U/L for women at admission. Patients with normal alanine aminotransferase levels were included in the control group. Reverse transcription polymerase chain reaction was used to confirm severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, and patients symptomatic with SARS-CoV-2 infection were defined as patients with COVID-19. Epidemiological, demographic, clinical, laboratory, treatment, and outcome data were collected and compared. RESULTS: Of 788 patients with COVID-19, 222 (28.2%) patients had elevated liver enzyme levels (median [interquartile range {IQR}] age, 47.0 [35.0-55.0] years; 40.5% women). Being male, overweight, and smoking increased the risk of liver enzyme level elevation. The liver enzyme level elevation group had lesser pharyngalgia and more diarrhea than the control group. The median time from illness onset to admission was 3 days for liver enzyme level elevation groups (IQR, 2-6), whereas the median hospitalization time for 86 (38.7%) discharged patients was 13 days (IQR, 11-16). No differences in disease severity and clinical outcomes were noted between the groups. DISCUSSION: We found that 28.2% of patients with COVID-19 presented with elevated liver enzyme levels on admission, which could partially be related to SARS-CoV-2 infection. Male patients had a higher risk of liver enzyme level elevation. With early medical intervention, liver enzyme level elevation did not worsen the outcomes of patients with COVID-19.

Association of Genetic and Environmental Factors with Non-Alcoholic Fatty Liver Disease in a Chinese Han Population.

Lifestyle choices such as the intake of sweets, history of diseases, and genetic variants seem to play a role in the pathogenesis of non-alcoholic fatty liver disease (NAFLD). To explore which genetic and environmental factors are associated with NAFLD in a Chinese Han population, we conducted this study. We collected the medical reports, lifestyle details, and blood samples of individuals and used the polymerase chain reaction-ligase detection reaction method to genotype the single-nucleotide polymorphism (SNPs) from the 2113 eligible people. The GG genotype of the additive model of rs7493 in the PON2, the CC genotype of the additive and recessive models of rs7593130 in the ADCY3, together with dyslipidemia, regular intake of egg and sweets and hypertension, increased the risk of NAFLD (adjusted OR > 1, p < 0.05). The TT genotype of the additive and dominant models of rs11583680 in the PCSK9, together with the regular intake of vegetable, reduced the risk of NAFLD (adjusted OR < 1, p < 0.05). In addition, interactions between some variables were found. Eventually, we identified three SNPs and six environmental factors associated with NAFLD. These results provide the theoretical basis for gene and other risk factors screening to prevent NAFLD.

Progressive Metabolic Dysfunction and Nutritional Variability Precedes Necrotizing Enterocolitis.

Necrotizing Enterocolitis (NEC) is associated with prematurity, enteral feedings, and enteral dysbiosis. Accordingly, we hypothesized that along with nutritional variability, metabolic dysfunction would be associated with NEC onset. Methods: We queried a multicenter longitudinal database that included 995 preterm infants (<32 weeks gestation) and included 73 cases of NEC. Dried blood spot samples were obtained on day of life 1, 7, 28, and 42. Metabolite data from each time point included 72 amino acid (AA) and acylcarnitine (AC) measures. Nutrition data were averaged at each of the same time points. Odds ratios and 95% confidence intervals were calculated using samples obtained prior to NEC diagnosis and adjusted for potential confounding variables. Nutritional and metabolic data were plotted longitudinally to determine relationship to NEC onset. Results: Day 1 analyte levels of alanine, phenylalanine, free carnitine, C16, arginine, C14:1/C16, and citrulline/phenylalanine were associated with the subsequent development of NEC. Over time, differences in individual analyte levels associated with NEC onset shifted from predominantly AAs at birth to predominantly ACs by day 42. Subjects who developed NEC received significantly lower weight-adjusted total calories (p < 0.001) overall, a trend that emerged by day of life 7 (p = 0.020), and persisted until day of life 28 (p < 0.001) and 42 (p < 0.001). Conclusion: Premature infants demonstrate metabolic differences at birth. Metabolite abnormalities progress in parallel to significant differences in nutritional delivery signifying metabolic dysfunction in premature newborns prior to NEC onset. These observations provide new insights to potential contributing pathophysiology of NEC and opportunity for clinical care-based prevention.

Identification of elders at higher risk for fall with statewide electronic health records and a machine learning algorithm.

OBJECTIVE: Predicting the risk of falls in advance can benefit the quality of care and potentially reduce mortality and morbidity in the older population. The aim of this study was to construct and validate an electronic health record-based fall risk predictive tool to identify elders at a higher risk of falls. METHODS: The one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort. The data were collected from electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age). RESULTS: This model attained a validated C-statistic of 0.807, where 50 % of the identified high-risk true positives were confirmed to fall during the first 94 days of next year. The model also captured in advance 58.01 % and 54.93 % of falls that happened within the first 30 and 30-60 days of next year. The identified high-risk patients of fall showed conditions of severe disease comorbidities, an enrichment of fall-increasing cardiovascular and mental medication prescriptions and increased historical clinical utilization, revealing the complexity of the underlying fall etiology. The XGBoost algorithm captured 157 impactful predictors into the final predictive model, where cognitive disorders, abnormalities of gait and balance, Parkinson's disease, fall history and osteoporosis were identified as the top-5 strongest predictors of the future fall event. CONCLUSIONS: By using the EHR data, this risk assessment tool attained an improved discriminative ability and can be immediately deployed in the health system to provide automatic early warnings to older adults with increased fall risk and identify their personalized risk factors to facilitate customized fall interventions.

Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records.

Suicide is the tenth leading cause of death in the United States (US). An early-warning system (EWS) for suicide attempt could prove valuable for identifying those at risk of suicide attempts, and analyzing the contribution of repeated attempts to the risk of eventual death by suicide. In this study we sought to develop an EWS for high-risk suicide attempt patients through the development of a population-based risk stratification surveillance system. Advanced machine-learning algorithms and deep neural networks were utilized to build models with the data from electronic health records (EHRs). A final risk score was calculated for each individual and calibrated to indicate the probability of a suicide attempt in the following 1-year time period. Risk scores were subjected to individual-level analysis in order to aid in the interpretation of the results for health-care providers managing the at-risk cohorts. The 1-year suicide attempt risk model attained an area under the curve (AUC ROC) of 0.792 and 0.769 in the retrospective and prospective cohorts, respectively. The suicide attempt rate in the "very high risk" category was 60 times greater than the population baseline when tested in the prospective cohorts. Mental health disorders including depression, bipolar disorders and anxiety, along with substance abuse, impulse control disorders, clinical utilization indicators, and socioeconomic determinants were recognized as significant features associated with incident suicide attempt.

A multi-locus predictiveness curve and its summary assessment for genetic risk prediction.

Genetic association studies using high-throughput genotyping and sequencing technologies have identified a large number of genetic variants associated with complex human diseases. These findings have provided an unprecedented opportunity to identify individuals in the population at high risk for disease who carry causal genetic mutations and hold great promise for early intervention and individualized medicine. While interest is high in building risk prediction models based on recent genetic findings, it is crucial to have appropriate statistical measurements to assess the performance of a genetic risk prediction model. Predictiveness curves were recently proposed as a graphic tool for evaluating a risk prediction model on the basis of a single continuous biomarker. The curve evaluates a risk prediction model for classification performance as well as its usefulness when applied to a population. In this article, we extend the predictiveness curve to measure the collective contribution of multiple genetic variants. We further propose a nonparametric, U-statistics-based measurement, referred to as the U-Index, to quantify the performance of a multi-locus predictiveness curve. In particular, a global U-Index and a partial U-Index can be used in the general population and a subpopulation of particular clinical interest, respectively. Through simulation studies, we demonstrate that the proposed U-Index has advantages over several existing summary statistics under various disease models. We also show that the partial U-Index can have its own uniqueness when rare variants have a substantial contribution to disease risk. Finally, we use the proposed predictiveness curve and its corresponding U-Index to evaluate the performance of a genetic risk prediction model for nicotine dependence.

A Real-Time Early Warning System for Monitoring Inpatient Mortality Risk: Prospective Study Using Electronic Medical Record Data.

BACKGROUND: The rapid deterioration observed in the condition of some hospitalized patients can be attributed to either disease progression or imperfect triage and level of care assignment after their admission. An early warning system (EWS) to identify patients at high risk of subsequent intrahospital death can be an effective tool for ensuring patient safety and quality of care and reducing avoidable harm and costs. OBJECTIVE: The aim of this study was to prospectively validate a real-time EWS designed to predict patients at high risk of inpatient mortality during their hospital episodes. METHODS: Data were collected from the system-wide electronic medical record (EMR) of two acute Berkshire Health System hospitals, comprising 54,246 inpatient admissions from January 1, 2015, to September 30, 2017, of which 2.30% (1248/54,246) resulted in intrahospital deaths. Multiple machine learning methods (linear and nonlinear) were explored and compared. The tree-based random forest method was selected to develop the predictive application for the intrahospital mortality assessment. After constructing the model, we prospectively validated the algorithms as a real-time inpatient EWS for mortality. RESULTS: The EWS algorithm scored patients' daily and long-term risk of inpatient mortality probability after admission and stratified them into distinct risk groups. In the prospective validation, the EWS prospectively attained a c-statistic of 0.884, where 99 encounters were captured in the highest risk group, 69% (68/99) of whom died during the episodes. It accurately predicted the possibility of death for the top 13.3% (34/255) of the patients at least 40.8 hours before death. Important clinical utilization features, together with coded diagnoses, vital signs, and laboratory test results were recognized as impactful predictors in the final EWS. CONCLUSIONS: In this study, we prospectively demonstrated the capability of the newly-designed EWS to monitor and alert clinicians about patients at high risk of in-hospital death in real time, thereby providing opportunities for timely interventions. This real-time EWS is able to assist clinical decision making and enable more actionable and effective individualized care for patients' better health outcomes in target medical facilities.