Development and Validation of a Non-Invasive, Chairside Oral Cavity Cancer Risk Assessment Prototype Using Machine Learning Approach.

Oral cavity cancer (OCC) is associated with high morbidity and mortality rates when diagnosed at late stages. Early detection of increased risk provides an opportunity for implementing prevention strategies surrounding modifiable risk factors and screening to promote early detection and intervention. Historical evidence identified a gap in the training of primary care providers (PCPs) surrounding the examination of the oral cavity. The absence of clinically applicable analytical tools to identify patients with high-risk OCC phenotypes at point-of-care (POC) causes missed opportunities for implementing patient-specific interventional strategies. This study developed an OCC risk assessment tool prototype by applying machine learning (ML) approaches to a rich retrospectively collected data set abstracted from a clinical enterprise data warehouse. We compared the performance of six ML classifiers by applying the 10-fold cross-validation approach. Accuracy, recall, precision, specificity, area under the receiver operating characteristic curve, and recall-precision curves for the derived voting algorithm were: 78%, 64%, 88%, 92%, 0.83, and 0.81, respectively. The performance of two classifiers, multilayer perceptron and AdaBoost, closely mirrored the voting algorithm. Integration of the OCC risk assessment tool developed by clinical informatics application into an electronic health record as a clinical decision support tool can assist PCPs in targeting at-risk patients for personalized interventional care.

Patterns of farm exposure are associated with reduced incidence of atopic dermatitis in early life.

BACKGROUND: Farm exposures may reduce the risk of atopic dermatitis (AD) in children, but this is controversial and US data are limited. OBJECTIVE: This study was conducted to identify patterns of farm exposure in Wisconsin family farms that modify AD incidence and prevalence in early childhood. METHODS: Environmental exposures, health history, and clinical outcomes were prospectively recorded for 111 farm families and 129 non-farm families enrolled in the Wisconsin Infant Study Cohort birth cohort study. Exposures from the prenatal and early postnatal (2-month) visits were evaluated together with parental report of AD diagnosis by a health care provider through age 24 months. Latent class analysis was performed with prenatal and early postnatal farm-exposure variables to assign farm children to 3 classes. RESULTS: Overall, children of farm families had reduced AD incidence (P = .03). Within farm families, exposures including poultry (3% vs 28%; P = .003), pig (4% vs 25%; P = .04), feed grain (13% vs 34%; P = .02), and number of animal species were inversely associated with AD incidence. Among the latent class groups, children in families with diverse or more intense farm exposures (classes A and B) had reduced AD incidence, whereas low-exposure (class C) infants had AD incidence similar to that in nonfarm children. CONCLUSIONS: Infants in Wisconsin farm families had reduced AD incidence, and patterns of farm exposures further defined AD risk. These findings suggest that exposure to diverse farm animals, feed, and bedding during the prenatal period and in early infancy reduce the risk of early-onset AD, a phenotype associated with multiple other atopic diseases.

Respiratory health, allergies, and the farm environment: design, methods and enrollment in the observational Wisconsin Infant Study Cohort (WISC): a research proposal.

Epidemiologic and cross-sectional studies suggest that early life farming and animal exposures are associated with major health benefits, influencing immune development and modifying the subsequent risk of allergic diseases, including asthma. The Wisconsin Infant Study Cohort (WISC) study was established in central Wisconsin to test the hypothesis that early life animal farm exposures are associated with distinct innate immune cell maturation trajectories, decreased allergen sensitization and reduced respiratory viral illness burden during the first 2 years of life. Beginning in 2013, a total of 240 families have been enrolled, 16,522 biospecimens have been collected, and 4098 questionnaires have been administered and entered into a secure database. Study endpoints include nasal respiratory virus identification and respiratory illness burden score, allergic sensitization, expression of allergic disease, and anti-viral immune response maturation and profiles. The WISC study prospective design, broad biospecimen collections, and unique US rural community will provide insights into the role of environmental exposures on early life immune maturation profiles associated with protection from allergic sensitization and significant respiratory viral disease burden. The WISC study findings will ultimately inform development of new strategies to promote resistance to severe respiratory viral illnesses and design primary prevention approaches for allergic diseases for all infants.

A gene-based recessive diplotype exome scan discovers FGF6, a novel hepcidin-regulating iron-metabolism gene.

Standard analyses applied to genome-wide association data are well designed to detect additive effects of moderate strength. However, the power for standard genome-wide association study (GWAS) analyses to identify effects from recessive diplotypes is not typically high. We proposed and conducted a gene-based compound heterozygosity test to reveal additional genes underlying complex diseases. With this approach applied to iron overload, a strong association signal was identified between the fibroblast growth factor-encoding gene, FGF6, and hemochromatosis in the central Wisconsin population. Functional validation showed that fibroblast growth factor 6 protein (FGF-6) regulates iron homeostasis and induces transcriptional regulation of hepcidin. Moreover, specific identified FGF6 variants differentially impact iron metabolism. In addition, FGF6 downregulation correlated with iron-metabolism dysfunction in systemic sclerosis and cancer cells. Using the recessive diplotype approach revealed a novel susceptibility hemochromatosis gene and has extended our understanding of the mechanisms involved in iron metabolism.

Sibling Recurrence Risk and Cross-aggregation of Attention-Deficit/Hyperactivity Disorder and Autism Spectrum Disorder.

Importance: Attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) are believed to partially share genetic factors and biological influences. As the number of children with these diagnoses rises, so does the number of younger siblings at presumed risk for ADHD and ASD; reliable recurrence risk estimates within and across diagnoses may aid screening and early detection efforts and enhance understanding of potential shared causes. Objective: To examine within-diagnosis sibling recurrence risk and sibling cross-aggregation of ADHD and ASD among later-born siblings of children with either disorder. Design, Setting, and Participants: Using data extracted from medical records of 2 large health care systems in the United States, estimates of recurrence risk and cross-aggregation in later-born siblings of children with ADHD or ASD were compared with later-born siblings of children without these diagnoses. One data set included children seen between January 1, 1995, and December 31, 2013; the other included children born between January 1, 1998, and May 17, 2010. Participants included 15 175 later-born siblings of children with ADHD, ASD, and no known diagnosis. The study was conducted from October 2, 2017, to August 14, 2018. Main Outcomes and Measures: Diagnoses of ASD or ADHD in the later-born sibling, ascertained from medical records, were the primary outcomes of interest; moderators included sex, gestational age, and maternal age. Results: A total of 15 175 later-born siblings were classified by familial risk status based on the older child's diagnostic status: ADHD risk (n = 730; male [51.92%]), ASD risk (n = 158; male [48.10%]), and no known risk (n = 14 287; male [50.73%]). Compared with later-born siblings of children without ADHD or ASD, later-born siblings of children with ASD were more likely to be diagnosed with ASD (odds ratio [OR], 30.38; 95% CI, 17.73-52.06) or ADHD in the absence of ASD (OR, 3.70; 95% CI, 1.67-8.21). Compared with later-born siblings of children without a diagnosis, later-born siblings of children with ADHD were more likely to be diagnosed with ADHD (OR, 13.05; 95% CI, 9.86-17.27) or ASD in the absence of ADHD (OR, 4.35; 95% CI, 2.43-7.79). Conclusions and Relevance: Later-born siblings of children with ASD or ADHD appear to be at elevated risk for the same disorder, but also of being diagnosed with the other disorder. These findings provide further support for shared familial mechanisms underlying ASD and ADHD, which may be useful for genetic and prospective developmental studies. Later-born siblings of children with ADHD or ASD should be monitored for both conditions.

Maternal prepregnancy body mass index and offspring attention-deficit/hyperactivity disorder: a quasi-experimental sibling-comparison, population-based design.

BACKGROUND: High maternal prepregnancy body mass index (BMI) has been associated with increased risk of offspring attention-deficit/hyperactivity disorder (ADHD). However, whether this effect is attributable to maternal or familial level confounds has been little examined. METHODS: The present study sought to examine these associations, utilizing data from the medical records of a health care system which treats 350,000 patients annually and a sibling-comparison design in a sample of 4,682 children born to 3,645 mothers. RESULTS: When examining the overall maternal effect, a linear association was observed between maternal prepregnancy BMI and child ADHD [b = 0.04, 95% confidence interval (95% CI) = 0.02-0.06, p = .0003], such that a one-unit (i.e. 1 kg/m2 ) increase in prepregnancy BMI was associated with a 4% increase in the odds of ADHD (exp b = 1.04). However, when the model was reparameterized to take full advantage of the sibling design to allow for the examination of both maternal and child-specific effects, the child-specific prepregnancy BMI effect was not reliably different from zero (b = -0.08, 95% CI = -0.23 to 0.06, p = .24). In contrast, at the maternal-level, average prepregnancy BMI was a reliably non-zero predictor of child ADHD (b = 0.04, 95% CI = 0.02-0.06, p < .0001) with each one-unit increase in maternal prepregnancy BMI associated with a 4.2% increase in the odds of ADHD (exp b = 1.04, 95% CI = 1.02-1.06). CONCLUSIONS: The association between maternal prepregnancy BMI and offspring ADHD may be better accounted for by familial or maternal confounds rather than a direct causal effect of BMI.

An effectiveness study of a culturally enriched school-based CBT anxiety prevention program.

Anxiety disorders are prevalent in the school-aged population and are present across cultural groups. Scant research exists on culturally relevant prevention and intervention programs for mental health problems in the Aboriginal populations. An established cognitive behavioral program, FRIENDS for Life, was enriched to include content that was culturally relevant to Aboriginal students. Students (N = 533), including 192 students of Aboriginal background, participated in the cluster randomized control study. Data were collected three times over 1 year. A series of multilevel models were conducted to examine the effect of the culturally enriched FRIENDS program on anxiety. These analyses revealed that the FRIENDS program did not effectively reduce anxiety for the total sample or for Aboriginal children specifically. However, all students, regardless of intervention condition, Aboriginal status, or gender, reported a consistent decrease in feelings of anxiety over the 6-month study period.

Evaluation of the factor structure of the child-reported parenting questionnaire in the National Longitudinal Survey of Children and Youth.

BACKGROUND: The effect of parenting behaviours is important in child health and development research. This study evaluates three child-reported parenting behaviour scales (nurturance, rejection and monitoring) in the Canadian National Longitudinal Survey of Children and Youth (NLSCY). DATA AND METHODS: The sample consisted of two longitudinal cohorts (n = 1,164) who were interviewed at ages 10 to 11, 12 to 13, and 14 to 15. The factor structure of each scale was evaluated using confirmatory factor analysis with weighted least squares estimation on polychoric correlation matrices. RESULTS: The 7-item NLSCY Parental Nurturance model appeared to be a good fit to the data for children aged 10 to 11 and 12 to 13, but not for those aged 14 to 15. The 7-item Parental Rejection model was not a good fit to the data across any of the three time points. The 5-item Parental Monitoring model was a good fit to the data across all three time points. Removal of one item from the nurturance and one item from the monitoring scale improved the fit to the data. INTERPRETATION: The revised models appeared to be useful in assessing parental nurturance and monitoring. The model for parental rejection was not confirmed for this sample of adolescents.