Application of data science methods to identify school and home risk factors for asthma and allergy-related symptoms among children in New York

A Comparative Study of CO2 Forecasting Strategies in School Classrooms: A Step Toward Improving Indoor Air Quality

This paper comprehensively investigates the performance of various strategies for predicting CO2 levels in school classrooms over different time horizons by using data collected through IoT devices. We gathered Indoor Air Quality (IAQ) data from fifteen schools in Navarra, Spain between 10 January and 3 April 2022, with measurements taken at 10-min intervals. Three prediction strategies divided into seven models were trained on the data and compared using statistical tests. The study confirms that simple methodologies are effective for short-term predictions, while Machine Learning (ML)-based models perform better over longer prediction horizons. Furthermore, this study demonstrates the feasibility of using low-cost devices combined with ML models for forecasting, which can help to improve IAQ in sensitive environments such as schools.

School built environment and children's health: a scientometric analysis

The school built environment is closely related to children's health, and research on this topic is increasing. However, bibliometric analyses seeking to provide a comprehensive understanding of the research landscape and key themes in the field are lacking. This study comprehensively explored the global trends and research hotspots on the associations between school built environment and children's health. We used a scientometric analysis to review the research progress. The temporal distribution of publications, scientific collaborations, research hotspots, research frontiers, and co-citations over the past 30 years were analyzed. The results show that the number of publications in this field rose significantly between 1987 and 2025, with research hotspots focusing on physical activity, performance, behavior, perception, thermal comfort, and indoor air quality. Environmental themes related to children's health fall into four main groups: the built environment related to children's activities, intelligent learning environments, indoor environments and interiors, and natural environments. Health outcomes and measures that reflect physiological, psychological, cognitive, behavioral, and physical factors are discussed. This study provides a broad understanding of research issues and trends related to the school built environment and children's health.

Exploring Machine Learning Applications in Pediatric Asthma Management: Scoping Review

BACKGROUND

The integration of machine learning (ML) in predicting asthma-related outcomes in children presents a novel approach in pediatric health care.

OBJECTIVE

This scoping review aims to analyze studies published since 2019, focusing on ML algorithms, their applications, and predictive performances.

METHODS

We searched Ovid MEDLINE ALL and Embase on Ovid, the Cochrane Library (Wiley), CINAHL (EBSCO), and Web of Science (core collection). The search covered the period from January 1, 2019, to July 18, 2023. Studies applying ML models in predicting asthma-related outcomes in children aged <18 years were included. Covidence was used for citation management, and the risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool.

RESULTS

From 1231 initial articles, 15 met our inclusion criteria. The sample size ranged from 74 to 87,413 patients. Most studies used multiple ML techniques, with logistic regression (n=7, 47%) and random forests (n=6, 40%) being the most common. Key outcomes included predicting asthma exacerbations, classifying asthma phenotypes, predicting asthma diagnoses, and identifying potential risk factors. For predicting exacerbations, recurrent neural networks and XGBoost showed high performance, with XGBoost achieving an area under the receiver operating characteristic curve (AUROC) of 0.76. In classifying asthma phenotypes, support vector machines were highly effective, achieving an AUROC of 0.79. For diagnosis prediction, artificial neural networks outperformed logistic regression, with an AUROC of 0.63. To identify risk factors focused on symptom severity and lung function, random forests achieved an AUROC of 0.88. Sound-based studies distinguished wheezing from nonwheezing and asthmatic from normal coughs. The risk of bias assessment revealed that most studies (n=8, 53%) exhibited low to moderate risk, ensuring a reasonable level of confidence in the findings. Common limitations across studies included data quality issues, sample size constraints, and interpretability concerns.

CONCLUSIONS

This review highlights the diverse application of ML in predicting pediatric asthma outcomes, with each model offering unique strengths and challenges. Future research should address data quality, increase sample sizes, and enhance model interpretability to optimize ML utility in clinical settings for pediatric asthma management.

Predicting distant metastasis in nasopharyngeal carcinoma using gradient boosting tree model based on detailed magnetic resonance imaging reports

BACKGROUND

Development of distant metastasis (DM) is a major concern during treatment of nasopharyngeal carcinoma (NPC). However, studies have demonstrated improved distant control and survival in patients with advanced NPC with the addition of chemotherapy to concomitant chemoradiotherapy. Therefore, precise prediction of metastasis in patients with NPC is crucial.

AIM

To develop a predictive model for metastasis in NPC using detailed magnetic resonance imaging (MRI) reports.

METHODS

This retrospective study included 792 patients with non-distant metastatic NPC. A total of 469 imaging variables were obtained from detailed MRI reports. Data were stratified and randomly split into training (50%) and testing sets. Gradient boosting tree (GBT) models were built and used to select variables for predicting DM. A full model comprising all variables and a reduced model with the top-five variables were built. Model performance was assessed by area under the curve (AUC).

RESULTS

Among the 792 patients, 94 developed DM during follow-up. The number of metastatic cervical nodes (30.9%), tumor invasion in the posterior half of the nasal cavity (9.7%), two sides of the pharyngeal recess (6.2%), tubal torus (3.3%), and single side of the parapharyngeal space (2.7%) were the top-five contributors for predicting DM, based on their relative importance in GBT models. The testing AUC of the full model was 0.75 (95% confidence interval [CI]: 0.69-0.82). The testing AUC of the reduced model was 0.75 (95%CI: 0.68-0.82). For the whole dataset, the full (AUC = 0.76, 95%CI: 0.72-0.82) and reduced models (AUC = 0.76, 95%CI: 0.71-0.81) outperformed the tumor node-staging system (AUC = 0.67, 95%CI: 0.61-0.73).

CONCLUSION

The GBT model outperformed the tumor node-staging system in predicting metastasis in NPC. The number of metastatic cervical nodes was identified as the principal contributing variable.

Sociodemographic factors, health behavior, parental or workplace smoking, and adult asthma risk in the United States

BACKGROUND

Although several studies have found a link between parental or workplace smoking and asthma risk, particularly in children and adolescents, only a few studies have found this link in adults.

OBJECTIVE

This study aimed to investigate the associations of sociodemographic factors, health behavior, and parental or workplace smoking with adult asthma risk in the United States (US).

METHODS

A secondary data analysis on 874 participants aged 25-45 was performed using data from the 2011-2014 National Survey of Midlife Development in the United States Refresher. Participants were divided into smokers and nonsmokers. Participants were further divided into groups A (a father or mother with a smoking history) and B (others in the house or colleagues in the workplace who had a smoking history).

RESULTS

Findings from the FREQ procedure revealed that sociodemographic (female, black, school or college education, unmarried/divorced, and employed) and lifestyle (no alcohol intake, physically inactive, and obese) and clinical (diabetes and joint disease) factors were significantly associated with one- or more-fold odds of asthma among adult smokers than nonsmokers. Adult smokers in group A, particularly females, those with a high school or college education, physically inactive, and overweight or obese, had a higher risk of asthma than those in group B.

CONCLUSION

Adult smokers' risk of developing asthma is increased in the US by having smoked with their parents, being a woman, being black, having a school or college education, being single or divorced, working, not drinking alcohol, being physically inactive, being obese, having diabetes, and having a joint disease.

Gas cooking and respiratory outcomes in children: A systematic review

The most recent meta-analysis of gas cooking and respiratory outcomes in children was conducted by Lin et al. [93] in 2013. Since then, a number of epidemiology studies have been published on this topic. We conducted the first systematic review of this epidemiology literature that includes an in-depth evaluation of study heterogeneity and study quality, neither of which was systematically evaluated in earlier reviews. We reviewed a total of 66 relevant studies, including those in the Lin et al. [93] meta-analysis. Most of the studies are cross-sectional by design, precluding causal inference. Only a few are cohort studies that could establish temporality and they have largely reported null results. There is large variability across studies in terms of study region, age of children, gas cooking exposure definition, and asthma or wheeze outcome definition, precluding clear interpretations of meta-analysis estimates such as those reported in Lin et al. [93]. Further, our systematic study quality evaluation reveals that a large proportion of the studies to date are subject to multiple sources of bias and inaccuracy, primarily due to self-reported gas cooking exposure or respiratory outcomes, insufficient adjustment for key confounders (e.g., environmental tobacco smoke, family history of asthma or allergies, socioeconomic status or home environment), and unestablished temporality. We conclude that the epidemiology literature is limited by high heterogeneity and low study quality and, therefore, it does not provide sufficient evidence regarding causal relationships between gas cooking or indoor NO2 and asthma or wheeze. We caution against over-interpreting the quantitative evidence synthesis estimates from meta-analyses of these studies.

Telemedicine beyond the pandemic: challenges in the pediatric immunology clinic

INTRODUCTION

Telemedicine and electronic medical records (EMRs) have revolutionized healthcare in recent years, offering numerous benefits that improve the delivery of care and the overall patient outcomes.

AREAS COVERED

Telemedicine allows providers to diagnose and treat patients remotely, often eliminating the need for face-to-face visits. Its benefits include improved access to care, convenience for patients, and reduced costs both for patients and providers. When used with remote patient monitoring and remote therapeutic monitoring, continuous care becomes possible. EMRs allow providers to store, access, and share patient information more efficiently than paper charts. The benefits of EMRs include improved patient safety, increased efficiency, and reduced costs.

EXPERT OPINION

The combination of telemedicine with EMRs makes it possible to envision the advent of computer-assisted diagnosis (CAD). This technology uses artificial intelligence and machine learning algorithms to analyze medical information including images, clinical and physiologic data, test results and remotely obtained information to support healthcare providers in making accurate diagnoses. By providing providers with what is essentially a second opinion, CAD systems can help prevent misdiagnoses and improve the quality of care. Such systems are not meant to replace healthcare providers, but rather to support them in making more informed and accurate diagnoses.

Assessing the relevance of allergenic pollen in indoor environments-current knowledge base and research needs

Airborne pollen allergens-a relevant component of bioaerosols and, therefore, of airborne particulate matter-are considered an important metric in air quality assessments. Although the measurement of airborne pollen allergen concentrations in outdoor environments (namely, in urban areas) has been recognized as a key environmental health indicator, no such obligation exists for indoor environments (dwellings or occupational settings). However, people spend most of their daily time (80-90%) indoors, where the majority of their exposure to air pollution, including pollen allergens, occurs. Nonetheless, the relative importance of airborne pollen allergen exposure indoors differs from outdoors because of differences in pollen loads, sources, dispersion, and degree of penetration from the outdoor surroundings, as well as the differences in the allergenic pollen profiles. In this brief review, we mined the literature over the last 10 years to summarize what existing measurements reveal about the relevance of airborne allergenic pollen in indoor environments. The research priorities on this topic are presented, highlighting the challenges and the motivations for obtaining pollen data in built environments which are key to understand the extent and mechanisms of human exposure to airborne pollen allergens. Thus, we provide a comprehensive assessment of the relevance of airborne allergenic pollen in indoor environments, highlighting knowledge gaps and research needs related to their health effects.

Gender differences in the association between biomarkers of environmental smoke exposure and developmental disorders in children and adolescents

Effects of environmental tobacco smoke (ETS) exposure on children and adolescent health outcomes have been attracted more and more attention. In the present study, we seek to examine the gender-specific difference association of environmental smoke exposure biomarkers and developmental disorders in children and adolescents aged 6-15 years. US nationally representative sample collected from the National Health and Nutrition Examination Survey (NHANES) 2007-2014 was enrolled (N = 4428). Developmental disorders (DDs) are defined as a positive answer to the question, "Does your child receive special education or early intervention services?" Serum cotinine and urinary 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanol (NNAL) were utilized as acute and chronic exposure biomarkers of ETS, respectively. Participants with serum cotinine >0.015 ng/mL were considered as with acute ETS exposure, and participants with creatinine-adjusted NNAL >0.0006 ng/mL were considered as with chronic ETS exposure. A survey logistic regression model was used to estimate the association between ETS exposure biomarkers and DDs. Additive interaction was utilized to examine the interaction of gender and biomarkers of ETS. Overall, approximately 9% of children were defined as DDs, and 65% of children had serum cotinine and urinary NNAL levels above the limit of detection. In the adjusted models, the association of ETS exposure biomarkers with DDs was only observed in girls. Girls with low cotinine levels and high urinary NNAL levels had 2.074 (95% CI: 1.012-4.247) and 1.851 (95% CI: 1.049-3.265) times higher odds of being DDs than those without ETS exposure, respectively. However, the effects of boys and NNAL exposure on DDs have additively interacted. Our findings first provided strong evidence for gender differences in the association between two tobacco metabolites and DDs in children, disclosing the public health implications and economic burdens of environmental tobacco smoke exposure.

Building a predictive model to identify clinical indicators for COVID-19 using machine learning method

Although some studies tried to identify risk factors for COVID-19, the evidence comparing COVID-19 and community-acquired pneumonia (CAP) is inconclusive, and CAP is the most common pneumonia with similar symptoms as COVID-19. We conducted a case-control study with 35 routine-collected clinical indicators and demographic factors to identify predictors for COVID-19 with CAP as controls. We randomly split the dataset into a training set (70%) and testing set (30%). We built Explainable Boosting Machine to select the important factors and built a decision tree on selected variables to interpret their relationships. The top five individual predictors of COVID-19 are albumin, total bilirubin, monocyte count, alanine aminotransferase, and percentage of monocyte with the importance scores ranging from 0.078 to 0.567. The top systematic predictors for COVID-19 are liver function, monocyte increasing, plasma protein, granulocyte, and renal function (importance scores ranging 0.009-0.096). We identified five combinations of important indicators to screen COVID-19 patients from CAP patients with differentiating abilities ranging 83.3-100%. An online predictive tool for our model was published. Certain clinical indicators collected routinely from most hospitals could help screen and distinguish COVID-19 from CAP. While further verification is needed, our findings and predictive tool could help screen suspected COVID-19 cases.