Prediction models for childhood asthma: A systematic review

Risk factors and predictors of venous thromboembolism in patients with acute spontaneous intracerebral hemorrhage: A systematic review and meta-analysis

BACKGROUND

Venous thromboembolism (VTE), including deep vein thrombosis (DVT) and pulmonary embolism (PE), is a common and preventable complication of patients with acute spontaneous intracerebral hemorrhages (ICH). Knowledge of VTE risk factors in patients with acute spontaneous ICH continues to evolve while remains controversial. Therefore, this study aims to summarize the risk factors and predictors of VTE in patients with acute spontaneous ICH.

METHODS

EMBASE, PubMed, Web of Science and Cochrane databases were searched for articles containing Mesh words "Cerebral hemorrhage" and "Venous thromboembolism." Eligibility screening, data extraction, and quality assessment of the retrieved articles were conducted independently by two reviewers. We performed meta-analysis to determine risk factors for the development of VTE in acute spontaneous ICH patients. Sensitivity analysis were performed to explore the sources of heterogeneity.

RESULTS

Of the 12,362 articles retrieved, 17 cohort studies were included.Meta-analysis showed that longer hospital stay [OR=15.46, 95 % CI (12.54, 18.39), P<0.00001], infection [OR=5.59, 95 % CI (1.53, 20.42), P=0.009], intubation [OR=4.32, 95 % CI (2.79, 6.69), P<0.00001] and presence of intraventricular hemorrhage (IVH) [OR=1.89, 95 % CI (1.50, 2.38), P<0.00001] were significant risk factors for VTE in acute spontaneous ICH patients. Of the 17 studies included, five studies reported six prediction models, including 15 predictors. The area under the receiver operating curve (AUC) ranged from 0.71 to 0.95. One of the models was externally validated.

CONCLUSION

Infection, the intubation, presence of IVH and longer hospital stay were risk factors for the development of VTE in acute spontaneous ICH patients. Prediction models of VTE based on acute spontaneous ICH patients have been poorly reported and more research will be needed before such models can be applied in clinical settings.

Early prediction of pediatric asthma in the Canadian Healthy Infant Longitudinal Development (CHILD) birth cohort using machine learning

BACKGROUND

Early identification of children at risk of asthma can have significant clinical implications for effective intervention and treatment. This study aims to disentangle the relative timing and importance of early markers of asthma.

METHODS

Using the CHILD Cohort Study, 132 variables measured in 1754 multi-ethnic children were included in the analysis for asthma prediction. Data up to 4 years of age was used in multiple machine learning models to predict physician-diagnosed asthma at age 5 years. Both predictive performance and variable importance was assessed in these models.

RESULTS

Early-life data (≤1 year) has limited predictive ability for physician-diagnosed asthma at age 5 years (area under the precision-recall curve (AUPRC) < 0.35). The earliest reliable prediction of asthma is achieved at age 3 years, (area under the receiver-operator curve (AUROC) > 0.90) and (AUPRC > 0.80). Maternal asthma, antibiotic exposure, and lower respiratory tract infections remained highly predictive throughout childhood. Wheezing status and atopy are the most important predictors of early childhood asthma from among the factors included in this study.

CONCLUSIONS

Childhood asthma is predictable from non-biological measurements from the age of 3 years, primarily using parental asthma and patient history of wheezing, atopy, antibiotic exposure, and lower respiratory tract infections.

IMPACT

Machine learning models can predict physician-diagnosed asthma in early childhood (AUROC > 0.90 and AUPRC > 0.80) using ≥3 years of non-biological and non-genetic information, whereas prediction with the same patient information available before 1 year of age is challenging. Wheezing, atopy, antibiotic exposure, lower respiratory tract infections, and the child's mother having asthma were the strongest early markers of 5-year asthma diagnosis, suggesting an opportunity for earlier diagnosis and intervention and focused assessment of patients at risk for asthma, with an evolving risk stratification over time.

Acoustic biomarkers in asthma: a systematic review

OBJECTIVE

Current monitoring methods of asthma, such as peak expiratory flow testing, have important limitations. The emergence of automated acoustic sound analysis, capturing cough, wheeze, and inhaler use, offers a promising avenue for improving asthma diagnosis and monitoring. This systematic review evaluated the validity of acoustic biomarkers in supporting the diagnosis of asthma and its monitoring.

DATA SOURCES

A search was performed using two databases (PubMed and Embase) for all relevant studies published before November 2023.

STUDY SELECTION

27 studies were included for analysis. Eligible studies focused on acoustic signals as digital biomarkers in asthma, utilizing recording devices to register or analyze sound.

RESULTS

Various respiratory acoustic signal types were analyzed, with cough and wheeze being predominant. Data collection methods included smartphones, custom sensors and digital stethoscopes. Across all studies, automated acoustic algorithms achieved average accuracy of cough and wheeze detection of 88.7% (range: 61.0 - 100.0%) with a median of 92.0%. The sensitivity of sound detection ranged from 54.0 to 100.0%, with a median of 90.3%; specificity ranged from 67.0 to 99.7%, with a median of 95.0%. Moreover, 70.4% (19/27) studies had a risk of bias identified.

CONCLUSIONS

This systematic review establishes the promising role of acoustic biomarkers, particularly cough and wheeze, in supporting the diagnosis of asthma and monitoring. The evidence suggests the potential for clinical integration of acoustic biomarkers, emphasizing the need for further validation in larger, clinically-diverse populations.

An integrated molecular risk score early in life for subsequent childhood asthma risk

BACKGROUND

Numerous children present with early wheeze symptoms, yet solely a subgroup develops childhood asthma. Early identification of children at risk is key for clinical monitoring, timely patient-tailored treatment, and preventing chronic, severe sequelae. For early prediction of childhood asthma, we aimed to define an integrated risk score combining established risk factors with genome-wide molecular markers at birth, complemented by subsequent clinical symptoms/diagnoses (wheezing, atopic dermatitis, food allergy).

METHODS

Three longitudinal birth cohorts (PAULINA/PAULCHEN, n = 190 + 93 = 283, PASTURE, n = 1133) were used to predict childhood asthma (age 5-11) including epidemiological characteristics and molecular markers: genotype, DNA methylation and mRNA expression (RNASeq/NanoString). Apparent (ap) and optimism-corrected (oc) performance (AUC/R2) was assessed leveraging evidence from independent studies (Naïve-Bayes approach) combined with high-dimensional logistic regression models (LASSO).

RESULTS

Asthma prediction with epidemiological characteristics at birth (maternal asthma, sex, farm environment) yielded an ocAUC = 0.65. Inclusion of molecular markers as predictors resulted in an improvement in apparent prediction performance, however, for optimism-corrected performance only a moderate increase was observed (upto ocAUC = 0.68). The greatest discriminate power was reached by adding the first symptoms/diagnosis (up to ocAUC = 0.76; increase of 0.08, p = .002). Longitudinal analysis of selected mRNA expression in PASTURE (cord blood, 1, 4.5, 6 years) showed that expression at age six had the strongest association with asthma and correlation of genes getting larger over time (r = .59, p < .001, 4.5-6 years).

CONCLUSION

Applying epidemiological predictors alone showed moderate predictive abilities. Molecular markers from birth modestly improved prediction. Allergic symptoms/diagnoses enhanced the power of prediction, which is important for clinical practice and for the design of future studies with molecular markers.

Emergency management and asthma risk in young Medicaid-enrolled children with recurrent wheeze

OBJECTIVES

To describe clinical characteristics of young children presenting to the emergency department (ED) for early recurrent wheeze, and determine factors associated with subsequent persistent wheeze and risk for early childhood asthma.

METHODS

Retrospective cohort study of Medicaid-enrolled children 0-3 years old with an index ED visit for wheeze (e.g. bronchiolitis, reactive airway disease) from 2009 to 2013, and at least one prior documented episode of wheeze at an ED or primary care visit. The primary outcome was persistent wheeze between 4 and 6 years of age. Demographics and clinical characteristics were collected from the index ED visit. Logistic regression was used to estimate the association between potential risk factors and subsequent persistent wheeze.

RESULTS

During the study period, 41,710 children presented to the ED for recurrent wheeze. Mean age was 1.3 years; 59% were male, 42% Black, and 6% Hispanic. At index ED visits, the most common diagnosis was acute bronchiolitis (40%); 77% of children received an oral corticosteroid prescription. Between 4 and 6 years of age, 11,708 (28%) children had persistent wheeze. A greater number of wheezing episodes was associated with an increased odds of ED treatment with asthma medications. Subsequent persistent wheeze was associated with male sex, Black race, atopy, prescription for bronchodilators or corticosteroids, and greater number of visits for wheeze.

CONCLUSIONS

Young children with persistent wheeze are at risk for childhood asthma. Thus, identification of risk factors associated with persistent wheeze in young children with recurrent wheeze might aid in early detection of asthma and initiation of preventative therapies.

Asthma prediction via affinity graph enhanced classifier: a machine learning approach based on routine blood biomarkers

BACKGROUND

Asthma is a chronic respiratory disease affecting millions of people worldwide, but early detection can be challenging due to the time-consuming nature of the traditional technique. Machine learning has shown great potential in the prompt prediction of asthma. However, because of the inherent complexity of asthma-related patterns, current models often fail to capture the correlation between data samples, limiting their accuracy. Our objective was to use our novel model to address the above problem via an Affinity Graph Enhanced Classifier (AGEC) to improve predictive accuracy.

METHODS

The clinical dataset used in this study consisted of 152 samples, where 24 routine blood markers were extracted as features to participate in the classification due to their ease of sourcing and relevance to asthma. Specifically, our model begins by constructing a projection matrix to reduce the dimensionality of the feature space while preserving the most discriminative features. Simultaneously, an affinity graph is learned through the resulting subspace to capture the internal relationship between samples better. Leveraging domain knowledge from the affinity graph, a new classifier (AGEC) is introduced for asthma prediction. AGEC's performance was compared with five state-of-the-art predictive models.

RESULTS

Experimental findings reveal the superior predictive capabilities of AGEC in asthma prediction. AGEC achieved an accuracy of 72.50%, surpassing FWAdaBoost (61.02%), MLFE (60.98%), SVR (64.01%), SVM (69.80%) and ERM (68.40%). These results provide evidence that capturing the correlation between samples can enhance the accuracy of asthma prediction. Moreover, the obtained [Formula: see text] values also suggest that the differences between our model and other models are statistically significant, and the effect of our model does not exist by chance.

CONCLUSION

As observed from the experimental results, advanced statistical machine learning approaches such as AGEC can enable accurate diagnosis of asthma. This finding holds promising implications for improving asthma management.

Genetics of preschool wheeze and its progression to childhood asthma

Wheezing is a common and heterogeneous condition in preschool children. In some countries, the prevalence can be as high as 30% and up to 50% of all children experience wheezing before the age of 6. Asthma often starts with preschool wheeze, but not all wheezing children will develop asthma at school age. At this moment, it is not possible to accurately predict which wheezing children will develop asthma. Recently, studying the genetics of wheeze and the childhood-onset of asthma have grown in interest. Childhood-onset asthma has a stronger heritability in comparison with adult-onset asthma. In early childhood asthma exacerbations, CDHR3, which encodes the receptor for Rhinovirus C, was identified, as well as IL33, and the 17q locus that includes GSDMB and ORMDL3 genes. The 17q locus is the strongest wheeze and childhood-onset asthma locus, and was shown to interact with many environmental factors, including smoking and infections. Finally, ANXA1 was recently associated with early-onset, persistent wheeze. ANXA1 may help resolve eosinophilic inflammation. Overall, despite its complexities, genetic approaches to unravel the early-onset of wheeze and asthma are promising, since these shed more light on mechanisms of childhood asthma-onset. Implicated genes point toward airway epithelium and its response to external factors, such as viral infections. However, the heterogeneity of wheeze phenotypes complicates genetic studies. It is therefore important to define accurate wheezing phenotypes and forge larger international collaborations to gain a better understanding of the pathways underlying early-onset asthma.

Epigenetics, hypersensibility and asthma: what do we know so far?

In this review, we describe recent advances in understanding the relationship between epigenetic changes, especially DNA methylation (DNAm), with hypersensitivity and respiratory disorders such as asthma in childhood. It is clearly described that epigenetic mechanisms can induce short to long-term changes in cells, tissues, and organs. Through the growing number of studies on the Origins of Health Development and Diseases, more and more data exist on how environmental and genomic aspects in early life can induce allergies and asthma. The lack of biomarkers, standardized assays, and access to more accessible tools for data collection and analysis are still a challenge for future studies. Through this review, the authors draw a panorama with the available information that can assist in the establishment of an epigenetic approach for the risk analysis of these pathologies.

Sociome Data Commons: A scalable and sustainable platform for investigating the full social context and determinants of health

Background/Objective

Non-clinical aspects of life, such as social, environmental, behavioral, psychological, and economic factors, what we call the sociome, play significant roles in shaping patient health and health outcomes. This paper introduces the Sociome Data Commons (SDC), a new research platform that enables large-scale data analysis for investigating such factors.

Methods

This platform focuses on "hyper-local" data, i.e., at the neighborhood or point level, a geospatial scale of data not adequately considered in existing tools and projects. We enumerate key insights gained regarding data quality standards, data governance, and organizational structure for long-term project sustainability. A pilot use case investigating sociome factors associated with asthma exacerbations in children residing on the South Side of Chicago used machine learning and six SDC datasets.

Results

The pilot use case reveals one dominant spatial cluster for asthma exacerbations and important roles of housing conditions and cost, proximity to Superfund pollution sites, urban flooding, violent crime, lack of insurance, and a poverty index.

Conclusion

The SDC has been purposefully designed to support and encourage extension of the platform into new data sets as well as the continued development, refinement, and adoption of standards for dataset quality, dataset inclusion, metadata annotation, and data access/governance. The asthma pilot has served as the first driver use case and demonstrates promise for future investigation into the sociome and clinical outcomes. Additional projects will be selected, in part for their ability to exercise and grow the capacity of the SDC to meet its ambitious goals.

Prediction of adult asthma risk in early childhood using novel adult asthma predictive risk scores

BACKGROUND

Numerous risk scores have been developed to predict childhood asthma. However, they may not predict asthma beyond childhood. We aim to create childhood risk scores that predict development and persistence of asthma up to young adult life.

METHODS

The Isle of Wight Birth Cohort (n = 1456) was prospectively assessed up to 26 years of age. Asthma predictive scores were developed based on factors during the first 4 years, using logistic regression and tested for sensitivity, specificity and area under the curve (AUC) for prediction of asthma at (i) 18 and (ii) 26 years, and persistent asthma (PA) (iii) at 10 and 18 years, and (iv) at 10, 18 and 26 years. Models were internally and externally validated.

RESULTS

Four models were generated for prediction of each asthma outcome. ASthma PredIctive Risk scorE (ASPIRE)-1: a 2-factor model (recurrent wheeze [RW] and positive skin prick test [+SPT] at 4 years) for asthma at 18 years (sensitivity: 0.49, specificity: 0.80, AUC: 0.65). ASPIRE-2: a 3-factor model (RW, +SPT and maternal rhinitis) for asthma at 26 years (sensitivity: 0.60, specificity: 0.79, AUC: 0.73). ASPIRE-3: a 3-factor model (RW, +SPT and eczema at 4 years) for PA-18 (sensitivity: 0.63, specificity: 0.87, AUC: 0.77). ASPIRE-4: a 3-factor model (RW, +SPT at 4 years and recurrent chest infection at 2 years) for PA-26 (sensitivity: 0.68, specificity: 0.87, AUC: 0.80). ASPIRE-1 and ASPIRE-3 scores were replicated externally. Further assessments indicated that ASPIRE-1 can be used in place of ASPIRE-2-4 with same predictive accuracy.

CONCLUSION

ASPIRE predicts persistent asthma up to young adult life.

Performance of the Pediatric Asthma Risk Score across Diverse Populations

BACKGROUND: Methods to determine whether a toddler is likely to develop asthma are of value to parents and clinical trialists testing primary prevention strategies. The Pediatric Asthma Risk Score (PARS) is a 14-point score of six factors designed to predict asthma in early life. PARS was developed and validated in relatively homogenous populations, so its generalizability is unknown. METHODS: We computed PARS using the six factors of self-declared race (parent-reported as “Black” or “not Black”), parental asthma, eczema, any wheezing, wheezing without a cold, and polysensitization in 5634 children from birth to 3 years of age. The primary outcome of our analysis was the ability of PARS to predict asthma development at 5 to 10 years of age using the area under the receiver operating curve in each cohort and across all cohorts with varying ethnicity, sex, cohort type, birth decades, missing PARS factors, and polysensitization definition. We also performed a meta-analysis across all the cohorts. Finally, we compared PARS predictive ability with the binary Asthma Predictive Index (API). RESULTS: Across 10 cohorts, the area under the receiver operating curve for PARS was 0.76. PARS performance did not differ by ethnicity, sex, cohort type, enrollment decade, missing PARS factors, or polysensitization definition (all P>0.05). The weights of each factor in the meta-analysis were similar to the original PARS weights. PARS and API equally identified children at high risk for developing asthma or not; API missed 31% of children at moderate asthma risk. CONCLUSIONS: PARS provided robust estimates of asthma risk in children from a wide range of ethnicities, backgrounds, and susceptibility. (Funded by the National Institute of Allergy and Infectious Diseases and others.)

Developing a prediction model of children asthma risk using population-based family history health records

BACKGROUND

Identifying children at high risk of developing asthma can facilitate prevention and early management strategies. We developed a prediction model of children's asthma risk using objectively collected population-based children and parental histories of comorbidities.

METHODS

We conducted a retrospective population-based cohort study using administrative data from Manitoba, Canada, and included children born from 1974 to 2000 with linkages to ≥1 parent. We identified asthma and prior comorbid condition diagnoses from hospital and outpatient records. We used two machine-learning models: least absolute shrinkage and selection operator (LASSO) logistic regression (LR) and random forest (RF) to identify important predictors. The predictors in the base model included children's demographics, allergic conditions, respiratory infections, and parental asthma. Subsequent models included additional multiple comorbidities for children and parents.

RESULTS

The cohort included 195,666 children: 51.3% were males and 17.7% had asthma diagnosis. The base LR model achieved a low predictive performance with sensitivity of 0.47, 95% confidence interval (0.45-0.48), and specificity of 0.67 (0.66-0.67) using a predicted probability threshold of 0.20. Sensitivity significantly improved when children's comorbidities were included using LASSO LR: 0.71 (0.69-0.72). Predictive performance further improved by including parental comorbidities (sensitivity = 0.72 [0.70-0.73], specificity = 0.69 [0.69-0.70]). We observed similar results for the RF models. Children's menstrual disorders and mood and anxiety disorders, parental lipid metabolism disorders and asthma were among the most important variables that predicted asthma risk.

CONCLUSION

Including children and parental comorbidities to children's asthma prediction models improves their accuracy.

Early Prediction of Asthma

The clinical manifestations of asthma in children are highly variable, are associated with different molecular and cellular mechanisms, and are characterized by common symptoms that may diversify in frequency and intensity throughout life. It is a disease that generally begins in the first five years of life, and it is essential to promptly identify patients at high risk of developing asthma by using different prediction models. The aim of this review regarding the early prediction of asthma is to summarize predictive factors for the course of asthma, including lung function, allergic comorbidity, and relevant data from the patient's medical history, among other factors. This review also highlights the epigenetic factors that are involved, such as DNA methylation and asthma risk, microRNA expression, and histone modification. The different tools that have been developed in recent years for use in asthma prediction, including machine learning approaches, are presented and compared. In this review, emphasis is placed on molecular mechanisms and biomarkers that can be used as predictors of asthma in children.

The ADEM2 project: early pathogenic mechanisms of preschool wheeze and a randomised controlled trial assessing the gain in health and cost-effectiveness by application of the breath test for the diagnosis of asthma in wheezing preschool children

BACKGROUND

The prevalence of asthma-like symptoms in preschool children is high. Despite numerous efforts, there still is no clinically available diagnostic tool to discriminate asthmatic children from children with transient wheeze at preschool age. This leads to potential overtreatment of children outgrowing their symptoms, and to potential undertreatment of children who turn out to have asthma. Our research group developed a breath test (using GC-tof-MS for VOC-analysis in exhaled breath) that is able to predict a diagnosis of asthma at preschool age. The ADEM2 study assesses the improvement in health gain and costs of care with the application of this breath test in wheezing preschool children.

METHODS

This study is a combination of a multi-centre, parallel group, two arm, randomised controlled trial and a multi-centre longitudinal observational cohort study. The preschool children randomised into the treatment arm of the RCT receive a probability diagnosis (and corresponding treatment recommendations) of either asthma or transient wheeze based on the exhaled breath test. Children in the usual care arm do not receive a probability diagnosis. Participants are longitudinally followed up until the age of 6 years. The primary outcome is disease control after 1 and 2 years of follow-up. Participants of the RCT, together with a group of healthy preschool children, also contribute to the parallel observational cohort study developed to assess the validity of alternative VOC-sensing techniques and to explore numerous other potential discriminating biological parameters (such as allergic sensitisation, immunological markers, epigenetics, transcriptomics, microbiomics) and the subsequent identification of underlying disease pathways and relation to the discriminative VOCs in exhaled breath.

DISCUSSION

The potential societal and clinical impact of the diagnostic tool for wheezing preschool children is substantial. By means of the breath test, it will become possible to deliver customized and high qualitative care to the large group of vulnerable preschool children with asthma-like symptoms. By applying a multi-omics approach to an extensive set of biological parameters we aim to explore (new) pathogenic mechanisms in the early development of asthma, creating potentially interesting targets for the development of new therapies.

TRIAL REGISTRATION

Netherlands Trial Register, NL7336, Date registered 11-10-2018.

Development and validation of a prediction model to predict school-age asthma in preschool children

OBJECTIVE

To develop and validate a clinical prediction model to identify school-age asthma in preschool asthmatic children.

STUDY DESIGN

In this retrospective prognosis cohort study, asthmatic children aged 3-5 years were enrolled with at least 2 years of follow-up, and their potential variables at baseline and the prognosis of school-age asthma were collected from medical records. A clinical prediction model was developed using Logistic regression. The performance of prediction model was assessed and quantified by discrimination of the area under the receiver operating characteristic curve (AUC) and calibration of Brier score. The model was validated by the temporal-validation method.

RESULTS

In the development dataset, 2748 preschool asthmatic children were included for model development, and 883 (32.13%) children were translated to school-age asthma. The independent prognostic variables with an increased risk for school-age asthma were used to develop the prediction model, including: age, parental asthma, early frequent wheezing, allergic rhinitis, eczema, allergic conjunctivitis, obesity, and aeroallergen of dust mite. While assessing model performance, the discrimination power of AUC was moderate [0.788 (0.770-0.805)] with sensitivity (81.5%) and specificity (60.9%), and the calibration of Brier score was 0.169, supporting the calibration ability. In the temporal-validation dataset of 583 preschool asthmatic children, our model showed satisfactory discrimination (AUC 0.818) and calibration (Brier score 0.150). The prediction model was presented by the web-based calculator (https://casthma.shinyapps.io/dynnomapp/) and a nomogram for clinical application.

CONCLUSION

In preschool asthmatic children, our prediction model could be used to predict the risk of school-age asthma.

Network analyses of upper and lower airway transcriptomes identify shared mechanisms among children with recurrent wheezing and school-age asthma

Background

Predicting which preschool children with recurrent wheezing (RW) will develop school-age asthma (SA) is difficult, highlighting the critical need to clarify the pathogenesis of RW and the mechanistic relationship between RW and SA. Despite shared environmental exposures and genetic determinants, RW and SA are usually studied in isolation. Based on network analysis of nasal and tracheal transcriptomes, we aimed to identify convergent transcriptomic mechanisms in RW and SA.

Methods

RNA-sequencing data from nasal and tracheal brushing samples were acquired from the Gene Expression Omnibus. Combined with single-cell transcriptome data, cell deconvolution was used to infer the composition of 18 cellular components within the airway. Consensus weighted gene co-expression network analysis was performed to identify consensus modules closely related to both RW and SA. Shared pathways underlying consensus modules between RW and SA were explored by enrichment analysis. Hub genes between RW and SA were identified using machine learning strategies and validated using external datasets and quantitative reverse transcription-polymerase chain reaction (qRT-PCR). Finally, the potential value of hub genes in defining RW subsets was determined using nasal and tracheal transcriptome data.

Results

Co-expression network analysis revealed similarities in the transcriptional networks of RW and SA in the upper and lower airways. Cell deconvolution analysis revealed an increase in mast cell fraction but decrease in club cell fraction in both RW and SA airways compared to controls. Consensus network analysis identified two consensus modules highly associated with both RW and SA. Enrichment analysis of the two consensus modules indicated that fatty acid metabolism-related pathways were shared key signals between RW and SA. Furthermore, machine learning strategies identified five hub genes, i.e., CST1, CST2, CST4, POSTN, and NRTK2, with the up-regulated hub genes in RW and SA validated using three independent external datasets and qRT-PCR. The gene signatures of the five hub genes could potentially be used to determine type 2 (T2)-high and T2-low subsets in preschoolers with RW.

Conclusions

These findings improve our understanding of the molecular pathogenesis of RW and provide a rationale for future exploration of the mechanistic relationship between RW and SA.

The use of machine learning and artificial intelligence within pediatric critical care

The field of pediatric critical care has been hampered in the era of precision medicine by our inability to accurately define and subclassify disease phenotypes. This has been caused by heterogeneity across age groups that further challenges the ability to perform randomized controlled trials in pediatrics. One approach to overcome these inherent challenges include the use of machine learning algorithms that can assist in generating more meaningful interpretations from clinical data. This review summarizes machine learning and artificial intelligence techniques that are currently in use for clinical data modeling with relevance to pediatric critical care. Focus has been placed on the differences between techniques and the role of each in the clinical arena. The various forms of clinical decision support that utilize machine learning are also described. We review the applications and limitations of machine learning techniques to empower clinicians to make informed decisions at the bedside. IMPACT: Critical care units generate large amounts of under-utilized data that can be processed through artificial intelligence. This review summarizes the machine learning and artificial intelligence techniques currently being used to process clinical data. The review highlights the applications and limitations of these techniques within a clinical context to aid providers in making more informed decisions at the bedside.

Diagnosis and management of asthma in infants and preschoolers

Asthma is one of the most common chronic disease affecting children, and it often starts in infancy and preschool years. In previous birth cohorts, frequent wheezing in early life was associated with the development of asthma in later childhood and reduced lung function persisting into adulthood. Preschool wheezing is considered an umbrella term for distinctive diseases with different clinical features (phenotypes), each of which may be related to different underlying pathophysiologic mechanisms (endotypes). The classification of phenotypes of early wheezing is needed to identify children at high risk for developing asthma later who might benefit from early intervention. However, diagnosis of asthma in infants and preschoolers is particularly difficult because objective lung function tests cannot be performed and definitive biomarkers are lacking. Moreover, management of early asthma is challenging because of its different phenotypic presentations. Many prediction models and asthma guidelines have been developed to provide useful information for physicians to assess young children with recurrent wheezing and manage them appropriately. Many recent studies have investigated the application of personalized medicine for early asthma by identifying specific phenotypes and biomarkers. Further researches, including genetic and molecular studies, are needed to establish a clear definition of asthma and develop more targeted therapeutic approaches in this age group.

Predicting the course of asthma from childhood until early adulthood

PURPOSE OF REVIEW

To communicate recent insights about the natural history of childhood asthma, with a focus on prediction of persistence and remission of childhood asthma, up to early adulthood.

RECENT FINDINGS

Lung function around the age of 8-9 years is the strongest predictor: obstructive lung function predicts asthma persistence up to early adulthood, whereas normal lung function predicts remission. The ability to predict asthma remission improves when lung function is combined with blood eosinophil levels and degree of bronchial hyperresponsiveness. Interventions, such as inhaled corticosteroids and immunotherapy do not appear to alter the course of asthma. Epigenetic studies have revealed potential novel biomarkers of asthma remission, such as micro-RNA patterns in blood. Specifically, lower serum levels of mi-R221-5p, which is associated with lower IL-6 release and eosinophilic inflammation, predict remission. Higher levels of blood DNA-methylation of a CpG site in Peroxisomal Biogenesis Factor 11 Beta were associated with asthma remission.

SUMMARY

Lung function, allergic comorbidity and polysensitization in childhood predict the course of asthma. Recent epigenetic studies have provided a better understanding of underlying pathological processes in asthma remission, which may be used to improve prediction or develop novel treatments aimed at altering the course of asthma.

Effect Evaluation of Electronic Health PDCA Nursing in Treatment of Childhood Asthma with Artificial Intelligence

Asthma in children has a long duration and is prone to recurring attacks. Children will feel chest tightness, shortness of breath, cough, and difficulty breathing when they are onset, which has a serious impact on their health. Clinical nursing is of great significance in the treatment of childhood asthma. At present, the electronic health PDCA nursing model is widely used in clinical nursing as a common and effective nursing method. Therefore, it is very important to evaluate the efficacy of the PDCA nursing model in the treatment of childhood asthma. With the development of artificial intelligence, artificial intelligence can be used to evaluate the effect of the PDCA nursing model in the treatment of childhood asthma. The BP network can effectively perform data training and discrimination, but its training efficiency is low, and it is easily affected by initial weights and thresholds. Aiming at this defect, this work uses the genetic simulated annealing (GSA) algorithm to improve it. In view of the problems that the genetic algorithm falls into local minimum and simulated annealing algorithm has a slow convergence speed, the improved genetic simulated annealing algorithm is used to optimize the BP neural network, and an improved genetic simulated annealing BP network (IGSA-BP) is proposed. The algorithm not only reduces the problem that the BP network has an influence on initial weight and threshold on the algorithm but also improves the population diversity and avoids falling into local optimum by improving the crossover and mutation probability formula and improving Metropolis criterion. The proposed method has more efficient performance.

Does machine learning have a role in the prediction of asthma in children?

Asthma is the most common chronic lung disease in childhood. There has been a significant worldwide effort to develop tools/methods to identify children's risk for asthma as early as possible for preventative and early management strategies. Unfortunately, most childhood asthma prediction tools using conventional statistical models have modest accuracy, sensitivity, and positive predictive value. Machine learning is an approach that may improve on conventional models by finding patterns and trends from large and complex datasets. Thus far, few studies have utilized machine learning to predict asthma in children. This review aims to critically assess these studies, describe their limitations, and discuss future directions to move from proof-of-concept to clinical application.

Persistence of parental-reported asthma at early ages: A longitudinal twin study

BACKGROUND

Currently, we cannot predict whether a pre-school child with asthma-like symptoms will have asthma at school age. Whether genetic information can help in this prediction depends on the role of genetic factors in persistence of pre-school to school-age asthma. We examined to what extent genetic and environmental factors contribute to persistence of asthma-like symptoms at ages 3 to asthma at age 7 using a bivariate genetic model for longitudinal twin data.

METHODS

We performed a cohort study in monozygotic and dizygotic twins from the Netherlands Twin Register (NTR, n = 21,541 twin pairs). Bivariate genetic models were fitted to longitudinal data on asthma-like symptoms reported by parents at age 3 and 7 years to estimate the contribution of genetic and environmental factors.

RESULTS

Bivariate genetic modeling showed a correlation on the liability scale between asthma-like symptoms at age 3 and asthma at age 7 of 0.746 and the contribution of genetics was estimated to be 0.917. The genetic analyses indicated a substantial influence of genetic factors on asthma-like symptoms at ages 3 and 7 (heritability 80% and 90%, respectively); hence, contribution of environmental factors was low. Persistence was explained by a high (rg = 0.807) genetic correlation.

CONCLUSION

Parental-reported asthma-like symptoms at age 3 and asthma at age 7 are highly heritably. The phenotype of asthma-like symptoms at age 3 and 7 was highly correlated and mainly due to heritable factors, indicating high persistence of asthma development over ages 3 and 7.

Integration of Genomic Risk Scores to Improve the Prediction of Childhood Asthma Diagnosis

Genome-wide and epigenome-wide association studies have identified genetic variants and differentially methylated nucleotides associated with childhood asthma. Incorporation of such genomic data may improve performance of childhood asthma prediction models which use phenotypic and environmental data. Using genome-wide genotype and methylation data at birth from the Isle of Wight Birth Cohort (n = 1456), a polygenic risk score (PRS), and newborn (nMRS) and childhood (cMRS) methylation risk scores, were developed to predict childhood asthma diagnosis. Each risk score was integrated with two previously published childhood asthma prediction models (CAPE and CAPP) and were validated in the Manchester Asthma and Allergy Study. Individually, the genomic risk scores demonstrated modest-to-moderate discriminative performance (area under the receiver operating characteristic curve, AUC: PRS = 0.64, nMRS = 0.55, cMRS = 0.54), and their integration only marginally improved the performance of the CAPE (AUC: 0.75 vs. 0.71) and CAPP models (AUC: 0.84 vs. 0.82). The limited predictive performance of each genomic risk score individually and their inability to substantially improve upon the performance of the CAPE and CAPP models suggests that genetic and epigenetic predictors of the broad phenotype of asthma are unlikely to have clinical utility. Hence, further studies predicting specific asthma endotypes are warranted.

Development of childhood asthma prediction models using machine learning approaches

BACKGROUND

Respiratory symptoms are common in early life and often transient. It is difficult to identify in which children these will persist and result in asthma. Machine learning (ML) approaches have the potential for better predictive performance and generalisability over existing childhood asthma prediction models. This study applied ML approaches to predict school-age asthma (age 10) in early life (Childhood Asthma Prediction in Early life, CAPE model) and at preschool age (Childhood Asthma Prediction at Preschool age, CAPP model).

METHODS

Clinical and environmental exposure data was collected from children enrolled in the Isle of Wight Birth Cohort (N = 1368, ∼15% asthma prevalence). Recursive Feature Elimination (RFE) identified an optimal subset of features predictive of school-age asthma for each model. Seven state-of-the-art ML classification algorithms were used to develop prognostic models. Training was performed by applying fivefold cross-validation, imputation, and resampling. Predictive performance was evaluated on the test set. Models were further externally validated in the Manchester Asthma and Allergy Study (MAAS) cohort.

RESULTS

RFE identified eight and twelve predictors for the CAPE and CAPP models, respectively. Support Vector Machine (SVM) algorithms provided the best performance for both the CAPE (area under the receiver operating characteristic curve, AUC = 0.71) and CAPP (AUC = 0.82) models. Both models demonstrated good generalisability in MAAS (CAPE 8-year = 0.71, 11-year = 0.71, CAPP 8-year = 0.83, 11-year = 0.79) and excellent sensitivity to predict a subgroup of persistent wheezers.

CONCLUSION

Using ML approaches improved upon the predictive performance of existing regression-based models, with good generalisability and ability to rule in asthma and predict persistent wheeze.

Performance of Three Asthma Predictive Tools in a Cohort of Infants Hospitalized With Severe Bronchiolitis

Childhood asthma develops in 30–40% of children with severe bronchiolitis but accurate prediction remains challenging. In a severe bronchiolitis cohort, we applied the Asthma Predictive Index (API), the modified Asthma Predictive Index (mAPI), and the Pediatric Asthma Risk Score (PARS) to predict asthma at age 5 years. We applied the API, mAPI, and PARS to the 17-center cohort of infants hospitalized with severe bronchiolitis during 2011–2014 (35th Multicenter Airway Research Collaboration, MARC-35). We used data from the first 3 years of life including parent interviews, chart review, and specific IgE testing to predict asthma at age 5 years, defined as parent report of clinician-diagnosed asthma. Among 875/921 (95%) children with outcome data, parent-reported asthma was 294/875 (34%). In MARC-35, a positive index/score for stringent and loose API, mAPI, and PARS were 24, 68, 6, and 55%, respectively. The prediction tools' AUCs (95%CI) ranged from 0.57 (95%CI 0.54–0.59) to 0.68 (95%CI 0.65–0.71). The positive likelihood ratios were lower in MARC-35 compared to the published results from the original cohorts. In this high-risk population of infants hospitalized with severe bronchiolitis, API, mAPI, and PARS had sub-optimal performance (AUC &lt;0.8). Highly accurate (AUC &gt;0.8) asthma prediction tools are desired in infants hospitalized with severe bronchiolitis.

Decision tree-based rules outperform risk scores for childhood asthma prognosis

BACKGROUND

There are no widely accepted prognostic tools for childhood asthma; this is in part due to the multifactorial and time-dependent nature of mechanisms and risk factors that contribute to asthma development. Our study objective was to develop and evaluate the prognostic performance of conditional inference decision tree-based rules using the Pediatric Asthma Risk Score (PARS) predictors as an alternative to the existing logistic regression-based risk score for childhood asthma prediction at 7 years in a high-risk population.

METHODS

The Canadian Asthma Primary Prevention Study data were used to develop, compare, and contrast the prognostic performance (area under the curve [AUC], sensitivity, and specificity) of conditional inference tree-based decision rules to the pediatric asthma risk score for the prediction of childhood asthma at 7 years.

RESULTS

Conditional inference decision tree-based rules have higher prognostic performance (AUC: 0.85; 95% CI: 0.81, 0.88; sensitivity = 47%; specificity = 93%) than the pediatric asthma risk score at an optimal cutoff of ≥6 (AUC: 0.71; 95% CI: 0.67, 0.76; sensitivity = 60%; specificity = 74%). Moreover, the pediatric asthma risk score is not linearly related to asthma risk, and at any given pediatric asthma risk score value, different combinations of its pediatric asthma risk score clinical variables differentially predict asthma risk.

CONCLUSION

Conditional inference tree-based decision rules could be a useful childhood asthma prognostic tool, providing an alternative way to identify unique subgroups of at-risk children, and insights into associations and effect mechanisms that are suggestive of appropriate tailored preventive interventions. However, the feasibility and effectiveness of such decision rules in clinical practice is warranted.

Association between maternal ritodrine hydrochloride administration during pregnancy and childhood wheezing up to three years of age: The Japan environment and children's study

BACKGROUND

The effects of maternal ritodrine hydrochloride administration (MRA) during pregnancy on fetuses and offspring are not entirely clear. The present study aimed to evaluate the association between MRA and childhood wheezing using data from a nationwide Japanese birth cohort study.

METHODS

This study analyzed the data of the participants enrolled in the Japan Environment and Children's Study, a nationwide prospective birth cohort study, between 2011 and 2014. Data of women with singleton live births after 22 weeks of gestation were analyzed. The participants were divided according to MRA status. Considering childhood factors affecting the incidence of wheezing, including smoking environment and childhood viral infections, a logistic regression model was used to calculate odds ratios for "wheezing ever," diagnosis of asthma in the last 12 months, and "asthma ever" in women with MRA, with women who did not receive MRA as the reference. Additionally, participants were stratified by term births, and odds ratios for outcomes were calculated using a logistic regression model.

RESULTS

A total of 68,123 participants were analyzed. The adjusted odds ratio for wheezing was 1.17 (95% confidence interval, 1.12-1.22). The adjusted odds ratios for the other outcomes did not significantly increase after adjusting for childhood factors. The same tendency was confirmed after excluding women with preterm births.

CONCLUSION

MRA was associated with a slightly increased incidence of childhood wheezing up to three years, irrespective of term or preterm birth status. It is important that perinatal physicians consider the potential effects of MRA on the offspring's childhood health.

The predictive role of small airway dysfunction and airway inflammation biomarkers for asthma in preschool and school-age children: a study protocol for a prospective cohort study

BACKGROUND

Preschool children are at a high risk of developing asthma. Asthma in preschool children could remit in most cases, but could persist into school age, adolescence, or even adulthood in some cases. However, it is difficult to predict which children with preschool asthma will develop into school-age asthma. We present a cohort study protocol to explore the predictive role of small airway dysfunction and airway inflammation biomarkers of asthma in preschool and school-age children.

METHODS

A prospective cohort study will be conducted with at least 205 children with preschool asthma. All patients will be recruited when they consult a pediatric pulmonologist at the Children's Hospital of Chongqing Medical University and will be followed up to 6 years of age. Initially, patients' demographic information, medical history, physical findings, and questionnaire information will be collected, and baseline small airway function and inflammation biomarkers will be detected. During the follow-up period, medical history, physical findings, and the questionnaire results will be collected every 3 months, and small airway function will be tested by impulse oscillometry (IOS) every 6 months. At the final visit, a definite diagnosis of school-age asthma will be made by a pediatric pulmonologist based on the criteria of the Global Initiative for Asthma 2020.

DISCUSSION

The study will be the first to be conducted in preschool children assessing whether small airway dysfunction combined with airway eosinophilic biomarkers and club cell secretory protein is associated with school-age asthma. This study may provide new promising predictors of persistent asthma from preschool to school age.

TRIAL REGISTRATION

The study has been registered at the Chinese Clinical Trial Registry (ChiCTR2000039583). Registered on November 1, 2020. Protocol version: version 1.0, August 16, 2021.

Application of machine learning models for predicting acute kidney injury following donation after cardiac death liver transplantation

BACKGROUND

Acute kidney injury (AKI) is a common complication after liver transplantation (LT) and is an indicator of poor prognosis. The establishment of a more accurate preoperative prediction model of AKI could help to improve the prognosis of LT. Machine learning algorithms provide a potentially effective approach.

METHODS

A total of 493 patients with donation after cardiac death LT (DCDLT) were enrolled. AKI was defined according to the clinical practice guidelines of kidney disease: improving global outcomes (KDIGO). The clinical data of patients with AKI (AKI group) and without AKI (non-AKI group) were compared. With logistic regression analysis as a conventional model, four predictive machine learning models were developed using the following algorithms: random forest, support vector machine, classical decision tree, and conditional inference tree. The predictive power of these models was then evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

The incidence of AKI was 35.7% (176/493) during the follow-up period. Compared with the non-AKI group, the AKI group showed a remarkably lower survival rate (P < 0.001). The random forest model demonstrated the highest prediction accuracy of 0.79 with AUC of 0.850 [95% confidence interval (CI): 0.794-0.905], which was significantly higher than the AUCs of the other machine learning algorithms and logistic regression models (P < 0.001).

CONCLUSIONS

The random forest model based on machine learning algorithms for predicting AKI occurring after DCDLT demonstrated stronger predictive power than other models in our study. This suggests that machine learning methods may provide feasible tools for forecasting AKI after DCDLT.

Machine learning in asthma research: moving toward a more integrated approach

Introduction: Big data are reshaping the future of medicine. The growing availability and increasing complexity of data have favored the adoption of modern analytical and computational methodologies in every area of medicine. Over the past decades, asthma research has been characterized by a shift in the way studies are conducted and data are analyzed. Motivated by the assumptions that 'data will speak for themselves', hypothesis-driven approaches have been replaced by data-driven hypotheses-generating methods to explore hidden patterns and underlying mechanisms. However, even with all the advancement in technologies and the new important insight that we gained to understand and characterize asthma heterogeneity, very few research findings have been translated into clinically actionable solutions.Areas covered: To investigate some of the fundamental analytical approaches adopted in the current literature and appraise their impact and usefulness in medicine, we conducted a bibliometric analysis of big data analytics in asthma research in the past 50 years.Expert opinion: No single data source or methodology can uncover the complexity of human health and disease. To fully capitalize on the potential of 'big data', we will have to embrace the collaborative science and encourage the creation of integrated cross-disciplinary teams brought together around technological advances.

Asthma susceptible genes in children: A meta-analysis

BACKGROUND

During the last decade, a number of studies have evaluated the potential association between some genetic polymorphisms and childhood asthma risk, however, the results of published studies appear conflicts. The aim of the present study was to investigate association between genetic polymorphisms and pediatric asthma.

METHODS

Relevant studies were searched in PubMed, Embase, Web of Science, CNKI (China National Knowledge Infrastructure), Wanfang, and Weipu database. Pooled odds ratios (OR) with 95% confidence interval (CI) were calculated to evaluate the strength of the associations.

RESULTS

Fifty five case-control studies were finally included in this meta-analysis, including 17,971 pediatric asthma cases and 17,500 controls. Eighteen polymorphisms were identified, of which, 9 polymorphisms were found to be associated with asthma risk in overall populations: IL-13 +2044G/A, IL-4 -590C/T, ADAM33 F+1, ADAM33 T2, ADAM33 T1, ADAM33 ST+4,ORMDL3 rs7216389, VDR FokI, VDR TaqI. Furthermore, IL-13 +2044G/A, IL-4 -590C/T, ADAM33 T2, ADAM33 T1, VDR BsmI polymorphisms may cause an increased risk of asthma among Chinese children.

CONCLUSIONS

This meta-analysis found that IL-13 +2044G/A, IL-4 -590C/T, ADAM33 F+1, ADAM33 T2, ADAM33 T1, ADAM33 ST+4,ORMDL3 rs7216389, VDR FokI, and VDR TaqI polymorphisms might be risk factors for childhood asthma. Further study with large population and more ethnicities is needed to estimate these associations.