Artificial intelligence and wheezing in children: where are we now?

Wheezing is a common condition in childhood, and its prevalence has increased in the last decade. Up to one-third of preschoolers develop recurrent wheezing, significantly impacting their quality of life and healthcare resources. Artificial Intelligence (AI) technologies have recently been applied in paediatric allergology and pulmonology, contributing to disease recognition, risk stratification, and decision support. Additionally, the COVID-19 pandemic has shaped healthcare systems, resulting in an increased workload and the necessity to reduce access to hospital facilities. In this view, AI and Machine Learning (ML) approaches can help address current issues in managing preschool wheezing, from its recognition with AI-augmented stethoscopes and monitoring with smartphone applications, aiming to improve parent-led/self-management and reducing economic and social costs. Moreover, in the last decade, ML algorithms have been applied in wheezing phenotyping, also contributing to identifying specific genes, and have been proven to even predict asthma in preschoolers. This minireview aims to update our knowledge on recent advancements of AI applications in childhood wheezing, summarizing and discussing the current evidence in recognition, diagnosis, phenotyping, and asthma prediction, with an overview of home monitoring and tele-management.

Machine learning approaches for asthma disease prediction among adults in Sri Lanka

Objectives: Addressing the challenge of cost-effective asthma diagnosis amidst diverse symptom patterns among patients, this study aims to develop a machine learning-based asthma prediction tool for self-detection of asthma. Methods: Data from 6,665 participants in the Sri Lanka Health and Ageing Study (2018-2019) are used for this research. Thirteen machine learning algorithms, including Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Naïve Bayes, K-Nearest Neighbors, Gradient Boost, XGBoost, AdaBoost, CatBoost, LightGBM, Multi-Layer Perceptron, and Probabilistic Neural Network, are employed. Results: A hybrid version of Logistic Regression and LightGBM outperformed other models, achieving an AUC of 0.9062 and 79.85% sensitivity. Key predictive features for asthma include wheezing, breathlessness with wheezing, shortness of breath attacks, coughing attacks, chest tightness, nasal allergies, physical activity, passive smoking, ethnicity, and residential sector. Conclusion: Combining Logistic Regression and LightGBM models can effectively predict adult asthma based on self-reported symptoms and demographic and behavioural characteristics. The proposed expert system assists clinicians and patients in diagnosing potential asthma cases.

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.

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.

Prediction models for childhood asthma: A systematic review

BACKGROUND

The inability to objectively diagnose childhood asthma before age five often results in both under-treatment and over-treatment of asthma in preschool children. Prediction tools for estimating a child's risk of developing asthma by school-age could assist physicians in early asthma care for preschool children. This review aimed to systematically identify and critically appraise studies which either developed novel or updated existing prediction models for predicting school-age asthma.

METHODS

Three databases (MEDLINE, Embase and Web of Science Core Collection) were searched up to July 2019 to identify studies utilizing information from children ≤5 years of age to predict asthma in school-age children (6-13 years). Validation studies were evaluated as a secondary objective.

RESULTS

Twenty-four studies describing the development of 26 predictive models published between 2000 and 2019 were identified. Models were either regression-based (n = 21) or utilized machine learning approaches (n = 5). Nine studies conducted validations of six regression-based models. Fifteen (out of 21) models required additional clinical tests. Overall model performance, assessed by area under the receiver operating curve (AUC), ranged between 0.66 and 0.87. Models demonstrated moderate ability to either rule in or rule out asthma development, but not both. Where external validation was performed, models demonstrated modest generalizability (AUC range: 0.62-0.83).

CONCLUSION

Existing prediction models demonstrated moderate predictive performance, often with modest generalizability when independently validated. Limitations of traditional methods have shown to impair predictive accuracy and resolution. Exploration of novel methods such as machine learning approaches may address these limitations for future school-age asthma prediction.

Neural Network-Based Clinical Prediction System for Identifying the Clinical Effects of Saffron (Crocus sativus L) Supplement Therapy on Allergic Asthma: Model Evaluation Study

Background

Asthma is commonly associated with chronic airway inflammation and is the underlying cause of over a million deaths each year. Crocus sativus L, commonly known as saffron, when used in the form of traditional medicines, has demonstrated anti-inflammatory effects which may be beneficial to individuals with asthma.

Objective

The objective of this study was to develop a clinical prediction system using an artificial neural network to detect the effects of C sativus L supplements on patients with allergic asthma.

Methods

A genetic algorithm–modified neural network predictor system was developed to detect the level of effectiveness of C sativus L using features extracted from the clinical, immunologic, hematologic, and demographic information of patients with asthma. The study included data from men (n=40) and women (n=40) individuals with mild or moderate allergic asthma from 18 to 65 years of age. The aim of the model was to estimate and predict the level of effect of C sativus L supplements on each asthma risk factor and to predict the level of alleviation in patients with asthma. A genetic algorithm was used to extract input features for the clinical prediction system to improve its predictive performance. Moreover, an optimization model was developed for the artificial neural network component that classifies the patients with asthma using C sativus L supplement therapy.

Results

The best overall performance of the clinical prediction system was an accuracy greater than 99% for training and testing data. The genetic algorithm–modified neural network predicted the level of effect with high accuracy for anti–heat shock protein (anti-HSP), high sensitivity C-reactive protein (hs-CRP), forced expiratory volume in the first second of expiration (FEV₁), forced vital capacity (FVC), the ratio of FEV₁/FVC, and forced expiratory flow (FEF_25%-75%) for testing data (anti-HSP: 96.5%; hs-CRP: 98.9%; FEV₁: 98.1%; FVC: 97.5%; FEV₁/FVC ratio: 97%; and FEF_25%-75%: 96.7%, respectively).

Conclusions

The clinical prediction system developed in this study was effective in predicting the effect of C sativus L supplements on patients with allergic asthma. This clinical prediction system may help clinicians to identify early on which clinical factors in asthma will improve over the course of treatment and, in doing so, help clinicians to develop effective treatment plans for patients with asthma.

Comparative study of whole exome sequencing-based copy number variation detection tools

Background

With the rapid development of whole exome sequencing (WES), an increasing number of tools are being proposed for copy number variation (CNV) detection based on this technique. However, no comprehensive guide is available for the use of these tools in clinical settings, which renders them inapplicable in practice. To resolve this problem, in this study, we evaluated the performances of four WES-based CNV tools, and established a guideline for the recommendation of a suitable tool according to the application requirements.

Results

In this study, first, we selected four WES-based CNV detection tools: CoNIFER, cn.MOPS, CNVkit and exomeCopy. Then, we evaluated their performances in terms of three aspects: sensitivity and specificity, overlapping consistency and computational costs. From this evaluation, we obtained four main results: (1) The sensitivity increases and subsequently stabilizes as the coverage or CNV size increases, while the specificity decreases. (2) CoNIFER performs better for CNV insertions than for CNV deletions, while the remaining tools exhibit the opposite trend. (3) CoNIFER, cn.MOPS and CNVkit realize satisfactory overlapping consistency, which indicates their results are trustworthy. (4) CoNIFER has the best space complexity and cn.MOPS has the best time complexity among these four tools. Finally, we established a guideline for tools’ usage according to these results.

Conclusion

No available tool performs excellently under all conditions; however, some tools perform excellently in some scenarios. Users can obtain a CNV tool recommendation from our paper according to the targeted CNV size, the CNV type or computational costs of their projects, as presented in Table 1, which is helpful even for users with limited knowledge of computer science.

A systematic review of predictive models for asthma development in children

BACKGROUND

Asthma is the most common pediatric chronic disease affecting 9.6 % of American children. Delay in asthma diagnosis is prevalent, resulting in suboptimal asthma management. To help avoid delay in asthma diagnosis and advance asthma prevention research, researchers have proposed various models to predict asthma development in children. This paper reviews these models.

METHODS

A systematic review was conducted through searching in PubMed, EMBASE, CINAHL, Scopus, the Cochrane Library, the ACM Digital Library, IEEE Xplore, and OpenGrey up to June 3, 2015. The literature on predictive models for asthma development in children was retrieved, with search results limited to human subjects and children (birth to 18 years). Two independent reviewers screened the literature, performed data extraction, and assessed article quality.

RESULTS

The literature search returned 13,101 references in total. After manual review, 32 of these references were determined to be relevant and are discussed in the paper. We identify several limitations of existing predictive models for asthma development in children, and provide preliminary thoughts on how to address these limitations.

CONCLUSIONS

Existing predictive models for asthma development in children have inadequate accuracy. Efforts to improve these models' performance are needed, but are limited by a lack of a gold standard for asthma development in children.