Predicting Treatment Outcomes Using Explainable Machine Learning in Children with Asthma

Machine Learning for the Identification of Key Predictors to Bayley Outcomes: A Preterm Cohort Study

BACKGROUND

The aim of this study was to understand how neurological development of preterm infants can be predicted at earlier stages and explore the possibility of applying personalized approaches.

METHODS

Our study included a cohort of 64 preterm infants, between 24 and 34 weeks of gestation. Linear and nonlinear models were used to evaluate feature predictability to Bayley outcomes at the corrected age of 2 years. The outcomes were classified into motor, language, cognitive, and socio-emotional categories. Pediatricians' opinions about the predictability of the same features were compared with machine learning.

RESULTS

According to our linear analysis sepsis, brain MRI findings and Apgar score at 5th minute were predictive for cognitive, Amiel-Tison neurological assessment at 12 months of corrected age for motor, while sepsis was predictive for socio-emotional outcome. None of the features were predictive for language outcome. Based on the machine learning analysis, sepsis was the key predictor for cognitive and motor outcome. For language outcome, gestational age, duration of hospitalization, and Apgar score at 5th minute were predictive, while for socio-emotional, gestational age, sepsis, and duration of hospitalization were predictive. Pediatricians' opinions were that cardiopulmonary resuscitation is the key predictor for cognitive, motor, and socio-emotional, but gestational age for language outcome.

CONCLUSIONS

The application of machine learning in predicting neurodevelopmental outcomes of preterm infants represents a significant advancement in neonatal care. The integration of machine learning models with clinical workflows requires ongoing education and collaboration between data scientists and healthcare professionals to ensure the models' practical applicability and interpretability.

Epigenomic partitioning of a polygenic risk score for asthma reveals distinct genetically driven disease pathways

BACKGROUND

Individual differences in susceptibility to developing asthma, a heterogeneous chronic inflammatory lung disease, are poorly understood. Whether genetics can predict asthma risk and how genetic variants modulate the complex pathophysiology of asthma are still debated.

AIM

To build polygenic risk scores for asthma risk prediction and epigenomically link predictive genetic variants to pathophysiological mechanisms.

METHODS

Restricted polygenic risk scores were constructed using single nucleotide variants derived from genome-wide association studies and validated using data generated in the Rotterdam Study, a Dutch prospective cohort of 14 926 individuals. Outcomes used were asthma, childhood-onset asthma, adulthood-onset asthma, eosinophilic asthma and asthma exacerbations. Genome-wide chromatin analysis data from 19 disease-relevant cell types were used for epigenomic polygenic risk score partitioning.

RESULTS

The polygenic risk scores obtained predicted asthma and related outcomes, with the strongest associations observed for childhood-onset asthma (2.55 odds ratios per polygenic risk score standard deviation, area under the curve of 0.760). Polygenic risk scores allowed for the classification of individuals into high-risk and low-risk groups. Polygenic risk score partitioning using epigenomic profiles identified five clusters of variants within putative gene regulatory regions linked to specific asthma-relevant cells, genes and biological pathways.

CONCLUSIONS

Polygenic risk scores were associated with asthma(-related traits) in a Dutch prospective cohort, with substantially higher predictive power observed for childhood-onset than adult-onset asthma. Importantly, polygenic risk score variants could be epigenomically partitioned into clusters of regulatory variants with different pathophysiological association patterns and effect estimates, which likely represent distinct genetically driven disease pathways. Our findings have potential implications for personalised risk mitigation and treatment strategies.

Investigating Machine Learning Techniques for Predicting Risk of Asthma Exacerbations: A Systematic Review

Asthma, a common chronic respiratory disease among children and adults, affects more than 200 million people worldwide and causes about 450,000 deaths each year. Machine learning is increasingly applied in healthcare to assist health practitioners in decision-making. In asthma management, machine learning excels in performing well-defined tasks, such as diagnosis, prediction, medication, and management. However, there remain uncertainties about how machine learning can be applied to predict asthma exacerbation. This study aimed to systematically review recent applications of machine learning techniques in predicting the risk of asthma attacks to assist asthma control and management. A total of 860 studies were initially identified from five databases. After the screening and full-text review, 20 studies were selected for inclusion in this review. The review considered recent studies published from January 2010 to February 2023. The 20 studies used machine learning techniques to support future asthma risk prediction by using various data sources such as clinical, medical, biological, and socio-demographic data sources, as well as environmental and meteorological data. While some studies considered prediction as a category, other studies predicted the probability of exacerbation. Only a group of studies applied prediction windows. The paper proposes a conceptual model to summarise how machine learning and available data sources can be leveraged to produce effective models for the early detection of asthma attacks. The review also generated a list of data sources that other researchers may use in similar work. Furthermore, we present opportunities for further research and the limitations of the preceding studies.

Current state and prospects of artificial intelligence in allergy

The field of medicine is witnessing an exponential growth of interest in artificial intelligence (AI), which enables new research questions and the analysis of larger and new types of data. Nevertheless, applications that go beyond proof of concepts and deliver clinical value remain rare, especially in the field of allergy. This narrative review provides a fundamental understanding of the core concepts of AI and critically discusses its limitations and open challenges, such as data availability and bias, along with potential directions to surmount them. We provide a conceptual framework to structure AI applications within this field and discuss forefront case examples. Most of these applications of AI and machine learning in allergy concern supervised learning and unsupervised clustering, with a strong emphasis on diagnosis and subtyping. A perspective is shared on guidelines for good AI practice to guide readers in applying it effectively and safely, along with prospects of field advancement and initiatives to increase clinical impact. We anticipate that AI can further deepen our knowledge of disease mechanisms and contribute to precision medicine in allergy.

Characteristics of Severe Asthma Patients and Predictors of Asthma Control in the Swiss Severe Asthma Registry

BACKGROUND

Asthma is a chronic airway disease, affecting over 300 million people worldwide. 5-10% of patients suffer from severe asthma and account for 50% of asthma-related financial burden. Availability of real-life data about the clinical course of severe asthma is insufficient.

OBJECTIVES

The aims of this study were to characterize patients with severe asthma in Switzerland, enrolled in the Swiss Severe Asthma Registry (SSAR), and evaluate predictors for asthma control.

METHOD

A descriptive characterisation of 278 patients was performed, who were prospectively enrolled in the registry until January 2022. Socio-demographic variables, comorbidities, diagnostic values, asthma treatment, and healthcare utilisation were evaluated. Groups of controlled and uncontrolled asthma according to the asthma control test were compared.

RESULTS

Forty-eight percent of patients were female and the mean age was 55.8 years (range 13-87). The mean body mass index (BMI) was 27.4 kg/m2 (±6). 10.8% of patients were current smokers. Allergic comorbidities occurred in 54.3% of patients, followed by chronic rhinosinusitis (46.4%) and nasal polyps (34.1%). According to the ACT score, 54.7% had well controlled, 16.2% partly controlled and 25.9% uncontrolled asthma. The most common inhalation therapy was combined inhaled corticosteroids/long-acting β2-agonists (78.8%). Biologics were administered to 81.7% of patients and 19.1% received oral steroids. The multivariable analysis indicated that treatment with biologics was positively associated with asthma control whereas higher BMI, oral steroids, exacerbations, and COPD were negative predictors for asthma control.

CONCLUSION

Biologics are associated with improved control in severe asthma. Further studies are required to complete the picture of severe asthma in order to provide improved care for those patients.

Machine learning model for classification of predominantly allergic and non-allergic asthma among preschool children with asthma hospitalization

OBJECTIVE

Asthma is the most frequent chronic airway illness in preschool children and is difficult to diagnose due to the disease's heterogeneity. This study aimed to investigate different machine learning models and suggested the most effective one to classify two forms of asthma in preschool children (predominantly allergic asthma and non-allergic asthma) using a minimum number of features.

METHODS

After pre-processing, 127 patients (70 with non-allergic asthma and 57 with predominantly allergic asthma) were chosen for final analysis from the Frankfurt dataset, which had asthma-related information on 205 patients. The Random Forest algorithm and Chi-square were used to select the key features from a total of 63 features. Six machine learning models: random forest, extreme gradient boosting, support vector machines, adaptive boosting, extra tree classifier, and logistic regression were then trained and tested using 10-fold stratified cross-validation.

RESULTS

Among all features, age, weight, C-reactive protein, eosinophilic granulocytes, oxygen saturation, pre-medication inhaled corticosteroid + long-acting beta2-agonist (PM-ICS + LABA), PM-other (other pre-medication), H-Pulmicort/celestamine (Pulmicort/celestamine during hospitalization), and H-azithromycin (azithromycin during hospitalization) were found to be highly important. The support vector machine approach with a linear kernel was able to diffrentiate between predominantly allergic asthma and non-allergic asthma with higher accuracy (77.8%), precision (0.81), with a true positive rate of 0.73 and a true negative rate of 0.81, a F1 score of 0.81, and a ROC-AUC score of 0.79. Logistic regression was found to be the second-best classifier with an overall accuracy of 76.2%.

CONCLUSION

Predominantly allergic and non-allergic asthma can be classified using machine learning approaches based on nine features.

Supplemental data for this article is available online at at www.tandfonline.com/ijas .

Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review

Machine learning (ML) holds great potential for predicting clinical outcomes in heterogeneous chronic respiratory diseases (CRD) affecting children, where timely individualised treatments offer opportunities for health optimisation. This paper identifies rate-limiting steps in ML prediction model development that impair clinical translation and discusses regulatory, clinical and ethical considerations for ML implementation. A scoping review of ML prediction models in paediatric CRDs was undertaken using the PRISMA extension scoping review guidelines. From 1209 results, 25 articles published between 2013 and 2021 were evaluated for features of a good clinical prediction model using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines.

Most of the studies were in asthma (80%), with few in cystic fibrosis (12%), bronchiolitis (4%) and childhood wheeze (4%). There were inconsistencies in model reporting and studies were limited by a lack of validation, and absence of equations or code for replication. Clinician involvement during ML model development is essential and diversity, equity and inclusion should be assessed at each step of the ML pipeline to ensure algorithms do not promote or amplify health disparities among marginalised groups. As ML prediction studies become more frequent, it is important that models are rigorously developed using published guidelines and take account of regulatory frameworks which depend on model complexity, patient safety, accountability and liability.

Prediction Models of Early Childhood Caries Based on Machine Learning Algorithms

In this study, we developed machine learning-based prediction models for early childhood caries and compared their performances with the traditional regression model. We analyzed the data of 4195 children aged 1-5 years from the Korea National Health and Nutrition Examination Survey data (2007-2018). Moreover, we developed prediction models using the XGBoost (version 1.3.1), random forest, and LightGBM (version 3.1.1) algorithms in addition to logistic regression. Two different methods were applied for variable selection, including a regression-based backward elimination and a random forest-based permutation importance classifier. We compared the area under the receiver operating characteristic (AUROC) values and misclassification rates of the different models and observed that all four prediction models had AUROC values ranging between 0.774 and 0.785. Furthermore, no significant difference was observed between the AUROC values of the four models. Based on the results, we can confirm that both traditional logistic regression and ML-based models can show favorable performance and can be used to predict early childhood caries, identify ECC high-risk groups, and implement active preventive treatments. However, further research is essential to improving the performance of the prediction model using recent methods, such as deep learning.

Treatment outcome clustering patterns correspond to discrete asthma phenotypes in children

Despite widely and regularly used therapy asthma in children is not fully controlled. Recognizing the complexity of asthma phenotypes and endotypes imposed the concept of precision medicine in asthma treatment. By applying machine learning algorithms assessed with respect to their accuracy in predicting treatment outcome, we have successfully identified 4 distinct clusters in a pediatric asthma cohort with specific treatment outcome patterns according to changes in lung function (FEV₁ and MEF₅₀), airway inflammation (FENO) and disease control likely affected by discrete phenotypes at initial disease presentation, differing in the type and level of inflammation, age of onset, comorbidities, certain genetic and other physiologic traits. The smallest and the largest of the 4 clusters- 1 (N = 58) and 3 (N = 138) had better treatment outcomes compared to clusters 2 and 4 and were characterized by more prominent atopic markers and a predominant allelic (A allele) effect for rs37973 in the GLCCI1 gene previously associated with positive treatment outcomes in asthmatics. These patients also had a relatively later onset of disease (6 + yrs). Clusters 2 (N = 87) and 4 (N = 64) had poorer treatment success, but varied in the type of inflammation (predominantly neutrophilic for cluster 4 and likely mixed-type for cluster 2), comorbidities (obesity for cluster 2), level of systemic inflammation (highest hsCRP for cluster 2) and platelet count (lowest for cluster 4). The results of this study emphasize the issues in asthma management due to the overgeneralized approach to the disease, not taking into account specific disease phenotypes.