Machine learning did not beat logistic regression in time series prediction for severe asthma exacerbations

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.

Machine Learning Approaches to Predict Asthma Exacerbations: A Narrative Review

The implementation of artificial intelligence (AI) and machine learning (ML) techniques in healthcare has garnered significant attention in recent years, especially as a result of their potential to revolutionize personalized medicine. Despite advances in the treatment and management of asthma, a significant proportion of patients continue to suffer acute exacerbations, irrespective of disease severity and therapeutic regimen. The situation is further complicated by the constellation of factors that influence disease activity in a patient with asthma, such as medical history, biomarker phenotype, pulmonary function, level of healthcare access, treatment compliance, comorbidities, personal habits, and environmental conditions. A growing body of work has demonstrated the potential for AI and ML to accurately predict asthma exacerbations while also capturing the entirety of the patient experience. However, application in the clinical setting remains mostly unexplored, and important questions on the strengths and limitations of this technology remain. This review presents an overview of the rapidly evolving landscape of AI and ML integration into asthma management by providing a snapshot of the existing scientific evidence and proposing potential avenues for future applications.

Development of an Asthma Exacerbation Risk Prediction Model for Conversational Use by Adults in England

Background

Improving accurate risk assessment of asthma exacerbations, and reduction via relevant behaviour change among people with asthma could save lives and reduce health care costs. We developed a simple personalised risk prediction model for asthma exacerbations using factors collected in routine healthcare data for use in a risk modelling feature for automated conversational systems.

Methods

We used pseudonymised primary care electronic healthcare records from the Clinical Practice Research Datalink (CPRD) Aurum database in England. We combined variables for prediction of asthma exacerbations using logistic regression including age, gender, ethnicity, Index of Multiple Deprivation, geographical region and clinical variables related to asthma events.

Results

We included 1,203,741 patients divided into three cohorts to implement temporal validation: 898,763 (74.7%) in the training sample, 226,754 (18.8%) in the testing sample and 78,224 (6.5%) in the validation sample. The Area under the ROC curve (AUC) for the full model was 0.72 and for the restricted model was 0.71. Using a cut-off point of 0.1, approximately 27 asthma reviews by clinicians per 100 patients would be prevented compared with a strategy that all patients are regarded as high risk. Compared with patients without an exacerbation, patients who exacerbated were older, more likely to be female, prescribed more SABA and ICS in the preceding 12 months, have history of GORD, COPD, anxiety, depression, live in very deprived areas and have more severe disease.

Conclusion

Using information available from routinely collected electronic healthcare record data, we developed a model that has moderate ability to separate patients who had an asthma exacerbation within 3 months from their index date from patients who did not. When comparing this model with a simplified model with variables that can easily be self-reported through a WhatsApp chatbot, we have shown that the predictive performance of the model is not substantially different.

Analysis of factors affecting nonalcoholic fatty liver disease in Chinese steel workers and risk assessment studies

BACKGROUND

The global incidence of nonalcoholic fatty liver disease (NAFLD) is rapidly escalating, positioning it as a principal public health challenge with significant implications for population well-being. Given its status as a cornerstone of China's economic structure, the steel industry employs a substantial workforce, consequently bringing associated health issues under increasing scrutiny. Establishing a risk assessment model for NAFLD within steelworkers aids in disease risk stratification among this demographic, thereby facilitating early intervention measures to protect the health of this significant populace.

METHODS

Use of cross-sectional studies. A total of 3328 steelworkers who underwent occupational health evaluations between January and September 2017 were included in this study. Hepatic steatosis was uniformly diagnosed via abdominal ultrasound. Influential factors were pinpointed using chi-square (χ2) tests and unconditional logistic regression analysis, with model inclusion variables identified by pertinent literature. Assessment models encompassing logistic regression, random forest, and XGBoost were constructed, and their effectiveness was juxtaposed in terms of accuracy, area under the curve (AUC), and F1 score. Subsequently, a scoring system for NAFLD risk was established, premised on the optimal model.

RESULTS

The findings indicated that sex, overweight, obesity, hyperuricemia, dyslipidemia, occupational dust exposure, and ALT serve as risk factors for NAFLD in steelworkers, with corresponding odds ratios (OR, 95% confidence interval (CI)) of 0.672 (0.487-0.928), 4.971 (3.981-6.207), 16.887 (12.99-21.953), 2.124 (1.77-2.548), 2.315 (1.63-3.288), 1.254 (1.014-1.551), and 3.629 (2.705-4.869), respectively. The sensitivity of the three models was reported as 0.607, 0.680 and 0.564, respectively, while the precision was 0.708, 0.643, and 0.701, respectively. The AUC measurements were 0.839, 0.839, and 0.832, and the Brier scores were 0.150, 0.153, and 0.155, respectively. The F1 score results were 0.654, 0.661, and 0.625, with log loss measures at 0.460, 0.661, and 0.564, respectively. R2 values were reported as 0.789, 0.771, and 0.778, respectively. Performance was comparable across all three models, with no significant differences observed. The NAFLD risk score system exhibited exceptional risk detection capabilities with an established cutoff value of 86.

CONCLUSIONS

The study identified sex, BMI, dyslipidemia, hyperuricemia, occupational dust exposure, and ALT as significant risk factors for NAFLD among steelworkers. The traditional logistic regression model proved equally effective as the random forest and XGBoost models in assessing NAFLD risk. The optimal cutoff value for risk assessment was determined to be 86. This study provides clinicians with a visually accessible risk stratification approach to gauge the propensity for NAFLD in steelworkers, thereby aiding early identification and intervention among those at risk.

Machine learning for prediction of asthma exacerbations among asthmatic patients: a systematic review and meta-analysis

BACKGROUND

Asthma exacerbations reduce the patient's quality of life and are also responsible for significant disease burdens and economic costs. Machine learning (ML)-based prediction models have been increasingly developed to predict asthma exacerbations in recent years. This systematic review and meta-analysis aimed to identify the prediction performance of ML-based prediction models for asthma exacerbations and address the uncertainty of whether modern ML methods could become an alternative option to predict asthma exacerbations.

METHODS

PubMed, Cochrane Library, EMBASE, and Web of Science were searched for studies published up to December 15, 2022. Studies that applied ML methods to develop prediction models for asthma exacerbations among asthmatic patients older than five years and were published in English were eligible. The prediction model risk of bias assessment tool (PROBAST) was utilized to estimate the risk of bias and the applicability of included studies. Stata software (version 15.0) was used for the random effects meta-analysis of performance measures. Subgroup analyses stratified by ML methods, sample size, age groups, and outcome definitions were conducted.

RESULTS

Eleven studies, including 23 prediction models, were identified. Most of the studies were published in recent three years. Logistic regression, boosting, and random forest were the most used ML methods. The most common important predictors were systemic steroid use, short-acting beta2-agonists, emergency department visit, age, and exacerbation history. The overall pooled area under the curve of the receiver operating characteristics (AUROC) of 11 studies (23 prediction models) was 0.80 (95% CI 0.77-0.83). Subgroup analysis based on different ML models showed that boosting method achieved the best performance, with an overall pooled AUROC of 0.84 (95% CI 0.81-0.87).

CONCLUSION

This study identified that ML was the potential tool to achieve great performance in predicting asthma exacerbations. However, the methodology within these models was heterogeneous. Future studies should focus on improving the generalization ability and practicability, thus driving the application of these models in clinical practice.