Understanding the importance of key risk factors in predicting chronic bronchitic symptoms using a machine learning approach

Clinical prediction models in children that use repeated measurements with time-varying covariates: a scoping review

BACKGROUND

Emerging evidence suggests that clinical prediction models that use repeated (time-varying) measurements within each patient may have higher predictive accuracy than models that use patient information from a single measurement.

OBJECTIVE

To determine the breadth of the published literature reporting the development of clinical prediction models in children that use time-varying predictors.

DATA SOURCES

MEDLINE, EMBASE and Cochrane databases.

ELIGIBILITY CRITERIA

We included studies reporting the development of a multivariable clinical prediction model in children, with or without validation, to predict a repeatedly measured binary or time-to-event outcome and utilizing at least one repeatedly measured predictor.

SYNTHESIS METHODS

We categorized included studies by the method used to model time-varying predictors.

RESULTS

Of 99 clinical prediction model studies that had a repeated measurements data structure, only 27 (27%) used methods that incorporated the repeated measurements as time-varying predictors in a single model. Among these 27 time-varying prediction model studies, we grouped model types into nine categories: time-dependent Cox regression, generalized estimating equations, random effects model, landmark model, joint model, neural network, K-nearest neighbor, support vector machine and tree-based algorithms. Where there was comparison of time-varying models to single measurement models, using time-varying predictors improved predictive accuracy.

CONCLUSIONS

Various methods have been used to develop time-varying prediction models in children, but there is a paucity of pediatric time-varying models in the literature. Incorporating time-varying covariates in pediatric prediction models may improve predictive accuracy. Future research in pediatric prediction model development should further investigate whether incorporation of time-varying covariates improves predictive accuracy.

Machine learning-driven identification of air toxic combinations associated with asthma symptoms among elementary school children in Spokane, Washington, USA

Air toxics are atmospheric pollutants with hazardous effects on health and the environment. Although methodological constraints have limited the number of air toxics assessed for associations with health and disease, advances in machine learning (ML) enable the assessment of a much larger set of environmental exposures. We used ML methods to conduct a retrospective study to identify combinations of 109 air toxics associated with asthma symptoms among 269 elementary school students in Spokane, Washington. Data on the frequency of asthma symptoms for these children were obtained from Spokane Public Schools. Their exposure to air toxics was estimated by using the Environmental Protection Agency's Air Toxics Screening Assessment and National Air Toxics Assessment. We defined three exposure periods: the most recent year (2019), the last three years (2017-2019), and the last five years (2014-2019). We analyzed the data using the ML-based Data-driven ExposurE Profile (DEEP) extraction method. DEEP identified 25 air toxic combinations associated with asthma symptoms in at least one exposure period. Three combinations (1,1,1-trichloroethane, 2-nitropropane, and 2,4,6-trichlorophenol) were significantly associated with asthma symptoms in all three exposure periods. Four air toxics (1,1,1-trichloroethane, 1,1,2,2-tetrachloroethane, BIS (2-ethylhexyl) phthalate (DEHP), and 2,4-dinitrophenol) were associated only in combination with other toxics, and would not have been identified by traditional statistical methods. The application of DEEP also identified a vulnerable subpopulation of children who were exposed to 13 of the 25 significant combinations in at least one exposure period. On average, these children experienced the largest number of asthma symptoms in our sample. By providing evidence on air toxic combinations associated with childhood asthma, our findings may contribute to the regulation of these toxics to improve children's respiratory health.

Near-roadway air pollution, immune cells and adipokines among obese young adults

BACKGROUND

Air pollution has been associated with metabolic disease and obesity. Adipokines are potential mediators of these effects, but studies of air pollution-adipokine relationships are inconclusive. Macrophage and T cells in adipose tissue (AT) and blood modulate inflammation; however, the role of immune cells in air pollution-induced dysregulation of adipokines has not been studied. We examined the association between air pollution exposure and circulating and AT adipokine concentrations, and whether these relationships were modified by macrophage and T cell numbers in the blood and AT.

METHODS

Fasting blood and abdominal subcutaneous AT biopsies were collected from 30 overweight/obese 18-26 year-old volunteers. Flow cytometry was used to quantify T effector (Teff, inflammatory) and regulatory (Treg, anti-inflammatory) lymphocytes and M1 [inflammatory] and M2 [anti-inflammatory]) macrophage cell number. Serum and AT leptin and adiponectin were measured using enzyme-linked immunosorbent assay (ELISA). Exposure to near-roadway air pollution (NRAP) from freeway and non-freeway vehicular sources and to regional particulate matter, nitrogen dioxide and ozone were estimated for the year prior to biopsy, based on participants' residential addresses. Linear regression models were used to examine the association between air pollution exposures and adipokines and to evaluate effect modification by immune cell counts.

RESULTS

An interquartile increase in non-freeway NRAP exposure during 1 year prior to biopsy was associated with higher leptin levels in both serum [31.7% (95% CI: 10.4, 52.9%)] and AT [19.4% (2.2, 36.6%)]. Non-freeway NRAP exposure effect estimates were greater among participants with greater than median Teff/Treg ratio and M1/M2 ratio in blood, and with greater M1 counts in AT. No adipokine associations with regional air pollutants were found.

DISCUSSION

Our results suggest that NRAP may increase serum leptin levels in obese young adults, and this association may be promoted in a pro-inflammatory immune cell environment in blood and AT.

Machine learning-driven identification of early-life air toxic combinations associated with childhood asthma outcomes

Air pollution is a well-known contributor to asthma. Air toxics are hazardous air pollutants that cause or may cause serious health effects. Although individual air toxics have been associated with asthma, only a limited number of studies have specifically examined combinations of air toxics associated with the disease. We geocoded air toxic levels from the US National Air Toxics Assessment (NATA) to residential locations for participants of our AiRway in Asthma (ARIA) study. We then applied Data-driven ExposurE Profile extraction (DEEP), a machine learning-based method, to discover combinations of early-life air toxics associated with current use of daily asthma controller medication, lifetime emergency department visit for asthma, and lifetime overnight hospitalization for asthma. We discovered 20 multi-air toxic combinations and 18 single air toxics associated with at least 1 outcome. The multi-air toxic combinations included those containing acrylic acid, ethylidene dichloride, and hydroquinone, and they were significantly associated with asthma outcomes. Several air toxic members of the combinations would not have been identified by single air toxic analyses, supporting the use of machine learning-based methods designed to detect combinatorial effects. Our findings provide knowledge about air toxic combinations associated with childhood asthma.

Machine Learning Prediction of Length of Stay in Adult Spinal Deformity Patients Undergoing Posterior Spine Fusion Surgery

(1) Background: Length of stay (LOS) is a commonly reported metric used to assess surgical success, patient outcomes, and economic impact. The focus of this study is to use a variety of machine learning algorithms to reliably predict whether a patient undergoing posterior spinal fusion surgery treatment for Adult Spine Deformity (ASD) will experience a prolonged LOS. (2) Methods: Patients undergoing treatment for ASD with posterior spinal fusion surgery were selected from the American College of Surgeon's NSQIP dataset. Prolonged LOS was defined as a LOS greater than or equal to 9 days. Data was analyzed with the Logistic Regression, Decision Tree, Random Forest, XGBoost, and Gradient Boosting functions in Python with the Sci-Kit learn package. Prediction accuracy and area under the curve (AUC) were calculated. (3) Results: 1281 posterior patients were analyzed. The five algorithms had prediction accuracies between 68% and 83% for posterior cases (AUC: 0.566-0.821). Multivariable regression indicated that increased Work Relative Value Units (RVU), elevated American Society of Anesthesiologists (ASA) class, and longer operating times were linked to longer LOS. (4) Conclusions: Machine learning algorithms can predict if patients will experience an increased LOS following ASD surgery. Therefore, medical resources can be more appropriately allocated towards patients who are at risk of prolonged LOS.

Reflection on modern methods: generalized linear models for prognosis and intervention-theory, practice and implications for machine learning

Prediction and causal explanation are fundamentally distinct tasks of data analysis. In health applications, this difference can be understood in terms of the difference between prognosis (prediction) and prevention/treatment (causal explanation). Nevertheless, these two concepts are often conflated in practice. We use the framework of generalized linear models (GLMs) to illustrate that predictive and causal queries require distinct processes for their application and subsequent interpretation of results. In particular, we identify five primary ways in which GLMs for prediction differ from GLMs for causal inference: (i) the covariates that should be considered for inclusion in (and possibly exclusion from) the model; (ii) how a suitable set of covariates to include in the model is determined; (iii) which covariates are ultimately selected and what functional form (i.e. parameterization) they take; (iv) how the model is evaluated; and (v) how the model is interpreted. We outline some of the potential consequences of failing to acknowledge and respect these differences, and additionally consider the implications for machine learning (ML) methods. We then conclude with three recommendations that we hope will help ensure that both prediction and causal modelling are used appropriately and to greatest effect in health research.

Machine Learning Within Studies of Early-Life Environmental Exposures and Child Health: Review of the Current Literature and Discussion of Next Steps

PURPOSE OF REVIEW

The goal of this article is to review the use of machine learning (ML) within studies of environmental exposures and children's health, identify common themes across studies, and provide recommendations to advance their use in research and practice.

RECENT FINDINGS

We identified 42 articles reporting upon the use of ML within studies of environmental exposures and children's health between 2017 and 2019. The common themes among the articles were analysis of mixture data, exposure prediction, disease prediction and forecasting, analysis of complex data, and causal inference. With the increasing complexity of environmental health data, we anticipate greater use of ML to address the challenges that cannot be handled by traditional analytics. In order for these methods to beneficially impact public health, the ML techniques we use need to be appropriate for our study questions, rigorously evaluated and reported in a way that can be critically assessed by the scientific community.