1
|
Irzan H, Hütel M, O'Reilly H, Ourselin S, Marlow N, Melbourne A. Multi-source multi-modal markers for Bayesian Networks: Application to the extremely preterm born brain. Med Image Anal 2024; 92:103037. [PMID: 38056163 PMCID: PMC7616207 DOI: 10.1016/j.media.2023.103037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2022] [Revised: 10/26/2023] [Accepted: 11/15/2023] [Indexed: 12/08/2023]
Abstract
The preterm phenotype results from the interplay of multiple disorders affecting the brain and cognitive outcomes. Accurately characterising these interactions can reveal prematurity markers. Bayesian Networks (BNs) are powerful tools to disentangle these relationships, as they inherently measure associations between variables while mitigating confounding factors. We present Modified PC-HC (MPC-HC), a Bayesian Network (BN) structural learning algorithm. MPC-HC employs statistical testing and search-and-score techniques to explore equivalent classes. We employ MPC-HC to estimate BNs for extremely preterm (EP) young adults and full-term controls. Using MRI measurements and cognitive performance markers, we investigate predictive relationships and mutual influences through predictions and sensitivity analysis. We assess the confidence in the estimated BN structures using bootstrapping. Furthermore, MPC-HC's validation involves assessing its ability to recover benchmark BN structures. MPC-HC achieves an average prediction accuracy of 72.5% compared to 62.5% of PC, 64.5% of MMHC, and 71.5% of HC, while it outperforms PC, MMHC, and HC algorithms in reconstructing the true structure of benchmark BNs. The sensitivity analysis shows that MRI measurements mainly affect EP cognitive scores. Our work has two key contributions: first, the introduction and validation of a new BN structure learning method. Second, demonstrating the potential of BNs in modelling variable relationships, predicting variables of interest, modelling uncertainty, and evaluating how variables impact each other. Finally, we demonstrate this by characterising complex phenotypes, such as preterm birth, and discovering results consistent with literature findings.
Collapse
Affiliation(s)
- Hassna Irzan
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, SE17EU, UK; Department of Medical Physics and Biomedical Engineering, University College London, London, WC1E6BT, UK.
| | - Michael Hütel
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, SE17EU, UK
| | - Helen O'Reilly
- Institute for Women's Health, University College London, London, WC1E6HU, UK; Department of Psychology, University College Dublin, Dublin, D04C1P1, Ireland
| | - Sebastien Ourselin
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, SE17EU, UK
| | - Neil Marlow
- Institute for Women's Health, University College London, London, WC1E6HU, UK
| | - Andrew Melbourne
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, SE17EU, UK
| |
Collapse
|
2
|
Khanam UA, Gao Z, Adamko D, Kusalik A, Rennie DC, Goodridge D, Chu L, Lawson JA. A scoping review of asthma and machine learning. J Asthma 2023; 60:213-226. [PMID: 35171725 DOI: 10.1080/02770903.2022.2043364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
OBJECTIVE The objective of this study was to determine the extent of machine learning (ML) application in asthma research and to identify research gaps while mapping the existing literature. DATA SOURCES We conducted a scoping review. PubMed, ProQuest, and Embase Scopus databases were searched with an end date of September 18, 2020. STUDY SELECTION DistillerSR was used for data management. Inclusion criteria were an asthma focus, human participants, ML techniques, and written in English. Exclusion criteria were abstract only, simulation-based, not human based, or were reviews or commentaries. Descriptive statistics were presented. RESULTS A total of 6,317 potential articles were found. After removing duplicates, and reviewing the titles and abstracts, 102 articles were included for the full text analysis. Asthma episode prediction (24.5%), asthma phenotype classification (16.7%), and genetic profiling of asthma (12.7%) were the top three study topics. Cohort (52.9%), cross-sectional (20.6%), and case-control studies (11.8%) were the study designs most frequently used. Regarding the ML techniques, 34.3% of the studies used more than one technique. Neural networks, clustering, and random forests were the most common ML techniques used where they were used in 20.6%, 18.6%, and 17.6% of studies, respectively. Very few studies considered location of residence (i.e. urban or rural status). CONCLUSIONS The use of ML in asthma studies has been increasing with most of this focused on the three major topics (>50%). Future research using ML could focus on gaps such as a broader range of study topics and focus on its use in additional populations (e.g. location of residence). Supplemental data for this article is available online at http://dx.doi.org/ .
Collapse
Affiliation(s)
- Ulfat A Khanam
- Health Sciences Program, College of Medicine, Canadian Centre for Health and Safety in Agriculture, Respiratory Research Centre, University of Saskatchewan, Saskatoon, SK, Canada
| | - Zhiwei Gao
- Department of Medicine, Memorial University of Newfoundland, St. John's, NL, Canada
| | - Darryl Adamko
- Department of Paediatrics, College of Medicine, University of Saskatchewan, Saskatoon, SK, Canada
| | - Anthony Kusalik
- Department of Computer Science, College of Arts and Science, University of Saskatchewan, Saskatoon, SK, Canada
| | - Donna C Rennie
- College of Nursing and Canadian Centre for Health and Safety in Agriculture, University of Saskatchewan, Saskatoon, SK, Canada
| | - Donna Goodridge
- Department of Medicine, College of Medicine, University of Saskatchewan, Saskatoon, SK, Canada
| | - Luan Chu
- Provincial Research Data Services, Alberta Health Service, Calgary, AB, Canada
| | - Joshua A Lawson
- Department of Medicine, Canadian Centre for Health and Safety in Agriculture, and Respiratory Research Centre, College of Medicine, University of Saskatchewan, Saskatoon, SK, Canada
| |
Collapse
|
3
|
Li J, Wang Y, Sheng Q, Liu X, Xing Z, Sun F, Wang Y, Li S, Li Y, Yu Y, Yu G. Interpretable modeling and discovery of key predictors for pneumonia diagnosis in children based on electronic medical records. Digit Health 2022; 8:20552076221131185. [PMID: 36276188 PMCID: PMC9583222 DOI: 10.1177/20552076221131185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2022] [Accepted: 09/20/2022] [Indexed: 11/15/2022] Open
Abstract
Background Community-acquired pneumonia is one of the most common infectious diseases in children and is a leading cause of death among children under 5 years of age, resulting in high rates of antibiotic usage and hospitalization. It is of extremely practical significance to make full use of the existing electronic medical records to study pneumonia and to establish automatic diagnosis models for pneumonia. Methods We established pneumonia diagnosis models of Bayesian network using a total of 13,448 electronic medical records. We investigated learning network structure and parameter estimation and evaluated different structure learning strategies and various modeling methods. By identifying the key predictors of model, the pneumonia status was analyzed. Results The performance of the proposed Bayesian network was evaluated using a set of 3361 cases with a precision of 0.7861, a recall of 0.9889, and an F1-score of 0.8759. On an independent external validation set containing 4925 cases, Bayesian network achieved a precision of 0.7382, a recall of 0.9947, and an F1-score of 0.8475. Our proposed Bayesian network outperformed all other methods, including CatBoost, XGBoost, LightGBM, logistic regression, and ridge classification. Conclusion The appropriate feature selection improved the performance of Bayesian networks. The proposed Bayesian network had good generalizability and could be directly applied to clinical research centers. And the key predictors identified by the network demonstrated good clinical interpretability, allowing for a better understanding of pneumonia status and complications. This study had important clinical value and practical significance for the research and diagnosis of pediatric pneumonia.
Collapse
Affiliation(s)
- Jing Li
- Department of Data and Information, The Children's Hospital,
Zhejiang University School of Medicine, Hangzhou, China,Sino-Finland Joint AI Laboratory for Child Health of Zhejiang
Province, Hangzhou, China
| | - Yingshuo Wang
- Department of Pulmonology, The Children's Hospital, Zhejiang
University School of Medicine, Hangzhou, China
| | - Qiuyang Sheng
- Deepwise Healthcare Artificial Intelligence Laboratory, Beijing,
China
| | - Xiaoqing Liu
- Deepwise Healthcare Artificial Intelligence Laboratory, Beijing,
China
| | - Zijian Xing
- Deepwise Healthcare Artificial Intelligence Laboratory, Beijing,
China
| | - Fenglei Sun
- Deepwise Healthcare Artificial Intelligence Laboratory, Beijing,
China
| | - Yuqi Wang
- Department of Pulmonology, The Children's Hospital, Zhejiang
University School of Medicine, Hangzhou, China
| | - Shuxian Li
- Department of Pulmonology, The Children's Hospital, Zhejiang
University School of Medicine, Hangzhou, China
| | - Yiming Li
- Deepwise Healthcare Artificial Intelligence Laboratory, Beijing,
China
| | - Yizhou Yu
- Deepwise Healthcare Artificial Intelligence Laboratory, Beijing,
China,Yizhou Yu, Deepwise Healthcare Artificial
Intelligence Laboratory, 13th Floor, Building 2, Yard 2, Xisanhuan North Road,
Haidian District, Beijing, China.
| | - Gang Yu
- Department of Data and Information, The Children's Hospital,
Zhejiang University School of Medicine, Hangzhou, China,Sino-Finland Joint AI Laboratory for Child Health of Zhejiang
Province, Hangzhou, China,Polytechnic Institute, Zhejiang University, Hangzhou, China ,Gang Yu, Department of Data and
Information, The Children’s Hospital, Zhejiang University School of Medicine,
3333 Binsheng Road, Binjiang District, Hangzhou 310052, China.
| |
Collapse
|
4
|
Research on the Influence Mechanism of Street Vitality in Mountainous Cities Based on a Bayesian Network: A Case Study of the Main Urban Area of Chongqing. LAND 2022. [DOI: 10.3390/land11050728] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
As the main spatial carrier for people’s social activities, street space occupies an important position in the urban space. However, under the direction of traffic-driven urban planning, the social function of street space has been neglected, resulting in the gradual loss of vitality. In mountainous cities with rugged terrain, the factors influencing the vitality of streets may be different compared to those in plain areas. In order to explore the influence mechanism of street vitality in mountainous cities, a new quantitative research method based on the new data environment and a Bayesian network is proposed. In this study, Python and GIS are used to obtain spatial data of streets, and Bayesian networks are used to construct street vitality models to identify important influencing factors and causal relationships between influencing factors. The results demonstrate strong causal dependencies between the factors influencing street vitality in mountainous cities. The mechanism of influence of street vitality revolves around functionality and street texture in terms of its own environment and external environment, respectively. The combination of factor group with functional density as the root node achieved the maximum probability of high vitality of the street. The results of this study have implications for community or urban planners with respect to urban regeneration and street vitality promotion.
Collapse
|
5
|
Filipow N, Main E, Sebire NJ, Booth J, Taylor AM, Davies G, Stanojevic S. Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review. BMJ Open Respir Res 2022; 9:9/1/e001165. [PMID: 35297371 PMCID: PMC8928277 DOI: 10.1136/bmjresp-2021-001165] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Accepted: 03/06/2022] [Indexed: 11/23/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Nicole Filipow
- UCL Great Ormond Street Institute of Child Health, University College London, London, UK
| | - Eleanor Main
- UCL Great Ormond Street Institute of Child Health, University College London, London, UK
| | - Neil J Sebire
- Population, Policy and Practice Research and Teaching Department, UCL Great Ormond Street Institute of Child Health, University College London, London, UK.,GOSH NIHR BRC, Great Ormond Street Hospital for Children, London, UK
| | - John Booth
- Population, Policy and Practice Research and Teaching Department, UCL Great Ormond Street Institute of Child Health, University College London, London, UK.,GOSH NIHR BRC, Great Ormond Street Hospital for Children, London, UK
| | - Andrew M Taylor
- GOSH NIHR BRC, Great Ormond Street Hospital for Children, London, UK.,Institute of Cardiovascular Science, University College London, London, UK
| | - Gwyneth Davies
- Population, Policy and Practice Research and Teaching Department, UCL Great Ormond Street Institute of Child Health, University College London, London, UK.,GOSH NIHR BRC, Great Ormond Street Hospital for Children, London, UK
| | - Sanja Stanojevic
- Community Health and Epidemiology, Dalhousie University, Halifax, Nova Scotia, Canada
| |
Collapse
|
6
|
Kyrimi E, Dube K, Fenton N, Fahmi A, Neves MR, Marsh W, McLachlan S. Bayesian networks in healthcare: What is preventing their adoption? Artif Intell Med 2021; 116:102079. [PMID: 34020755 DOI: 10.1016/j.artmed.2021.102079] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2020] [Revised: 04/14/2021] [Accepted: 04/20/2021] [Indexed: 12/15/2022]
Abstract
There has been much research effort expended toward the use of Bayesian networks (BNs) in medical decision-making. However, because of the gap between developing an accurate BN and demonstrating its clinical usefulness, this has not resulted in any widespread BN adoption in clinical practice. This paper investigates this problem with the aim of finding an explanation and ways to address the problem through a comprehensive literature review of articles describing BNs in healthcare. Based on the literature collection that has been systematically narrowed down from 3810 to 116 most relevant articles, this paper analyses the benefits, barriers and facilitating factors (BBF) for implementing BN-based systems in healthcare using the ITPOSMO-BBF framework. A key finding is that works in the literature rarely consider barriers and even when these were identified they were not connected to facilitating factors. The main finding is that the barriers can be grouped into: (1) data inadequacies; (2) clinicians' resistance to new technologies; (3) lack of clinical credibility; (4) failure to demonstrate clinical impact; (5) absence of an acceptable predictive performance; and (6) absence of evidence for model's generalisability. The facilitating factors can be grouped into: (1) data collection improvements; (2) software and technological improvements; (3) having interpretable and easy to use BN-based systems; (4) clinical involvement in the development or review of the model; (5) investigation of model's clinical impact; (6) internal validation of the model's performance; and (7) external validation of the model. These groupings form a strong basis for a generic framework that could be used for formulating strategies for ensuring BN-based clinical decision-support system adoption in frontline care settings. The output of this review is expected to enhance the dialogue among researchers by providing a deeper understanding for the neglected issue of BN adoption in practice and promoting efforts for implementing BN-based systems.
Collapse
Affiliation(s)
- Evangelia Kyrimi
- School of Electronic Engineering & Computer Science, Queen Mary University of London, Mile End Road, London, E1 4NS, UK.
| | - Kudakwashe Dube
- Health Informatics and Knowledge Engineering Research (HiKER) Group; School of Fundamental Sciences, Massey University, Palmerston North, 4442, New Zealand
| | - Norman Fenton
- School of Electronic Engineering & Computer Science, Queen Mary University of London, Mile End Road, London, E1 4NS, UK
| | - Ali Fahmi
- School of Electronic Engineering & Computer Science, Queen Mary University of London, Mile End Road, London, E1 4NS, UK
| | - Mariana Raniere Neves
- School of Electronic Engineering & Computer Science, Queen Mary University of London, Mile End Road, London, E1 4NS, UK
| | - William Marsh
- School of Electronic Engineering & Computer Science, Queen Mary University of London, Mile End Road, London, E1 4NS, UK
| | - Scott McLachlan
- School of Electronic Engineering & Computer Science, Queen Mary University of London, Mile End Road, London, E1 4NS, UK; Health Informatics and Knowledge Engineering Research (HiKER) Group
| |
Collapse
|
7
|
Xiang Y, Ji H, Zhou Y, Li F, Du J, Rasmy L, Wu S, Zheng WJ, Xu H, Zhi D, Zhang Y, Tao C. Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study. J Med Internet Res 2020; 22:e16981. [PMID: 32735224 PMCID: PMC7428917 DOI: 10.2196/16981] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2019] [Revised: 03/02/2020] [Accepted: 05/13/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Asthma exacerbation is an acute or subacute episode of progressive worsening of asthma symptoms and can have a significant impact on patients' quality of life. However, efficient methods that can help identify personalized risk factors and make early predictions are lacking. OBJECTIVE This study aims to use advanced deep learning models to better predict the risk of asthma exacerbations and to explore potential risk factors involved in progressive asthma. METHODS We proposed a novel time-sensitive, attentive neural network to predict asthma exacerbation using clinical variables from large electronic health records. The clinical variables were collected from the Cerner Health Facts database between 1992 and 2015, including 31,433 adult patients with asthma. Interpretations on both patient and cohort levels were investigated based on the model parameters. RESULTS The proposed model obtained an area under the curve value of 0.7003 through a five-fold cross-validation, which outperformed the baseline methods. The results also demonstrated that the addition of elapsed time embeddings considerably improved the prediction performance. Further analysis observed diverse distributions of contributing factors across patients as well as some possible cohort-level risk factors, which could be found supporting evidence from peer-reviewed literature such as respiratory diseases and esophageal reflux. CONCLUSIONS The proposed neural network model performed better than previous methods for the prediction of asthma exacerbation. We believe that personalized risk scores and analyses of contributing factors can help clinicians better assess the individual's level of disease progression and afford the opportunity to adjust treatment, prevent exacerbation, and improve outcomes.
Collapse
Affiliation(s)
- Yang Xiang
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Hangyu Ji
- Division of Gastroenterology, Guang'anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| | - Yujia Zhou
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Fang Li
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Jingcheng Du
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Laila Rasmy
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Stephen Wu
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - W Jim Zheng
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Hua Xu
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Degui Zhi
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Yaoyun Zhang
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| | - Cui Tao
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United States
| |
Collapse
|
8
|
Bayesian networks in healthcare: Distribution by medical condition. Artif Intell Med 2020; 107:101912. [DOI: 10.1016/j.artmed.2020.101912] [Citation(s) in RCA: 42] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2020] [Revised: 04/27/2020] [Accepted: 06/09/2020] [Indexed: 12/11/2022]
|
9
|
Do QT, Doig AK, Son TC. Deep Q-learning for Predicting Asthma Attack with Considering Personalized Environmental Triggers' Risk Scores. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020; 2019:562-565. [PMID: 31945961 DOI: 10.1109/embc.2019.8857172] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
The purpose of our present study was to develop a forecasting method that would help asthmatic individuals to take evasive action when the probability of an attack was at THEIR PERSONAL THRESHOLD levels. The results are encouraging. Risk factor analysis helps improve the agent's performance (by allowing it to consider personalized risk score of asthma attack triggers while making a decision and being able to ignore the non-triggers), increasing transparency of deep reinforcement learning in medicine applications (by using the results of analyzing risk factors and its association to take actions), and increase accuracy over time since the association risk factor indicators are also changing over time with more accuracy rate. It also brings the possibility of including population-based health in personalized health, which could support a more efficient self-management of chronic diseases.
Collapse
|
10
|
Deng H, Urman R, Gilliland FD, Eckel SP. Understanding the importance of key risk factors in predicting chronic bronchitic symptoms using a machine learning approach. BMC Med Res Methodol 2019; 19:70. [PMID: 30925901 PMCID: PMC6441159 DOI: 10.1186/s12874-019-0708-x] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2018] [Accepted: 03/11/2019] [Indexed: 12/21/2022] Open
Abstract
BACKGROUND Chronic respiratory symptoms involving bronchitis, cough and phlegm in children are underappreciated but pose a significant public health burden. Efforts for prevention and management could be supported by an understanding of the relative importance of determinants, including environmental exposures. Thus, we aim to develop a prediction model for bronchitic symptoms. METHODS Schoolchildren from the population-based southern California Children's Health Study were visited annually from 2003 to 2012. Bronchitic symptoms over the prior 12 months were assessed by questionnaire. A gradient boosting model was fit using groups of risk factors (including traffic/air pollution exposures) for all children and by asthma status. Training data consisted of one observation per participant in a random study year (for 50% of participants). Validation data consisted of: (1) a random (later) year in the same participants (within-participant); (2) a random year in participants excluded from the training data (across-participant). RESULTS At baseline, 13.2% of children had asthma and 18.1% reported bronchitic symptoms. Models performed similarly within- and across-participant. Previous year symptoms/medication use provided much of the predictive ability (across-participant area under the receiver operating characteristic curve (AUC): 0.76 vs 0.78 for all risk factors, in all participants). Traffic/air pollution exposures added modestly to prediction as did body mass index percentile, age and parent stress. CONCLUSIONS Regardless of asthma status, previous symptoms were the most important predictors of current symptoms. Traffic/air pollution variables contribute modest predictive information, but impact large populations. Methods proposed here could be generalized to personalized exacerbation predictions in future longitudinal studies to support targeted prevention efforts.
Collapse
Affiliation(s)
- Huiyu Deng
- Department of Preventive Medicine, University of Southern California, 2001 N. Soto Street, MC-9234, Los Angeles, CA, 90089, USA
| | - Robert Urman
- Department of Preventive Medicine, University of Southern California, 2001 N. Soto Street, MC-9234, Los Angeles, CA, 90089, USA
| | - Frank D Gilliland
- Department of Preventive Medicine, University of Southern California, 2001 N. Soto Street, MC-9234, Los Angeles, CA, 90089, USA
| | - Sandrah P Eckel
- Department of Preventive Medicine, University of Southern California, 2001 N. Soto Street, MC-9234, Los Angeles, CA, 90089, USA.
| |
Collapse
|