1
|
Chowdhury MZI, Leung AA, Walker RL, Sikdar KC, O’Beirne M, Quan H, Turin TC. A comparison of machine learning algorithms and traditional regression-based statistical modeling for predicting hypertension incidence in a Canadian population. Sci Rep 2023; 13:13. [PMID: 36593280 PMCID: PMC9807553 DOI: 10.1038/s41598-022-27264-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2022] [Accepted: 12/29/2022] [Indexed: 01/03/2023] Open
Abstract
Risk prediction models are frequently used to identify individuals at risk of developing hypertension. This study evaluates different machine learning algorithms and compares their predictive performance with the conventional Cox proportional hazards (PH) model to predict hypertension incidence using survival data. This study analyzed 18,322 participants on 24 candidate features from the large Alberta's Tomorrow Project (ATP) to develop different prediction models. To select the top features, we applied five feature selection methods, including two filter-based: a univariate Cox p-value and C-index; two embedded-based: random survival forest and least absolute shrinkage and selection operator (Lasso); and one constraint-based: the statistically equivalent signature (SES). Five machine learning algorithms were developed to predict hypertension incidence: penalized regression Ridge, Lasso, Elastic Net (EN), random survival forest (RSF), and gradient boosting (GB), along with the conventional Cox PH model. The predictive performance of the models was assessed using C-index. The performance of machine learning algorithms was observed, similar to the conventional Cox PH model. Average C-indexes were 0.78, 0.78, 0.78, 0.76, 0.76, and 0.77 for Ridge, Lasso, EN, RSF, GB and Cox PH, respectively. Important features associated with each model were also presented. Our study findings demonstrate little predictive performance difference between machine learning algorithms and the conventional Cox PH regression model in predicting hypertension incidence. In a moderate dataset with a reasonable number of features, conventional regression-based models perform similar to machine learning algorithms with good predictive accuracy.
Collapse
Affiliation(s)
- Mohammad Ziaul Islam Chowdhury
- grid.22072.350000 0004 1936 7697Department of Community Health Sciences, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada ,grid.22072.350000 0004 1936 7697Department of Family Medicine, University of Calgary, 3330 Hospital Drive NW, Calgary, AB T2N 4N1 Canada ,grid.22072.350000 0004 1936 7697Present Address: Department of Psychiatry, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada
| | - Alexander A. Leung
- grid.22072.350000 0004 1936 7697Department of Community Health Sciences, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada ,grid.22072.350000 0004 1936 7697Department of Medicine, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada
| | - Robin L. Walker
- grid.22072.350000 0004 1936 7697Department of Community Health Sciences, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada ,grid.413574.00000 0001 0693 8815Primary Health Care Integration Network, Primary Health Care, Alberta Health Services, Calgary, AB Canada
| | - Khokan C. Sikdar
- grid.413574.00000 0001 0693 8815Health Status Assessment, Surveillance and Reporting, Public Health Surveillance and Infrastructure, Provincial Population and Public Health, Alberta Health Services, 10101 Southport Rd. SW, Calgary, AB T2W 3N2 Canada
| | - Maeve O’Beirne
- grid.22072.350000 0004 1936 7697Department of Family Medicine, University of Calgary, 3330 Hospital Drive NW, Calgary, AB T2N 4N1 Canada
| | - Hude Quan
- grid.22072.350000 0004 1936 7697Department of Community Health Sciences, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada
| | - Tanvir C. Turin
- grid.22072.350000 0004 1936 7697Department of Community Health Sciences, University of Calgary, 3280 Hospital Drive NW, Calgary, AB T2N 4Z6 Canada ,grid.22072.350000 0004 1936 7697Department of Family Medicine, University of Calgary, 3330 Hospital Drive NW, Calgary, AB T2N 4N1 Canada
| |
Collapse
|
2
|
Chowdhury MZI, Naeem I, Quan H, Leung AA, Sikdar KC, O’Beirne M, Turin TC. Prediction of hypertension using traditional regression and machine learning models: A systematic review and meta-analysis. PLoS One 2022; 17:e0266334. [PMID: 35390039 PMCID: PMC8989291 DOI: 10.1371/journal.pone.0266334] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Accepted: 03/19/2022] [Indexed: 11/19/2022] Open
Abstract
OBJECTIVE We aimed to identify existing hypertension risk prediction models developed using traditional regression-based or machine learning approaches and compare their predictive performance. METHODS We systematically searched MEDLINE, EMBASE, Web of Science, Scopus, and the grey literature for studies predicting the risk of hypertension among the general adult population. Summary statistics from the individual studies were the C-statistic, and a random-effects meta-analysis was used to obtain pooled estimates. The predictive performance of pooled estimates was compared between traditional regression-based models and machine learning-based models. The potential sources of heterogeneity were assessed using meta-regression, and study quality was assessed using the PROBAST (Prediction model Risk Of Bias ASsessment Tool) checklist. RESULTS Of 14,778 articles, 52 articles were selected for systematic review and 32 for meta-analysis. The overall pooled C-statistics was 0.75 [0.73-0.77] for the traditional regression-based models and 0.76 [0.72-0.79] for the machine learning-based models. High heterogeneity in C-statistic was observed. The age (p = 0.011), and sex (p = 0.044) of the participants and the number of risk factors considered in the model (p = 0.001) were identified as a source of heterogeneity in traditional regression-based models. CONCLUSION We attempted to provide a comprehensive evaluation of hypertension risk prediction models. Many models with acceptable-to-good predictive performance were identified. Only a few models were externally validated, and the risk of bias and applicability was a concern in many studies. Overall discrimination was similar between models derived from traditional regression analysis and machine learning methods. More external validation and impact studies to implement the hypertension risk prediction model in clinical practice are required.
Collapse
Affiliation(s)
- Mohammad Ziaul Islam Chowdhury
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Family Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Psychiatry, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Iffat Naeem
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Hude Quan
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Alexander A. Leung
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Khokan C. Sikdar
- Health Status Assessment, Surveillance, and Reporting, Public Health Surveillance and Infrastructure, Population, Public and Indigenous Health, Alberta Health Services, Calgary, Alberta, Canada
| | - Maeve O’Beirne
- Department of Family Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Tanvir C. Turin
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Family Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| |
Collapse
|
3
|
Santhanam P, Ahima RS. Machine learning and blood pressure. J Clin Hypertens (Greenwich) 2019; 21:1735-1737. [PMID: 31536164 DOI: 10.1111/jch.13700] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2019] [Accepted: 08/26/2019] [Indexed: 12/25/2022]
Abstract
Machine learning (ML) is a type of artificial intelligence (AI) based on pattern recognition. There are different forms of supervised and unsupervised learning algorithms that are being used to identify and predict blood pressure (BP) and other measures of cardiovascular risk. Since 1999, starting with neural network methods, ML has been used to gauge the relationship between BP and pulse wave forms. Since then, the scope of the research has expanded to using different cardiometabolic risk factors like BMI, waist circumference, waist-to-hip ratio in concert with BP and its various pharmaceutical agents to estimate biochemical measures (like HDL cholesterol, LDL and total cholesterol, fibrinogen, and uric acid) as well as effectiveness of anti-hypertensive regimens. Data from large clinical trials like the SPRINT are being re-analyzed by ML methods to unearth new findings and identify unique relationships between predictors and outcomes. In summary, AI and ML methods are gaining immense attention in the management of chronic disease. Elevated BP is a very important early metric for the risk of development of cardiovascular and renal injury; therefore, advances in AI and ML will aid in early disease prediction and intervention.
Collapse
Affiliation(s)
- Prasanna Santhanam
- Division of Endocrinology, Diabetes, & Metabolism, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Rexford S Ahima
- Division of Endocrinology, Diabetes, & Metabolism, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| |
Collapse
|
4
|
Rezaei-Hachesu P, Oliyaee A, Safaie N, Ferdousi R. Comparison of coronary artery disease guidelines with extracted knowledge from data mining. J Cardiovasc Thorac Res 2017; 9:95-101. [PMID: 28740629 PMCID: PMC5516058 DOI: 10.15171/jcvtr.2017.16] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2016] [Accepted: 03/19/2017] [Indexed: 11/09/2022] Open
Abstract
Introduction: Coronary artery disease (CAD) is one of the major causes of disability and death in the world. Accordingly utilizing from a national and update guideline in heart-related disease are essential. Finding interesting rules from CAD data and comparison with guidelines was the objectives of this study. Methods: In this study 1993 valid and completed records related to patients (from 2009 to 2014) who had suffered from CAD were recruited and analyzed. Total of 25 variable including a target variable (CAD) and 24 inputs or predictor variables were used for knowledge discovery. To perform comparison between extracted knowledge and well trusted guidelines, Canadian Cardiovascular Society (CCS) guideline and US National Institute of Health (NIH) guideline were selected. Results of valid datamining rules were compared with guidelines and then were ranked based on their importance. Results: The most significant factor influencing CAD was chest pain. Elderly males (age >54) have a high probability to be diagnosed with CAD. Diagnostic methods that are listed in guidelines were confirmed and ranked based on analyzing of local CAD patients data. Knowledge discovery revealed that blood test has more diagnostic value among other medical tests that were recommended in guidelines. Conclusion: Guidelines confirm the achieved results from data mining (DM) techniques and help to rank important risk factors based on national and local information. Evaluation of extracted rules determined new patterns for CAD patients.
Collapse
Affiliation(s)
- Peyman Rezaei-Hachesu
- Health Information Technology Department, School of Management and Medical Informatics, Road Traffic Injury Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Azadeh Oliyaee
- Industrial Engineering Faculty, Sharif University Technology, Tehran, Iran
| | - Naser Safaie
- Cardiovascular Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Reza Ferdousi
- Health Information Technology Department, School of Management and Medical Informatics, Road Traffic Injury Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
| |
Collapse
|
5
|
Neural networks for genetic epidemiology: past, present, and future. BioData Min 2008; 1:3. [PMID: 18822147 PMCID: PMC2553772 DOI: 10.1186/1756-0381-1-3] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2008] [Accepted: 07/17/2008] [Indexed: 01/17/2023] Open
Abstract
During the past two decades, the field of human genetics has experienced an information explosion. The completion of the human genome project and the development of high throughput SNP technologies have created a wealth of data; however, the analysis and interpretation of these data have created a research bottleneck. While technology facilitates the measurement of hundreds or thousands of genes, statistical and computational methodologies are lacking for the analysis of these data. New statistical methods and variable selection strategies must be explored for identifying disease susceptibility genes for common, complex diseases. Neural networks (NN) are a class of pattern recognition methods that have been successfully implemented for data mining and prediction in a variety of fields. The application of NN for statistical genetics studies is an active area of research. Neural networks have been applied in both linkage and association analysis for the identification of disease susceptibility genes. In the current review, we consider how NN have been used for both linkage and association analyses in genetic epidemiology. We discuss both the successes of these initial NN applications, and the questions that arose during the previous studies. Finally, we introduce evolutionary computing strategies, Genetic Programming Neural Networks (GPNN) and Grammatical Evolution Neural Networks (GENN), for using NN in association studies of complex human diseases that address some of the caveats illuminated by previous work.
Collapse
|
6
|
Falk CT, Finch SJ, Kim W, Mukhopadhyay ND, Gong B, Hinrichs A, Li X, Liu X, Malhotra A, Mehta T, Page G, Rao S, Saccone N, Shete S, Yang Y, Yu R, Zhao JH, Zhou X. Data mining of RNA expression and DNA genotype data: presentation group 5 contributions to Genetic Analysis Workshop 15. Genet Epidemiol 2007; 31 Suppl 1:S43-50. [PMID: 18046764 DOI: 10.1002/gepi.20279] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
The complexity of data available in human genetics continues to grow at an explosive rate. With that growth, the challenges to understanding the meaning of the underlying information also grow. A currently popular approach to dissecting such information falls under the broad category of data mining. This can apply to any approach that tries to extract relevant information from large amounts of data, but often refers to methods that deal, in a non-linear fashion, with very large numbers of variables that cannot be simultaneously handled by more conventional statistical methods. To explore the usefulness of some of these approaches, 13 groups applied a variety of strategies to the first dataset provided to GAW 15 participants. With the extensive microarray and SNP data provided for 14 CEPH families, these groups explored multistage analyses, machine learning methods, network construction, and other techniques to try to answer questions about gene-gene interaction, functional similarities, co-regulated gene expression and the mapping of gene expression determinants, among others. In general, the methods offered strategies to provide a better understanding of the complex pathways involved in gene expression and function. These are still "works in progress," often exploratory in nature, but they provide insights into ways in which the data might be interpreted. Despite the still preliminary nature of some of these methods and the diversity of the approaches, some common themes emerged. The collection of papers and methods offer a starting point for further exploration of complex interactions in human genetic data now readily available.
Collapse
|
7
|
Abstract
Large population-based cohorts are ideal for the study of common, complex disorders because they allow characterization of gene-gene and gene-environment interactions. We propose a clinical phenome scanning approach to genotype-phenotype association studies, as this approach acknowledges the heterogeneous nature of common diseases and takes advantage of the unprecedented density of phenotypic data available in population-based DNA biobanks. By analogy to genome-wide scanning, the construction of a clinical phenome scan includes a complete scan of all clinically available information (housed in electronic medical records). This is done on a subject-by-subject basis and the resulting phenomes can subsequently be interrogated for association with a single allele for any given gene. By prioritizing phenotype (rather than genotype), this approach allows investigators to ask the question "Which disease is associated with a given gene?" rather than "Which gene is associated with a given disease?".
Collapse
Affiliation(s)
- Nader Ghebranious
- Marshfield Clinic, Molecular Diagnostics Genotyping Laboratory, Marshfield, WI, USA. .,Marshfield Clinic Research Foundation, Center for Human Genetics, Marshfield, WI, USA
| | - Catherine A McCarty
- Marshfield Clinic Research Foundation, Center for Human Genetics, Marshfield, WI, USA
| | - Russell A Wilke
- Marshfield Clinic Research Foundation, Center for Human Genetics, Marshfield, WI, USA.,Marshfield Clinic, Department of Internal Medicine, Marshfield, WI, USA
| |
Collapse
|
8
|
Pan WH, Lynn KS, Chen CH, Wu YL, Lin CY, Chang HY. Using endophenotypes for pathway clusters to map complex disease genes. Genet Epidemiol 2006; 30:143-54. [PMID: 16437587 DOI: 10.1002/gepi.20136] [Citation(s) in RCA: 27] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
Nature determines the complexity of disease etiology and the likelihood of revealing disease genes. While culprit genes for many monogenic diseases have been successfully unraveled, efforts to map major complex disease genes have not been as productive as hoped. The conceptual framework currently adopted to deal with the heterogeneous nature of complex diseases focuses on using homogeneous internal features of the disease phenotype for mapping. However, phenotypic homogeneity does not equal genotypic homogeneity. In this report, we advocate working with well-measured phenotypes portrayed by amounts of transcripts and activities of gene products or their metabolites, which are pertinent to relatively small pathway clusters. Reliable and controlled measures for oligogenic traits resulting from proper dissection efforts may enhance statistical power. The large amounts of information obtained on gene and protein expression from technological advances can add to the power of gene finding, particularly for diseases with unclear etiology. Data-mining tools for dimension reduction can assist biologists to reveal novel molecular endophenotypes. However, there are still hurdles to overcome, including high cost, relatively poor reproducibility and comparability among platforms, the cross-sectional nature of the information, and the accessibility of human tissues. Concerted efforts are required to carry out large-scale prospective studies that are integrated at the levels of phenotype characterization, high throughput experimental techniques, data analyses, and beyond.
Collapse
Affiliation(s)
- Wen-Harn Pan
- Institute of Biomedical Sciences, Academia Sinica, No. 128 Section 2 Academia Road, Taipei, Taiwan 11529.
| | | | | | | | | | | |
Collapse
|
9
|
Costello TJ, Falk CT, Ye KQ. Data mining and computationally intensive methods: summary of Group 7 contributions to Genetic Analysis Workshop 13. Genet Epidemiol 2004; 25 Suppl 1:S57-63. [PMID: 14635170 DOI: 10.1002/gepi.10285] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
The Framingham Heart Study data, as well as a related simulated data set, were generously provided to the participants of the Genetic Analysis Workshop 13 in order that newly developed and emerging statistical methodologies could be tested on that well-characterized data set. The impetus driving the development of novel methods is to elucidate the contributions of genes, environment, and interactions between and among them, as well as to allow comparison between and validation of methods. The seven papers that comprise this group used data-mining methodologies (tree-based methods, neural networks, discriminant analysis, and Bayesian variable selection) in an attempt to identify the underlying genetics of cardiovascular disease and related traits in the presence of environmental and genetic covariates. Data-mining strategies are gaining popularity because they are extremely flexible and may have greater efficiency and potential in identifying the factors involved in complex disorders. While the methods grouped together here constitute a diverse collection, some papers asked similar questions with very different methods, while others used the same underlying methodology to ask very different questions. This paper briefly describes the data-mining methodologies applied to the Genetic Analysis Workshop 13 data sets and the results of those investigations.
Collapse
Affiliation(s)
- Tracy J Costello
- Department of Epidemiology, University of Texas M.D. Anderson Cancer Center, Houston, USA
| | | | | |
Collapse
|