Risk Prediction of Barrett’s Esophagus in a Taiwanese Health Examination Center Based on Regression Models
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Population and Data Collection
2.2. Model Development
3. Results
3.1. Characteristics of the Subjects and Variables Selection
3.2. LR and ANN Models Development and Their Predictive Performance Comparisons
3.3. Final Mean LR Model
- x1 is the age
- x2 is 1 if the sex is male, otherwise 0
- x3 is 1 if the patient has presented GERD symptoms in the past 3 months, otherwise 0
- x4 is 1 if the patient’s cumulative smoking exposure is >0 but ≤20 pack-years, otherwise 0
- x5 is 1 if the patient’s cumulative smoking exposure is >20 pack-years, otherwise 0
4. Discussion
- is the adjusted age
- is 1, because the patient is male.
- is 1, because of the GERD symptoms in the past 3 months.
- is 0, because the cumulative smoking exposure is 0.
- is 0, because the cumulative smoking exposure is 0.
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Di Pietro, M.; Chan, D.; Fitzgerald, R.C.; Wang, K.K. Screening for Barrett’s Esophagus. Gastroenterology 2015, 148, 912–923. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Edgren, G.; Adami, H.O.; Weiderpass, E.; Nyrén, O. A global assessment of the oesophageal adenocarcinoma epidemic. Gut 2013, 62, 1406–1414. [Google Scholar] [CrossRef] [PubMed]
- Hur, C.; Miller, M.; Kong, C.Y.; Dowling, E.C.; Nattinger, K.J.; Dunn, M.; Feuer, E.J. Trends in esophageal adenocarcinoma incidence and mortality. Cancer 2013, 119, 1149–1158. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Fan, Y.J.; Song, X.; Li, J.L.; Li, X.M.; Liu, B.; Wang, R.; Fan, Z.M.; Wang, L.D. Esophageal and gastric cardia cancers on 4238 Chinese patients residing in municipal and rural regions: A histopathological comparison during 24-year period. World J. Surg. 2008, 32, 1980–1988. [Google Scholar] [CrossRef] [PubMed]
- Shibata, A.; Matsuda, T.; Ajiki, W.; Sobueet, T. Trend in incidence of adenocarcinoma of the esophagus in Japan, 1993–2001. Jpn. J. Clin. Oncol. 2008, 38, 464–468. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Shiota, S.; Singh, S.; Anshasi, A.; El-Serag, H.B. Prevalence of Barrett’s Esophagus in Asian Countries: A Systematic Review and Meta-analysis. Clin. Gastroenterol. Hepatol. 2015, 13, 1907–1918. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Ho, K.Y.; Asia-Pacific Barrett’s, C. Is Barrett’s esophagus an over-hyped disease in the West, and an underdiagnosed disease in the East? Dig. Endosc. 2013, 25 (Suppl. 2), 157–161. [Google Scholar] [CrossRef] [Green Version]
- Codipilly, D.C.; Chandar, A.K.; Singh, S.; Wani, S.; Shaheen, N.J.; Inadomi, J.M.; Chak, A.; Iyer, P.G. The Effect of Endoscopic Surveillance in Patients With Barrett’s Esophagus: A Systematic Review and Meta-analysis. Gastroenterology 2018, 154, 2068–2086.e5. [Google Scholar] [CrossRef] [Green Version]
- Fitzgerald, R.C.; Di Pietro, M.; Ragunath, K.; Ang, Y.; Kang, J.Y.; Watson, P.; Trudgill, N.; Patel, P.; Kaye, P.V.; Sanders, S.; et al. British Society of Gastroenterology guidelines on the diagnosis and management of Barrett’s oesophagus. Gut 2014, 63, 7–42. [Google Scholar] [CrossRef] [Green Version]
- Shaheen, N.J.; Falk, G.W.; Iyer, P.G.; Gerson, L.B.; American College of Gastroenterology. ACG Clinical Guideline: Diagnosis and Management of Barrett’s Esophagus. Am. J. Gastroenterol. 2016, 111, 30–50. [Google Scholar] [CrossRef]
- Rubenstein, J.H.; Morgenstern, H.; Appelman, H.; Scheiman, J.; Schoenfeld, P.; McMahon, L.F., Jr.; Metko, V.; Near, E.; Kellenberg, J.; Kalish, T.; et al. Prediction of Barrett’s esophagus among men. Am. J. Gastroenterol. 2013, 108, 353–362. [Google Scholar] [CrossRef] [Green Version]
- Tang, Z.H.; Liu, J.; Zeng, F.; Li, Z.; Yu, X.; Zhou, L. Comparison of prediction model for cardiovascular autonomic dysfunction using artificial neural network and logistic regression analysis. PLoS ONE 2013, 8, e70571. [Google Scholar] [CrossRef] [Green Version]
- Wong, G.L.; Ma, A.J.; Deng, H.; Ching, J.Y.; Wong, V.W.; Tse, Y.K. Machine learning model to predict recurrent ulcer bleeding in patients with history of idiopathic gastroduodenal ulcer bleeding. Aliment Pharmacol. Ther. 2019, 49, 912–918. [Google Scholar] [CrossRef]
- Hsieh, M.H.; Sun, L.-M.; Lin, C.-L.; Hsieh, M.J.; Hsu, C.Y.; Kao, C.H. Development of a prediction model for pancreatic cancer in patients with type 2 diabetes using logistic regression and artificial neural network models. Cancer Manag. Res. 2018, 10, 6317–6324. [Google Scholar] [CrossRef] [Green Version]
- Gaddam, S.; Rastogi, A.; Gupta, N.; Wani, S.B.; Bansal, A.; Singh, M.; Singh, V.; Reddymasu, S.; Moloney, B.; Sharma, P. Prediction of Barrett’s Esophagus (BE) in Patients With Gastroesophageal Reflux Disease (GERD) Using Logistic Regression Model (LRM) and Artificial Neural Network (ANN). Gastrointest. Endosc. 2010, 71, AB245. [Google Scholar] [CrossRef]
- Thrift, A.P.; Kendall, B.J.; Pandeya, N.; Vaughan, T.L.; Whiteman, D.C. Study of Digestive Health. A clinical risk prediction model for Barrett esophagus. Cancer Prev. Res. 2012, 5, 1115–1123. [Google Scholar] [CrossRef] [Green Version]
- Liu, X.; Wong, A.; Kadri, S.R.; Corovic, A.; O’Donovan, M.; Lao-Sirieix, P.; Lovat, L.B.; Burnham, R.W.; Fitzgerald, R.C. Gastro-esophageal reflux disease symptoms and demographic factors as a pre-screening tool for Barrett’s esophagus. PLoS ONE 2014, 9, e94163. [Google Scholar] [CrossRef] [Green Version]
- Ireland, C.J.; Fielder, A.L.; Thompson, S.K.; Laws, T.A.; Watson, D.I.; Esterman, A. Development of a risk prediction model for Barrett’s esophagus in an Australian population. Dis. Esophagus. 2017, 30, 1–8. [Google Scholar] [CrossRef]
- Baldwin-Hunter, B.L.; Knotts, R.M.; Leeds, S.D.; Rubenstein, J.H.; Lightdale, C.J.; Abrams, J.A. Use of the Electronic Health Record to Target Patients for Non-endoscopic Barrett’s Esophagus Screening. Dig. Dis. Sci. 2019, 64, 3463–3470. [Google Scholar] [CrossRef]
- Rosenfeld, A.; Graham, D.G.; Jevons, S.; Ariza, J.; Hagan, D.; Wilson, A.; Lovat, S.J.; Sami, S.S.; Ahmad, O.F.; Novelli, M.; et al. Development and validation of a risk prediction model to diagnose Barrett’s oesophagus (MARK-BE): A case-control machine learning approach. Lancet Digit. Health 2020, 2, E37–E48. [Google Scholar] [CrossRef] [Green Version]
- Lee, H.S.; Jeon, S.W. Barrett esophagus in Asia: Same disease with different pattern. Clin. Endosc. 2014, 47, 15–22. [Google Scholar] [CrossRef] [PubMed]
- Christodoulou, E.; Ma, J.; Collins, G.S.; Steyerberg, E.W.; Verbakel, J.Y.; Calster, B.V. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J. Clin. Epidemiol. 2019, 110, 12–22. [Google Scholar] [CrossRef] [PubMed]
- Abiodun, O.I.; Jantan, A.; Omolara, A.E.; Dada, K.V.; Mohamed, N.A.; Arshad, H. State-of-the-art in artificial neural network applications: A survey. Heliyon 2018, 4, e00938. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Seabold, S.P.J. Statsmodels Econometric and Statistical Modeling with Python. In Proceedings of the 9th Python in Science Conference, Austin, TX, USA, 28 June–3 July; 2010; Volume 57, p. 61. [Google Scholar]
- Pedregosa, F.; Varoquaux, G.; Gramfort, A. Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
- Chollet, F. “Keras”. 2015. Available online: https://github.com/fchollet/keras (accessed on 16 May 2021).
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout:A Simple Way to Prevent Neural Networks from Overfitting. J. Mach. Learn. Res. 2014, 15, 1929–1958. [Google Scholar]
- Wu, S.; Li, G.; Deng, L.; Liu, L.; Xie, Y.; Shi, L. L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks. IEEE Trans. Neural Netw. Learn Syst. 2019, 30, 2043–2051. [Google Scholar] [CrossRef] [Green Version]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Perkins Neil, J.; Schisterman Enrique, F. The Inconsistency of “Optimal” Cut-points Using Two ROC Based Criteria. Am. J. Epidemiol. 2006, 163, 670–675. [Google Scholar]
- Ayer, T.C.J.; Alagoz, O.; Kahn, C.E., Jr.; Woods, R.W.; Burnside, E.S. Informatics in radiology: Comparison of logistic regression and artificial neural network models in breast cancer risk estimation. Radiographics 2010, 30, 13–22. [Google Scholar] [CrossRef] [Green Version]
- Cameron, A.J. Barrett’s esophagus: Prevalence and size of hiatal hernia. Am. J. Gastroenterol. 1999, 94, 2054–2059. [Google Scholar] [CrossRef]
- Fischbach, L.A.; Graham, D.Y.; Kramer, J.R.; Rugge, M.; Verstovsek, G.; Parente, P.; Alsarraj, A.; Fitzgerald, S.; Shaib, Y.; Abraham, N.S.; et al. Association between Helicobacterpylori and Barrett’s esophagus: A case-control study. Am. J. Gastroenterol. 2014, 109, 357–368. [Google Scholar] [CrossRef] [Green Version]
Variables | BE (−) N = 9404 | BE (+) N = 242 | Grand Mean [SD] |
---|---|---|---|
Mean age [SD] (years) | 50.3 [11.7] | 54.7 [11.4] | 50.4 [11.8] |
Gender | |||
Male | 5020 (53.4%) | 184 (76.0%) | |
Female | 4384 (46.6%) | 58 (24.0%) | |
Height [SD] (cm) | 166.0 [8.5] | 168.1 [8.1] | 166.1 [8.5] |
Weight [SD] (kg) | 65.9 [13.2] | 70.8 [12.0] | 66.0 [13.1] |
BMI [SD] (kg/m2) | 23.7 [3.6] | 24.9 [3.1] | 23.8 [3.6] |
Waist circumference [SD] (cm) | 83.8 [9.8] | 87.6 [8.7] | 83.9 [9.8] |
Hypertension | 1597 (17.0%) | 67 (27.7%) | |
Diabetes mellitus | 662 (7.0%) | 31 (12.8%) | |
GERD symptoms | 1605 (17.1%) | 81 (33.5%) | |
Alcohol intake | |||
No | 3992 (42.5%) | 86 (35.5%) | |
Not heavy drinking † | 4973 (52.9%) | 142 (58.7%) | |
Heavy drinking † | 439 (4.7%) | 14 (5.8%) | |
Smoking | |||
Non-smoker | 6711 (71.4%) | 125 (51.7%) | |
≤20 pack-years | 1790 (19.0%) | 61 (25.2%) | |
>20 pack-years | 903 (9.6%) | 56 (23.1%) | |
Having Exercise habits (≥3 times/week and ≥30 mins/time) | 2675 (28.4%) | 77 (31.8%) |
Variables | Odds Ratio | 95%CI | p Value |
---|---|---|---|
Age | 1.03 | 1.01–1.04 | <0.001 * |
Gender (male) | 1.80 | 1.15–2.82 | 0.01 * |
Height (cm) | 0.99 | 0.95–1.03 | 0.63 |
Weight (kg) | 1.01 | 0.97–1.06 | 0.49 |
BMI (kg/m2) | 0.99 | 0.87–1.13 | 0.91 |
Waist circumference (cm) | 1.01 | 0.98–1.04 | 0.66 |
Hypertension | 1.11 | 0.80–1.52 | 0.54 |
Diabetes mellitus | 1.19 | 0.79–1.78 | 0.41 |
GERD symptoms | 2.14 | 1.63–2.83 | <0.001 * |
Alcohol intake | 0.92 | 0.73–1.17 | 0.52 |
Smoking | 1.44 | 1.20–1.72 | <0.001 * |
Having exercise habits | 0.97 | 0.73–1.30 | 0.86 |
Prevalence = 2.51% | LR Model | ANN Model | ||||
---|---|---|---|---|---|---|
Threshold Setting | Sensitivity | Specificity | Accuracy | Sensitivity | Specificity | Accuracy |
Sensitivity~90% | 0.90 | 0.31 | 0.32 | 0.90 | 0.20 | 0.22 |
Specificity~90% | 0.30 | 0.90 | 0.88 | 0.28 | 0.90 | 0.88 |
The Closest to (0,1) Criteria | 0.65 | 0.68 | 0.68 | 0.63 | 0.65 | 0.65 |
Coefficients and Adjusted OR | Performances of Whole Data Input in Final Mean LR Model | |||||
---|---|---|---|---|---|---|
Variables | Adjusted OR | Threshold Setting | Cutoff Point | Sensitivity | Specificity | Accuracy |
Age [SD] | 1.43 | Specificity~90% | 0.67 | 0.30 | 0.90 | 0.88 |
Gender(male) [SD] | 2.01 | Specificity~80% | 0.58 | 0.46 | 0.80 | 0.80 |
GERD [SD] | 2.05 | Sensitivity~90% | 0.33 | 0.90 | 0.32 | 0.33 |
Smoking | Sensitivity~80% | 0.46 | 0.80 | 0.46 | 0.40 | |
Non smokers | 1 | The Closest to (0,1) Criteria | 0.52 | 0.65 | 0.69 | 0.70 |
≤20 pack-years [SD] | 1.34 | |||||
>20 pack-years [SD] | 2.28 | |||||
Intercept |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lin, P.-H.; Hsieh, J.-G.; Yu, H.-C.; Jeng, J.-H.; Hsu, C.-L.; Chen, C.-H.; Wu, P.-C. Risk Prediction of Barrett’s Esophagus in a Taiwanese Health Examination Center Based on Regression Models. Int. J. Environ. Res. Public Health 2021, 18, 5332. https://doi.org/10.3390/ijerph18105332
Lin P-H, Hsieh J-G, Yu H-C, Jeng J-H, Hsu C-L, Chen C-H, Wu P-C. Risk Prediction of Barrett’s Esophagus in a Taiwanese Health Examination Center Based on Regression Models. International Journal of Environmental Research and Public Health. 2021; 18(10):5332. https://doi.org/10.3390/ijerph18105332
Chicago/Turabian StyleLin, Po-Hsiang, Jer-Guang Hsieh, Hsien-Chung Yu, Jyh-Horng Jeng, Chiao-Lin Hsu, Chien-Hua Chen, and Pin-Chieh Wu. 2021. "Risk Prediction of Barrett’s Esophagus in a Taiwanese Health Examination Center Based on Regression Models" International Journal of Environmental Research and Public Health 18, no. 10: 5332. https://doi.org/10.3390/ijerph18105332