Advertisement

Development of Predictive Models in Patients with Epiphora Using Lacrimal Scintigraphy and Machine Learning

  • Yong-Jin Park
  • Ji Hoon Bae
  • Mu Heon Shin
  • Seung Hyup Hyun
  • Young Seok Cho
  • Yearn Seong Choe
  • Joon Young Choi
  • Kyung-Han Lee
  • Byung-Tae Kim
  • Seung Hwan MoonEmail author
Original Article
  • 10 Downloads

Abstract

Purpose

We developed predictive models using different programming languages and different computing platforms for machine learning (ML) and deep learning (DL) that classify clinical diagnoses in patients with epiphora. We evaluated the diagnostic performance of these models.

Methods

Between January 2016 and September 2017, 250 patients with epiphora who underwent dacryocystography (DCG) and lacrimal scintigraphy (LS) were included in the study. We developed five different predictive models using ML tools, Python-based TensorFlow, R, and Microsoft Azure Machine Learning Studio (MAMLS). A total of 27 clinical characteristics and parameters including variables related to epiphora (VE) and variables related to dacryocystography (VDCG) were used as input data. Apart from this, we developed two predictive convolutional neural network (CNN) models for diagnosing LS images. We conducted this study using supervised learning.

Results

Among 500 eyes of 250 patients, 59 eyes had anatomical obstruction, 338 eyes had functional obstruction, and the remaining 103 eyes were normal. For the data set that excluded VE and VDCG, the test accuracies in Python-based TensorFlow, R, multiclass logistic regression in MAMLS, multiclass neural network in MAMLS, and nuclear medicine physician were 81.70%, 80.60%, 81.70%, 73.10%, and 80.60%, respectively. The test accuracies of CNN models in three-class classification diagnosis and binary classification diagnosis were 72.00% and 77.42%, respectively.

Conclusions

ML-based predictive models using different programming languages and different computing platforms were useful for classifying clinical diagnoses in patients with epiphora and were similar to a clinician’s diagnostic ability.

Keywords

Epiphora Dacryocystography Lacrimal scintigraphy Machine learning Deep learning Convolutional neural network 

Notes

Compliance with Ethical Standards

Conflict of Interest

Yong-Jin Park, Ji Hoon Bae, Mu Heon Shin, Seung Hyup Hyun, Young Seok Cho, Yearn Seong Choe, Joon Young Choi, Kyung-Han Lee, Byung-Tae Kim, and Seung Hwan Moon declare that they have no conflict of interest.

Ethical Approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of our institutional review board and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed Consent

The institutional review board of our institute approved this retrospective study, and the requirement to obtain informed consent was waived.

Supplementary material

13139_2019_574_MOESM1_ESM.docx (28 kb)
ESM 1 (DOCX 27 kb)
13139_2019_574_Fig6_ESM.png (786 kb)
Supplementary Figure 1

(PNG 785 kb)

13139_2019_574_MOESM2_ESM.tif (44.8 mb)
High resolution image (TIF 45920 kb)
13139_2019_574_Fig7_ESM.png (4 mb)
Supplementary Figure 2

(PNG 4086 kb)

13139_2019_574_MOESM3_ESM.tif (163.9 mb)
High resolution image (TIF 167858 kb)
13139_2019_574_Fig8_ESM.png (2.5 mb)
Supplementary Figure 3

(PNG 2527 kb)

13139_2019_574_MOESM4_ESM.tif (197.2 mb)
High resolution image (TIF 201941 kb)

References

  1. 1.
    Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol. 2017;18:570–84.CrossRefGoogle Scholar
  2. 2.
    Choi H. Deep learning in nuclear medicine and molecular imaging: current perspectives and future directions. Nucl Med Mol Imaging. 2018;52:109–18.CrossRefGoogle Scholar
  3. 3.
    Fau KK, Wu D, Fau WD, Gong K, Fau GK, Dutta J, et al. Penalized PET reconstruction using deep learning prior and local linear fitting. IEEE Trans Med Imaging. 2018;37.Google Scholar
  4. 4.
    Choi JY. Radiomics and deep learning in clinical imaging: what should we do? Nucl Med Mol Imaging. 2018;52:89–90.CrossRefGoogle Scholar
  5. 5.
    Muhlestein WE, Akagi DS, Kallos JA, Morone PJ, Weaver KD, Thompson RC, et al. Using a guided machine learning ensemble model to predict discharge disposition following meningioma resection. J Neurol Surg B Skull Base. 2018;79:123–30.CrossRefGoogle Scholar
  6. 6.
    Papp L, Potsch N, Grahovac M, Schmidbauer V, Woehrer A, Preusser M, et al. Glioma survival prediction with combined analysis of in vivo (11)C-MET PET features, ex vivo features, and patient features by supervised machine learning. J Nucl Med. 2018;59:892–9.CrossRefGoogle Scholar
  7. 7.
    Juarez-Orozco LE, Knol RJJ, Sanchez-Catasus CA, Martinez-Manzanera O, van der Zant FM, Knuuti J. Machine learning in the integration of simple variables for identifying patients with myocardial ischemia. J Nucl Cardiol 2018.Google Scholar
  8. 8.
    Betancur J, Otaki Y, Motwani M, Fish MB, Lemley M, Dey D, et al. Prognostic value of combined clinical and myocardial perfusion imaging data using machine learning. J Am Coll Cardiol Img 2017.Google Scholar
  9. 9.
    Vonica OA, Obi E, Sipkova Z, Soare C, Pearson AR. The value of lacrimal scintillography in the assessment of patients with epiphora. Eye (Lond). 2017;31:1020–6.CrossRefGoogle Scholar
  10. 10.
    Sagili S, Selva D, Malhotra R, Malhotra R. Lacrimal scintigraphy: “interpretation more art than science”. Orbit. 2012;31:77–85.CrossRefGoogle Scholar
  11. 11.
    Cuthbertson FM, Webber S. Assessment of functional nasolacrimal duct obstruction—a survey of ophthalmologists in the southwest. Eye (Lond). 2004;18:20–3.CrossRefGoogle Scholar
  12. 12.
    Okser S, Pahikkala T, Airola A, Salakoski T, Ripatti S, Aittokallio T. Regularized machine learning in the genetic prediction of complex traits. PLoS Genet. 2014;10:e1004754.CrossRefGoogle Scholar
  13. 13.
    Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial intelligence in precision cardiovascular medicine. J Am Coll Cardiol. 2017;69:2657–64.CrossRefGoogle Scholar
  14. 14.
    Burlina P, Pacheco KD, Joshi N, Freund DE, Bressler NM. Comparing humans and deep learning performance for grading AMD: a study in using universal deep features and transfer learning for automated AMD analysis. Comput Biol Med. 2017;82:80–6.CrossRefGoogle Scholar
  15. 15.
    Gibbons C, Richards S, Valderas JM, Campbell J. Supervised machine learning algorithms can classify open-text feedback of doctor performance with human-level accuracy. J Med Internet Res. 2017;19:e65.CrossRefGoogle Scholar
  16. 16.
    Sun B, Lam D, Yang D, Grantham K, Zhang T, Mutic S, et al. A machine learning approach to the accurate prediction of monitor units for a compact proton machine. Med Phys. 2018;45:2243–51.CrossRefGoogle Scholar
  17. 17.
    Pan L, Cheng C, Haberkorn U, Dimitrakopoulou-Strauss A. Machine learning-based kinetic modeling: a robust and reproducible solution for quantitative analysis of dynamic PET data. Phys Med Biol. 2017;62:3566–81.CrossRefGoogle Scholar
  18. 18.
    Fontenla-Romero O, Perez-Sanchez B, Guijarro-Berdinas B. LANN-SVD: a non-iterative SVD-based learning algorithm for one-layer neural networks. IEEE Trans Neural Netw Learn Syst 2017:1–6.Google Scholar
  19. 19.
    Yao Y, Rosasco L, Caponnetto A. On early stopping in gradient descent learning. Constr Approx. 2007;26:289–315.CrossRefGoogle Scholar
  20. 20.
    Baldi P, Sadowski P. The dropout learning algorithm. Artif Intell. 2014;210:78–122.CrossRefGoogle Scholar
  21. 21.
    Hira ZM, Gillies DF. A review of feature selection and feature extraction methods applied on microarray data. Adv Bioinforma. 2015;2015:198363.CrossRefGoogle Scholar
  22. 22.
    Figueroa RL, Zeng-Treitler Q, Kandula S, Ngo LH. Predicting sample size required for classification performance. BMC Med Inform Decis Mak. 2012;12:8.CrossRefGoogle Scholar

Copyright information

© Korean Society of Nuclear Medicine 2019

Authors and Affiliations

  • Yong-Jin Park
    • 1
  • Ji Hoon Bae
    • 1
  • Mu Heon Shin
    • 1
  • Seung Hyup Hyun
    • 1
  • Young Seok Cho
    • 1
  • Yearn Seong Choe
    • 1
  • Joon Young Choi
    • 1
  • Kyung-Han Lee
    • 1
  • Byung-Tae Kim
    • 1
  • Seung Hwan Moon
    • 1
    Email author
  1. 1.Departments of Nuclear Medicine, Samsung Medical CenterSungkyunkwan University School of MedicineSeoulSouth Korea

Personalised recommendations