Neural network and logistic regression diagnostic prediction models for giant cell arteritis: Development and validation

Edsel B. Ing, Neil R. Miller, Angeline Nguyen, Wanhua Su, Lulu L.C.D. Bursztyn, Meredith Poole, Vinay Kansal, Andrew Toren, Dana Albreki, Jack G. Mouhanna, Alla Muladzanov, Mikaël Bernier, Mark Gans, Dongho Lee, Colten Wendel, Claire Sheldon, Marc Shields, Lorne Bellan, Matthew Lee-Wing, Yasaman MohadjerNavdeep Nijhawan, Felix Tyndel, Arun N.E. Sundaram, Martin W. Ten Hove, John J. Chen, Amadeo R. Rodriguez, Angela Hu, Nader Khalidi, Royce Ing, Samuel W.K. Wong, Nurhan Torun

Research output: Contribution to journalArticle

10 Scopus citations

Abstract

Purpose: To develop and validate neural network (NN) vs logistic regression (LR) diagnostic prediction models in patients with suspected giant cell arteritis (GCA). Design: Multicenter retrospective chart review. Methods: An audit of consecutive patients undergoing temporal artery biopsy (TABx) for suspected GCA was conducted at 14 international medical centers. The outcome variable was biopsy-proven GCA. The predictor variables were age, gender, headache, clinical temporal artery abnormality, jaw claudication, vision loss, diplopia, erythrocyte sedimentation rate, C-reactive protein, and platelet level. The data were divided into three groups to train, validate, and test the models. The NN model with the lowest false-negative rate was chosen. Internal and external validations were performed. Results: Of 1,833 patients who underwent TABx, there was complete information on 1,201 patients, 300 (25%) of whom had a positive TABx. On multivariable LR age, platelets, jaw claudication, vision loss, log C-reactive protein, log erythrocyte sedimentation rate, headache, and clinical temporal artery abnormality were statistically significant predictors of a positive TABx (P≤0.05). The area under the receiver operating characteristic curve/Hosmer-Lemeshow P for LR was 0.867 (95% CI, 0.794, 0.917)/0.119 vs NN 0.860 (95% CI, 0.786, 0.911)/0.805, with no statistically significant difference of the area under the curves (P=0.316). The misclassification rate/false-negative rate of LR was 20.6%/47.5% vs 18.1%/30.5% for NN. Missing data analysis did not change the results. Conclusion: Statistical models can aid in the triage of patients with suspected GCA. Misclassification remains a concern, but cutoff values for 95% and 99% sensitivities are provided (https://goo.gl/THCnuU).

Original languageEnglish (US)
Pages (from-to)421-430
Number of pages10
JournalClinical Ophthalmology
Volume13
DOIs
StatePublished - 2019

Keywords

  • Giant cell arteritis
  • Logistic regression
  • Neural network
  • Ophthalmology
  • Prediction models
  • Rheumatology
  • Temporal artery biopsy

ASJC Scopus subject areas

  • Ophthalmology

Fingerprint Dive into the research topics of 'Neural network and logistic regression diagnostic prediction models for giant cell arteritis: Development and validation'. Together they form a unique fingerprint.

  • Cite this

    Ing, E. B., Miller, N. R., Nguyen, A., Su, W., Bursztyn, L. L. C. D., Poole, M., Kansal, V., Toren, A., Albreki, D., Mouhanna, J. G., Muladzanov, A., Bernier, M., Gans, M., Lee, D., Wendel, C., Sheldon, C., Shields, M., Bellan, L., Lee-Wing, M., ... Torun, N. (2019). Neural network and logistic regression diagnostic prediction models for giant cell arteritis: Development and validation. Clinical Ophthalmology, 13, 421-430. https://doi.org/10.2147/OPTH.S193460