TY - JOUR
T1 - Neural network and logistic regression diagnostic prediction models for giant cell arteritis
T2 - Development and validation
AU - Ing, Edsel B.
AU - Miller, Neil R.
AU - Nguyen, Angeline
AU - Su, Wanhua
AU - Bursztyn, Lulu L.C.D.
AU - Poole, Meredith
AU - Kansal, Vinay
AU - Toren, Andrew
AU - Albreki, Dana
AU - Mouhanna, Jack G.
AU - Muladzanov, Alla
AU - Bernier, Mikaël
AU - Gans, Mark
AU - Lee, Dongho
AU - Wendel, Colten
AU - Sheldon, Claire
AU - Shields, Marc
AU - Bellan, Lorne
AU - Lee-Wing, Matthew
AU - Mohadjer, Yasaman
AU - Nijhawan, Navdeep
AU - Tyndel, Felix
AU - Sundaram, Arun N.E.
AU - Ten Hove, Martin W.
AU - Chen, John J.
AU - Rodriguez, Amadeo R.
AU - Hu, Angela
AU - Khalidi, Nader
AU - Ing, Royce
AU - Wong, Samuel W.K.
AU - Torun, Nurhan
N1 - Publisher Copyright:
© 2019 Ing et al.
PY - 2019
Y1 - 2019
N2 - 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).
AB - 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).
KW - Giant cell arteritis
KW - Logistic regression
KW - Neural network
KW - Ophthalmology
KW - Prediction models
KW - Rheumatology
KW - Temporal artery biopsy
UR - http://www.scopus.com/inward/record.url?scp=85065293212&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85065293212&partnerID=8YFLogxK
U2 - 10.2147/OPTH.S193460
DO - 10.2147/OPTH.S193460
M3 - Article
C2 - 30863010
AN - SCOPUS:85065293212
SN - 1177-5467
VL - 13
SP - 421
EP - 430
JO - Clinical Ophthalmology
JF - Clinical Ophthalmology
ER -