목적 : To compare the goodness of fit and predictive performance for four pointwise regression models in measuring the visual field (VF) decay rate of progression in patients with open-angle glaucoma.
방법 : We selected Humphrey VF data from patients with open-angle glaucoma with a minimum follow-up time of 6 years. For each eye (n=798 from 588 patients), we regressed the threshold sensitivity (y) at each VF test location for the entire VF series against follow-up time (x) with four candidate first order regression models: 1) ordinary least-squares linear regression model (y=β0+β1x); 2) non-decay exponential regression model (y=β0+β1ex); 3) decay exponential regression model (y=eβ0+β1x); and 4) Tobit censored, maximum-likelihood linear regression model (y*=ß0+ß1x+ε,
결과 : : The average (±SD) baseline VF mean deviation (MD), mean follow-up, and the number of follow-up VFs were −8.2 (±5.5) dB, 8.7 (±1.9) years, and 14.7 (±4.4), respectively. The decay exponential model was the best fitting model (42.7% of locations) and the best forecasting model (65.5% of locations). The decay exponential model was the best prediction model in all categories of severity.
결론 : : It is not clear that the ordinary least-squares linear regression model should persist as the favoured model for fitting and forecasting VF data in glaucoma. The pointwise decay exponential regression (PER) model was the best fitting and predicting model across a wide range of glaucoma severity and can be readily understood by clinicians.
|