Objective: To compare performance of pointwise linear regression, Glaucoma Change Probability Analysis (GCPA), and the Advanced Glaucoma Intervention Study (AGIS) method in predicting visual field progression in glaucoma.
Design: Longitudinal visual field data from AGIS. Proportion of progressing eyes and time to progression were the main outcome measures. One hundred fifty-six patients with 8 or more years of follow-up were included. Prediction of outcomes at 8 years was used to evaluate the performance of each method (pointwise linear regression, GCPA, and AGIS).
Results: Visual field progression at 8 years was detected in 35%, 31%, and 22% of patients by pointwise linear regression, GCPA, and the AGIS method, respectively. Baseline mean deviation was not different for nonprogressing vs progressing eyes for all methods (P > .05). Pointwise linear regression and GCPA had the highest pairwise concordance (kappa = 0.58 [SD, 0.07]). The false prediction rates at 4 and 8 years varied between 1% and 3%. Glaucoma Change Probability Analysis predicted final outcomes better than pointwise linear regression at 4 years (P = .001).
Conclusions: All algorithms had low false prediction rates. Glaucoma Change Probability Analysis predicted outcomes better than pointwise linear regression early during follow-up. Algorithms did not perform differently as a function of baseline damage. Pointwise linear regression and GCPA did not agree well regarding spatial distribution of worsening test locations.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1001/archopht.125.9.1176 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Bayesian modeling framework for optimizing pre-hospital stroke triage decisions.
J Appl Stat
May 2024
Department of Biostatistics, College of Public Health, University of Iowa, Iowa City, IA, USA.
Ischemic stroke is responsible for significant morbidity and mortality in the United States and worldwide. Stroke treatment optimization requires emergency medical personnel to make rapid triage decisions concerning destination hospitals that may differ in their ability to provide highly time-sensitive pharmaceutical and surgical interventions. These decisions are particularly crucial in rural areas, where transport decisions can have a large impact on treatment times - often involving a trade-off between delay in pharmaceutical therapy or a delay in endovascular thrombectomy.
View Article and Find Full Text PDFAssessing Balance of Baseline Time-Dependent Covariates via the Fréchet Distance.
Biom J
February 2025
Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, Ohio, USA.
Assessment of covariate balance is a key step when performing comparisons between groups particularly in real-world data. We generally evaluate it on baseline covariates, but rarely on longitudinal ones prior to a management decision. We could use pointwise standardized mean differences, standardized differences of slopes, or weights from the model for such purpose.
View Article and Find Full Text PDFPredictive model of castration resistance in advanced prostate cancer by machine learning using genetic and clinical data: KYUCOG-1401-A study.
BJC Rep
September 2024
Department of Urology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
Article Synopsis
- The study aimed to improve predictions of castration resistance in advanced prostate cancer during primary androgen deprivation therapy (ADT) by combining genetic and clinical data using machine learning techniques.
- Researchers utilized clinical data and single nucleotide polymorphisms (SNPs) from Japanese patients treated in the KYUCOG-1401-A study and tested multiple machine learning algorithms, finding that the point-wise linear (PWL) algorithm provided the best predictive performance.
- Results indicated that models incorporating SNPs outperformed clinical data alone in predicting outcomes, showing promise for better treatment choices in advanced prostate cancer management.
A Novel Approach To Predict Glaucomatous Impairment in the Central 10° Visual Field, Excluding the Effect of Cataract.
Transl Vis Sci Technol
October 2024
Department of Ophthalmology, Shimane University Faculty of Medicine, Izumo, Shimane, Japan.
Article Synopsis
- The study aimed to enhance the accuracy of predicting glaucomatous visual field (VF) impairment by using pointwise total deviation (TD) values with a machine-learning method called random forest model (RFM) and examining the role of ganglion cell-inner plexiform layer (GCIPL) thickness.
- Researchers analyzed data from 89 eyes with open-angle glaucoma that had cataract surgery, using various predictive models to calculate mean TD.
- Results showed that RFM provided more accurate predictions than traditional methods, and incorporating GCIPL measurements did not significantly improve the model’s accuracy.
Estimation of Linear Functionals in High-Dimensional Linear Models: From Sparsity to Nonsparsity.
J Am Stat Assoc
June 2023
Professor, Department of Statistics and Operations Research, Department of Genetics, Department of Biostatistics, Carolina Center for Genome Sciences, Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, NC 27599, USA.
High dimensional linear models are commonly used in practice. In many applications, one is interested in linear transformations of regression coefficients , where is a specific point and is not required to be identically distributed as the training data. One common approach is the plug-in technique which first estimates , then plugs the estimator in the linear transformation for prediction.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!