{"doi":"10.1016/j.xops.2023.100454","title":"Performance of Linear Mixed Models in Estimating Structural Rates of Glaucoma Progression Using Varied Random Effect Distributions","abstract":"PurposeTo compare how linear mixed models using Gaussian, Student t, and log-gamma (LG) random effect distributions estimate rates of structural loss in a glaucomatous population using optical coherence tomography (OCT), and to compare model performance to ordinary least squares (OLS) regression.DesignRetrospective cohort study.SubjectsPatients in the Bascom Palmer Glaucoma Repository (BPGR).MethodsEyes with ≥5 reliable peripapillary retinal nerve fiber layer (RNFL) OCT tests over ≥2 years were identified from the BPGR. RNFL thickness values from each reliable test (signal strength ≥ 7/10) and associated timepoints were collected. Data were modeled using ordinary least square (OLS) regression as well as linear mixed models using different random effect distributions. Predictive modeling involved constructing LMMs with (n-1) tests to predict the RNFL thickness of subsequent tests. A total of 1,200 simulated eyes of different baseline RNFL thickness values and progression rates were developed to evaluate likelihood of declared progression and predicted rates.Outcome MeasuresModel fit assessed by Watanabe-Akaike information criterion (WAIC) and mean absolute error (MAE) when predicting future RNFL thickness values. Log-rank test and median time to progression with simulated eyes.ResultsA total of 35,862 OCT scans from 5,766 eyes of 3,491 subjects were included. Mean follow-up period was 7.0±2.3 years, with an average of 6.2±1.4 tests per eye. The Student t model produced the lowest WAIC. In predictive models, all linear mixed models demonstrated significant reduction in MAE when estimating future RNFL thickness values compared to OLS (p<0.001). Gaussian and Student t models were similar and significantly better than the LG model in estimating future RNFL thickness values (p<0.001). Simulated eyes confirmed LMM performance in declaring progression sooner than OLS regression among moderate and fast progressors (p<0.01).ConclusionsLinear mixed models outperformed conventional approaches for estimating rates of OCT RNFL thickness loss in a glaucomatous population. The Student t model provides the best model fit for estimating rates of change in RNFL thickness, although use of the Gaussian or Student t distribution in models led to similar improvements in accurately estimating RNFL loss.","journal":"Ophthalmology Science","year":2023,"id":363266,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":8,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.923,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":294907,"name":"Samuel I. Berchuck","orcid":"0000-0001-5705-3144","position":1,"is_corresponding":false},{"id":515087,"name":"Jinmeng Rao","orcid":"0000-0003-2370-5129","position":2,"is_corresponding":false},{"id":6874,"name":"Felipe A. Medeiros","orcid":"0000-0003-3924-2720","position":3,"is_corresponding":false},{"id":405038,"name":"Swarup S. Swaminathan","orcid":"0000-0001-7198-6602","position":0,"is_corresponding":true}],"reference_count":18,"raw_metadata":null,"created_at":"2026-07-19T01:14:28.054440Z","pmid":"38317870","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}