{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:52:00Z","timestamp":1782384720223,"version":"3.54.5"},"posted":{"date-parts":[[2026,6,25]]},"group-title":"In Review","reference-count":40,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,11]]},"abstract":"<title>Abstract<\/title>\n                <p>Glaucoma progression forecasting from sparse longitudinal data remains unsolved, as existing models require dense multi-year inputs and lack the biological constraints. We introduce a sparse-observation framework that predicts multi-horizon outcomes from only two visits, incorporating a novel TCMH (Temporally Consistent Multi-Horizon) loss that enforces monotonic risk ordering to reflect irreversible disease biology. Applied to glaucoma progression, we integrate circumpapillary retinal nerve fiber layer (cpRNFL) images, visual field total deviation (VFTD) maps, and clinical covariates through ConvNeXt architecture trained with TCMH loss. In 3,593 patients (13,087 sequences), our model achieved AUROC 0.968 and accuracy 0.947 for two-, three-, and four-year progression forecasting, with 10.2% better calibration than baseline and 0.0163 maximum demographic disparity. At 90% coverage, classification error remained 2.5%, enabling automated risk stratification with expert review for only uncertain cases. The model exceeded three independent specialist graders on specificity (0.98 vs. 0.57\u20130.73) on 108 held-out eyes. These results establish sparse-observation temporally consistent forecasting as a generalizable paradigm for calibrated long-horizon risk prediction in irreversible progressive diseases.<\/p>","DOI":"10.21203\/rs.3.rs-10009600\/v1","type":"posted-content","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:20:49Z","timestamp":1782382849000},"source":"Crossref","is-referenced-by-count":0,"title":["Sparse-Observation Multi-Horizon Glaucoma Progression Forecasting with Biologically Constrained Temporal Consistency: A Glaucoma Case Study"],"prefix":"10.21203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1763-9401","authenticated-orcid":false,"given":"Nazlee","family":"Zebardast","sequence":"first","affiliation":[{"name":"Massachusetts Eye and Ear"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0020-7365","authenticated-orcid":false,"given":"Mousa","family":"Moradi","sequence":"additional","affiliation":[{"name":"Harvard Ophthalmology AI Lab, Schepens Eye Research Institute, Massachusetts Eye and Ear, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0263-9937","authenticated-orcid":false,"given":"Jerry","family":"Cao-Xue","sequence":"additional","affiliation":[{"name":"University of Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2251-4363","authenticated-orcid":false,"given":"Asahi","family":"Fujita","sequence":"additional","affiliation":[{"name":"Massachusetts Eye and Ear, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Liebman","sequence":"additional","affiliation":[{"name":"Massachusetts Eye and Ear, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5341-8353","authenticated-orcid":false,"given":"Alessandro","family":"Jammal","sequence":"additional","affiliation":[{"name":"Massachusetts Eye and Ear, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Harvard Ophthalmology AI lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2032-0496","authenticated-orcid":false,"given":"Tobias","family":"Elze","sequence":"additional","affiliation":[{"name":"Massachusetts Eye and Ear"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6570-2826","authenticated-orcid":false,"given":"Mohammad","family":"Eslami","sequence":"additional","affiliation":[{"name":"Harvard Ophthalmology AI lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1001\/jama.2014.3192","article-title":"The pathophysiology and treatment of glaucoma: a review","volume":"311","author":"Weinreb RN","year":"2014","unstructured":"Weinreb RN, Aung T, Medeiros FA (2014) The pathophysiology and treatment of glaucoma: a review. JAMA 311:1901\u20131911","journal-title":"JAMA"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/1471-2415-10-31","article-title":"Clinical risk factors for age-related macular degeneration: a systematic review and meta-analysis","volume":"10","author":"Chakravarthy U","year":"2010","unstructured":"Chakravarthy U et al (2010) Clinical risk factors for age-related macular degeneration: a systematic review and meta-analysis. BMC Ophthalmol 10:31","journal-title":"BMC Ophthalmol"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1056\/NEJMra1005073","article-title":"Mechanisms of disease diabetic retinopathy","volume":"366","author":"David A","year":"2012","unstructured":"David A, Klein R, Gardner T (2012) Mechanisms of disease diabetic retinopathy. N Engl Med J 366:1227\u20131239","journal-title":"N Engl Med J"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1136\/bjo.2005.081224","article-title":"The number of people with glaucoma worldwide in 2010 and 2020","volume":"90","author":"Quigley HA","year":"2006","unstructured":"Quigley HA, Broman AT (2006) The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol 90:262\u2013267","journal-title":"Br J Ophthalmol"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"556","DOI":"10.2337\/dc11-1909","article-title":"Global prevalence and major risk factors of diabetic retinopathy","volume":"35","author":"Yau JW","year":"2012","unstructured":"Yau JW et al (2012) Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care 35:556\u2013564","journal-title":"Diabetes Care"},{"key":"ref6","author":"Wong WanLing WW","year":"2014","unstructured":"Wong WanLing WW et al (2014) Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"106512","DOI":"10.1016\/j.compbiomed.2022.106512","article-title":"Deep ensemble learning for automated non-advanced AMD classification using optimized retinal layer segmentation and SD-OCT scans","volume":"154","author":"Moradi M","year":"2023","unstructured":"Moradi M, Chen Y, Du X, Seddon JM (2023) Deep ensemble learning for automated non-advanced AMD classification using optimized retinal layer segmentation and SD-OCT scans. Comput Biol Med 154:106512. 10.1016\/j.compbiomed.2022.106512","journal-title":"Comput Biol Med"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"e144","DOI":"10.1016\/S2214-109X(20)30489-7","article-title":"GBD 2019 Blindness and Vision Impairment Collaborators. Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: The Right to Sight: An analysis for the Global Burden of Disease Study","volume":"9","author":"Bourne R","year":"2021","unstructured":"Bourne R et al (2021) GBD 2019 Blindness and Vision Impairment Collaborators. Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: The Right to Sight: An analysis for the Global Burden of Disease Study. Lancet Glob Health 9:e144\u2013e160","journal-title":"Lancet Glob Health"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1016\/j.ophtha.2020.12.020","article-title":"Assessing glaucoma progression using machine learning trained on longitudinal visual field and clinical data","volume":"128","author":"Dixit A","year":"2021","unstructured":"Dixit A, Yohannan J, Boland MV (2021) Assessing glaucoma progression using machine learning trained on longitudinal visual field and clinical data. Ophthalmology 128:1016\u20131026","journal-title":"Ophthalmology"},{"key":"ref10","article-title":"Predicting longitudinal visual field progression with class imbalanced data","author":"Chen L","year":"2025","unstructured":"Chen L, Chen C-H, Wang W, Lu D-W, Tseng VS (2025) Predicting longitudinal visual field progression with class imbalanced data. IEEE J Biomedical Health Inf","journal-title":"IEEE J Biomedical Health Inf"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring fairness in machine learning to advance health equity","volume":"169","author":"Rajkomar A","year":"2018","unstructured":"Rajkomar A, Hardt M, Howell MD, Corrado G, Chin MH (2018) Ensuring fairness in machine learning to advance health equity. Ann Intern Med 169:866\u2013872","journal-title":"Ann Intern Med"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1080\/09286580701501931","article-title":"Open-angle glaucoma\u2014an epidemiologic overview","volume":"14","author":"Leske MC","year":"2007","unstructured":"Leske MC (2007) Open-angle glaucoma\u2014an epidemiologic overview. Ophthalmic Epidemiol 14:166\u2013172","journal-title":"Ophthalmic Epidemiol"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"e70094","DOI":"10.1002\/sim.70094","article-title":"Why Recommended Visit Intervals Should Be Extracted When Conducting Longitudinal Analyses Using Electronic Health Record Data: Examining Visit Mechanism and Sensitivity to Assessment Not at Random","volume":"44","author":"Garrett RH","year":"2025","unstructured":"Garrett RH, Patel M, Feldman BM, Pullenayegum EM (2025) Why Recommended Visit Intervals Should Be Extracted When Conducting Longitudinal Analyses Using Electronic Health Record Data: Examining Visit Mechanism and Sensitivity to Assessment Not at Random. Stat Med 44:e70094","journal-title":"Stat Med"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1001\/jamaophthalmol.2019.3501","article-title":"Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs","volume":"137","author":"Liu H","year":"2019","unstructured":"Liu H et al (2019) Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. JAMA Ophthalmol 137:1353\u20131360","journal-title":"JAMA Ophthalmol"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"Fauw J","year":"2018","unstructured":"De Fauw J et al (2018) Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med 24:1342\u20131350","journal-title":"Nat Med"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"57125","DOI":"10.52202\/075280-2498","article-title":"Transformers as statisticians: Provable in-context learning with in-context algorithm selection","volume":"36","author":"Bai Y","year":"2023","unstructured":"Bai Y, Chen F, Wang H, Xiong C, Mei S (2023) Transformers as statisticians: Provable in-context learning with in-context algorithm selection. Adv Neural Inf Process Syst 36:57125\u201357211","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.ophtha.2019.09.036","article-title":"Deep learning approaches predict glaucomatous visual field damage from OCT optic nerve head en face images and retinal nerve fiber layer thickness maps","volume":"127","author":"Christopher M","year":"2020","unstructured":"Christopher M et al (2020) Deep learning approaches predict glaucomatous visual field damage from OCT optic nerve head en face images and retinal nerve fiber layer thickness maps. Ophthalmology 127:346\u2013356","journal-title":"Ophthalmology"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1109\/JBHI.2019.2949075","article-title":"Clinical interpretable deep learning model for glaucoma diagnosis","volume":"24","author":"Liao W","year":"2019","unstructured":"Liao W et al (2019) Clinical interpretable deep learning model for glaucoma diagnosis. IEEE J biomedical health Inf 24:1405\u20131412","journal-title":"IEEE J biomedical health Inf"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1109\/TBME.2013.2295605","article-title":"Glaucoma progression detection using structural retinal nerve fiber layer measurements and functional visual field points","volume":"61","author":"Yousefi S","year":"2013","unstructured":"Yousefi S et al (2013) Glaucoma progression detection using structural retinal nerve fiber layer measurements and functional visual field points. IEEE Trans Biomed Eng 61:1143\u20131154","journal-title":"IEEE Trans Biomed Eng"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1831","DOI":"10.3390\/healthcare10101831","article-title":"Classification algorithms used in predicting glaucoma progression","volume":"10","author":"Tarcoveanu F","year":"2022","unstructured":"Tarcoveanu F et al (2022) Classification algorithms used in predicting glaucoma progression. Healthcare 10:1831","journal-title":"Healthcare"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1038\/s41746-025-01884-9","article-title":"Equity-enhanced glaucoma progression prediction from OCT with knowledge distillation","volume":"8","author":"Afolabi SO","year":"2025","unstructured":"Afolabi SO et al (2025) Equity-enhanced glaucoma progression prediction from OCT with knowledge distillation. npj Digit Med 8:477","journal-title":"npj Digit Med"},{"key":"ref22","author":"Liu Z","year":"2022","unstructured":"Liu Z et al (2022) A convnet for the 2020s. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 11976\u201311986"},{"key":"ref23","author":"Dosovitskiy A","year":"2010","unstructured":"Dosovitskiy A et al An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:(2010). 11929 (2020)"},{"key":"ref24","author":"Howard AG","year":"2017","unstructured":"Howard AG et al (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"ref25","author":"Tan M","year":"2019","unstructured":"Tan M (2019) doi rethinking model scaling for convolutional neural networks. arXiv. : 10.48550. ArXiv (1905)"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1109\/TITB.2012.2218661","article-title":"Novel fractal feature-based multiclass glaucoma detection and progression prediction","volume":"17","author":"Kim PY","year":"2013","unstructured":"Kim PY et al (2013) Novel fractal feature-based multiclass glaucoma detection and progression prediction. ieee J biomedical health Inf 17:269\u2013276","journal-title":"ieee J biomedical health Inf"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2271","DOI":"10.1016\/j.ophtha.2009.06.042","article-title":"M. G. T. Natural history of open-angle glaucoma","volume":"116","author":"Heijl A","year":"2009","unstructured":"Heijl A, Bengtsson B, Hyman L, Leske MC, Group E (2009) M. G. T. Natural history of open-angle glaucoma. Ophthalmology 116:2271\u20132276","journal-title":"Ophthalmology"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2228","DOI":"10.1167\/iovs.13-12261","article-title":"Baseline prognostic factors predict rapid visual field deterioration in glaucoma","volume":"55","author":"Lee JM","year":"2014","unstructured":"Lee JM et al (2014) Baseline prognostic factors predict rapid visual field deterioration in glaucoma. Investig Ophthalmol Vis Sci 55:2228\u20132236","journal-title":"Investig Ophthalmol Vis Sci"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1167\/iovs.09-3468","article-title":"Evaluation of retinal nerve fiber layer progression in glaucoma: a study on optical coherence tomography guided progression analysis","volume":"51","author":"Leung CK-s","year":"2010","unstructured":"Leung CK-s et al (2010) Evaluation of retinal nerve fiber layer progression in glaucoma: a study on optical coherence tomography guided progression analysis. Investig Ophthalmol Vis Sci 51:217\u2013222","journal-title":"Investig Ophthalmol Vis Sci"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"813","DOI":"10.3390\/e20110813","article-title":"A brief review of generalized entropies","volume":"20","author":"Amig\u00f3 JM","year":"2018","unstructured":"Amig\u00f3 JM, Balogh SG, Hern\u00e1ndez S (2018) A brief review of generalized entropies. Entropy 20:813","journal-title":"Entropy"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/0378-4371(95)00475-0","article-title":"Generalized entropy as a measure of quantum uncertainty","volume":"225","author":"Portesi M","year":"1996","unstructured":"Portesi M, Plastino A (1996) Generalized entropy as a measure of quantum uncertainty. Physica A 225:412\u2013430","journal-title":"Physica A"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.ogla.2022.08.017","article-title":"Comparison of 10\u2009\u2013\u20092 and 24\u2009\u2013\u20092 perimetry to diagnose glaucoma using OCT as an independent reference standard","volume":"6","author":"Onyekaba N-AE","year":"2023","unstructured":"Onyekaba N-AE et al (2023) Comparison of 10\u2009\u2013\u20092 and 24\u2009\u2013\u20092 perimetry to diagnose glaucoma using OCT as an independent reference standard. Ophthalmol Glaucoma 6:187\u2013197","journal-title":"Ophthalmol Glaucoma"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"541","DOI":"10.3390\/medicina61030541","article-title":"PyGlaucoMetrics: A Stacked Weight-Based Machine Learning Approach for Glaucoma Detection Using Visual Field Data","volume":"61","author":"Moradi M","year":"2025","unstructured":"Moradi M et al (2025) PyGlaucoMetrics: A Stacked Weight-Based Machine Learning Approach for Glaucoma Detection Using Visual Field Data. Medicina 61:541. 10.3390\/medicina61030541","journal-title":"Medicina"},{"key":"ref34","article-title":"Clinically informed semi-supervised learning improves disease annotation and equity from electronic health records: a glaucoma case study","author":"Moradi M","year":"2025","unstructured":"Moradi M et al (2025) Clinically informed semi-supervised learning improves disease annotation and equity from electronic health records: a glaucoma case study. npj Digit Med","journal-title":"npj Digit Med"},{"key":"ref35","author":"Tobias Elze DL","year":"2019","unstructured":"Tobias Elze DL (2019) Eun Young Choi. CRAN - Package vfprogression. doi:https:\/\/10.32614\/CRAN.package.vfprogression"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1167\/tvst.12.2.6","article-title":"PyVisualFields: A Python Package for Visual Field Analysis","volume":"12","author":"Eslami M","year":"2023","unstructured":"Eslami M et al (2023) PyVisualFields: A Python Package for Visual Field Analysis. Translational Vis Sci Technol 12:6\u20136","journal-title":"Translational Vis Sci Technol"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1016\/j.ophtha.2004.02.017","article-title":"Predictive factors for glaucomatous visual field progression in the Advanced Glaucoma Intervention Study","volume":"111","author":"Nouri-Mahdavi K","year":"2004","unstructured":"Nouri-Mahdavi K et al (2004) Predictive factors for glaucomatous visual field progression in the Advanced Glaucoma Intervention Study. Ophthalmology 111:1627\u20131635","journal-title":"Ophthalmology"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.ajo.2007.09.038","article-title":"A visual field index for calculation of glaucoma rate of progression","volume":"145","author":"Bengtsson B","year":"2008","unstructured":"Bengtsson B, Heijl A (2008) A visual field index for calculation of glaucoma rate of progression. Am J Ophthalmol 145:343\u2013353","journal-title":"Am J Ophthalmol"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1016\/j.ophtha.2014.02.021","article-title":"Using filtered forecasting techniques to determine personalized monitoring schedules for patients with open-angle glaucoma","volume":"121","author":"Schell GJ","year":"2014","unstructured":"Schell GJ et al (2014) Using filtered forecasting techniques to determine personalized monitoring schedules for patients with open-angle glaucoma. Ophthalmology 121:1539\u20131546","journal-title":"Ophthalmology"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.ophtha.2023.01.008","article-title":"Fast progressors in glaucoma: prevalence based on global and central visual field loss","volume":"130","author":"Jackson AB","year":"2023","unstructured":"Jackson AB et al (2023) Fast progressors in glaucoma: prevalence based on global and central visual field loss. Ophthalmology 130:462\u2013468","journal-title":"Ophthalmology"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10009600\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10009600\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:38:17Z","timestamp":1782383897000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10009600\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":40,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-10009600\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"subtype":"preprint"}}