Yasir Jamal Sepah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yasir Jamal Sepah has a total of 153 co-authors. Here are the top co-authors by number of shared publications:
- Quan Dong Nguyen
Byers Eye Institute, Stanford University School of Medicine, Palo Alto, USA
13 shared publications - Diana V. Do
Byers Eye Institute, Stanford University School of Medicine, Palo Alto, USA
7 shared publications - Muhammad Sohail Halim
Byers Eye Institute, Stanford University, Palo Alto, CA, USA
7 shared publications Rubbia Afridi
Ophthalmology, Stanford University Medicine, Palo Alto, California, United States
7 shared publicationsMuhammad Sohail Halim
Ophthalmology, Stanford University Medicine, Palo Alto, California, United States
6 shared publicationsQuan Dong Nguyen
6 shared publications
Latest Publications
- 30 October 2026
- Published by Springer Nature in Mammalian Genome
- Vol. 37 (1) , 117
Integration of biomarkers in common retinal neurodegenerative diseases: a comprehensive review
- 30 October 2026
- Published by Springer Nature in Mammalian Genome
- Vol. 37 (1) , 117
Integration of biomarkers in common retinal neurodegenerative diseases: a comprehensive review
- Open Access
- 28 October 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Unseen Insights: An AI-Powered Exploration of Secure Patient Messages in Ophthalmology (Preprint)
BACKGROUND Patient portal messaging has rapidly expanded as a key mode of communication in modern health systems, generating large volumes of unstructured patient-generated health data. However, the clinical relevance and operational implications of these messages in ophthalmology remain poorly characterized. OBJECTIVE To characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. METHODS This is a cross-sectional study of de-identified, patient-initiated secure messages sent between June 2014 and July 2024. Patients with ophthalmic conditions who initiated secure electronic health record portal messages. Of 48,516 extracted message threads, 30,390 patient medical advice request messages from 4,817 unique patients were included after exclusion of questionnaires, courtesy messages, and clinician responses. Natural language processing and large language model–assisted topic classification were used to categorize message content. Differences in message frequency by demographic subgroup were assessed using 2-proportion z tests. RESULTS Participants were 55.5% female, 56.9% aged 50 years or older, 48.7% White, and 85.7% non-Hispanic. Nearly half of all messages addressed administrative issues, including scheduling, medication refills, and insurance. Among clinical concerns, vision disturbances (20.8%), glaucoma-related symptoms (8.7%), imaging or tumor-related questions (7.5%), and postoperative concerns (7.4%) were most common. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. CONCLUSIONS Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- 28 October 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUnseen Insights: An AI-Powered Exploration of Secure Patient Messages in Ophthalmology (Preprint)
BACKGROUND Patient portal messaging has rapidly expanded as a key mode of communication in modern health systems, generating large volumes of unstructured patient-generated health data. However, the clinical relevance and operational implications of these messages in ophthalmology remain poorly characterized. OBJECTIVE To characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. METHODS This is a cross-sectional study of de-identified, patient-initiated secure messages sent between June 2014 and July 2024. Patients with ophthalmic conditions who initiated secure electronic health record portal messages. Of 48,516 extracted message threads, 30,390 patient medical advice request messages from 4,817 unique patients were included after exclusion of questionnaires, courtesy messages, and clinician responses. Natural language processing and large language model–assisted topic classification were used to categorize message content. Differences in message frequency by demographic subgroup were assessed using 2-proportion z tests. RESULTS Participants were 55.5% female, 56.9% aged 50 years or older, 48.7% White, and 85.7% non-Hispanic. Nearly half of all messages addressed administrative issues, including scheduling, medication refills, and insurance. Among clinical concerns, vision disturbances (20.8%), glaucoma-related symptoms (8.7%), imaging or tumor-related questions (7.5%), and postoperative concerns (7.4%) were most common. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. CONCLUSIONS Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- Open Access
- 28 October 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e96026
Secure Patient Messaging in Ophthalmology: Retrospective Natural Language Processing Study
Background: The rapid rise of secure patient messaging has transformed ophthalmic communication, with text volumes now exceeding prepandemic levels across health care systems. Our study uses a natural language processing (NLP) model to explore patterns in over 30,000 secure messages and identify common ocular complaints and differences by patient demographics. Objective: The objective of this study is to characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. Methods: We conducted a cross-sectional study of deidentified, patient-initiated secure messages sent between June 2014 and July 2024. Patients with ophthalmic conditions who initiated secure electronic health record (EHR) portal messages were included. Of the 52,388 extracted message threads, 30,390 (58%) patient medical advice request (PMAR) messages routed solely to the Department of Ophthalmology from 4817 unique patients were assessed after the exclusion of questionnaires, courtesy messages, clinician responses, and messages routed to other health care departments. Of these unique patients, 2673 (55.5%) were female, 2740 (56.9%) were aged 50 years or older, 2346 (48.7%) were White, 4392 (91.2%) were non-Hispanic, and 2774 (57.6%) were married. NLP and large language model (LLM)–assisted topic classification were used to categorize message content. The distribution of message topics and frequency of clinical concerns were assessed and stratified by age, sex, race, ethnicity, and marital status. Differences in message frequency by demographic subgroup were assessed using 2-proportion z-tests. Results: Following preprocessing and topic modeling, 14,284 (47%) of the 30,390 messages could be predefined in relation to a topic cluster and were included in the final analysis. Nearly half of all 14,284 predefined messages addressed administrative issues, including 4166 (29.2%) scheduling-related inquiries, 1352 (9.5%) pharmacy and medication refill requests, and 581 (4.1%) insurance document issues. Among clinical concerns, of the total 14,284 predefined messages, 2975 (20.8%) messages involved vision disturbances, 1241 (8.7%) involved glaucoma-related symptoms, 1074 (7.5%) involved tumor-related questions, and 1064 (7.4%) involved surgery-relevant concerns. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. Conclusions: Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- 28 October 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e96026
Open AccessSecure Patient Messaging in Ophthalmology: Retrospective Natural Language Processing Study
Background: The rapid rise of secure patient messaging has transformed ophthalmic communication, with text volumes now exceeding prepandemic levels across health care systems. Our study uses a natural language processing (NLP) model to explore patterns in over 30,000 secure messages and identify common ocular complaints and differences by patient demographics. Objective: The objective of this study is to characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. Methods: We conducted a cross-sectional study of deidentified, patient-initiated secure messages sent between June 2014 and July 2024. Patients with ophthalmic conditions who initiated secure electronic health record (EHR) portal messages were included. Of the 52,388 extracted message threads, 30,390 (58%) patient medical advice request (PMAR) messages routed solely to the Department of Ophthalmology from 4817 unique patients were assessed after the exclusion of questionnaires, courtesy messages, clinician responses, and messages routed to other health care departments. Of these unique patients, 2673 (55.5%) were female, 2740 (56.9%) were aged 50 years or older, 2346 (48.7%) were White, 4392 (91.2%) were non-Hispanic, and 2774 (57.6%) were married. NLP and large language model (LLM)–assisted topic classification were used to categorize message content. The distribution of message topics and frequency of clinical concerns were assessed and stratified by age, sex, race, ethnicity, and marital status. Differences in message frequency by demographic subgroup were assessed using 2-proportion z-tests. Results: Following preprocessing and topic modeling, 14,284 (47%) of the 30,390 messages could be predefined in relation to a topic cluster and were included in the final analysis. Nearly half of all 14,284 predefined messages addressed administrative issues, including 4166 (29.2%) scheduling-related inquiries, 1352 (9.5%) pharmacy and medication refill requests, and 581 (4.1%) insurance document issues. Among clinical concerns, of the total 14,284 predefined messages, 2975 (20.8%) messages involved vision disturbances, 1241 (8.7%) involved glaucoma-related symptoms, 1074 (7.5%) involved tumor-related questions, and 1064 (7.4%) involved surgery-relevant concerns. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. Conclusions: Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- Open Access
- 24 March 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Unseen Insights: An AI-Powered Exploration of Secure Patient Messages in Ophthalmology (Preprint)
BACKGROUND Patient portal messaging has rapidly expanded as a key mode of communication in modern health systems, generating large volumes of unstructured patient-generated health data. However, the clinical relevance and operational implications of these messages in ophthalmology remain poorly characterized. OBJECTIVE To characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. METHODS This is a cross-sectional study of de-identified, patient-initiated secure messages sent between June 2014 and July 2024. Patients with ophthalmic conditions who initiated secure electronic health record portal messages. Of 48,516 extracted message threads, 30,390 patient medical advice request messages from 4,817 unique patients were included after exclusion of questionnaires, courtesy messages, and clinician responses. Natural language processing and large language model–assisted topic classification were used to categorize message content. Differences in message frequency by demographic subgroup were assessed using 2-proportion z tests. RESULTS Participants were 55.5% female, 56.9% aged 50 years or older, 48.7% White, and 85.7% non-Hispanic. Nearly half of all messages addressed administrative issues, including scheduling, medication refills, and insurance. Among clinical concerns, vision disturbances (20.8%), glaucoma-related symptoms (8.7%), imaging or tumor-related questions (7.5%), and postoperative concerns (7.4%) were most common. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. CONCLUSIONS Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- 24 March 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUnseen Insights: An AI-Powered Exploration of Secure Patient Messages in Ophthalmology (Preprint)
BACKGROUND Patient portal messaging has rapidly expanded as a key mode of communication in modern health systems, generating large volumes of unstructured patient-generated health data. However, the clinical relevance and operational implications of these messages in ophthalmology remain poorly characterized. OBJECTIVE To characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. METHODS This is a cross-sectional study of de-identified, patient-initiated secure messages sent between June 2014 and July 2024. Patients with ophthalmic conditions who initiated secure electronic health record portal messages. Of 48,516 extracted message threads, 30,390 patient medical advice request messages from 4,817 unique patients were included after exclusion of questionnaires, courtesy messages, and clinician responses. Natural language processing and large language model–assisted topic classification were used to categorize message content. Differences in message frequency by demographic subgroup were assessed using 2-proportion z tests. RESULTS Participants were 55.5% female, 56.9% aged 50 years or older, 48.7% White, and 85.7% non-Hispanic. Nearly half of all messages addressed administrative issues, including scheduling, medication refills, and insurance. Among clinical concerns, vision disturbances (20.8%), glaucoma-related symptoms (8.7%), imaging or tumor-related questions (7.5%), and postoperative concerns (7.4%) were most common. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. CONCLUSIONS Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- Open Access
Unseen Insights: An AI–Powered Exploration of Secure Patient Messages in Ophthalmology
Objective: To characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. Design: Cross-sectional study of de-identified, patient-initiated secure messages sent between June 2014 and July 2024. Participants: Patients with ophthalmic conditions who initiated secure electronic health record portal messages. Of 48 516 extracted message threads, 30 390 patient medical advice request messages from 4 817 unique patients were included after exclusion of questionnaires, courtesy messages, and clinician responses. Participants were 55.5% female, 56.9% aged 50 years or older, 48.7% White, and 85.7% non-Hispanic. Methods: Natural language processing and large language model–assisted topic classification were used to categorize message content. Differences in message frequency by demographic subgroup were assessed using 2-proportion z tests. Main Outcomes and Measures: Distribution of message topics and frequency of clinical concerns stratified by age, sex, race, ethnicity, and marital status. Results: Nearly half of all messages addressed administrative issues, including scheduling, medication refills, and insurance. Among clinical concerns, vision disturbances (20.8%), glaucoma-related symptoms (8.7%), imaging or tumor-related questions (7.5%), and postoperative concerns (7.4%) were most common. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. Conclusions: Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
Open AccessUnseen Insights: An AI–Powered Exploration of Secure Patient Messages in Ophthalmology
Objective: To characterize the clinical and administrative concerns communicated through secure ophthalmology messaging and to assess differences in message content across patient sociodemographic groups. Design: Cross-sectional study of de-identified, patient-initiated secure messages sent between June 2014 and July 2024. Participants: Patients with ophthalmic conditions who initiated secure electronic health record portal messages. Of 48 516 extracted message threads, 30 390 patient medical advice request messages from 4 817 unique patients were included after exclusion of questionnaires, courtesy messages, and clinician responses. Participants were 55.5% female, 56.9% aged 50 years or older, 48.7% White, and 85.7% non-Hispanic. Methods: Natural language processing and large language model–assisted topic classification were used to categorize message content. Differences in message frequency by demographic subgroup were assessed using 2-proportion z tests. Main Outcomes and Measures: Distribution of message topics and frequency of clinical concerns stratified by age, sex, race, ethnicity, and marital status. Results: Nearly half of all messages addressed administrative issues, including scheduling, medication refills, and insurance. Among clinical concerns, vision disturbances (20.8%), glaucoma-related symptoms (8.7%), imaging or tumor-related questions (7.5%), and postoperative concerns (7.4%) were most common. Message content differed significantly by demographic characteristics. Non-White patients more frequently raised issues related to pharmacy refills, insurance, glaucoma, and disability documentation, whereas White patients more often reported surgical concerns. Older patients more frequently messaged about glaucoma, surgery, and tumor-related issues, while female patients more often reported complications and swelling or infection. Conclusions: Secure patient messages frequently include clinically relevant symptoms with potential triage implications and demonstrate demographic differences in care-seeking behavior. Systematic analysis of message content may support safer triage, improved workflow efficiency, and more equitable delivery of ophthalmic care.
- Open Access
- 21 January 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (5)
Assessing the Safety and Efficacy of Agonistic Monoclonal Antibody against Robo4 versus Ranibizumab in Neovascular Age-Related Macular Degeneration and Diabetic Macular Edema: A Phase I, Open-Label, Multicenter Study
- 21 January 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (5)
Open AccessAssessing the Safety and Efficacy of Agonistic Monoclonal Antibody against Robo4 versus Ranibizumab in Neovascular Age-Related Macular Degeneration and Diabetic Macular Edema: A Phase I, Open-Label, Multicenter Study
- Open Access
- 20 January 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (4) , 101080
Automated Quantification of Decreased Fundus Autofluorescence in Stargardt Disease Using Starguage: Validation against Manual Grading Standards
- 20 January 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (4) , 101080
Open AccessAutomated Quantification of Decreased Fundus Autofluorescence in Stargardt Disease Using Starguage: Validation against Manual Grading Standards
- Open Access
Objective Assessment of Microperimetry Exam Using EEG Signals
Purpose: To test the hypothesis that deep learning can decode single-trial cortical responses from electroencephalography (EEG) to individual, long-duration microperimetry (MP) stimuli, thereby providing a basis for an objective measure of visual pathway integrity. We also investigated whether occipital EEG signals could automatically register microperimetry stimuli, replacing the patient’s manual button press to improve exam reliability. Methods: We collected pilot EEG data from two healthy participants (12 trials total) during microperimetry (Nidek MP1) at low (3.2 cd/m 2 ) and high (127 cd/m 2 ) stimulus intensities. Occipital EEG signals (8-channel OpenBCI) were bandpass filtered (4–49 Hz), z-score normalized, and segmented into 600 ms epochs time-locked to stimuli. A bidirectional LSTM (Bi-LSTM) deep neural network then classified each epoch as stimulus or non-stimulus. Results: In seven low-intensity trials (16 dB), the model achieved up to ∼77.4% accuracy in distinguishing stimulus vs. non-stimulus EEG segments using the O1/O2 channels. In five high-intensity trials (0 dB), accuracy reached ∼80%. Occipital electrodes (O1, O2) outperformed parietal or combined parieto-occipital montages for detecting the flash stimuli. Consistent with the neuroanatomy of the primary visual cortex, classification performance was maximal using the bilateral occipital electrodes (O1, O2). Conclusion: Integrating occipital EEG with microperimetry provides a proof-of-concept objective framework that reduces reliance on subjective patient feedback and could enhance diagnostic precision. While our pilot study was limited by a small sample and lack of precise EEG–stimulus synchronization, the findings warrant further refinement for clinical translation. Translational Relevance: Enabling automated stimulus registration can improve microperimetry’s reliability in pediatric and challenging populations.
Open AccessObjective Assessment of Microperimetry Exam Using EEG Signals
Purpose: To test the hypothesis that deep learning can decode single-trial cortical responses from electroencephalography (EEG) to individual, long-duration microperimetry (MP) stimuli, thereby providing a basis for an objective measure of visual pathway integrity. We also investigated whether occipital EEG signals could automatically register microperimetry stimuli, replacing the patient’s manual button press to improve exam reliability. Methods: We collected pilot EEG data from two healthy participants (12 trials total) during microperimetry (Nidek MP1) at low (3.2 cd/m 2 ) and high (127 cd/m 2 ) stimulus intensities. Occipital EEG signals (8-channel OpenBCI) were bandpass filtered (4–49 Hz), z-score normalized, and segmented into 600 ms epochs time-locked to stimuli. A bidirectional LSTM (Bi-LSTM) deep neural network then classified each epoch as stimulus or non-stimulus. Results: In seven low-intensity trials (16 dB), the model achieved up to ∼77.4% accuracy in distinguishing stimulus vs. non-stimulus EEG segments using the O1/O2 channels. In five high-intensity trials (0 dB), accuracy reached ∼80%. Occipital electrodes (O1, O2) outperformed parietal or combined parieto-occipital montages for detecting the flash stimuli. Consistent with the neuroanatomy of the primary visual cortex, classification performance was maximal using the bilateral occipital electrodes (O1, O2). Conclusion: Integrating occipital EEG with microperimetry provides a proof-of-concept objective framework that reduces reliance on subjective patient feedback and could enhance diagnostic precision. While our pilot study was limited by a small sample and lack of precise EEG–stimulus synchronization, the findings warrant further refinement for clinical translation. Translational Relevance: Enabling automated stimulus registration can improve microperimetry’s reliability in pediatric and challenging populations.
- Open Access
Treating Vision, Not Signs: A Post-hoc Analysis Evaluating BCVA as an Early Indicator in Treat-and-Extend Management of DME
Purpose: To determine whether significant changes in best-corrected visual acuity (BCVA) precede or coincide with increases in central retinal thickness (CRT) in diabetic macular edema (DME) during a treat-and-extend (T&E) regimen following initial edema resolution. Methods: This post-hoc analysis included 60 eyes (60 participants) from the READ-3 clinical trial that achieved CRT <250 µm and were followed until edema recurrence. Following a six-month ranibizumab loading phase, patients were monitored through 24 months with as-needed retreatment. Significant changes were defined as ≥4 Early Treatment Diabetic Retinopathy Study (ETDRS) letters and ≥30 µm on time-domain optical coherence tomography (TD-OCT). The temporal relationship between functional (BCVA) and anatomical (CRT) changes was analyzed. Results: Median time to edema resolution was 10 months (IQR: 6-16) and to recurrence was 3 months (IQR: 2-3). 52 eyes (86.7%) had functional worsening and 43 (71.7%) had anatomical worsening. In 39 eyes exhibiting both types of deterioration, changes were concurrent in 24 (61.5%). Vision loss preceded anatomical recurrence (BCVA-led) in 23.1% of eyes, with a lead time of 1-4 months. Conversely, anatomical thickening preceded vision loss (OCT-led) in 15.4% of eyes, by a maximum of 2 months. Conclusions: BCVA fluctuations frequently mirror CRT changes and can precede structural relapse, suggesting that BCVA is a sensitive indicator of DME activity. In resource-limited settings, BCVA may allow for earlier detection of recurrence than OCT alone. Translational Relevance: Functional vision loss can precede structural edema recurrence, supporting the potential for home-based BCVA monitoring as a validated bridge for timely clinical intervention in DME.
Open AccessTreating Vision, Not Signs: A Post-hoc Analysis Evaluating BCVA as an Early Indicator in Treat-and-Extend Management of DME
Purpose: To determine whether significant changes in best-corrected visual acuity (BCVA) precede or coincide with increases in central retinal thickness (CRT) in diabetic macular edema (DME) during a treat-and-extend (T&E) regimen following initial edema resolution. Methods: This post-hoc analysis included 60 eyes (60 participants) from the READ-3 clinical trial that achieved CRT <250 µm and were followed until edema recurrence. Following a six-month ranibizumab loading phase, patients were monitored through 24 months with as-needed retreatment. Significant changes were defined as ≥4 Early Treatment Diabetic Retinopathy Study (ETDRS) letters and ≥30 µm on time-domain optical coherence tomography (TD-OCT). The temporal relationship between functional (BCVA) and anatomical (CRT) changes was analyzed. Results: Median time to edema resolution was 10 months (IQR: 6-16) and to recurrence was 3 months (IQR: 2-3). 52 eyes (86.7%) had functional worsening and 43 (71.7%) had anatomical worsening. In 39 eyes exhibiting both types of deterioration, changes were concurrent in 24 (61.5%). Vision loss preceded anatomical recurrence (BCVA-led) in 23.1% of eyes, with a lead time of 1-4 months. Conversely, anatomical thickening preceded vision loss (OCT-led) in 15.4% of eyes, by a maximum of 2 months. Conclusions: BCVA fluctuations frequently mirror CRT changes and can precede structural relapse, suggesting that BCVA is a sensitive indicator of DME activity. In resource-limited settings, BCVA may allow for earlier detection of recurrence than OCT alone. Translational Relevance: Functional vision loss can precede structural edema recurrence, supporting the potential for home-based BCVA monitoring as a validated bridge for timely clinical intervention in DME.
- Open Access
Automated Quantification of Decreased FAF in Stargardt Disease: Validation of a Novel Method Compared to Manual Grading Standards
Purpose To evaluate the repeatability and reproducibility of a novel automated method compared with manual segmentation for measuring decreased autofluorescence (DAF) and definitely decreased autofluorescence (DDAF) in fundus autofluorescence (FAF) images of patients with Stargardt disease. Design Cross-sectional reproducibility and agreement study. Participants A total of 316 eyes from 158 genetically confirmed Stargardt patients were analyzed. For intra–grader repeatability, 114 FAF images were reassessed in a masked, repeated–measures design. Methods DAF and DDAF lesion areas were independently quantified by five certified graders using either manual delineation with Heidelberg RegionFinder or a threshold-based automated algorithm. Agreement and repeatability were assessed using intraclass correlation coefficients (ICC), standard error of measurement (SEM), minimal detectable change (MDC), Lin concordance correlation coefficient (CCC), Bland–Altman plots, and Passing–Bablok regression. Both raw and square–root transformed lesion areas were evaluated. Main Outcome Measures Repeatability (intra–grader ICC, SEM, MDC), reproducibility (inter–grader ICC), and agreement (CCC, bias in regression analysis) between and within manual and automated methods. Results The automated method achieved excellent intra–grader repeatability for both DAF and DDAF (ICCs≥0.988, SEM≤0.71 mm2, MDC≤1.98 mm2), with minimal operator influence. Manual measurements showed variable repeatability (DAF ICCs 0.909-0.974; DDAF ICCs as low as 0.837), with square–root transformation reducing SEM and MDC. Inter–grader reproducibility was highest for automated methods (ICC = 0.989–0.992), whereas manual methods ranged from 0.764–0.939 (raw) and 0.867–0.922 (transformed). Cross–method agreement was strong (CCC = 0.91–0.96), though minor proportional and constant bias was observed in raw DAF data. Conclusions The automated approach provides near–perfect repeatability and high agreement with manual grading, offering a scalable, objective alternative for quantifying hypofluorescent lesions in Stargardt disease. Manual methods are generally reliable but more variable, especially for DDAF, and benefit from square–root transformation.
Open AccessAutomated Quantification of Decreased FAF in Stargardt Disease: Validation of a Novel Method Compared to Manual Grading Standards
Purpose To evaluate the repeatability and reproducibility of a novel automated method compared with manual segmentation for measuring decreased autofluorescence (DAF) and definitely decreased autofluorescence (DDAF) in fundus autofluorescence (FAF) images of patients with Stargardt disease. Design Cross-sectional reproducibility and agreement study. Participants A total of 316 eyes from 158 genetically confirmed Stargardt patients were analyzed. For intra–grader repeatability, 114 FAF images were reassessed in a masked, repeated–measures design. Methods DAF and DDAF lesion areas were independently quantified by five certified graders using either manual delineation with Heidelberg RegionFinder or a threshold-based automated algorithm. Agreement and repeatability were assessed using intraclass correlation coefficients (ICC), standard error of measurement (SEM), minimal detectable change (MDC), Lin concordance correlation coefficient (CCC), Bland–Altman plots, and Passing–Bablok regression. Both raw and square–root transformed lesion areas were evaluated. Main Outcome Measures Repeatability (intra–grader ICC, SEM, MDC), reproducibility (inter–grader ICC), and agreement (CCC, bias in regression analysis) between and within manual and automated methods. Results The automated method achieved excellent intra–grader repeatability for both DAF and DDAF (ICCs≥0.988, SEM≤0.71 mm2, MDC≤1.98 mm2), with minimal operator influence. Manual measurements showed variable repeatability (DAF ICCs 0.909-0.974; DDAF ICCs as low as 0.837), with square–root transformation reducing SEM and MDC. Inter–grader reproducibility was highest for automated methods (ICC = 0.989–0.992), whereas manual methods ranged from 0.764–0.939 (raw) and 0.867–0.922 (transformed). Cross–method agreement was strong (CCC = 0.91–0.96), though minor proportional and constant bias was observed in raw DAF data. Conclusions The automated approach provides near–perfect repeatability and high agreement with manual grading, offering a scalable, objective alternative for quantifying hypofluorescent lesions in Stargardt disease. Manual methods are generally reliable but more variable, especially for DDAF, and benefit from square–root transformation.