About

Michael John Allingham is an Assistant Professor of Ophthalmology at Duke University. His professional role involves clinical and research activities within the Department of Ophthalmology, focusing on vitreoretinal disease. He is associated with the Duke Pediatric Retina and Optic Nerve Center (DPROC) and is engaged in advancing understanding and treatment of retinal conditions. His work is situated within a comprehensive ophthalmology program that includes various specialized divisions such as Glaucoma, Cornea, and Neuro-Ophthalmology, among others. Based at Duke University, he contributes to the department's mission of education, research, and patient care in ophthalmology.

Research topics

• Medicine
• Ophthalmology
• Internal medicine
• Bioinformatics
• Pathology
• Biology
• Surgery

Selected publications

• Deep Learning Algorithm for the Diagnosis and Prediction of Hydroxychloroquine Retinopathy

  Ophthalmology Retina · 2025-06-11 · 2 citations

  articleOpen access

  PURPOSE: We present a deep learning algorithm-HCQuery-that detects the presence of hydroxychloroquine retinopathy and predicts its future occurrence from spectral-domain OCT (SD-OCT) images. DESIGN: We trained and validated a deep learning algorithm using retrospective SD-OCT images from patients taking hydroxychloroquine. SUBJECTS: The study involved a retrospective, nonconsecutive collection of 409 patients (171 positive for hydroxychloroquine retinopathy and 238 negative) and 8251 SD-OCT b-scans (1988 volumes) from 5 independent international clinical locations. METHODS: Imaging macular volumes from 2 different SD-OCT devices (Heidelberg Spectralis and Zeiss Cirrus) at 2 clinical sites were used to train and validate a convolutional neural network (EfficientNet-b4) to produce a likelihood of retinopathy score for each SD-OCT b-scan. Likelihood of retinopathy score were processed across SD-OCT volumes for an eye-level and patient-level binary decision output for the presence or absence of retinopathy. The adjudicated consensus of ≤3 independent retina specialists using patient clinical data and multimodal testing served as the reference standard for hydroxychloroquine retinopathy. The algorithm was tested on 4 withheld test sets, 1 internal (data set 1), and 3 external (data sets 3-5). The test sets were obtained in 2 countries (United States and United Kingdom) and represented 2 SD-OCT devices each with diverse acquisition parameters. MAIN OUTCOME MEASURES: Sensitivity, specificity, accuracy, negative predictive value, positive predictive value, area under the receiver-operator characteristic curve, and area under the precision-recall curve for the detection of hydroxychloroquine retinopathy either at the time of clinical diagnosis or ≤18 months in advance of clinical diagnosis. RESULTS: The algorithm discriminated hydroxychloroquine retinopathy at the time of clinical diagnosis as well as in advance of clinical diagnosis (mean: 220.8 days before clinical diagnosis; accuracy: 0.987 [95% CI: 0.962-1.00]; sensitivity: 1.00 [95% CI: 0.833-1.00]; specificity: 0.983 [95% CI: 0.952-1.00]; positive predictive value: 0.944 [95% CI: 0.836-1.00]; negative predictive value: 1.00 [95% CI: 0.937-1.00]). For eyes that developed retinopathy, it was identified as positive 2.74 years in advance of the clinical diagnosis on average. CONCLUSIONS: Our algorithm can detect retinopathy at all stages of disease, as well as predict retinopathy years in advance of clinical diagnosis. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

  PublisherDOI

• Association of Hyperautofluorescence Signals with Geographic Atrophy Progression in the METformin for the MINimization of Geographic Atrophy Progression Trial

  Ophthalmology Science · 2024-09-12 · 5 citations

  articleOpen access

  <h3>Purpose</h3> To investigate the association between rim area focal hyperautofluorescence (RAFH) signals and geographic atrophy (GA) growth rates, as well as the impact of oral metformin on the longitudinal change of RAFH. <h3>Design</h3> Secondary analysis of a randomized controlled trial. <h3>Participants</h3> Seventy-one eyes from 44 participants with GA and ≥6 months of follow-up in the METformin for the MINimization of geographic atrophy progression study. <h3>Methods</h3> Fundus autofluorescence images were captured using a 488 nm excitation wavelength. Two masked graders identified and measured RAFH lesions using proprietary semiautomatic segmentation software and ImageJ. We calculated RAFH by dividing the areas of hyperautofluorescence within a 450-μm rim circumscribing the GA by the total area enclosed within this rim. <h3>Main Outcome Measures</h3> Longitudinal changes in RAFH and GA area. <h3>Results</h3> Baseline RAFH was positively associated with the baseline square root of GA area 0.065/year (<i>P</i> < 0.001). In the entire study cohort, higher baseline RAFH was associated with a faster GA area growth rate in mm²/year (Spearman's ρ = 0.53; <i>P</i> < 0.001). The association became weaker in square root-transformed GA area growth (ρ = 0.19, <i>P</i> = 0.11) and perimeter-adjusted GA growth rate (ρ = 0.28, <i>P</i> = 0.02), achieving statistical significance only in the latter. When this analysis was stratified into 3 baseline GA tertiles, the first and second tertiles showed weak to moderate association with statistical significance in all 3 modes of GA growth rates. Rim area focal hyperautofluorescence increased slightly but significantly over time at 0.020/year (<i>P</i> < 0.01). Rim area focal hyperautofluorescence increased slightly but significantly over time at 0.020/year (<i>P</i> < 0.01). The use of oral metformin was not significantly associated with the change in RAFH over time compared with the observation group (0.023/year vs. 0.016/year; <i>P</i> = 0.29). <h3>Conclusions</h3> Increased baseline RAFH is associated with faster GA area progression. However, the effect size of this association may depend on the baseline GA lesion size such that small to medium-sized GA lesions display this relationship regardless of the mode of the calculation of GA growth rate. <h3>Financial Disclosures</h3> Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

  PublisherOA PDFDOI

• A Deep-Learning Algorithm to Predict Short-Term Progression to Geographic Atrophy on Spectral-Domain Optical Coherence Tomography

  JAMA Ophthalmology · 2023-10-19 · 18 citations

  articleOpen access

  Importance: The identification of patients at risk of progressing from intermediate age-related macular degeneration (iAMD) to geographic atrophy (GA) is essential for clinical trials aimed at preventing disease progression. DeepGAze is a fully automated and accurate convolutional neural network-based deep learning algorithm for predicting progression from iAMD to GA within 1 year from spectral-domain optical coherence tomography (SD-OCT) scans. Objective: To develop a deep-learning algorithm based on volumetric SD-OCT scans to predict the progression from iAMD to GA during the year following the scan. Design, Setting, and Participants: This retrospective cohort study included participants with iAMD at baseline and who either progressed or did not progress to GA within the subsequent 13 months. Participants were included from centers in 4 US states. Data set 1 included patients from the Age-Related Eye Disease Study 2 AREDS2 (Ancillary Spectral-Domain Optical Coherence Tomography) A2A study (July 2008 to August 2015). Data sets 2 and 3 included patients with imaging taken in routine clinical care at a tertiary referral center and associated satellites between January 2013 and January 2023. The stored imaging data were retrieved for the purpose of this study from July 1, 2022, to February 1, 2023. Data were analyzed from May 2021 to July 2023. Exposure: A position-aware convolutional neural network with proactive pseudointervention was trained and cross-validated on Bioptigen SD-OCT volumes (data set 1) and validated on 2 external data sets comprising Heidelberg Spectralis SD-OCT scans (data sets 2 and 3). Main Outcomes and Measures: Prediction of progression to GA within 13 months was evaluated with area under the receiver-operator characteristic curves (AUROC) as well as area under the precision-recall curve (AUPRC), sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Results: The study included a total of 417 patients: 316 in data set 1 (mean [SD] age, 74 [8]; 185 [59%] female), 53 in data set 2, (mean [SD] age, 83 [8]; 32 [60%] female), and 48 in data set 3 (mean [SD] age, 81 [8]; 32 [67%] female). The AUROC for prediction of progression from iAMD to GA within 1 year was 0.94 (95% CI, 0.92-0.95; AUPRC, 0.90 [95% CI, 0.85-0.95]; sensitivity, 0.88 [95% CI, 0.84-0.92]; specificity, 0.90 [95% CI, 0.87-0.92]) for data set 1. The addition of expert-annotated SD-OCT features to the model resulted in no improvement compared to the fully autonomous model (AUROC, 0.95; 95% CI, 0.92-0.95; P = .19). On an independent validation data set (data set 2), the model predicted progression to GA with an AUROC of 0.94 (95% CI, 0.91-0.96; AUPRC, 0.92 [0.89-0.94]; sensitivity, 0.91 [95% CI, 0.74-0.98]; specificity, 0.80 [95% CI, 0.63-0.91]). At a high-specificity operating point, simulated clinical trial recruitment was enriched for patients progressing to GA within 1 year by 8.3- to 20.7-fold (data sets 2 and 3). Conclusions and Relevance: The fully automated, position-aware deep-learning algorithm assessed in this study successfully predicted progression from iAMD to GA over a clinically meaningful time frame. The ability to predict imminent GA progression could facilitate clinical trials aimed at preventing the condition and could guide clinical decision-making regarding screening frequency or treatment initiation.

  PublisherOA PDFDOI

• Fluorescein CorneoGraphy (FCG): Use of a repurposed fluorescein imaging technique to objectively standardize corneal staining

  The Ocular Surface · 2022-12-01 · 5 citations

  letterOpen access
  PublisherOA PDFDOI

• Immunological Aspects of Age-Related Macular Degeneration

  Advances in experimental medicine and biology · 2021-01-01 · 26 citations

  book-chapter1st authorCorresponding
  PublisherDOI

• Mitochondrial dysfunction causes retraction of Müller cell lateral processes.

  Investigative Ophthalmology & Visual Science · 2021-06-21

  articleOpen access1st authorCorresponding
  Publisher

• Phase 1 Clinical Trial of Elamipretide in Intermediate Age-Related Macular Degeneration and High-Risk Drusen

  Ophthalmology Science · 2021 · 29 citations

  1st authorCorresponding
  • Medicine
  • Ophthalmology
  • Internal medicine

  Purpose: To assess safety, tolerability, and feasibility of subcutaneous administration of the mitochondrial-targeted drug elamipretide in patients with intermediate age-related macular degeneration (AMD) and high-risk drusen (HRD) and to perform exploratory analyses of change in visual function. Design: Phase 1, single-center, open-label, 24-week clinical trial with preplanned HRD cohort. Participants: Adult patients ≥55 years of age with intermediate AMD and HRD. Methods: Participants received subcutaneous elamipretide 40 mg daily, with safety and tolerability assessed throughout the study. Ocular assessments included normal-luminance best-corrected visual acuity (BCVA), low-luminance best-corrected visual acuity (LLVA), normal-luminance binocular reading acuity (NLRA), low-luminance binocular reading acuity (LLRA), spectral-domain OCT, fundus autofluorescence (FAF), mesopic microperimetry, dark adaptation, and low-luminance questionnaire (LLQ). Main Outcome Measures: The primary end point was safety and tolerability. Prespecified exploratory end points included changes from baseline in BCVA, LLVA, NLRA, LLRA, retinal pigment epithelium (RPE)-drusen complex (DC) volume by OCT, FAF, mesopic microperimetry, dark adaptation, and LLQ results. Results: 0.0015). No significant changes were observed for RPE-DC volume, FAF, mesopic microperimetry, or dark adaptation. Conclusions: Elamipretide appeared to be generally safe and well tolerated in treating intermediate AMD and HRD. Exploratory analyses demonstrate a positive effect on visual function, particularly under low-luminance conditions. Further study of elamipretide for treatment of intermediate AMD with HRD is warranted.

  PublisherOA PDFDOI

• Phase 1 Clinical Trial of Elamipretide in Dry Age-Related Macular Degeneration and Noncentral Geographic Atrophy

  Ophthalmology Science · 2021-11-27 · 23 citations

  articleOpen access

  Purpose: Assess the safety, tolerability, and feasibility of subcutaneous administration of the mitochondrial-targeted drug elamipretide in patients with dry age-related macular degeneration (AMD) and noncentral geographic atrophy (NCGA) and to perform exploratory analyses of change in visual function. Design: Phase 1, single-center, open-label, 24-week clinical trial with preplanned NCGA cohort. Participants: Adults ≥ 55 years of age with dry AMD and NCGA. Methods: Participants received subcutaneous elamipretide 40-mg daily; safety and tolerability assessed throughout. Ocular assessments included normal-luminance best-corrected visual acuity (BCVA), low-luminance BCVA (LLBCVA), normal-luminance binocular reading acuity (NLBRA), low-luminance binocular reading acuity (LLBRA), spectral-domain OCT, fundus autofluorescence (FAF), and patient self-reported function by low-luminance questionnaire (LLQ). Main Outcome Measures: Primary end point was safety and tolerability. Prespecified exploratory end-points included changes in BCVA, LLBCVA, NLBRA, LLBRA, geographic atrophy (GA) area, and LLQ. Results: = 0.005). Mean ± SD change in GA area (square root transformation) from baseline to week 24 was 0.14 ± 0.08 mm by FAF and 0.13 ± 0.14 mm by OCT. Improvement was observed in LLQ for dim light reading and general dim light vision. Conclusions: Elamipretide seems to be well tolerated without serious AEs in patients with dry AMD and NCGA. Exploratory analyses demonstrated possible positive effect on visual function, particularly under low luminance. A Phase 2b trial is underway to evaluate elamipretide further in dry AMD and NCGA.

  PublisherDOI

• RhoG regulates endothelial apical cup assembly downstream from ICAM1 engagement and is involved in leukocyte trans-endothelial migration

  UNC Libraries · 2020-10-31

  articleOpen access

  During trans-endothelial migration (TEM), leukocytes use adhesion receptors such as intercellular adhesion molecule-1 (ICAM1) to adhere to the endothelium. In response to this interaction, the endothelium throws up dynamic membrane protrusions, forming a cup that partially surrounds the adherent leukocyte. Little is known about the signaling pathways that regulate cup formation. In this study, we show that RhoG is activated downstream from ICAM1 engagement. This activation requires the intracellular domain of ICAM1. ICAM1 colocalizes with RhoG and binds to the RhoG-specific SH3-containing guanine-nucleotide exchange factor (SGEF). The SH3 domain of SGEF mediates this interaction. Depletion of endothelial RhoG by small interfering RNA does not affect leukocyte adhesion but decreases cup formation and inhibits leukocyte TEM. Silencing SGEF also results in a substantial reduction in RhoG activity, cup formation, and TEM. Together, these results identify a new signaling pathway involving RhoG and its exchange factor SGEF downstream from ICAM1 that is critical for leukocyte TEM.

  PublisherDOI

• Deep learning-based single-shot prediction of differential effects of anti-VEGF treatment in patients with diabetic macular edema

  Biomedical Optics Express · 2020 · 77 citations

  • Medicine
  • Ophthalmology
  • Surgery

  Anti-vascular endothelial growth factor (VEGF) agents are widely regarded as the first line of therapy for diabetic macular edema (DME) but are not universally effective. An automatic method that can predict whether a patient is likely to respond to anti-VEGF therapy can avoid unnecessary trial and error treatment strategies and promote the selection of more effective first-line therapies. The objective of this study is to automatically predict the efficacy of anti-VEGF treatment of DME in individual patients based on optical coherence tomography (OCT) images. We performed a retrospective study of 127 subjects treated for DME with three consecutive injections of anti-VEGF agents. Patients' retinas were imaged using spectral-domain OCT (SD-OCT) before and after anti-VEGF therapy, and the total retinal thicknesses before and after treatment were extracted from OCT B-scans. A novel deep convolutional neural network was designed and evaluated using pre-treatment OCT scans as input and differential retinal thickness as output, with 5-fold cross-validation. The group of patients responsive to anti-VEGF treatment was defined as those with at least a 10% reduction in retinal thickness following treatment. The predictive performance of the system was evaluated by calculating the precision, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). The algorithm achieved an average AUC of 0.866 in discriminating responsive from non-responsive patients, with an average precision, sensitivity, and specificity of 85.5%, 80.1%, and 85.0%, respectively. Classification precision was significantly higher when differentiating between very responsive and very unresponsive patients. The proposed automatic algorithm accurately predicts the response to anti-VEGF treatment in DME patients based on OCT images. This pilot study is a critical step toward using non-invasive imaging and automated analysis to select the most effective therapy for a patient's specific disease condition.

  PublisherDOI

Recent grants

• Muller glial dysfunction in retinal edema

  NIH · $639k · 2016–2020

Frequent coauthors

• Scott W. Cousins

  29 shared

• Sina Farsiu

  Duke University

  29 shared

• Priyatham S. Mettu

  25 shared

• Cynthia A. Toth

  Duke University

  14 shared

• Sharon F. Freedman

  Duke Medical Center

  13 shared

• Du Tran-Viet

  Duke University

  12 shared

• Rachelle V. O’Connell

  12 shared

• Ramiro S. Maldonado

  Duke University

  12 shared