Shazia Dharssi, MD

All Publications

• Epidemiology of Orbital and Preseptal Cellulitis in the United States: A 13-Year Analysis. Ophthalmic epidemiology Dharssi, S., Taneja, K., Rajaii, F. 2025; 32 (5): 553-560

  Abstract

  To determine the incidence rates, risk factors, and economic burden of orbital and preseptal cellulitis in the United States (US).This retrospective longitudinal study was completed using data from the US Nationwide Emergency Department Sample dataset. An estimated 732,105 emergency department (ED) visits with a primary or secondary diagnosis of orbital and preseptal cellulitis from 2006 to 2018 were included. Incidence rates, descriptive statistics, and risk factors were calculated using linear and multivariate logistic regression models.The incidence rates of preseptal cellulitis increased from 6.2 in 2006 to 19.2 per 100,000 US population in 2018. In contrast, orbital cellulitis incidence rates have been decreasing from 6.1 to 2.8 per 100,000 US population from 2006 to 2018, respectively. Young adults (ages 21-44) comprise a majority of patients with either preseptal or orbital cellulitis (31.7%; 95% CI, 30.5-33.0%). Hypertension (11.8%, 12.9%), tobacco use (11.2%, 9.6%), and sinusitis (9.2%, 4.3%) were the most commonly associated diagnoses for orbital and preseptal cellulitis, respectively. Only 27.6% of patients with orbital cellulitis were admitted with 64.7% of patients routinely discharged. The inflation-adjusted ED charges for patients with orbital and preseptal cellulitis from 2006 to 2018 totalled over $997 million.Orbital and preseptal cellulitis are costly infections in the US with increasing incidence rates for preseptal cellulitis. High rates of routine discharge from the ED for orbital cellulitis may represent a knowledge gap amongst providers and an opportunity to improve care. Identifying individuals at risk for infection is key for diagnosis and appropriate triage of care.

  View details for DOI 10.1080/09286586.2024.2443541

  View details for PubMedID 39812389

• Inflammatory Markers as Predictors of Orbital Infection Severity. Ophthalmic plastic and reconstructive surgery Gibbons, A., Cherkas, E., Kaur, M., Dharssi, S., Elsharawi, R., Ashraf, D. C., Li, E. 2025; 41 (5): 530-534

  Abstract

  To assess the utility of inflammatory marker levels in defining orbital cellulitis (OC) severity.A retrospective cohort study was conducted at 2 tertiary care centers using a medical record search of billing codes from January 1, 2000, to January 1, 2023. Patients were categorized into 2 cohorts-uncomplicated OC and OC with complication [subperiosteal abscess (SPA), orbital abscess (OA), or cavernous sinus thrombosis (CST)]. Values at presentation of the following markers were recorded: absolute neutrophil count (ANC), white blood cell count (WBC), platelet count, C-reactive protein (CRP), and neutrophil-to-lymphocyte ratio (NLR). Logistic regression, controlled for immunosuppression and age, compared levels between patients with uncomplicated OC versus OC with complication, surgical versus nonsurgical management, and abnormal versus normal presenting and final vision.A total of 785 patients-413 uncomplicated OC (52.6%) and 372 OC with complication (47.4%) (272 SPA [73.2%], 85 OA [22.8%], and 15 CST [4.0%])-met criteria. The sample was majority male (58.2%) and White (65.9%), with a mean age of 31.6 ± 26.4 years. Platelet count, ANC, WBC, and NLR levels were significantly higher in patients with complicated OC (p < 0.001). Levels of ANC, WBC, CRP, and NLR were significantly higher in surgical patients (p < 0.001). Higher levels of NLR and ANC were associated with worse visual acuity and an relative afferent pupillary defect at presentation (p = 0.006 and p = 0.032, respectively) but not at the final follow-up.Levels of NLR, ANC, and WBC at presentation may have clinical utility in identifying severe orbital infections and may aid management.

  View details for DOI 10.1097/IOP.0000000000002903

  View details for PubMedID 40919987

• Autoimmune Antibodies in Thyroid Eye Disease Dharssi , S., Rosas-Gonzalez , M., Rajaii , F. Advances in Ophthalmology and Optometry. 2025 277-295
• Crystalline lens dislocation as a presenting sign of Streptococcus pyogenes invasive infections Liberman , P., Light , J., Howard , T., Lu , J., Simner , P., Carroll , K., Ho , C. Access Microbiology. 2025
• Multiple Retinal Emboli and Medial Canthal Swelling Following Injection of Acellular Porcine Urinary Bladder Matrix for Hair Restoration. Ophthalmic plastic and reconstructive surgery Schultz, H., Dharssi, S., Bacorn, C., Priluck, A. Z., Cai, S., Mahoney, N. R. 2023; 39 (4): e126-e128

  Abstract

  Acellular porcine urinary bladder matrix promotes wound healing and is also used to stimulate hair growth. A 64-year-old female presented with acute-onset OD pain and decreased visual acuity after subcutaneous injection of acellular porcine urinary bladder matrix at the hairline. Fundus examination revealed multiple emboli at retinal arcade branch points, and fluorescein angiography demonstrated corresponding areas of peripheral nonperfusion. Two weeks later, external examination revealed new swelling of the right medial canthus without erythema or fluctuance, which was felt to possibly represent recruitment of vessels after occlusion in the facial vasculature. At 1-month follow up, visual acuity of the OD improved with resolution of right medial canthal swelling. Fundus examination was normal with no visible emboli. Herein, the authors present a case of retinal occlusion and medial canthal swelling following injection of acellular porcine urinary bladder matrix for hair restoration, which to the authors knowledge has not been previously reported.

  View details for DOI 10.1097/IOP.0000000000002383

  View details for PubMedID 37010050

• Ophthalmic applicant perceptions of two residency application services: the San Francisco Match Central Application Service and Electronic Residency Application Service Dharssi , S., Woreta , F., Boland , M. Journal of Academic Ophthalmology. 2021
• Objective resident characteristics associated with performance on the Ophthalmic Knowledge Assessment Program Examination Fliotsos , M., Zafar , S., Dharssi, S., Srikumaran, D., Chow , J., Singman , E., Woreta , F. Journal of Academic Ophthalmology. 2021
• A Deep Learning Approach for Automated Detection of Geographic Atrophy from Color Fundus Photographs. Ophthalmology Keenan, T. D., Dharssi, S., Peng, Y., Chen, Q., Agrón, E., Wong, W. T., Lu, Z., Chew, E. Y. 2019; 126 (11): 1533-1540

  Abstract

  To assess the utility of deep learning in the detection of geographic atrophy (GA) from color fundus photographs and to explore potential utility in detecting central GA (CGA).A deep learning model was developed to detect the presence of GA in color fundus photographs, and 2 additional models were developed to detect CGA in different scenarios.A total of 59 812 color fundus photographs from longitudinal follow-up of 4582 participants in the Age-Related Eye Disease Study (AREDS) dataset. Gold standard labels were from human expert reading center graders using a standardized protocol.A deep learning model was trained to use color fundus photographs to predict GA presence from a population of eyes with no AMD to advanced AMD. A second model was trained to predict CGA presence from the same population. A third model was trained to predict CGA presence from the subset of eyes with GA. For training and testing, 5-fold cross-validation was used. For comparison with human clinician performance, model performance was compared with that of 88 retinal specialists.Area under the curve (AUC), accuracy, sensitivity, specificity, and precision.The deep learning models (GA detection, CGA detection from all eyes, and centrality detection from GA eyes) had AUCs of 0.933-0.976, 0.939-0.976, and 0.827-0.888, respectively. The GA detection model had accuracy, sensitivity, specificity, and precision of 0.965 (95% confidence interval [CI], 0.959-0.971), 0.692 (0.560-0.825), 0.978 (0.970-0.985), and 0.584 (0.491-0.676), respectively, compared with 0.975 (0.971-0.980), 0.588 (0.468-0.707), 0.982 (0.978-0.985), and 0.368 (0.230-0.505) for the retinal specialists. The CGA detection model had values of 0.966 (0.957-0.975), 0.763 (0.641-0.885), 0.971 (0.960-0.982), and 0.394 (0.341-0.448). The centrality detection model had values of 0.762 (0.725-0.799), 0.782 (0.618-0.945), 0.729 (0.543-0.916), and 0.799 (0.710-0.888).A deep learning model demonstrated high accuracy for the automated detection of GA. The AUC was noninferior to that of human retinal specialists. Deep learning approaches may also be applied to the identification of CGA. The code and pretrained models are publicly available at https://github.com/ncbi-nlp/DeepSeeNet.

  View details for DOI 10.1016/j.ophtha.2019.06.005

  View details for PubMedID 31358385

  View details for PubMedCentralID PMC6810830

• A multi-task deep learning model for the classification of Age-related Macular Degeneration. AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Chen, Q., Peng, Y., Keenan, T., Dharssi, S., Agro N, E., Wong, W. T., Chew, E. Y., Lu, Z. 2019; 2019: 505-514

  Abstract

  Age-related Macular Degeneration (AMD) is a leading cause of blindness. Although the Age-Related Eye Disease Study group previously developed a 9-step AMD severity scale for manual classification of AMD severity from color fundus images, manual grading of images is time-consuming and expensive. Built on our previous work DeepSeeNet, we developed a novel deep learning model for automated classification of images into the 9-step scale. Instead of predicting the 9-step score directly, our approach simulates the reading center grading process. It first detects four AMD characteristics (drusen area, geographic atrophy, increased pigment, and depigmentation), then combines these to derive the overall 9-step score. Importantly, we applied multi-task learning techniques, which allowed us to train classification of the four characteristics in parallel, share representation, and prevent overfitting. Evaluation on two image datasets showed that the accuracy of the model exceeded the current state-of-the-art model by > 10%. Availability: https://github.com/ncbi-nlp/DeepSeeNet.

  View details for PubMedID 31259005

  View details for PubMedCentralID PMC6568069

• DeepSeeNet: A Deep Learning Model for Automated Classification of Patient-based Age-related Macular Degeneration Severity from Color Fundus Photographs. Ophthalmology Peng, Y., Dharssi, S., Chen, Q., Keenan, T. D., Agrón, E., Wong, W. T., Chew, E. Y., Lu, Z. 2019; 126 (4): 565-575

  Abstract

  In assessing the severity of age-related macular degeneration (AMD), the Age-Related Eye Disease Study (AREDS) Simplified Severity Scale predicts the risk of progression to late AMD. However, its manual use requires the time-consuming participation of expert practitioners. Although several automated deep learning systems have been developed for classifying color fundus photographs (CFP) of individual eyes by AREDS severity score, none to date has used a patient-based scoring system that uses images from both eyes to assign a severity score.DeepSeeNet, a deep learning model, was developed to classify patients automatically by the AREDS Simplified Severity Scale (score 0-5) using bilateral CFP.DeepSeeNet was trained on 58 402 and tested on 900 images from the longitudinal follow-up of 4549 participants from AREDS. Gold standard labels were obtained using reading center grades.DeepSeeNet simulates the human grading process by first detecting individual AMD risk factors (drusen size, pigmentary abnormalities) for each eye and then calculating a patient-based AMD severity score using the AREDS Simplified Severity Scale.Overall accuracy, specificity, sensitivity, Cohen's kappa, and area under the curve (AUC). The performance of DeepSeeNet was compared with that of retinal specialists.DeepSeeNet performed better on patient-based classification (accuracy = 0.671; kappa = 0.558) than retinal specialists (accuracy = 0.599; kappa = 0.467) with high AUC in the detection of large drusen (0.94), pigmentary abnormalities (0.93), and late AMD (0.97). DeepSeeNet also outperformed retinal specialists in the detection of large drusen (accuracy 0.742 vs. 0.696; kappa 0.601 vs. 0.517) and pigmentary abnormalities (accuracy 0.890 vs. 0.813; kappa 0.723 vs. 0.535) but showed lower performance in the detection of late AMD (accuracy 0.967 vs. 0.973; kappa 0.663 vs. 0.754).By simulating the human grading process, DeepSeeNet demonstrated high accuracy with increased transparency in the automated assignment of individual patients to AMD risk categories based on the AREDS Simplified Severity Scale. These results highlight the potential of deep learning to assist and enhance clinical decision-making in patients with AMD, such as early AMD detection and risk prediction for developing late AMD. DeepSeeNet is publicly available on https://github.com/ncbi-nlp/DeepSeeNet.

  View details for DOI 10.1016/j.ophtha.2018.11.015

  View details for PubMedID 30471319

  View details for PubMedCentralID PMC6435402

• Text Mining for Drug Discovery. Methods in molecular biology (Clifton, N.J.) Zheng, S., Dharssi, S., Wu, M., Li, J., Lu, Z. 2019; 1939: 231-252

  Abstract

  Recent advances in technology have led to the exponential growth of scientific literature in biomedical sciences. This rapid increase in information has surpassed the threshold for manual curation efforts, necessitating the use of text mining approaches in the field of life sciences. One such application of text mining is in fostering in silico drug discovery such as drug target screening, pharmacogenomics, adverse drug event detection, etc. This chapter serves as an introduction to the applications of various text mining approaches in drug discovery. It is divided into two parts with the first half as an overview of text mining in the biosciences. The second half of the chapter reviews strategies and methods for four unique applications of text mining in drug discovery.

  View details for DOI 10.1007/978-1-4939-9089-4_13

  View details for PubMedID 30848465

• Improved partial volume correction method for detecting brain activation in disease using Arterial Spin Labeling (ASL) fMRI. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Bruening, D. E., Dharssi, S., Lazar, R. M., Marshall, R. S., Asllani, I. 2015; 2015: 5441-4

  Abstract

  The insight provided by fMRI, particularly BOLD fMRI, has been critical to the understanding of human brain function. Unfortunately, the application of fMRI techniques in clinical research has been held back by several factors. In order for the clinical field to successfully apply fMRI, two main challenges posed by aging and diseased brains need to be overcome: (1) difficulties in signal measurement and interpretation, and (2) partial voluming effects (PVE). Recent work has addressed the first challenge by developing fMRI methods that, in contrast to BOLD, provide a direct measurement of a physiological correlate of function. One such method is Arterial Spin Labeling (ASL) fMRI, which provides images of cerebral blood flow (CBF) in physiologically meaningful units. Although the problems caused by PVE can be mitigated to some degree through the acquisition of high spatial resolution fMRI data, both hardware and experimental design considerations limit this solution. Our team has developed a PVE correction (PVEc) algorithm that produces CBF images that are theoretically independent of tissue content and the associated PVE. The main drawback of the current PVEc method is that it introduces an inherent smoothing of the functional data. This smoothing effect can reduce the sensitivity of the method, complicating the detection of local changes in CBF, such as those due to stroke or activation. Here, we present results from an improved PVEc algorithm (ssPVEc), which uses high-resolution structural space information to correct for the tissue-driven heterogeneity in the ASL signal. We tested the ssPVEc method on ASL images obtained on patients with asymptomatic carotid occlusive disease during rest and motor activation. Our results showed that the sensitivity of the ssPVEc method (defined as the average T-value in the activated region) was at least 1.5 times greater than that of the original, functional space, fsPVEc, for all patients.

  View details for DOI 10.1109/EMBC.2015.7319622

  View details for PubMedID 26737522

  View details for PubMedCentralID PMC4791174