Robotic Optical Coherence Tomography Retinal Imaging for Emergency Department Patients: A Pilot Study for Emergency Physicians’ Diagnostic Performance

Song, Ailin; Roh, Kyung-Min; Lusk, Jay B; Valikodath, Nita; Lad, Eleonora M.; Draelos, Mark; Ortiz, Pablo; Theophanous, Rebecca G.; Izatt, Joseph A.; McNabb, Ryan P.; Kuo, Anthony N.

doi:10.1016/j.annemergmed.2022.10.016

Cited by 4 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A previous study conducted by our group demonstrated that retinal OCT imaging could substantially improve emergency physicians’ sensitivity for abnormalities in the posterior segment of the eye, compared with their existing standard of care examination, direct ophthalmoscopy. 25 These results complement the results from the present study because deep learning has the potential to help emergency physicians further improve their diagnostic accuracy based on OCT. Simultaneously, this prior study demonstrated that emergency physicians could make reasonable referral decisions independent of clinical decision support tools, should they disagree with the model classification.…”

Section: Discussionsupporting

confidence: 87%

“… 23 , 24 We recently demonstrated that the use of RAOCT images improved emergency physicians’ sensitivity for retinal and optic nerve abnormalities from 0% to 69%. 25 The diagnostic performance may be further improved if this imaging modality is combined with a deep learning model capable of autonomous triage of the images, which would create a diagnostic image acquisition and interpretation pipeline novel to the literature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

RobOCTNet: Robotics and Deep Learning for Referable Posterior Segment Pathology Detection in an Emergency Department Population

Song,

Lusk,

Roh

et al. 2024

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Purpose To evaluate the diagnostic performance of a robotically aligned optical coherence tomography (RAOCT) system coupled with a deep learning model in detecting referable posterior segment pathology in OCT images of emergency department patients. Methods A deep learning model, RobOCTNet, was trained and internally tested to classify OCT images as referable versus non-referable for ophthalmology consultation. For external testing, emergency department patients with signs or symptoms warranting evaluation of the posterior segment were imaged with RAOCT. RobOCTNet was used to classify the images. Model performance was evaluated against a reference standard based on clinical diagnosis and retina specialist OCT review. Results We included 90,250 OCT images for training and 1489 images for internal testing. RobOCTNet achieved an area under the curve (AUC) of 1.00 (95% confidence interval [CI], 0.99–1.00) for detection of referable posterior segment pathology in the internal test set. For external testing, RAOCT was used to image 72 eyes of 38 emergency department patients. In this set, RobOCTNet had an AUC of 0.91 (95% CI, 0.82–0.97), a sensitivity of 95% (95% CI, 87%–100%), and a specificity of 76% (95% CI, 62%–91%). The model's performance was comparable to two human experts’ performance. Conclusions A robotically aligned OCT coupled with a deep learning model demonstrated high diagnostic performance in detecting referable posterior segment pathology in a cohort of emergency department patients. Translational Relevance Robotically aligned OCT coupled with a deep learning model may have the potential to improve emergency department patient triage for ophthalmology referral.

show abstract

Section: Discussionsupporting

confidence: 87%

Section: Introductionmentioning

confidence: 99%

RobOCTNet: Robotics and Deep Learning for Referable Posterior Segment Pathology Detection in an Emergency Department Population

Song,

Lusk,

Roh

et al. 2024

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In parallel, some independent groups investigated the use of ML methods for characterising some diseases that are difficult to triage with classical indexes. For instance, Song et al., 34 developed a novel deep‐learning model to classify retinal images for ophthalmology consultation.…”

Section: Computational Methods For Predicting Severitymentioning

confidence: 99%

On the computational approaches for supporting triage systems

Defilippo,

Bertucci,

Zurzolo

et al. 2023

Interdisciplinary Medicine

View full text Add to dashboard Cite

Triage procedure is used in Emergency Departments (ED) to manage the patient's treatment and prioritise care access. This is a largely resourceconsuming phase and relevant to reduce risk and optimise resource management. Moreover, the presence of patients in the ED (both in treatment rooms and in waiting rooms after triage) may increase the patients' time of stay, thus creating problems for critical patients and for healthcare process management. Moreover, it has been proved that a large fraction of ED incoming patients do not require emergency treatments and might be treated in ambulatory or by family doctors. In such cases, the triage wastes resources and time. In addition, the decision of a low priority or no ED necessity is relevant considering that underestimating treatment necessity may cause errors in patient treatments. Improving triage related decisions is a relevant task.It has been shown that computational methods such as machine learning (ML) may support triage by providing better stratification of patients as well as better results in terms of outcome. We here present a literature review discussing some recent approaches to predict the severity of patients and in particular, we present recent approaches based on ML. We use PRISMA methodology to include works in our analysis. Finally, the future directions of research and open problems are highlighted. K E Y W O R D Sliterature review, machine learning, triage systems | INTRODUCTIONPatients go to Emergency Departments (EDs) to access the clinical care of hospitals. In Italy, access to ED is universal and accessible to all the people staying in Italy, without any restriction, as stated in the Constitution of the Italian Republic. Managing queues in ED is crucial for guaranteeing the best care to all people, thus minimising clinical risk, efficiency and, lastly, the cost for the healthcare system. [1][2][3] This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…Robotically-enabled OCT technology currently under investigation may be a promising solution to the problem, as it would remove the need for ophthalmic photographers. 49…”

Section: Optical Coherence Tomographymentioning

confidence: 99%

“…Professional ophthalmic photographers are often required, limiting the suitability of this technology in nonophthalmic screening environments. Robotically-enabled OCT technology currently under investigation may be a promising solution to the problem, as it would remove the need for ophthalmic photographers 49 …”

Section: Teleophthalmology Approaches To Diabetic Retinopathy Screeningmentioning

confidence: 99%

Advances in Teleophthalmology Screening for Diabetic Retinopathy

Song,

Borkar

2023

International Ophthalmology Clinics

Self Cite

View full text Add to dashboard Cite

Robotic Optical Coherence Tomography Retinal Imaging for Emergency Department Patients: A Pilot Study for Emergency Physicians’ Diagnostic Performance

Cited by 4 publications

References 11 publications

RobOCTNet: Robotics and Deep Learning for Referable Posterior Segment Pathology Detection in an Emergency Department Population

RobOCTNet: Robotics and Deep Learning for Referable Posterior Segment Pathology Detection in an Emergency Department Population

On the computational approaches for supporting triage systems

Advances in Teleophthalmology Screening for Diabetic Retinopathy

Contact Info

Product

Resources

About