Glorbit: A Modular, Web-Based Platform for AI Based Periorbital Measurement in Low-Resource Settings (Preprint) Article Swipe
George R. Nahass
,
Jacob van der Ende
,
Sasha Hubschman
,
Benjamin Beltran
,
Bhavana Kolli
,
Caitlin Berek
,
James D. Edmonds
,
R.V. Paul Chan
,
Pete Setabutr
,
James W. Larrick
,
Darvin Yi
,
Ann Q. Tran
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.2196/preprints.82859
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.2196/preprints.82859
BACKGROUND Periorbital measurements such as margin reflex distances (MRD1/2), palpebral fissure height, and scleral show are critical in diagnosing and managing conditions like ptosis and disorders of the eyelid. OBJECTIVE We developed and evaluated Glorbit, a lightweight, browser-based application for automated periorbital distance measurement using artificial intelligence (AI), designed for deployment in low-resource clinical environments. The goal was to assess its usability, cross-platform functionality, and readiness for real-world field deployment. METHODS The application integrates a DeepLabV3 segmentation model into a modular image processing pipeline with secure, site-specific Google Cloud storage. Glorbit supports offline mode, local preprocessing, and cloud upload through Firebase-authenticated logins. The full workflow—metadata entry, facial image capture, segmentation, and upload—was tested. Post-session, participants completed a Likert-style usability survey. RESULTS Glorbit successfully ran on all tested platforms, including laptops, tablets, and mobile phones across major browsers. A total of 15 volunteers were enrolled in this study where the app completed the full workflow without error on 100% of patients. The segmentation model succeeded on all images, and average session duration was 101.7 ± 17.5 seconds. Usability scores on a 5-point Likert scale were uniformly high: intuitiveness and efficiency (5.0 ± 0.0), workflow clarity (4.8 ± 0.4), output confidence (4.9 ± 0.3), and clinical usability (4.9 ± 0.3). CONCLUSIONS Glorbit is a functional, cross-platform solution for standardized periorbital measurement in clinical and low-resource settings. By combining a local image processing with secure, modular data storage and offline compatibility, the tool enables scalable deployment and secure data collection. These features support broader efforts in AI-driven oculoplastics including future development of real-time triage tools and multimodal datasets for personalized ophthalmic care. CLINICALTRIAL STUDY2025-0731
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.2196/preprints.82859
- OA Status
- gold
- References
- 31
- OpenAlex ID
- https://openalex.org/W4414465338
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414465338Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.2196/preprints.82859Digital Object Identifier
- Title
-
Glorbit: A Modular, Web-Based Platform for AI Based Periorbital Measurement in Low-Resource Settings (Preprint)Work title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-08-22Full publication date if available
- Authors
-
George R. Nahass, Jacob van der Ende, Sasha Hubschman, Benjamin Beltran, Bhavana Kolli, Caitlin Berek, James D. Edmonds, R.V. Paul Chan, Pete Setabutr, James W. Larrick, Darvin Yi, Ann Q. TranList of authors in order
- Landing page
-
https://doi.org/10.2196/preprints.82859Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.2196/preprints.82859Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
31Number of works referenced by this work
Full payload
| id | https://openalex.org/W4414465338 |
|---|---|
| doi | https://doi.org/10.2196/preprints.82859 |
| ids.doi | https://doi.org/10.2196/preprints.82859 |
| ids.openalex | https://openalex.org/W4414465338 |
| fwci | 0.0 |
| type | preprint |
| title | Glorbit: A Modular, Web-Based Platform for AI Based Periorbital Measurement in Low-Resource Settings (Preprint) |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11363 |
| topics[0].field.id | https://openalex.org/fields/35 |
| topics[0].field.display_name | Dentistry |
| topics[0].score | 0.9947999715805054 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3504 |
| topics[0].subfield.display_name | Oral Surgery |
| topics[0].display_name | Dental Radiography and Imaging |
| topics[1].id | https://openalex.org/T14510 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9840999841690063 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2204 |
| topics[1].subfield.display_name | Biomedical Engineering |
| topics[1].display_name | Medical Imaging and Analysis |
| topics[2].id | https://openalex.org/T11636 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.982200026512146 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2718 |
| topics[2].subfield.display_name | Health Informatics |
| topics[2].display_name | Artificial Intelligence in Healthcare and Education |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | doi:10.2196/preprints.82859 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.2196/preprints.82859 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5003704006 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9395-0862 |
| authorships[0].author.display_name | George R. Nahass |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | George R. Nahass |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5119715704 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Jacob van der Ende |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jacob van der Ende |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5109021974 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Sasha Hubschman |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Sasha Hubschman |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5119715705 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Benjamin Beltran |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Benjamin Beltran |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5119715706 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Bhavana Kolli |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Bhavana Kolli |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5119715707 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Caitlin Berek |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Caitlin Berek |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5040089436 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | James D. Edmonds |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | James D. Edmonds |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5049608028 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-1971-2249 |
| authorships[7].author.display_name | R.V. Paul Chan |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | R.V. Paul Chan |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5067273513 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Pete Setabutr |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Pete Setabutr |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5112814074 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | James W. Larrick |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | James W. Larrick |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5012971976 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Darvin Yi |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Darvin Yi |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5080741553 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-3176-5909 |
| authorships[11].author.display_name | Ann Q. Tran |
| authorships[11].author_position | last |
| authorships[11].raw_author_name | Ann Q. Tran |
| authorships[11].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.2196/preprints.82859 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Glorbit: A Modular, Web-Based Platform for AI Based Periorbital Measurement in Low-Resource Settings (Preprint) |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11363 |
| primary_topic.field.id | https://openalex.org/fields/35 |
| primary_topic.field.display_name | Dentistry |
| primary_topic.score | 0.9947999715805054 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3504 |
| primary_topic.subfield.display_name | Oral Surgery |
| primary_topic.display_name | Dental Radiography and Imaging |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.2196/preprints.82859 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.2196/preprints.82859 |
| primary_location.id | doi:10.2196/preprints.82859 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.2196/preprints.82859 |
| publication_date | 2025-08-22 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W2074274620, https://openalex.org/W2395970663, https://openalex.org/W2053539619, https://openalex.org/W2043668812, https://openalex.org/W2180840415, https://openalex.org/W4403321948, https://openalex.org/W4408248580, https://openalex.org/W3162108843, https://openalex.org/W4288282320, https://openalex.org/W4252608096, https://openalex.org/W3205313590, https://openalex.org/W4396675283, https://openalex.org/W3201480657, https://openalex.org/W3110890014, https://openalex.org/W4385416722, https://openalex.org/W2167258682, https://openalex.org/W4396820464, https://openalex.org/W4388327835, https://openalex.org/W3023773746, https://openalex.org/W4403502257, https://openalex.org/W4225740823, https://openalex.org/W4408129742, https://openalex.org/W4214515761, https://openalex.org/W4394873915, https://openalex.org/W4399499327, https://openalex.org/W4386697749, https://openalex.org/W4360603398, https://openalex.org/W4360603252, https://openalex.org/W4220776988, https://openalex.org/W2395639500, https://openalex.org/W4413018730 |
| referenced_works_count | 31 |
| abstract_inverted_index.A | 144 |
| abstract_inverted_index.a | 38, 79, 84, 121, 186, 220, 235 |
| abstract_inverted_index.15 | 147 |
| abstract_inverted_index.By | 233 |
| abstract_inverted_index.We | 33 |
| abstract_inverted_index.as | 5 |
| abstract_inverted_index.in | 18, 54, 151, 228, 261 |
| abstract_inverted_index.is | 219 |
| abstract_inverted_index.of | 27, 146, 165, 267 |
| abstract_inverted_index.on | 131, 163, 171, 185 |
| abstract_inverted_index.to | 61 |
| abstract_inverted_index.± | 180, 197, 202, 207, 213 |
| abstract_inverted_index.The | 58, 76, 107, 167 |
| abstract_inverted_index.all | 132, 172 |
| abstract_inverted_index.and | 13, 20, 25, 35, 67, 101, 115, 138, 174, 194, 209, 230, 244, 252, 271 |
| abstract_inverted_index.app | 156 |
| abstract_inverted_index.are | 16 |
| abstract_inverted_index.for | 42, 52, 69, 224, 274 |
| abstract_inverted_index.its | 63 |
| abstract_inverted_index.ran | 130 |
| abstract_inverted_index.the | 28, 155, 158, 247 |
| abstract_inverted_index.was | 60, 178 |
| abstract_inverted_index.(4.8 | 201 |
| abstract_inverted_index.(4.9 | 206, 212 |
| abstract_inverted_index.(5.0 | 196 |
| abstract_inverted_index.100% | 164 |
| abstract_inverted_index.17.5 | 181 |
| abstract_inverted_index.data | 242, 254 |
| abstract_inverted_index.full | 108, 159 |
| abstract_inverted_index.goal | 59 |
| abstract_inverted_index.into | 83 |
| abstract_inverted_index.like | 23 |
| abstract_inverted_index.show | 15 |
| abstract_inverted_index.such | 4 |
| abstract_inverted_index.this | 152 |
| abstract_inverted_index.tool | 248 |
| abstract_inverted_index.were | 149, 190 |
| abstract_inverted_index.with | 89, 239 |
| abstract_inverted_index.(AI), | 50 |
| abstract_inverted_index.0.0), | 198 |
| abstract_inverted_index.0.3), | 208 |
| abstract_inverted_index.0.3). | 214 |
| abstract_inverted_index.0.4), | 203 |
| abstract_inverted_index.101.7 | 179 |
| abstract_inverted_index.<sec> | 0, 31, 74, 126, 216, 279 |
| abstract_inverted_index.Cloud | 93 |
| abstract_inverted_index.These | 256 |
| abstract_inverted_index.care. | 277 |
| abstract_inverted_index.cloud | 102 |
| abstract_inverted_index.error | 162 |
| abstract_inverted_index.field | 71 |
| abstract_inverted_index.high: | 192 |
| abstract_inverted_index.image | 86, 112, 237 |
| abstract_inverted_index.local | 99, 236 |
| abstract_inverted_index.major | 142 |
| abstract_inverted_index.mode, | 98 |
| abstract_inverted_index.model | 82, 169 |
| abstract_inverted_index.scale | 189 |
| abstract_inverted_index.study | 153 |
| abstract_inverted_index.tools | 270 |
| abstract_inverted_index.total | 145 |
| abstract_inverted_index.using | 47 |
| abstract_inverted_index.where | 154 |
| abstract_inverted_index.</sec> | 30, 73, 125, 215, 278, 282 |
| abstract_inverted_index.Google | 92 |
| abstract_inverted_index.Likert | 188 |
| abstract_inverted_index.across | 141 |
| abstract_inverted_index.assess | 62 |
| abstract_inverted_index.entry, | 110 |
| abstract_inverted_index.facial | 111 |
| abstract_inverted_index.future | 265 |
| abstract_inverted_index.margin | 6 |
| abstract_inverted_index.mobile | 139 |
| abstract_inverted_index.output | 204 |
| abstract_inverted_index.phones | 140 |
| abstract_inverted_index.ptosis | 24 |
| abstract_inverted_index.reflex | 7 |
| abstract_inverted_index.scores | 184 |
| abstract_inverted_index.secure | 253 |
| abstract_inverted_index.tested | 133 |
| abstract_inverted_index.triage | 269 |
| abstract_inverted_index.upload | 103 |
| abstract_inverted_index.5-point | 187 |
| abstract_inverted_index.Glorbit | 95, 128, 218 |
| abstract_inverted_index.average | 175 |
| abstract_inverted_index.broader | 259 |
| abstract_inverted_index.clarity | 200 |
| abstract_inverted_index.efforts | 260 |
| abstract_inverted_index.enables | 249 |
| abstract_inverted_index.eyelid. | 29 |
| abstract_inverted_index.fissure | 11 |
| abstract_inverted_index.height, | 12 |
| abstract_inverted_index.images, | 173 |
| abstract_inverted_index.logins. | 106 |
| abstract_inverted_index.modular | 85, 241 |
| abstract_inverted_index.offline | 97, 245 |
| abstract_inverted_index.scleral | 14 |
| abstract_inverted_index.secure, | 90, 240 |
| abstract_inverted_index.session | 176 |
| abstract_inverted_index.storage | 243 |
| abstract_inverted_index.support | 258 |
| abstract_inverted_index.survey. | 124 |
| abstract_inverted_index.tested. | 117 |
| abstract_inverted_index.through | 104 |
| abstract_inverted_index.without | 161 |
| abstract_inverted_index.Glorbit, | 37 |
| abstract_inverted_index.capture, | 113 |
| abstract_inverted_index.clinical | 56, 210, 229 |
| abstract_inverted_index.critical | 17 |
| abstract_inverted_index.datasets | 273 |
| abstract_inverted_index.designed | 51 |
| abstract_inverted_index.distance | 45 |
| abstract_inverted_index.duration | 177 |
| abstract_inverted_index.enrolled | 150 |
| abstract_inverted_index.features | 257 |
| abstract_inverted_index.laptops, | 136 |
| abstract_inverted_index.managing | 21 |
| abstract_inverted_index.pipeline | 88 |
| abstract_inverted_index.scalable | 250 |
| abstract_inverted_index.seconds. | 182 |
| abstract_inverted_index.solution | 223 |
| abstract_inverted_index.storage. | 94 |
| abstract_inverted_index.supports | 96 |
| abstract_inverted_index.tablets, | 137 |
| abstract_inverted_index.workflow | 160, 199 |
| abstract_inverted_index.(MRD1/2), | 9 |
| abstract_inverted_index.AI-driven | 262 |
| abstract_inverted_index.DeepLabV3 | 80 |
| abstract_inverted_index.Usability | 183 |
| abstract_inverted_index.automated | 43 |
| abstract_inverted_index.browsers. | 143 |
| abstract_inverted_index.combining | 234 |
| abstract_inverted_index.completed | 120, 157 |
| abstract_inverted_index.developed | 34 |
| abstract_inverted_index.disorders | 26 |
| abstract_inverted_index.distances | 8 |
| abstract_inverted_index.evaluated | 36 |
| abstract_inverted_index.including | 135, 264 |
| abstract_inverted_index.palpebral | 10 |
| abstract_inverted_index.patients. | 166 |
| abstract_inverted_index.readiness | 68 |
| abstract_inverted_index.real-time | 268 |
| abstract_inverted_index.settings. | 232 |
| abstract_inverted_index.succeeded | 170 |
| abstract_inverted_index.uniformly | 191 |
| abstract_inverted_index.usability | 123, 211 |
| abstract_inverted_index.artificial | 48 |
| abstract_inverted_index.conditions | 22 |
| abstract_inverted_index.confidence | 205 |
| abstract_inverted_index.deployment | 53, 251 |
| abstract_inverted_index.diagnosing | 19 |
| abstract_inverted_index.efficiency | 195 |
| abstract_inverted_index.integrates | 78 |
| abstract_inverted_index.multimodal | 272 |
| abstract_inverted_index.ophthalmic | 276 |
| abstract_inverted_index.platforms, | 134 |
| abstract_inverted_index.processing | 87, 238 |
| abstract_inverted_index.real-world | 70 |
| abstract_inverted_index.usability, | 64 |
| abstract_inverted_index.volunteers | 148 |
| abstract_inverted_index.Periorbital | 2 |
| abstract_inverted_index.application | 41, 77 |
| abstract_inverted_index.collection. | 255 |
| abstract_inverted_index.deployment. | 72 |
| abstract_inverted_index.development | 266 |
| abstract_inverted_index.functional, | 221 |
| abstract_inverted_index.measurement | 46, 227 |
| abstract_inverted_index.periorbital | 44, 226 |
| abstract_inverted_index.Likert-style | 122 |
| abstract_inverted_index.intelligence | 49 |
| abstract_inverted_index.lightweight, | 39 |
| abstract_inverted_index.low-resource | 55, 231 |
| abstract_inverted_index.measurements | 3 |
| abstract_inverted_index.participants | 119 |
| abstract_inverted_index.personalized | 275 |
| abstract_inverted_index.segmentation | 81, 168 |
| abstract_inverted_index.standardized | 225 |
| abstract_inverted_index.successfully | 129 |
| abstract_inverted_index.upload—was | 116 |
| abstract_inverted_index.Post-session, | 118 |
| abstract_inverted_index.browser-based | 40 |
| abstract_inverted_index.environments. | 57 |
| abstract_inverted_index.intuitiveness | 193 |
| abstract_inverted_index.oculoplastics | 263 |
| abstract_inverted_index.segmentation, | 114 |
| abstract_inverted_index.site-specific | 91 |
| abstract_inverted_index.STUDY2025-0731 | 281 |
| abstract_inverted_index.compatibility, | 246 |
| abstract_inverted_index.cross-platform | 65, 222 |
| abstract_inverted_index.functionality, | 66 |
| abstract_inverted_index.preprocessing, | 100 |
| abstract_inverted_index.workflow—metadata | 109 |
| abstract_inverted_index.<title>METHODS</title> | 75 |
| abstract_inverted_index.<title>RESULTS</title> | 127 |
| abstract_inverted_index.Firebase-authenticated | 105 |
| abstract_inverted_index.<title>OBJECTIVE</title> | 32 |
| abstract_inverted_index.<title>BACKGROUND</title> | 1 |
| abstract_inverted_index.<title>CONCLUSIONS</title> | 217 |
| abstract_inverted_index.<title>CLINICALTRIAL</title> | 280 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 12 |
| citation_normalized_percentile.value | 0.59266011 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |