1
|
Storås AM, Fineide F, Magnø M, Thiede B, Chen X, Strümke I, Halvorsen P, Galtung H, Jensen JL, Utheim TP, Riegler MA. Using machine learning model explanations to identify proteins related to severity of meibomian gland dysfunction. Sci Rep 2023; 13:22946. [PMID: 38135766 PMCID: PMC10746717 DOI: 10.1038/s41598-023-50342-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Accepted: 12/19/2023] [Indexed: 12/24/2023] Open
Abstract
Meibomian gland dysfunction is the most common cause of dry eye disease and leads to significantly reduced quality of life and social burdens. Because meibomian gland dysfunction results in impaired function of the tear film lipid layer, studying the expression of tear proteins might increase the understanding of the etiology of the condition. Machine learning is able to detect patterns in complex data. This study applied machine learning to classify levels of meibomian gland dysfunction from tear proteins. The aim was to investigate proteomic changes between groups with different severity levels of meibomian gland dysfunction, as opposed to only separating patients with and without this condition. An established feature importance method was used to identify the most important proteins for the resulting models. Moreover, a new method that can take the uncertainty of the models into account when creating explanations was proposed. By examining the identified proteins, potential biomarkers for meibomian gland dysfunction were discovered. The overall findings are largely confirmatory, indicating that the presented machine learning approaches are promising for detecting clinically relevant proteins. While this study provides valuable insights into proteomic changes associated with varying severity levels of meibomian gland dysfunction, it should be noted that it was conducted without a healthy control group. Future research could benefit from including such a comparison to further validate and extend the findings presented here.
Collapse
Affiliation(s)
- Andrea M Storås
- Department of Holistic Systems, Simula Metropolitan Center for Digital Engineering, Oslo, Norway.
- Department of Computer Science, OsloMet - Oslo Metropolitan University, Oslo, Norway.
| | - Fredrik Fineide
- Department of Computer Science, OsloMet - Oslo Metropolitan University, Oslo, Norway
- The Norwegian Dry Eye Clinic, Oslo, Bergen, Norway
| | - Morten Magnø
- Department of Ophthalmology, Sørlandet Hospital Arendal, Arendal, Norway
- Department of Plastic and Reconstructive Surgery, Oslo University Hospital, Oslo, Norway
| | - Bernd Thiede
- Department of Biosciences, University of Oslo, Oslo, Norway
| | - Xiangjun Chen
- Department of Ophthalmology, Sørlandet Hospital Arendal, Arendal, Norway
- Department of Medical Biochemistry, Oslo University Hospital, Oslo, Norway
- Department of Ophthalmology, Vestre Viken Hospital Trust, Drammen, Norway
| | - Inga Strümke
- Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
| | - Pål Halvorsen
- Department of Holistic Systems, Simula Metropolitan Center for Digital Engineering, Oslo, Norway
- Department of Computer Science, OsloMet - Oslo Metropolitan University, Oslo, Norway
| | - Hilde Galtung
- Institute of Oral Biology, University of Oslo, Oslo, Norway
| | - Janicke L Jensen
- Department of Oral Surgery and Oral Medicine, University of Oslo, Oslo, Norway
| | - Tor P Utheim
- Department of Computer Science, OsloMet - Oslo Metropolitan University, Oslo, Norway
- The Norwegian Dry Eye Clinic, Oslo, Bergen, Norway
- Department of Ophthalmology, Sørlandet Hospital Arendal, Arendal, Norway
- Department of Medical Biochemistry, Oslo University Hospital, Oslo, Norway
- Department of Ophthalmology, Oslo University Hospital, Oslo, Norway
| | - Michael A Riegler
- Department of Holistic Systems, Simula Metropolitan Center for Digital Engineering, Oslo, Norway
- Department of Computer Science, OsloMet - Oslo Metropolitan University, Oslo, Norway
- Department of Computer Science, UiT The Arctic University of Norway, Tromsø, Norway
| |
Collapse
|
2
|
Silverstein SM, Sato MA, Meier EJ, Dai S, Bauskar A, Depperschmidt K, Blender N, Vantipalli S, Goldstein MH, Gurses Ozden R. Effects of Punctal Occlusion on Ocular Itching and Conjunctival Redness Associated with Allergic Conjunctivitis. Curr Eye Res 2023; 48:781-787. [PMID: 37199292 DOI: 10.1080/02713683.2023.2211247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 04/19/2023] [Accepted: 05/02/2023] [Indexed: 05/19/2023]
Abstract
PURPOSE Punctal occlusion using punctal plugs has been successfully used to treat the signs and symptoms of dry eye disease. However, the effects of punctal occlusion on the symptoms of allergic conjunctivitis (AC) have been less well documented. There is some concern among clinicians that punctal occlusion may make signs/symptoms of allergic conjunctivitis worse by trapping allergens on the eye. The objective of this post hoc analysis was to address this question and thus assess the effect of punctal occlusion alone on ocular itching and conjunctival redness associated with AC. METHODS This was a pooled post hoc analysis of three randomized, double-blind, placebo insert-controlled clinical trials in subjects with AC. Enrolled subjects were generally healthy adults with ocular allergies and a positive skin test reaction to perennial and/or seasonal allergens. The study used a modified version of the traditional conjunctival allergen challenge (CAC) model, which included multiple, repeated allergen challenges following placement of the intracanalicular insert. Subjects were rechallenged on Days 6, 7 and 8; Days 13, 14 and 15; and Days 26, 27 and 28. RESULTS The data set included 128 subjects that were administered placebo. Baseline mean (SD) ocular itching and conjunctival redness scores were 3.52 (0.44) and 2.97 (0.39), respectively. On post-insertion Days 7, 14 and 28, mean itching scores were 2.62, 2.26 and 1.91, respectively, representing 26%, 36% and 46% itching reductions, respectively (p < 0.001). On Days 7, 14 and 28, mean conjunctival redness scores were 1.98, 1.90, and 2.08, respectively, representing 33%, 36%, and 30% redness reductions, respectively (p < 0.001). CONCLUSIONS Based on this post hoc pooled analysis, punctal occlusion with a resorbable hydrogel intracanalicular insert did not worsen ocular itching or conjunctival redness in this patient population.
Collapse
Affiliation(s)
| | | | | | - Stella Dai
- Ocular Therapeutix, Inc., Bedford, MA, USA
| | | | | | | | | | | | | |
Collapse
|