1
|
Pucchio A, Krance SH, Pur DR, Bhatti J, Bassi A, Manichavagan K, Brahmbhatt S, Aggarwal I, Singh P, Virani A, Stanley M, Miranda RN, Felfeli T. Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review. Graefes Arch Clin Exp Ophthalmol 2024; 262:1041-1091. [PMID: 37421481 DOI: 10.1007/s00417-023-06100-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Revised: 04/25/2023] [Accepted: 05/06/2023] [Indexed: 07/10/2023] Open
Abstract
PURPOSE This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools. METHODS This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included. RESULTS A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data. CONCLUSION AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.
Collapse
Affiliation(s)
- Aidan Pucchio
- Department of Ophthalmology, Queen's University, Kingston, ON, Canada
- Queens School of Medicine, Kingston, ON, Canada
| | - Saffire H Krance
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | - Daiana R Pur
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | - Jasmine Bhatti
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | - Arshpreet Bassi
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | | | - Shaily Brahmbhatt
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | | | - Priyanka Singh
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | - Aleena Virani
- Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | | | - Rafael N Miranda
- The Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada
| | - Tina Felfeli
- The Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada.
- Department of Ophthalmology and Vision Sciences, University of Toronto, 340 College Street, Suite 400, Toronto, ON, M5T 3A9, Canada.
| |
Collapse
|
2
|
Dammak A, Pastrana C, Martin-Gil A, Carpena-Torres C, Peral Cerda A, Simovart M, Alarma P, Huete-Toral F, Carracedo G. Oxidative Stress in the Anterior Ocular Diseases: Diagnostic and Treatment. Biomedicines 2023; 11:biomedicines11020292. [PMID: 36830827 PMCID: PMC9952931 DOI: 10.3390/biomedicines11020292] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Revised: 01/16/2023] [Accepted: 01/17/2023] [Indexed: 01/26/2023] Open
Abstract
The eye is a metabolically active structure, constantly exposed to solar radiations making its structure vulnerable to the high burden of reactive oxygen species (ROS), presenting many molecular interactions. The biomolecular cascade modification is caused especially in diseases of the ocular surface, cornea, conjunctiva, uvea, and lens. In fact, the injury in the anterior segment of the eye takes its origin from the perturbation of the pro-oxidant/antioxidant balance and leads to increased oxidative damage, especially when the first line of antioxidant defence weakens with age. Furthermore, oxidative stress is related to mitochondrial dysfunction, DNA damage, lipid peroxidation, protein modification, apoptosis, and inflammation, which are involved in anterior ocular disease progression such as dry eye, keratoconus, uveitis, and cataract. The different pathologies are interconnected through various mechanisms such as inflammation, oxidative stress making the diagnostics more relevant in early stages. The end point of the molecular pathway is the release of different antioxidant biomarkers offering the potential of predictive diagnostics of the pathology. In this review, we have analysed the oxidative stress and inflammatory processes in the front of the eye to provide a better understanding of the pathomechanism, the importance of biomarkers for the diagnosis of eye diseases, and the recent treatment of anterior ocular diseases.
Collapse
|
3
|
Strachecka A, Krauze M, Olszewski K, Borsuk G, Paleolog J, Merska M, Chobotow J, Bajda M, Grzywnowicz K. Unexpectedly strong effect of caffeine on the vitality of western honeybees (Apis mellifera). BIOCHEMISTRY (MOSCOW) 2014; 79:1192-201. [DOI: 10.1134/s0006297914110066] [Citation(s) in RCA: 29] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
|
4
|
Influence of cataract maturity on aqueous humor lipid peroxidation markers and antioxidant enzymes. Eye (Lond) 2013; 28:72-7. [PMID: 24097121 DOI: 10.1038/eye.2013.207] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2012] [Accepted: 08/19/2013] [Indexed: 01/24/2023] Open
Abstract
PURPOSE The impact of cataract maturity on the aqueous humor (AH) oxidant/antioxidant balance is largely controversial. This study was aimed at assessing the relationships between cataract maturity and AH lipid peroxidation markers and enzymatic antioxidants. PATIENTS AND METHODS The concentrations of conjugated dienes (CD), lipofuscin-like fluorescent end-products (LLF), soluble proteins, as well as the activities of superoxide dismutase (SOD) and catalase (CAT) were measured in AH samples from nondiabetic patients with either immature (n=15) or mature (n=15) cataract. RESULTS In the overall AH sample, the mean values of CD, LLF, SOD, and CAT were 0.160 ± 0.024 (OD234), 166 ± 27 RFU, 24.5 ± 7.1 U/ml, and 31.9 ± 3.9 pmol/ml, respectively. CD was positively correlated with SOD (r=0.647; P<0.001), CAT (r=-0.394; P=0.031), and LLF (r=-0.399; P=0.029). The LLF was negatively correlated with SOD (r=-0.461; P=0.010). In samples adjusted for confounding factors, differences between immature and mature cataract groups regarding SOD, CD, LLF, and total proteins were significant (P<0.05; for all variables). The multiple logistic regression analysis identified LLF (OR=4.08; P=0.038) and SOD (OR=4.99; P=0.031) as independent predictors of cataract maturity. CONCLUSIONS These results suggest that AH lipid peroxidation markers and antioxidants may significantly depend on the cataract maturity stage.
Collapse
|