Accuracy of artificial intelligence model for infectious keratitis classification: a systematic review and meta-analysis

Artificial intelligence in ophthalmology

PURPOSE OF REVIEW

To review role of artificial intelligence in medicine.

RECENT FINDINGS

Artificial intelligence is continuing to revolutionize access, diagnosis, personalization of medicine, and treatment in healthcare. As a matter of fact, artificial intelligence contributed to the research that resulted in 2024 Nobel Prizes in physics, chemistry, and economics. We are only at the tip of the iceberg in utilizing the abilities of artificial intelligence in medicine to improve accuracy of diagnoses and to enhance patient outcomes. Artificial intelligence has allowed better image analysis, prediction of progression of disease, personalized treatment plans, incorporations of genomics, and improved efficiency in care and follow-up utilizing home monitoring. In ocular health diagnosis and treatment of diabetic retinopathy, macular degeneration, glaucoma, corneal infections, and ectasia are only a few examples of how the power of artificial intelligence has been harnessed. Even though there are still challenges that need more work in the areas of patient privacy, Health Insurance Portability and Accountability Act (HIPAA) compliance, reliability, and development of regulatory frameworks, artificial intelligence has revolutionized and will continue to revolutionize medicine.

SUMMARY

Artificial intelligence is enhancing medical diagnosis and treatment, as well as access and prevention. Ocular imaging, visual outcome, optics, intraocular pressure, and data points will continue to see growth it the field of artificial intelligence.

Artificial intelligence in fracture detection on radiographs: a literature review

Fractures are one of the most common reasons of admission to emergency department affecting individuals of all ages and regions worldwide that can be misdiagnosed during radiologic examination. Accurate and timely diagnosis of fracture is crucial for patients, and artificial intelligence that uses algorithms to imitate human intelligence to aid or enhance human performs is a promising solution to address this issue. In the last few years, numerous commercially available algorithms have been developed to enhance radiology practice and a large number of studies apply artificial intelligence to fracture detection. Recent contributions in literature have described numerous advantages showing how artificial intelligence performs better than doctors who have less experience in interpreting musculoskeletal X-rays, and assisting radiologists increases diagnostic accuracy and sensitivity, improves efficiency, and reduces interpretation time. Furthermore, algorithms perform better when they are trained with big data on a wide range of fracture patterns and variants and can provide standardized fracture identification across different radiologist, thanks to the structured report. In this review article, we discuss the use of artificial intelligence in fracture identification and its benefits and disadvantages. We also discuss its current potential impact on the field of radiology and radiomics.

Diagnostic performance of deep learning for infectious keratitis: a systematic review and meta-analysis

Background

Infectious keratitis (IK) is the leading cause of corneal blindness globally. Deep learning (DL) is an emerging tool for medical diagnosis, though its value in IK is unclear. We aimed to assess the diagnostic accuracy of DL for IK and its comparative accuracy with ophthalmologists.

Methods

In this systematic review and meta-analysis, we searched EMBASE, MEDLINE, and clinical registries for studies related to DL for IK published between 1974 and July 16, 2024. We performed meta-analyses using bivariate models to estimate summary sensitivities and specificities. This systematic review was registered with PROSPERO (CRD42022348596).

Findings

Of 963 studies identified, 35 studies (136,401 corneal images from >56,011 patients) were included. Most studies had low risk of bias (68.6%) and low applicability concern (91.4%) in all domains of QUADAS-2, except the index test domain. Against the reference standard of expert consensus and/or microbiological results (seven external validation studies; 10,675 images), the summary estimates (95% CI) for sensitivity and specificity of DL for IK were 86.2% (71.6-93.9) and 96.3% (91.5-98.5). From 28 internal validation studies (16,059 images), summary estimates for sensitivity and specificity were 91.6% (86.8-94.8) and 90.7% (84.8-94.5). Based on seven studies (4007 images), DL and ophthalmologists had comparable summary sensitivity [89.2% (82.2-93.6) versus 82.2% (71.5-89.5); P = 0.20] and specificity [(93.2% (85.5-97.0) versus 89.6% (78.8-95.2); P = 0.45].

Interpretation

DL models may have good diagnostic accuracy for IK and comparable performance to ophthalmologists. These findings should be interpreted with caution due to the image-based analysis that did not account for potential correlation within individuals, relatively homogeneous population studies, lack of pre-specification of DL thresholds, and limited external validation. Future studies should improve their reporting, data diversity, external validation, transparency, and explainability to increase the reliability and generalisability of DL models for clinical deployment.

Funding

NIH, Wellcome Trust, MRC, Fight for Sight, BHP, and ESCRS.

Blast injury: Impact to the cornea

Visual disorders are common even after mild traumatic brain injury (mTBI) or blast exposure. The cost of blast-induced vision loss in civilians, military personnel, and veterans is significant. The visual consequences of blasts associated with TBI are elusive. Active military personnel and veterans report various ocular pathologies including corneal disorders post-combat blasts. The wars and conflicts in Afghanistan, Iraq, Syria, and Ukraine have significantly increased the number of corneal and other ocular disorders among military personnel and veterans. Binocular vision, visual fields, and other visual functions could be impaired following blast-mediated TBI. Blast-associated injuries can cause visual disturbances, binocular system problems, and visual loss. About 25% of veterans exposed to blasts report corneal injury. Blast exposure induces corneal edema, corneal opacity, increased corneal thickness, damage of corneal epithelium, corneal abrasions, and stromal and endothelial abnormality including altered endothelial density, immune cell infiltration, corneal neovascularization, Descemet membrane rupture, and increased pain mediators in animal models and the blast-exposed military personnel including veterans. Immune response exacerbates blast-induced ocular injury. TBI is associated with dry eyes and pain in veterans. Subjects exposed to blasts that cause TBI should undergo immediate clinical visual and ocular examinations. Delayed visual care may lead to progressive vision loss, lengthening/impairing rehabilitation and ultimately may lead to permanent vision problems and blindness. Open-field blast exposure could induce corneal injuries and immune responses in the cornea. Further studies are warranted to understand corneal pathology after blast exposure. A review of current advancements in blast-induced corneal injury will help elucidate novel targets for potential therapeutic options. This review discusses the impact of blast exposure-associated corneal disorders.

[Distribution and Antibiotic Resistance Analysis of Ocular Bacterial Pathogens at a Tertiary Hospital From 2012 to 2021]

Objective

To analyze the distribution of ocular bacterial pathogens and their antibiotic resistance status at a tertiary-care hospital and to provide a reference for the appropriate use of antibiotics.

Methods

Retrospective analysis was conducted with bacteria isolated from the ophthalmic samples sent for lab analysis at a tertiary-care hospital from 2012 to 2021. The suspected bacterial strains were identified with automated systems for microbial identification and susceptibility analysis and matrix-assisted laser desorption/ionization time-of-flight mass spectrometer. VITEK 2 Compact, an automated microbial identification and antibiotic susceptibility analysis system, was used for antimicrobial susceptibility testing.

Results

A total of 1556 ophthalmology bacteria culture samples were collected, 574 of which showed bacterial growth, presenting an overall positive rate of 36.89%. Of the isolated bacteria, Gram-positive cocci, Gram-positive bacilli, Gram-negative bacilli, and Gram-negative cocci accounted for 63.15% (377/597), 18.76% (112/597), 17.09% (102/597), and 1.00% (6/597), respectively. Among the bacteria isolated in different years over the course of a decade, Gram-positive cocci always turned out to be the main cause of eye infections. Of the Gram-positive cocci, 73.47% (277/377) were isolated from patients with endophthalmitis, with the most important species being Staphylococcus epidermidis, which was followed by Streptococcus viridans. The rest, or 26.53% (100/377), of the Gram-positive cocci were isolated from patients with external eye infections, with the main isolated strains being Staphylococcus epidermidis, Streptococcus viridans, and Staphylococcus aureus. More than 70% of Staphylococcus epidermidis isolated from both endophthalmitis and external eye infections were resistant to methicillin. No strains resistant to vancomycin, linezolid, or tigecycline were detected. Staphylococcus epidermidis isolated from patients with external eye infections had a low rate of resistance to levofloxacin (2/27 or 7.41%), whereas those isolated from patients with endophthalmitis had a higher resistance rate (43/127 or 33.86%). The difference in drug resistance rate between the two groups was statistically significant (P<0.05).

Conclusion

The chief ocular bacterial pathogens identified in a tertiary-care hospital were Gram-positive cocci, among which, Staphylococcus epidermidis was the most common species. The Staphylococcus epidermidis identified in the hospital had a high rate of resistance to oxacillin, but remained highly sensitive to vancomycin, linezolid, and tigecycline. The endophthalmitis caused by Staphylococcus epidermidis in the hospital can be treated empirically with vancomycin and then the treatment plan can be further adjusted according to the results of the drug susceptibility test. However, the establishment of the breakpoint of drug susceptibility test is mainly based on the model of bloodstream infection and has limited reference value for the treatment of eye infection. The required drug distribution concentration at the infection site can be achieved by dose increase or local administration.