Accuracy of an artificial intelligence-based mobile application for detecting cataracts: Results from a field study

Purpose: To assess the accuracy of e?Paarvai, an artificial intelligence?based smartphone application (app) that detects and grades cataracts using images taken with a smartphone by comparing with slit lamp?based diagnoses by trained ophthalmologists. Methods: In this prospective diagnostic study conducted between January and April 2022 at a large tertiary?care eye hospital in South India, two screeners were trained to use the app. Patients aged >40 years and with a best?corrected visual acuity <20/40 were recruited for the study. The app is intended to determine whether the eye has immature cataract, mature cataract, posterior chamber intra?ocular lens, or no cataract. The diagnosis of the app was compared with that of trained ophthalmologists based on slit?lamp examinations, the gold standard, and a receiver operating characteristic (ROC) curve was estimated. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were computed. Results: The two screeners used the app to screen 2,619 eyes of 1,407 patients. In detecting cataracts, the app showed high sensitivity (96%) but low specificity (25%), an overall accuracy of 88%, a PPV of 92.3%, and an NPV of 57.8%. In terms of cataract grading, the accuracy of the app was high in detecting immature cataracts (1,875 eyes, 94.2%), but its accuracy was poor in detecting mature cataracts (73 eyes, 22%), posterior chamber intra?ocular lenses (55 eyes, 29.3%), and clear lenses (2 eyes, 2%). We found that the area under the curve in predicting ophthalmologists’ cataract diagnosis could potentially be improved beyond the app’s diagnosis based on using images only by incorporating information about patient sex and age (P < 0.0001) and best?corrected visual acuity (P < 0.0001). Conclusions: Although there is room for improvement, e?Paarvai app is a promising approach for diagnosing cataracts in difficult?to?reach populations. Integrating this with existing outreach programs can enhance the case detection rate.

Embracing technology in cataract surgical training � The way forward

While ophthalmology as a surgical branch itself has evolved technologically with newer instruments, techniques and procedures; ophthalmic surgical training appears to have stagnated in terms of how it is delivered and how trainees� learning and performance are assessed. This collaborative editorial attempts to identify the lacunae in ophthalmic residency training and highlight how technological tools such as surgical simulators can be incorporated into ophthalmic training even in limited-resource settings with good results

Comparative study on the incidence and outcomes of pigmented versus non pigmented keratomycosis.

Purpose: To determine the incidence, outcomes and establish factors determining visual prognosis of keratomycosis due to pigmented fungi in comparison with nonpigmented fungi. Materials and Methods: All culture-proven cases of fungal keratitis from January 2006 to August 2008 were drawn from a computerized database and cases with adequate documentation were analyzed for predisposing factors, clinical characteristics, microbiology and treatment methods. Outcomes of keratitis due to pigmented and nonpigmented fungi were compared using t-test and χ2 test. Results: Of 373 cases of keratomycosis during the study period, pigmented fungi were etiological agents in 117 eyes (31.3%) and nonpigmented fungi in 256 eyes (68.7%). Eyes with nonpigmented keratitis had significantly larger ulcers (14.96 mm2 ) and poorer vision (1.42 logMAR) at presentation compared to those with keratomycosis due to pigmented fungi (P=0.01). The characteristic macroscopic pigmentation was seen in only 14.5% in the pigmented keratitis group. Both groups responded favorably to medical therapy (78.1% vs. 69.1%) with scar formation (P=0.32) and showed a significant improvement in mean visual acuity compared with that at presentation (P<0.01). Visual improvement in terms of line gainers and losers in the subgroup of eyes that experienced healing was also similar. Location of the ulcer was the only factor that had significant predictive value for visual outcome (P=0.021). Conclusion: Incidence of keratomycosis due to pigmented fungi may be increasing as compared to previous data. These eyes have similar response to medical therapy and similar visual outcome compared to nonpigmented keratitis. Central ulcers have a poor visual outcome.

Risk factors for intraocular penetration of caterpillar hair in Ophthalmia Nodosa: A retrospective analysis.

We report risk factors associated with intraocular penetration of caterpillar hair seen at our institute from January 2005 to December 2007. Records of all patients with caterpillar hair induced ophthalmitis (CHIO) were retrospectively reviewed for clinical characteristics, anatomic location of lodgment of the caterpillar hair, treatment methods, and outcomes. Out of a total of 544 cases of CHIO, 19 eyes (seven in the anterior chamber and 12 in the posterior segment) experienced intraocular penetration (3.5%). The presence of deep intracorneal hair (80 cases, 14.7%) was found to be the only risk factor for intraocular penetration (P < 0.001). The removal of intracorneal hair was possible in only 29 out of 80 eyes (36%) and this was associated with a significantly reduced risk of intraocular penetration (P = 0.022). Patients with retained intracorneal hairs should be counseled regarding risk of intraocular penetration and closely followed up for at least six months.

Capsulotomy and hydroprocedures for nucleus prolapse in manual small incision cataract surgery.

Manual small incision cataract surgery (MSICS) involves the manual removal of nucleus through a scleral tunnel. To achieve 100% success every time, one has to do a good capsulotomy and should master the technique to prolapse the nucleus into anterior chamber. During conversion from extracapsular cataract surgery to MSICS, one can perform a can-opener capsulotomy and prolapse the nucleus. However, it is safer and better to perform a capsulorrhexis and hydroprolapse the nucleus, as it makes the rest of the steps of MSICS comfortable. Use of trypan blue in white and brown cataracts makes the capsulorrhexis and prolapse simple and safe. Extra caution should be taken in cases with hypermature cataracts with weak zonules and subluxated cataracts.