A mhealth application for automated detection and diagnosis of strabismus.

Abstract

Amblyopia is a public health problem, and strabismus is its primary cause. Our objective is to evaluate the concordance of the diagnosis of strabismus between strabismus expert ophthalmologist and the mhealth application developed for this purpose. We evaluated the concordance of the diagnosis of strabismus between the expert ophthalmologist and the mhealth application by screening 224 children and adolescents in the 5-15 years age group, with snapshots of patients' eyes and their analysis thereof. We were using a multifunctional cell phone with Android and the ophthalmologist's clinical evaluation by analyzing the ocular deviations using simple cover and prism and alternate cover. Fraction measurements were used with two cutoff points of 6 and 11 prismatic diopters (PD). Results were compared according to their concordances, with a fair Kappa equal to 0.43 (95%CI = [0.38; 0.48]), which was statistically significant (p < 0.0001) at the cutoff point of 6 PD and Kappa equal to 0.49 (95% CI = [0.35; 0.61]), which was statistically significant (p < 0.042) in the cutoff point of 11 PD. The cutoff point of 6 PD was chosen for screening by this mhealth application since it caused the loss of only two patients with strabismus, whereas, in the case of 11 PD, the loss was five patients in the universe of 224. These results are promising for the use of this software as a screening method for patients with strabismus.