Modelos computacionais baseados em inteligência artificial e estatística para o apoio à decisão médica na escolha das fórmulas biométricas em catarata

Abstract

Cataract is the leading cause of reversible blindness in the world, despite the safe, reproducible surgical treatment capable of correcting refractive errors and preventing photodystopic phenomena through the proper calculation, by means of biometric formulae, of the refractive power of the new intraocular lens. The technical results are good, but they present inadequate results in patients with eyes with atypical biometric measurements. In this study, we developed and presented multiple computational models capable of predicting the accuracy of each intraocular formula in certain groups, including different intraocular lenses and subgroups of individuals with similar biometric measures. The algorithms developed in this study are able to help the ophthalmologist in the decision making and bring better results in cataract surgery.