Classification tree to analyze factors connected with post operative complications of cataract surgery in a teaching hospital

Background: Artificial intelligence (AI) is becoming ever more frequently applied in medicine and, consequently, also in ophthalmology to improve both the quality of work for physicians and the quality of care for patients. The aim of this study is to use AI, in particular classification tree, for the evaluation of both ocular and systemic features involved in the onset of complications due to cataract surgery in a teaching hospital. Methods: The charts of 1392 eyes of 1392 patients, with a mean age of 71.3 ± 8.2 years old, were reviewed to collect the ocular and systemic data before, during and after cataract surgery, including post-operative complications. All these data were processed by a classification tree algorithm, producing more than 260 million simulations, aiming to develop a predictive model. Results: Postoperative complications were observed in 168 patients. According to the AI analysis, the pre-operative characteristics involved in the insurgence of complications were: ocular comorbidities, lower visual acuity, higher astigmatism and intra-operative complications. Conclusions: Artificial intelligence application may be an interesting tool in the physician’s hands to develop customized algorithms that can, in advance, define the post-operative complication risk. This may help in improving both the quality and the outcomes of the surgery as well as in preventing patient dissatisfaction.