Anatomical prognosis after idiopathic macular hole surgery: machine learning based-predection

Abstract

To develop a machine learning (ML) model for the prediction of the idiopathic macular hole (MH) status at 9 months after vitrectomy and inverted flap internal limiting membrane (ILM) peeling surgery. This single center was conducted at Department A, Institute Hedi Raies of Ophthalmology, Tunis, Tunisia. The study included 114 patients. In total, 120 eyes underwent optical coherence tomography (OCT) and inverted flap ILM peeling for surgery. Then 510 B scan of macular OCT was acquired 9 months after surgery. MH diameter, basal MH diameter (b), nasal and temporal arm lengths and macular hole angle were measured. Indices including hole form factor, MH index, diameter hole index (DHI) and tractional hole, MH area index and MH volume index were calculated. Receiver operating characteristic (ROC) curves and cut‑off values were derived for each indices predicting closure or not of the MH. The area under the receiver operating characteristic curve (AUC) and kappa value were calculated to evaluate performance of the medical decision support system (MDSS) in predicting the MH closure. From the ROC curve analysis, it was derived that MH indices like MH diameter, diameter hole index (DHI), MH index, and hole formation factor were capable of successfully predicting MH closure while basal diameter, DHI and MH area index predicted none closure MH. The MDSS achieved an AUC of 0.984 with a kappa value of 0.934. Based on the preoperative OCT parameters, our ML model achieved remarkable accuracy in predicting MH outcomes after pars plana vitrectomy and inverted flap ILM peeling. Therefore, MDSS may help optimize surgical planning for full thickness macular hole patients in the future.

Keywords

• macular hole
• prognosis
• artificial intelligence