Clinical decision support system based on deep learning for evaluating implantable collamer lens size and vault after implantable collamer lens surgery: a retrospective study.

OBJECTIVES: To aid doctors in selecting the optimal preoperative implantable collamer lens (ICL) size and to enhance the safety and surgical outcomes of ICL procedures, a clinical decision support system (CDSS) is proposed in our study.

DESIGN: A retrospective study of patients after ICL surgery.

SETTING: China Tertiary Myopia Prevention and Control Center.

PARTICIPANTS: 2772 eyes belonging to 1512 patients after ICL surgery. Data were collected between 2018 and 2022.

OUTCOME MEASURES: A CDSS is constructed and used to predict vault at 1 month postoperatively and preoperative ICL dimensions using various artificial intelligence methods. Accuracy metrics as well as area under curve (AUC) parameters are used to determine the CDSS prediction methods.

RESULTS: Among the ICL size prediction models, conventional neural networks (CNNs) achieve the best prediction accuracy at 91.37% and exhibit the highest AUC of 0.842. Regarding the prediction model for vault values 1 month after surgery, CNN surpasses the other methods with an accuracy of 85.27%, which has the uppermost AUC of 0.815. Thus, we select CNN as the prediction algorithm for the CDSS.

CONCLUSIONS: This study introduces a CDSS to assist doctors in selecting the optimal ICL size for patients while improving the safety and postoperative outcomes of ICL surgery.