Prediction of postoperative complications of pediatric cataract patients using data mining

Abstract

Background: The common treatment for pediatric cataracts is to replace the cloudy lens with an artificial one. However, patients may suffer complications (severe lens proliferation into the visual axis and abnormal high intraocular pressure; SLPVA and AHIP) within 1 year after surgery and factors causing these complications are unknown.

Methods: Apriori algorithm is employed to find association rules related to complications. We use random forest (RF) and Naïve Bayesian (NB) to predict the complications with datasets preprocessed by SMOTE (synthetic minority oversampling technique). Genetic feature selection is exploited to find real features related to complications.

Results: Average classification accuracies in three binary classification problems are over 75%. Second, the relationship between the classification performance and the number of random forest tree is studied. Results show except for gender and age at surgery (AS); other attributes are related to complications. Except for the secondary IOL placement, operation mode, AS and area of cataracts; other attributes are related to SLPVA. Except for the gender, operation mode, and laterality; other attributes are related to the AHIP. Next, the association rules related to the complications are mined out. Then additional 50 data were used to test the performance of RF and NB, both of then obtained the accuracies of over 65% for three classification problems. Finally, we developed a webserver to assist doctors.

Conclusions: The postoperative complications of pediatric cataracts patients can be predicted. Then the factors related to the complications are found. Finally, the association rules that is about the complications can provide reference to doctors.

Keywords: Association rules mining; Genetic feature selection; Medical decision making system; Naïve Bayesian; Random forest.

Fig. 1

Three grading standards of severity of pediatric cataracts. a the area of cataract is small; b the area of cataract is large; c the density of the cataract is sloppy; d the density of the cataract is dense; e the cataract covers the central area of lens; f the cataract does not covering the central area of lens

Fig. 2

ROC curves and AUC values in three binary classification problem. (ROC receiver operating characteristics curve, AUC: area under curve, RF random forest; SMOTE synthetic minority oversampling technique, NB Naïve Bayesian classifier)

Fig. 3

The relationship between accuracy and the number of trees of random forest. (RF means random forest)

Fig. 4

ROC curves and AUC values for additional testing

Fig. 5

Flowchart of postoperative complication prediction. (At first, the inputted data is preprocessed with data discretion method. Then one of the three models is applied to distinguish whether a patient suffers from complication. If the patient is not normal, then the remaining two models are used to judge whether the patient has two types of complication. If the patient is judged to be normal, the remaining two models will not be used)

Fig. 6

The relationship between threshold and the number of association rules