Development of Predictive Models in Patients with Epiphora Using Lacrimal Scintigraphy and Machine Learning / 대한핵의학회잡지

PURPOSE: We developed predictive models using different programming languages and different computing platforms for machine learning (ML) and deep learning (DL) that classify clinical diagnoses in patients with epiphora. We evaluated the diagnostic performance of these models.METHODS: Between January 2016 and September 2017, 250 patients with epiphora who underwent dacryocystography (DCG) and lacrimal scintigraphy (LS) were included in the study. We developed five different predictive models using ML tools, Python-based TensorFlow, R, and Microsoft Azure Machine Learning Studio (MAMLS). A total of 27 clinical characteristics and parameters including variables related to epiphora (VE) and variables related to dacryocystography (VDCG) were used as input data. Apart from this, we developed two predictive convolutional neural network (CNN) models for diagnosing LS images. We conducted this study using supervised learning.RESULTS: Among 500 eyes of 250 patients, 59 eyes had anatomical obstruction, 338 eyes had functional obstruction, and the remaining 103 eyes were normal. For the data set that excluded VE and VDCG, the test accuracies in Python-based TensorFlow, R, multiclass logistic regression in MAMLS, multiclass neural network in MAMLS, and nuclear medicine physician were 81.70%, 80.60%, 81.70%, 73.10%, and 80.60%, respectively. The test accuracies of CNN models in three-class classification diagnosis and binary classification diagnosis were 72.00% and 77.42%, respectively.CONCLUSIONS: ML-based predictive models using different programming languages and different computing platforms were useful for classifying clinical diagnoses in patients with epiphora and were similar to a clinician's diagnostic ability.

Comparison of Lacrimal Scintigraphy and Fluorescein Dye Disappearance Test in Functional Blockage of Lacrimal System

PURPOSE: To compare the usefulness of fluorescein dye disappearance test (FDDT) and dacryoscintigraphy in functional lacrimal blockage. METHODS: The present study included with 24 patients (37 eyes), who were diagnosed with functional lacrimal blockage and underwent silicone tube insertion in our clinic. Compared to postoperative symptom improvement, the results of FDDT and dacryoscintigraphy were analyzed. RESULTS: Significant correlations were observed with FDDT and dacryoscintigraphy results in 29 eyes before surgery. In 33 eyes, there were post-operative symptom improvements and the sensitivity of each exam was estimated at 87.8% in FDDT and 90.9% in dacryoscintigraphy. After intubation normal findings were observed in each examination and the symptoms improved in 7 out of 8 eyes. CONCLUSIONS: Both FDDT and dacryoscintigraphy were considered sensitive and efficient methods in the diagnosis and evaluation of functional lacrimal blockage. Both methods require caution regarding misinterpretation by false negatives and may be complementary as well as increasing diagnostic accuracy.