An approach to predict the risk of glaucoma development by integrating different attribute data

Abstract

Primary open-angle glaucoma (POAG) is one of the major causes of blindness worldwide and considered to be influenced by inherited and environmental factors. Recently, we demonstrated a genome-wide association study for the susceptibility to POAG by comparing patients and controls. In addition, the serum cytokine levels, which are affected by environmental and postnatal factors, could be also obtained in patients as well as in controls, simultaneously. Here, in order to predict the effective diagnosis of POAG, we developed an “integration approach” using different attribute data which were integrated simply with several machine learning methods and random sampling. Two data sets were prepared for this study. The one is the “training data set”, which consisted of 42 POAG and 42 controls. The other is the “test data set” consisted of 73 POAG and 52 controls. We first examined for genotype and cytokine data using the training data set with general machine learning methods. After the integration approach was applied, we obtained the stable accuracy, using the support vector machine method with the radial basis function. Although our approach was based on well-known machine learning methods and a simple process, we demonstrated that the integration with two kinds of attributes, genotype and cytokines, was effective and helpful in diagnostic prediction of POAG.

The role of artificial intelligence in analysis of biofluid markers for diagnosis and management of glaucoma: A systematic review

“…19,20,24 As such, biofluid marker AI models may be utilized for glaucoma diagnosis to augment existing imaging-based tools to increase accuracy. Tokuda et al (2012) demonstrate this principle, showing increased glaucoma diagnostic accuracy with combined genotype and cytokine data, when compared to each independantly. 61 As frequent procedures are common in the glaucoma patient population, serum or ocular fluids such as aqueous humour may be readily available for use in clinical tools.…”

“…While many studies looked at entire metabolomic or proteomic profiles to determine changes in POAG, there was heterogeneity in the data with reporting of over 175 unique, differentially expressed biomarkers, over 75 biological pathways implicated in POAG development, and over 50 unique biomarkers determined to be non-significant. 8 , 9 , 25 , 27 , 28 , 33 , 34 , 36 , 41 – 49 , 51 – 53 , 55 , 58 – 61 , 63 , 64 Studies each identified between one and 773 differentially expressed biomarkers. Many studies using unsupervised AI to look for differentially expressed markers did not report all non-significant biomarkers investigated.…”

“…ANN, discriminant analysis, support vector machine, random forest (RF), deep learning, and Naive Bayes Classifier were among the supervised tools utilized to develop models that differentiated between glaucoma subtypes and controls, with accuracy reported in 13 papers. 25 – 27 , 34 , 36 , 48 , 49 , 51 , 52 , 54 , 58 , 60 , 61 Nine of the papers reporting differentiating accuracy has the objective of identifying disease characteristics, while four were intended to develop diagnostic tools. While the goals of predictive models were variable between studies, all models sought to autonomously identify glaucoma patients from controls or other glaucoma subtypes given a test set of labelled samples, with the identifying disease characteristics focusing on the identification of a characteristic biomarker and the diagnostic studies focusing on maximization of algorithm accuracy ( Supplemental Table 1 ).…”

“…25 In studies that reported accuracy as the percentage of cases that were accurately classified, predictive accuracy ranged from 51% to 95%; generally ANNs were the most accurate while support vector machine were the least accurate. 26,49,61 The accuracies of all studies are summarized in Table 2. Selection of the AI algorithm had considerable influence on model accuracy.…”

Efficient and reliable establishment of lymphoblastoid cell lines by Epstein-Barr virus transformation from a limited amount of peripheral blood

“…This study was approved by the Institutional Review Board of KPUM as part of ongoing studies, some of which have been published elsewhere 6 7 8 9 20 21 22 . All procedures were conducted in accordance with the tenets set forth in the Declaration of Helsinki, and written informed consent was obtained from all participating volunteers after receiving a detailed explanation of the procedures and possible consequences of being involved in the study.…”