scholarly journals Full Accuracy of Machine Learning for Differentiation between Optic Neuropathies and Pseudopapilledema

2019 ◽  
Author(s):  
Jin Mo Ahn ◽  
Sangsoo Kim ◽  
Kwang-Sung Ahn ◽  
Sung-Hoon Cho ◽  
Ungsoo Kim
Keyword(s):  
Machine Learning ◽  
Visual Acuity ◽  
Optic Disc ◽  
Optic Neuropathy ◽  
Characteristic Curve ◽  
Machine Learning Techniques ◽  
Fundus Photography ◽  
Ischemic Optic Neuropathy ◽  
Machine Learning Classifiers ◽  
Learning Classifiers

Abstract Background: This study is to evaluate the accuracy of machine learning for differentiation between optic neuropathies and pseudopapilledema (PPE). Methods: Two hundred and ninety-five images of optic neuropathies, 295 images of PPE, and 779 control images were used. Pseudopapilledema was defined as follows: cases with elevated optic nerve head and blurred disc margin, with normal visual acuity (>0.8 Snellen visual acuity), visual field, color vision, and pupillary reflex. The optic neuropathy group included cases of ischemic optic neuropathy (177), optic neuritis (48), diabetic optic neuropathy (17), papilledema (22), and retinal disorders (31). We compared four machine learning classifiers (our model, GoogleNet Inception v3, 19-layer Very Deep Convolution Network from Visual Geometry group (VGG), and 50-layer Deep Residual Learning (ResNet)). Accuracy and area under receiver operating characteristic curve (AUROC) were analyzed Results: The accuracy of machine learning classifiers ranged from 95.89% to 98.63% (our model: 95.89%, Inception V3: 96.45%, ResNet: 98.63%, and VGG: 96.80%). A high AUROC score was noted in both ResNet and VGG (0.999). Conclusions: Machine learning techniques can be combined with fundus photography as an effective approach to distinguish between PPE and elevated optic disc associated with optic neuropathies. Keywords: Machine Learning; Pseudopapilledema; Optic neuropathy; Optic disc swelling.

scholarly journals Full Accuracy of Machine Learning for Differentiation between Optic Neuropathies and Pseudopapilledema

2019 ◽  
Author(s):  
Jin Mo Ahn ◽  
Sangsoo Kim ◽  
Kwang-Sung Ahn ◽  
Sung-Hoon Cho ◽  
Ungsoo Kim
Keyword(s):  
Machine Learning ◽  
Visual Acuity ◽  
Optic Neuropathy ◽  
Characteristic Curve ◽  
Machine Learning Techniques ◽  
Fundus Photography ◽  
Ischemic Optic Neuropathy ◽  
Pupillary Reflex ◽  
Machine Learning Classifiers ◽  
Learning Classifiers

Abstract Background: This study is to evaluate the accuracy of machine learning for differentiation between optic neuropathies and pseudopapilledema (PPE). Methods : Two hundred and ninety-five images of optic neuropathies, 295 images of PPE, and 779 control images were used. Pseudopapilledema was defined as follows: cases with elevated optic nerve head and blurred disc margin, with normal visual acuity (>0.8 Snellen visual acuity), visual field, color vision, and pupillary reflex. The optic neuropathy group included cases of ischemic optic neuropathy (177), optic neuritis (48), diabetic optic neuropathy (17), papilledema (22), and retinal disorders (31). We compared four machine learning classifiers (our model, GoogleNet Inception v3, 19-layer Very Deep Convolution Network from Visual Geometry group (VGG), and 50-layer Deep Residual Learning (ResNet)). Accuracy and area under receiver operating characteristic curve (AUROC) were analyzed Results: The accuracy of machine learning classifiers ranged from 95.89% to 98.63% (our model: 95.89%, Inception V3: 96.45%, ResNet: 98.63%, and VGG: 96.80%). A high AUROC score was noted in both ResNet and VGG (0.999). Conclusions: Machine learning techniques can be combined with fundus photography as an effective approach to distinguish between PPE and elevated optic disc associated with optic neuropathies.

scholarly journals Physician-Friendly Machine Learning: A Case Study with Cardiovascular Disease Risk Prediction

2019 ◽  
Vol 8 (7) ◽  
pp. 1050 ◽  
Author(s):  
Meghana Padmanabhan ◽  
Pengyu Yuan ◽  
Govind Chada ◽  
Hien Van Nguyen
Keyword(s):  
Machine Learning ◽  
Graduate Student ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Machine Learning Techniques ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Learning Techniques ◽  
Standard Code ◽  
Time Required

Machine learning is often perceived as a sophisticated technology accessible only by highly trained experts. This prevents many physicians and biologists from using this tool in their research. The goal of this paper is to eliminate this out-dated perception. We argue that the recent development of auto machine learning techniques enables biomedical researchers to quickly build competitive machine learning classifiers without requiring in-depth knowledge about the underlying algorithms. We study the case of predicting the risk of cardiovascular diseases. To support our claim, we compare auto machine learning techniques against a graduate student using several important metrics, including the total amounts of time required for building machine learning models and the final classification accuracies on unseen test datasets. In particular, the graduate student manually builds multiple machine learning classifiers and tunes their parameters for one month using scikit-learn library, which is a popular machine learning library to obtain ones that perform best on two given, publicly available datasets. We run an auto machine learning library called auto-sklearn on the same datasets. Our experiments find that automatic machine learning takes 1 h to produce classifiers that perform better than the ones built by the graduate student in one month. More importantly, building this classifier only requires a few lines of standard code. Our findings are expected to change the way physicians see machine learning and encourage wide adoption of Artificial Intelligence (AI) techniques in clinical domains.

Clinical and Etiological Profile of Patients with Optic Disc Edema in Tertiary Care Centre of Nepal

2019 ◽  
Vol 41 (1) ◽  
pp. 24-30
Author(s):  
Ritish K Shah
Keyword(s):  
Visual Acuity ◽  
Visual Field ◽  
Optic Neuritis ◽  
Color Vision ◽  
Optic Disc ◽  
Optic Neuropathy ◽  
Tertiary Care ◽  
Ischemic Optic Neuropathy ◽  
Optic Disc Edema ◽  
Disc Edema

Introduction: Optic disc edema can be a manifestation of various neurological disorders. Identification of those causes is possible in most cases using tests like visual acuity, color vision, visual field and suitable radiological imaging. Study in Nepalese population with regard to optic disc edema is scarce. Hence this study aims to act as a guideline for evaluation of such cases and help in further studies in this regard. Methods: A descriptive, cross-sectional study was conducted in all cases of optic disc edema presenting to neuro-ophthalmology clinic of B.P. Koirala Lions Centre for Ophthalmic Studies from January 2011 to June 2012. A detailed history was obtained and proper ocular and nervous examination was done by ophthalmologist and neuro-physician. Assessment of visual acuity, color vision, contrast sensitivity and visual field along with radiological tests were done in all possible cases. Results: Out of all the cases evaluated, 38 cases where causes of optic disc edema could be established were included in the study. The commonly affected age group was 31 to 40 years (26.3%) and most of them were males. The commonest cause observed was optic neuritis (36.8%). Others were papilledema, idiopathic intracranial hypertension, toxic optic neuropathy, non-arteritic anterior ischemic optic neuropathy (NA-AION), compressive and traumatic optic neuropathy. Conclusion: Optic neuritis and papilledema should be considered as common differential diagnosis in patients with optic disc edema. NA-AION is a relatively uncommon disease among Nepalese population.

scholarly journals Towards Predicting Student’s Dropout in University Courses Using Different Machine Learning Techniques

2021 ◽  
Vol 11 (7) ◽  
pp. 3130
Author(s):  
Janka Kabathova ◽  
Martin Drlik
Keyword(s):  
Machine Learning ◽  
Performance Metrics ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Unseen Data ◽  
E Learning ◽  
The Impact

Early and precisely predicting the students’ dropout based on available educational data belongs to the widespread research topic of the learning analytics research field. Despite the amount of already realized research, the progress is not significant and persists on all educational data levels. Even though various features have already been researched, there is still an open question, which features can be considered appropriate for different machine learning classifiers applied to the typical scarce set of educational data at the e-learning course level. Therefore, the main goal of the research is to emphasize the importance of the data understanding, data gathering phase, stress the limitations of the available datasets of educational data, compare the performance of several machine learning classifiers, and show that also a limited set of features, which are available for teachers in the e-learning course, can predict student’s dropout with sufficient accuracy if the performance metrics are thoroughly considered. The data collected from four academic years were analyzed. The features selected in this study proved to be applicable in predicting course completers and non-completers. The prediction accuracy varied between 77 and 93% on unseen data from the next academic year. In addition to the frequently used performance metrics, the comparison of machine learning classifiers homogeneity was analyzed to overcome the impact of the limited size of the dataset on obtained high values of performance metrics. The results showed that several machine learning algorithms could be successfully applied to a scarce dataset of educational data. Simultaneously, classification performance metrics should be thoroughly considered before deciding to deploy the best performance classification model to predict potential dropout cases and design beneficial intervention mechanisms.

scholarly journals Nonarteritic Anterior Ischemic Optic Neuropathy following COVID-19 Vaccination: Consequence or Coincidence

2021 ◽  
Vol 2021 ◽  
pp. 1-4
Author(s):  
Rika Tsukii ◽  
Yuka Kasuya ◽  
Shinji Makino
Keyword(s):  
Visual Acuity ◽  
Visual Field ◽  
Optic Disc ◽  
Optic Neuropathy ◽  
Visual Field Defect ◽  
Anterior Ischemic Optic Neuropathy ◽  
Ischemic Optic Neuropathy ◽  
Optic Disc Swelling ◽  
The Right ◽  
Field Defect

To report a patient with nonarteritic anterior ischemic optic neuropathy (NA-AION) occurring soon after the COVID-19 vaccination. A 55-year-old woman presented with a 4-day history of inferior visual field disturbance in the right eye 7 days after receiving the first dose of Pfizer-BioNTech COVID-19 vaccine. Examination revealed a best-corrected visual acuity of 20/20 in both eyes. A relative afferent pupillary defect was observed in the right eye. Fundoscopy revealed diffuse optic disc swelling in the right eye, which was prominent above the optic disc. Goldmann visual field testing identified an inferior altitudinal visual field defect with I/2 isopter in the right eye. Although typical complete inferior visual field defect was not detected, a diagnosis of NA-AION was made. The patient was followed without any treatment. During the 2-month follow-up period, the optic disc swelling was gradually improved, and visual acuity was maintained 20/20; however, the optic disc looked diffusely pale in the right eye. Although it is uncertain whether the development of NA-AION after COVID-19 vaccination was consequential or coincidental, we speculate that the close temporal relationship with COVID-19 vaccination suggests the possibility of vasculopathy on the microvascular network of optic nerve head as background of inflammatory or immune-mediated element to the timing of the onset of NA-AION. The aim of this case report is to present this biological plausibility and to elucidate potential ophthalmological complications.

scholarly journals Anterior ischemic optic neuropathy after transvenous coiling of dural arteriovenous fistulas: A case report

2019 ◽  
Author(s):  
Kazuyuki Majima ◽  
Kyoko Fujita ◽  
Shigeru Miyachi ◽  
Motohiro Kamei
Keyword(s):  
Visual Acuity ◽  
Optic Disc ◽  
Optic Neuropathy ◽  
Coil Embolization ◽  
Anterior Ischemic Optic Neuropathy ◽  
Ischemic Optic Neuropathy ◽  
Intraoperative Complication ◽  
Chorioretinal Atrophy ◽  
Nasal Defect ◽  
The Right

Abstract Background A dural arteriovenous fistula (dAVF) is defined as an abnormal arteriovenous direct connection in the dura mater, with the cavernous sinus (CS) being one of the most common locations. Transarterial or transvenous embolization remains the first-line treatment for most dAVF, although these procedures are associated with rare sight-threatening ophthalmic complications. We report a case of nonarteritic anterior ischemic optic neuropathy (nAION) following successful treatment of dAVF with a coil embolization. Case presentation A 76-year-old woman complained of conjunctival hyperemia in both eyes 1 month prior to visiting our hospital. She was diagnosed with bilateral dAVF based on magnetic resonance angiography (MRA). On ophthalmic examination, her best-corrected visual acuity (BCVA) was 0.8 in the right eye and 0.7 in the left. Intraocular pressure was 27 mmHg in the right and 24 mmHg in the left. Extraocular movements were limited in all directions. Slit lamp examination disclosed red eyes with dilated corkscrew vessels. Funduscopic examination revealed normal findings in both eyes except a partial chorioretinal atrophy in the left eye. Goldmann perimetry revealed an inferior nasal defect corresponding to the chorioretinal atrophy in the left eye and normal visual field in the right eye. Transvenous coil embolization of the right CS was performed. The dAVF was completely embolized and there was no intraoperative complication. Follow-up brain MRA showed no evidence of residual dural fistula. Ten days after embolization, she developed double vision and visual disturbance in the right eye. Her right BCVA was 0.8. Fundus examination revealed pallor papilledema and splinter hemorrhages at the optic disc edge in her right eye. Fluorescein angiography showed hypofluorescence around the optic disc and a nasal lesion in the early phase. Goldman perimetry revealed lower altitudinal hemianopsia in the right eye. From these findings, nAION was diagnosed. During hospitalization, her right BCVA decreased to 0.08. Ten months later, funduscopy revealed right temporal optic disc pallor without edema, and her right visual acuity remained at 0.08. Conclusions We report a case of nAION after embolization of dAVF located in CS. This complication should be considered after embolization for dAVF.

scholarly journals Machine Learning Classifiers for Twitter Surveillance of Vaping: Comparative Machine Learning Study

10.2196/17478 ◽  
2020 ◽  
Vol 22 (8) ◽  
pp. e17478 ◽  
Author(s):  
Shyam Visweswaran ◽  
Jason B Colditz ◽  
Patrick O’Halloran ◽  
Na-Rae Han ◽  
Sanya B Taneja ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Surveillance System ◽  
Short Term Memory ◽  
Characteristic Curve ◽  
Superior Performance ◽  
Support Vector ◽  
Data Set ◽  
Machine Learning Classifiers ◽  
Learning Classifiers

Background Twitter presents a valuable and relevant social media platform to study the prevalence of information and sentiment on vaping that may be useful for public health surveillance. Machine learning classifiers that identify vaping-relevant tweets and characterize sentiments in them can underpin a Twitter-based vaping surveillance system. Compared with traditional machine learning classifiers that are reliant on annotations that are expensive to obtain, deep learning classifiers offer the advantage of requiring fewer annotated tweets by leveraging the large numbers of readily available unannotated tweets. Objective This study aims to derive and evaluate traditional and deep learning classifiers that can identify tweets relevant to vaping, tweets of a commercial nature, and tweets with provape sentiments. Methods We continuously collected tweets that matched vaping-related keywords over 2 months from August 2018 to October 2018. From this data set of tweets, a set of 4000 tweets was selected, and each tweet was manually annotated for relevance (vape relevant or not), commercial nature (commercial or not), and sentiment (provape or not). Using the annotated data, we derived traditional classifiers that included logistic regression, random forest, linear support vector machine, and multinomial naive Bayes. In addition, using the annotated data set and a larger unannotated data set of tweets, we derived deep learning classifiers that included a convolutional neural network (CNN), long short-term memory (LSTM) network, LSTM-CNN network, and bidirectional LSTM (BiLSTM) network. The unannotated tweet data were used to derive word vectors that deep learning classifiers can leverage to improve performance. Results LSTM-CNN performed the best with the highest area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI 0.93-0.98) for relevance, all deep learning classifiers including LSTM-CNN performed better than the traditional classifiers with an AUC of 0.99 (95% CI 0.98-0.99) for distinguishing commercial from noncommercial tweets, and BiLSTM performed the best with an AUC of 0.83 (95% CI 0.78-0.89) for provape sentiment. Overall, LSTM-CNN performed the best across all 3 classification tasks. Conclusions We derived and evaluated traditional machine learning and deep learning classifiers to identify vaping-related relevant, commercial, and provape tweets. Overall, deep learning classifiers such as LSTM-CNN had superior performance and had the added advantage of requiring no preprocessing. The performance of these classifiers supports the development of a vaping surveillance system.

scholarly journals Classification of the glioma grading using radiomics analysis

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5982 ◽  
Author(s):  
Hwan-ho Cho ◽  
Seung-hak Lee ◽  
Jonghoon Kim ◽  
Hyunjin Park
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Characteristic Curve ◽  
Support Vector ◽  
Tumor Segmentation ◽  
Low Grade ◽  
Training Cohort ◽  
Machine Learning Classifiers ◽  
Glioma Grading ◽  
Learning Classifiers

Background Grading of gliomas is critical information related to prognosis and survival. We aimed to apply a radiomics approach using various machine learning classifiers to determine the glioma grading. Methods We considered 285 (high grade n = 210, low grade n = 75) cases obtained from the Brain Tumor Segmentation 2017 Challenge. Manual annotations of enhancing tumors, non-enhancing tumors, necrosis, and edema were provided by the database. Each case was multi-modal with T1-weighted, T1-contrast enhanced, T2-weighted, and FLAIR images. A five-fold cross validation was adopted to separate the training and test data. A total of 468 radiomics features were calculated for three types of regions of interest. The minimum redundancy maximum relevance algorithm was used to select features useful for classifying glioma grades in the training cohort. The selected features were used to build three classifier models of logistics, support vector machines, and random forest classifiers. The classification performance of the models was measured in the training cohort using accuracy, sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic curve. The trained classifier models were applied to the test cohort. Results Five significant features were selected for the machine learning classifiers and the three classifiers showed an average AUC of 0.9400 for training cohorts and 0.9030 (logistic regression 0.9010, support vector machine 0.8866, and random forest 0.9213) for test cohorts. Discussion Glioma grading could be accurately determined using machine learning and feature selection techniques in conjunction with a radiomics approach. The results of our study might contribute to high-throughput computer aided diagnosis system for gliomas.

scholarly journals Heidelberg Retina Tomograph Measurements of the Optic Disc and Parapapillary Retina for Detecting Glaucoma Analyzed by Machine Learning Classifiers

2004 ◽  
Vol 45 (9) ◽  
pp. 3144 ◽  
Author(s):  
Linda M. Zangwill ◽  
Kwokleung Chan ◽  
Christopher Bowd ◽  
Jicuang Hao ◽  
Te-Won Lee ◽  
...  
Keyword(s):  
Machine Learning ◽  
Optic Disc ◽  
Heidelberg Retina Tomograph ◽  
Machine Learning Classifiers ◽  
Learning Classifiers

scholarly journals Comparative Analysis of Intrusion Detection Attack Based on Machine Learning Classifiers

2021 ◽  
Vol 1 (2) ◽  
pp. 22-28
Author(s):  
Surafel Mehari Atnafu ◽  
Anuja Kumar Acharya
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Nearest Neighbor ◽  
Detection System ◽  
Machine Learning Techniques ◽  
K Nearest Neighbor ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Learning Techniques

In current day information transmitted from one place to another by using network communication technology. Due to such transmission of information, networking system required a high security environment. The main strategy to secure this environment is to correctly identify the packet and detect if the packet contains a malicious and any illegal activity happened in network environments. To accomplish this, we use intrusion detection system (IDS). Intrusion detection is a security technology that design detects and automatically alert or notify to a responsible person. However, creating an efficient Intrusion Detection System face a number of challenges. These challenges are false detection and the data contain high number of features. Currently many researchers use machine learning techniques to overcome the limitation of intrusion detection and increase the efficiency of intrusion detection for correctly identify the packet either the packet is normal or malicious. Many machine-learning techniques use in intrusion detection. However, the question is which machine learning classifiers has been potentially to address intrusion detection issue in network security environment. Choosing the appropriate machine learning techniques required to improve the accuracy of intrusion detection system. In this work, three machine learning classifiers are analyzed. Support vector Machine, Naïve Bayes Classifier and K-Nearest Neighbor classifiers. These algorithms tested using NSL KDD dataset by using the combination of Chi square and Extra Tree feature selection method and Python used to implement, analyze and evaluate the classifiers. Experimental result show that K-Nearest Neighbor classifiers outperform the method in categorizing the packet either is normal or malicious.

Sign in / Sign up

Export Citation Format

Share Document