scholarly journals Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images

2020 ◽  
Author(s):  
Parmita Mehta ◽  
Christine Petersen ◽  
Joanne C. Wen ◽  
Michael R. Banitt ◽  
Philip P. Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Model Performance ◽  
Image Data ◽  
Large Data ◽  
Population Level ◽  
High Rate ◽  
Data Set ◽  
Glaucoma Diagnosis ◽  
Model Interpretation ◽  
Glaucoma Detection

AbstractGlaucoma, the leading cause of irreversible blindness worldwide, is a disease that damages the optic nerve. Current machine learning (ML) approaches for glaucoma detection rely on features such as retinal thickness maps; however, the high rate of segmentation errors when creating these maps increase the likelihood of faulty diagnoses. This paper proposes a new, comprehensive, and more accurate ML-based approach for population-level glaucoma screening. Our contributions include: (1) a multi-modal model built upon a large data set that includes demographic, systemic and ocular data as well as raw image data taken from color fundus photos (CFPs) and macular Optical Coherence Tomography (OCT) scans, (2) model interpretation to identify and explain data features that lead to accurate model performance, and (3) model validation via comparison of model output with clinician interpretation of CFPs. We also validated the model on a cohort that was not diagnosed with glaucoma at the time of imaging but eventually received a glaucoma diagnosis. Results show that our model is highly accurate (AUC 0.97) and interpretable. It validated biological features known to be related to the disease, such as age, intraocular pressure and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary capacity and retinal outer layers.

A Hybrid Machine Learning Model Based on Global and Local Learner Algorithms for Diabetes Mellitus Prediction

2022 ◽  
Vol 54 ◽  
pp. 65-88
Author(s):  
Derara Duba Rufo ◽  
Taye Girma Debelee ◽  
Worku Gachena Negera
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Model Performance ◽  
High Rate ◽  
Data Sets ◽  
Global Learning ◽  
Data Set ◽  
Ensemble Technique ◽  
Model Based ◽  
Global And Local

Health is a critical condition for living things, even before the technology exists. Nowadays the healthcare domain provides a lot of scope for research as it has extremely evolved. The most researched areas of health sectors include diabetes mellitus (DM), breast cancer, brain tumor, etc. DM is a severe chronic disease that affects human health and has a high rate throughout the world. Early prediction of DM is important to reduce its risk and even avoid it. In this study, we propose a DM prediction model based on global and local learner algorithms. The proposed global and local learners stacking (GLLS) model; combines the prediction algorithms from two largely different but complementary machine learning paradigms, specifically XGBoost and NB from global learning whereas kNN and SVM (with RBF kernel) from local learning and aggregates them by stacking ensemble technique using LR as meta-learner. The effectiveness of the GLLS model was proved by comparing several performance measures and the results of different contrast experiments. The evaluation results on UCI Pima Indian diabetes data-set (PIDD) indicates the model has achieved the better prediction performance of 99.5%, 99.5%, 99.5%, 99.1%, and 100% in terms of accuracy, AUC, F1 score, sensitivity, and specificity respectively, compared to other research results mentioned in the literature. Moreover, to better validate the GLLS model performance, three additional medical data sets; Messidor, WBC, ILPD, are considered and the model also achieved an accuracy of 82.1%, 98.6%, and 89.3% respectively. Experimental results proved the effectiveness and superiority of our proposed GLLS model.

In silico Prediction of Inhibitory Constant of Thrombin Inhibitors Using Machine Learning

2019 ◽  
Vol 21 (9) ◽  
pp. 662-669 ◽  
Author(s):  
Junnan Zhao ◽  
Lu Zhu ◽  
Weineng Zhou ◽  
Lingfeng Yin ◽  
Yuchen Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Regression Tree ◽  
Large Data ◽  
Thrombin Inhibitors ◽  
Coagulation Cascade ◽  
Gradient Boosting ◽  
Support Vector ◽  
Data Set ◽  
Descriptor Selection

Background: Thrombin is the central protease of the vertebrate blood coagulation cascade, which is closely related to cardiovascular diseases. The inhibitory constant Ki is the most significant property of thrombin inhibitors. Method: This study was carried out to predict Ki values of thrombin inhibitors based on a large data set by using machine learning methods. Taking advantage of finding non-intuitive regularities on high-dimensional datasets, machine learning can be used to build effective predictive models. A total of 6554 descriptors for each compound were collected and an efficient descriptor selection method was chosen to find the appropriate descriptors. Four different methods including multiple linear regression (MLR), K Nearest Neighbors (KNN), Gradient Boosting Regression Tree (GBRT) and Support Vector Machine (SVM) were implemented to build prediction models with these selected descriptors. Results: The SVM model was the best one among these methods with R2=0.84, MSE=0.55 for the training set and R2=0.83, MSE=0.56 for the test set. Several validation methods such as yrandomization test and applicability domain evaluation, were adopted to assess the robustness and generalization ability of the model. The final model shows excellent stability and predictive ability and can be employed for rapid estimation of the inhibitory constant, which is full of help for designing novel thrombin inhibitors.

scholarly journals Generation of geometric interpolations of building types with deep variational autoencoders

2020 ◽  
Vol 6 ◽  
Author(s):  
Jaime de Miguel Rodríguez ◽  
Maria Eugenia Villafañe ◽  
Luka Piškorec ◽  
Fernando Sancho Caparrini
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Large Data ◽  
Learning Model ◽  
Large Data Sets ◽  
Data Sets ◽  
Connectivity Map ◽  
Data Set ◽  
3D Objects ◽  
Machine Learning Model

Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.

Forecasting the risk at infractions: an ensemble comparison of machine learning approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Lei Li ◽  
Desheng Wu
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Short Term Memory ◽  
Model Performance ◽  
Large Data ◽  
Support Vector ◽  
Learning Approaches ◽  
Content Type ◽  
Day To Day Operations ◽  
Prediction Approach

PurposeThe infraction of securities regulations (ISRs) of listed firms in their day-to-day operations and management has become one of common problems. This paper proposed several machine learning approaches to forecast the risk at infractions of listed corporates to solve financial problems that are not effective and precise in supervision.Design/methodology/approachThe overall proposed research framework designed for forecasting the infractions (ISRs) include data collection and cleaning, feature engineering, data split, prediction approach application and model performance evaluation. We select Logistic Regression, Naïve Bayes, Random Forest, Support Vector Machines, Artificial Neural Network and Long Short-Term Memory Networks (LSTMs) as ISRs prediction models.FindingsThe research results show that prediction performance of proposed models with the prior infractions provides a significant improvement of the ISRs than those without prior, especially for large sample set. The results also indicate when judging whether a company has infractions, we should pay attention to novel artificial intelligence methods, previous infractions of the company, and large data sets.Originality/valueThe findings could be utilized to address the problems of identifying listed corporates' ISRs at hand to a certain degree. Overall, results elucidate the value of the prior infraction of securities regulations (ISRs). This shows the importance of including more data sources when constructing distress models and not only focus on building increasingly more complex models on the same data. This is also beneficial to the regulatory authorities.

scholarly journals Artificial intelligence method to classify ophthalmic emergency severity based on symptoms: a validation study

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e037161
Author(s):  
Hyunmin Ahn
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Model Performance ◽  
Armed Forces ◽  
Validation Data ◽  
Data Set ◽  
Orange Yellow ◽  
Hospital Visits ◽  
Input Variables ◽  
Fully Connected

ObjectivesWe investigated the usefulness of machine learning artificial intelligence (AI) in classifying the severity of ophthalmic emergency for timely hospital visits.Study designThis retrospective study analysed the patients who first visited the Armed Forces Daegu Hospital between May and December 2019. General patient information, events and symptoms were input variables. Events, symptoms, diagnoses and treatments were output variables. The output variables were classified into four classes (red, orange, yellow and green, indicating immediate to no emergency cases). About 200 cases of the class-balanced validation data set were randomly selected before all training procedures. An ensemble AI model using combinations of fully connected neural networks with the synthetic minority oversampling technique algorithm was adopted.ParticipantsA total of 1681 patients were included.Major outcomesModel performance was evaluated using accuracy, precision, recall and F1 scores.ResultsThe accuracy of the model was 99.05%. The precision of each class (red, orange, yellow and green) was 100%, 98.10%, 92.73% and 100%. The recalls of each class were 100%, 100%, 98.08% and 95.33%. The F1 scores of each class were 100%, 99.04%, 95.33% and 96.00%.ConclusionsWe provided support for an AI method to classify ophthalmic emergency severity based on symptoms.

scholarly journals Precision-Recall versus Accuracy and the Role of Large Data Sets

2019 ◽  
Vol 33 ◽  
pp. 4039-4048 ◽  
Author(s):  
Brendan Juba ◽  
Hai S. Le
Keyword(s):  
Machine Learning ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Large Data ◽  
Constant Factor ◽  
Data Sets ◽  
Data Set ◽  
Small Constant ◽  
Classifier Performance ◽  
Necessary And Sufficient

Practitioners of data mining and machine learning have long observed that the imbalance of classes in a data set negatively impacts the quality of classifiers trained on that data. Numerous techniques for coping with such imbalances have been proposed, but nearly all lack any theoretical grounding. By contrast, the standard theoretical analysis of machine learning admits no dependence on the imbalance of classes at all. The basic theorems of statistical learning establish the number of examples needed to estimate the accuracy of a classifier as a function of its complexity (VC-dimension) and the confidence desired; the class imbalance does not enter these formulas anywhere. In this work, we consider the measures of classifier performance in terms of precision and recall, a measure that is widely suggested as more appropriate to the classification of imbalanced data. We observe that whenever the precision is moderately large, the worse of the precision and recall is within a small constant factor of the accuracy weighted by the class imbalance. A corollary of this observation is that a larger number of examples is necessary and sufficient to address class imbalance, a finding we also illustrate empirically.

HOMPer: A new hybrid system for opinion mining in the Persian language

2019 ◽  
Vol 46 (1) ◽  
pp. 101-117 ◽  
Author(s):  
Mohammad Ehsan Basiri ◽  
Arman Kabiri
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Opinion Mining ◽  
Feature Selection Method ◽  
Large Data ◽  
Data Set ◽  
Persian Language ◽  
Rating Prediction ◽  
Bayes Algorithm ◽  
Component Feature

Opinion mining is a subfield of data mining and natural language processing that concerns with extracting users’ opinion and attitude towards products or services from their comments on the Web. Persian opinion mining, in contrast to its counterpart in English, is a totally new field of study and hence, it has not received the attention it deserves. Existing methods for opinion mining in the Persian language may be classified into machine learning– and lexicon-based approaches. These methods have been proposed and successfully used for polarity-detection problem. However, when they should be used for more complex tasks like rating prediction, their results are not desirable. In this study, first an exhaustive investigation of machine learning– and lexicon-based methods is performed. Then, a new hybrid method is proposed for rating-prediction problem in the Persian language. Finally, the effect of machine learning component, feature-selection method, normalisation method and combination level are investigated. The experimental results on a large data set containing 16,000 Persian customers’ review show that this proposed system achieves higher performance in comparison to Naïve Bayes algorithm and a pure lexicon-based method. Moreover, results demonstrate that this proposed method may also be successfully used for polarity detection.

scholarly journals Machine Learning for Predicting Mycotoxin Occurrence in Maize

2021 ◽  
Vol 12 ◽  
Author(s):  
Marco Camardo Leggieri ◽  
Marco Mazzoni ◽  
Paola Battilani
Keyword(s):  
Machine Learning ◽  
Mechanistic Model ◽  
Cropping System ◽  
Large Data ◽  
Predictive Performance ◽  
Added Value ◽  
Linear Regression Models ◽  
Data Set ◽  
Input Variables ◽  
Aflatoxin B

Meteorological conditions are the main driving variables for mycotoxin-producing fungi and the resulting contamination in maize grain, but the cropping system used can mitigate this weather impact considerably. Several researchers have investigated cropping operations’ role in mycotoxin contamination, but these findings were inconclusive, precluding their use in predictive modeling. In this study a machine learning (ML) approach was considered, which included weather-based mechanistic model predictions for AFLA-maize and FER-maize [predicting aflatoxin B1 (AFB1) and fumonisins (FBs), respectively], and cropping system factors as the input variables. The occurrence of AFB1 and FBs in maize fields was recorded, and their corresponding cropping system data collected, over the years 2005–2018 in northern Italy. Two deep neural network (DNN) models were trained to predict, at harvest, which maize fields were contaminated beyond the legal limit with AFB1 and FBs. Both models reached an accuracy >75% demonstrating the ML approach added value with respect to classical statistical approaches (i.e., simple or multiple linear regression models). The improved predictive performance compared with that obtained for AFLA-maize and FER-maize was clearly demonstrated. This coupled to the large data set used, comprising a 13-year time series, and the good results for the statistical scores applied, together confirmed the robustness of the models developed here.

scholarly journals Prediction of Misclassification Data using Cognitive Bayes Computation Techniques (COBACO)

2020 ◽  
Vol 9 (3) ◽  
pp. 928-932
Keyword(s):  
Machine Learning ◽  
Missing Data ◽  
Large Data ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Accuracy Rate ◽  
Data Set ◽  
Predictive Values ◽  
Time Operation

Missing data arise major issues in the large database regarding quantitative analysis. Due to this issues, the inference of the computational process produce bias results, more damage of data, the error rate can increase, and more difficult to accomplish the process of imputation. Prediction of disguised missing data occurs in the large data sets are another major problems in real time operation. Machine learning (ML) techniques to connect with the classification of measurement to enforce the accuracy rate of predictive values. These techniques overcome the various challenges to the problem of losing data. Recent work based on the prediction of misclassification using supervised ML approach; to predict an output for an unseen input with limited parameters in a data set. When increase the size of parameter, then it generates the outcome of less accuracy rate. This article presented a new approach COBACO, an effective supervised machine learning technique. Several strategies describe the classification of predictive techniques for missing data analysis in efficient supervised machine learning techniques. The proposed predictive techniques COBACO generated more precise, accurate results than the other predictive approaches. The Experimental results obtained using both real and synthetic data set show that the proposed approach offers a valuable and promising insight to the problem of prediction of missing information.

scholarly journals In Vitro Determination of Concentration-Dependent Optical Properties of Hemoglobin

2018 ◽  
Vol 4 (1) ◽  
pp. 673-676
Author(s):  
Philipp Wegerich ◽  
Gehring Hartmut
Keyword(s):  
Machine Learning ◽  
Optical Properties ◽  
Layer Thickness ◽  
Internal Standard ◽  
High Rate ◽  
Integrating Sphere ◽  
Learning Approaches ◽  
Rate Data ◽  
Data Set

AbstractThe interest of this paper is the determination of the optical properties of oxygenated (saturation above 97 %) hemoglobin in clinical relevant concentrations (ranging from 5 to 15 g/dl), dependent on the layer thickness. Furthermore the generation of a high rate data set for training with machine learning approaches was intended. With a double integrating sphere setup (laser diodes from 780 to 1310 nm) - as a well referenced method - and flow through optical cuvettes ranging from 1 to 3 mm layer thickness, the transmission (𝑀𝑇) and reflection (𝑀𝑅) values of the samples were acquired. From those the layer thickness independent absorption (𝜇𝑎) and reduced scattering coefficients (𝜇𝑠’) were calculated by the means of the Inverse Adding Doubling (IAD) algorithm. For each sample the same coefficients should result correspondingly for all cuvette thicknesses in test. This relationship serves as an internal standard in the evaluation of the collected data sets. In parallel a spectrophotometer in the range from 690 to 1000 nm recorded transmission spectra for all samples as a second reference. First, the IAD algorithm provided optical coefficients (𝜇𝑎, 𝜇𝑠’) in all measurements, with few exceptions at low hemoglobin concentrations. The resulting coefficients match independently of the layer thickness. As a main second result, a high rate data set was generated which serves for further analysis - for example with machine learning approaches.

Sign in / Sign up

Export Citation Format

Share Document