A machine learning-based treatment prediction model using whole genome variants of hepatitis C virus

In recent years, the development of diagnostics using artificial intelligence (AI) has been remarkable. AI algorithms can go beyond human reasoning and build diagnostic models from a number of complex combinations. Using next-generation sequencing technology, we identified hepatitis C virus (HCV) variants resistant to directing-acting antivirals (DAA) by whole genome sequencing of full-length HCV genomes, and applied these variants to various machine-learning algorithms to evaluate a preliminary predictive model. HCV genomic RNA was extracted from serum from 173 patients (109 with subsequent sustained virological response [SVR] and 64 without) before DAA treatment. HCV genomes from the 109 SVR and 64 non-SVR patients were randomly divided into a training data set (57 SVR and 29 non-SVR) and a validation-data set (52 SVR and 35 non-SVR). The training data set was subject to nine machine-learning algorithms selected to identify the optimized combination of functional variants in relation to SVR status following DAA therapy. Subsequently, the prediction model was tested by the validation-data set. The most accurate learning method was the support vector machine (SVM) algorithm (validation accuracy, 0.95; kappa statistic, 0.90; F-value, 0.94). The second-most accurate learning algorithm was Multi-layer perceptron. Unfortunately, Decision Tree, and Naive Bayes algorithms could not be fitted with our data set due to low accuracy (< 0.8). Conclusively, with an accuracy rate of 95.4% in the generalization performance evaluation, SVM was identified as the best algorithm. Analytical methods based on genomic analysis and the construction of a predictive model by machine-learning may be applicable to the selection of the optimal treatment for other viral infections and cancer.

Download Full-text

A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients in China

10.21203/rs.3.rs-152663/v1 ◽

2021 ◽

Author(s):

Dong Wang ◽

JinBo Li ◽

Yali Sun ◽

Xianfei Ding ◽

Xiaojuan Zhang ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Prediction Model ◽

Secondary Analysis ◽

Adverse Outcomes ◽

Training Data ◽

Medical Systems ◽

Validation Data ◽

Data Set ◽

Icu Patients

Abstract Background: Although numerous studies are conducted every year on how to reduce the fatality rate associated with sepsis, it is still a major challenge faced by patients, clinicians, and medical systems worldwide. Early identification and prediction of patients at risk of sepsis and adverse outcomes associated with sepsis are critical. We aimed to develop an artificial intelligence algorithm that can predict sepsis early.Methods: This was a secondary analysis of an observational cohort study from the Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University. A total of 4449 infected patients were randomly assigned to the development and validation data set at a ratio of 4:1. After extracting electronic medical record data, a set of 55 features (variables) was calculated and passed to the random forest algorithm to predict the onset of sepsis.Results: The pre-procedure clinical variables were used to build a prediction model from the training data set using the random forest machine learning method; a 5-fold cross-validation was used to evaluate the prediction accuracy of the model. Finally, we tested the model using the validation data set. The area obtained by the model under the receiver operating characteristic (ROC) curve (AUC) was 0.91, the sensitivity was 87%, and the specificity was 89%.Conclusions: The newly established model can accurately predict the onset of sepsis in ICU patients in clinical settings as early as possible. Prospective studies are necessary to determine the clinical utility of the proposed sepsis prediction model.

Download Full-text

A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction

Briefings in Bioinformatics ◽

10.1093/bib/bbz051 ◽

2020 ◽

Vol 21 (4) ◽

pp. 1119-1135 ◽

Cited By ~ 27

Author(s):

Shutao Mei ◽

Fuyi Li ◽

André Leier ◽

Tatiana T Marquez-Lago ◽

Kailin Giam ◽

...

Keyword(s):

Machine Learning ◽

T Cell ◽

Peptide Binding ◽

Hla Class I ◽

Machine Learning Algorithms ◽

Class I ◽

Target Cells ◽

Binding Prediction ◽

Validation Data ◽

Data Set

Abstract Human leukocyte antigen class I (HLA-I) molecules are encoded by major histocompatibility complex (MHC) class I loci in humans. The binding and interaction between HLA-I molecules and intracellular peptides derived from a variety of proteolytic mechanisms play a crucial role in subsequent T-cell recognition of target cells and the specificity of the immune response. In this context, tools that predict the likelihood for a peptide to bind to specific HLA class I allotypes are important for selecting the most promising antigenic targets for immunotherapy. In this article, we comprehensively review a variety of currently available tools for predicting the binding of peptides to a selection of HLA-I allomorphs. Specifically, we compare their calculation methods for the prediction score, employed algorithms, evaluation strategies and software functionalities. In addition, we have evaluated the prediction performance of the reviewed tools based on an independent validation data set, containing 21 101 experimentally verified ligands across 19 HLA-I allotypes. The benchmarking results show that MixMHCpred 2.0.1 achieves the best performance for predicting peptides binding to most of the HLA-I allomorphs studied, while NetMHCpan 4.0 and NetMHCcons 1.1 outperform the other machine learning-based and consensus-based tools, respectively. Importantly, it should be noted that a peptide predicted with a higher binding score for a specific HLA allotype does not necessarily imply it will be immunogenic. That said, peptide-binding predictors are still very useful in that they can help to significantly reduce the large number of epitope candidates that need to be experimentally verified. Several other factors, including susceptibility to proteasome cleavage, peptide transport into the endoplasmic reticulum and T-cell receptor repertoire, also contribute to the immunogenicity of peptide antigens, and some of them can be considered by some predictors. Therefore, integrating features derived from these additional factors together with HLA-binding properties by using machine-learning algorithms may increase the prediction accuracy of immunogenic peptides. As such, we anticipate that this review and benchmarking survey will assist researchers in selecting appropriate prediction tools that best suit their purposes and provide useful guidelines for the development of improved antigen predictors in the future.

Download Full-text

Sedimentary environment prediction of grain-size data based on machine learning approach

Interpretation ◽

10.1190/int-2019-0153.1 ◽

2020 ◽

Vol 8 (3) ◽

pp. SL71-SL78

Author(s):

Qiao Su ◽

Yanhui Zhu ◽

Fang Hu ◽

Xingyong Xu

Keyword(s):

Machine Learning ◽

Grain Size ◽

Prediction Model ◽

Sedimentary Environment ◽

Machine Learning Algorithms ◽

Grain Size Analysis ◽

Size Analysis ◽

Data Set ◽

Sedimentary Environments ◽

Size Data

Grain size is one of the most important records for sedimentary environment, and researchers have made remarkable progress in the interpretation of sedimentary environments by grain size analysis in the past few decades. However, these advances often depend on the personal experience of the scholars and combination with other methods used together. Here, we constructed a prediction model using the K-nearest neighbors algorithm, one of the machine learning methods, which can predict the sedimentary environments of one core through a known core. Compared to the results of other studies based on the comprehensive data set of grain size and four other indicators, this model achieved a high precision value only using the grain size data. We have also compared our prediction model with other mainstream machine learning algorithms, and the experimental results of six evaluation metrics shed light on that this prediction model can achieve the higher precision. The main errors of the model reflect the length of the conversation area of sedimentary environment, which is controlled by the sedimentary dynamics. This model can provide a quick comparison method of the cores in a similar environment; thus, it may point out the preliminary guidance for further study.

Download Full-text

Can Short and Partial Observations Reduce Model Error and Facilitate Machine Learning Prediction?

Entropy ◽

10.3390/e22101075 ◽

2020 ◽

Vol 22 (10) ◽

pp. 1075

Author(s):

Nan Chen

Keyword(s):

Machine Learning ◽

Model Error ◽

Machine Learning Algorithms ◽

Training Data ◽

Conditional Sampling ◽

Data Set ◽

Partial Observations ◽

Sampling Algorithm ◽

Highly Nonlinear ◽

Non Gaussian

Predicting complex nonlinear turbulent dynamical systems is an important and practical topic. However, due to the lack of a complete understanding of nature, the ubiquitous model error may greatly affect the prediction performance. Machine learning algorithms can overcome the model error, but they are often impeded by inadequate and partial observations in predicting nature. In this article, an efficient and dynamically consistent conditional sampling algorithm is developed, which incorporates the conditional path-wise temporal dependence into a two-step forward-backward data assimilation procedure to sample multiple distinct nonlinear time series conditioned on short and partial observations using an imperfect model. The resulting sampled trajectories succeed in reducing the model error and greatly enrich the training data set for machine learning forecasts. For a rich class of nonlinear and non-Gaussian systems, the conditional sampling is carried out by solving a simple stochastic differential equation, which is computationally efficient and accurate. The sampling algorithm is applied to create massive training data of multiscale compressible shallow water flows from highly nonlinear and indirect observations. The resulting machine learning prediction significantly outweighs the imperfect model forecast. The sampling algorithm also facilitates the machine learning forecast of a highly non-Gaussian climate phenomenon using extremely short observations.

Download Full-text

Identification of Leukemia Subtypes from Microscopic Images Using Convolutional Neural Network

Diagnostics ◽

10.3390/diagnostics9030104 ◽

2019 ◽

Vol 9 (3) ◽

pp. 104 ◽

Cited By ~ 11

Author(s):

Ahmed ◽

Yigit ◽

Isik ◽

Alpkocak

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Nearest Neighbor ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Training Data ◽

Support Vector ◽

K Nearest Neighbor ◽

Data Set ◽

Leukemia Data

Leukemia is a fatal cancer and has two main types: Acute and chronic. Each type has two more subtypes: Lymphoid and myeloid. Hence, in total, there are four subtypes of leukemia. This study proposes a new approach for diagnosis of all subtypes of leukemia from microscopic blood cell images using convolutional neural networks (CNN), which requires a large training data set. Therefore, we also investigated the effects of data augmentation for an increasing number of training samples synthetically. We used two publicly available leukemia data sources: ALL-IDB and ASH Image Bank. Next, we applied seven different image transformation techniques as data augmentation. We designed a CNN architecture capable of recognizing all subtypes of leukemia. Besides, we also explored other well-known machine learning algorithms such as naive Bayes, support vector machine, k-nearest neighbor, and decision tree. To evaluate our approach, we set up a set of experiments and used 5-fold cross-validation. The results we obtained from experiments showed that our CNN model performance has 88.25% and 81.74% accuracy, in leukemia versus healthy and multiclass classification of all subtypes, respectively. Finally, we also showed that the CNN model has a better performance than other wellknown machine learning algorithms.

Download Full-text

Predicting Loan Approval of Bank Direct Marketing Data Using Ensemble Machine Learning Algorithms

International Journal of Circuits, Systems and Signal Processing ◽

10.46300/9106.2020.14.117 ◽

2020 ◽

Vol 14 ◽

Keyword(s):

Machine Learning ◽

Prediction Model ◽

Prediction Models ◽

Machine Learning Algorithms ◽

Decision Makers ◽

Machine Learning Techniques ◽

Data Set ◽

Ensemble Machine Learning ◽

Marketing Data ◽

Loan Approval

The Bank Marketing data set at Kaggle is mostly used in predicting if bank clients will subscribe a long-term deposit. We believe that this data set could provide more useful information such as predicting whether a bank client could be approved for a loan. This is a critical choice that has to be made by decision makers at the bank. Building a prediction model for such high-stakes decision does not only require high model prediction accuracy, but also needs a reasonable prediction interpretation. In this research, different ensemble machine learning techniques have been deployed such as Bagging and Boosting. Our research results showed that the loan approval prediction model has an accuracy of 83.97%, which is approximately 25% better than most state-of-the-art other loan prediction models found in the literature. As well, the model interpretation efforts done in this research was able to explain a few critical cases that the bank decision makers may encounter; therefore, the high accuracy of the designed models was accompanied with a trust in prediction. We believe that the achieved model accuracy accompanied with the provided interpretation information are vitally needed for decision makers to understand how to maintain balance between security and reliability of their financial lending system, while providing fair credit opportunities to their clients.

Download Full-text

Rotor Unbalance Kind and Severity Identification by Current Signature Analysis with Adaptative Update to Multiclass Machine Learning Algorithms

Studies in Engineering and Technology ◽

10.11114/set.v8i1.5213 ◽

2021 ◽

Vol 8 (1) ◽

pp. 28

Author(s):

S. L. Ávila ◽

H. M. Schaberle ◽

S. Youssef ◽

F. S. Pacheco ◽

C. A. Penz

Keyword(s):

Machine Learning ◽

Machine Learning Algorithms ◽

Training Data ◽

Machine Learning Techniques ◽

Support Vector ◽

Signature Analysis ◽

Data Set ◽

Learning Techniques ◽

Environmental Variations ◽

Current Signature

The health of a rotating electric machine can be evaluated by monitoring electrical and mechanical parameters. As more information is available, it easier can become the diagnosis of the machine operational condition. We built a laboratory test bench to study rotor unbalance issues according to ISO standards. Using the electric stator current harmonic analysis, this paper presents a comparison study among Support-Vector Machines, Decision Tree classifies, and One-vs-One strategy to identify rotor unbalance kind and severity problem – a nonlinear multiclass task. Moreover, we propose a methodology to update the classifier for dealing better with changes produced by environmental variations and natural machinery usage. The adaptative update means to update the training data set with an amount of recent data, saving the entire original historical data. It is relevant for engineering maintenance. Our results show that the current signature analysis is appropriate to identify the type and severity of the rotor unbalance problem. Moreover, we show that machine learning techniques can be effective for an industrial application.

Download Full-text

Prediction of Cardiac Arrest in the Emergency Department Based on Machine Learning and Sequential Characteristics: Model Development and Retrospective Clinical Validation Study (Preprint)

10.2196/preprints.15932 ◽

2019 ◽

Author(s):

Sungjun Hong ◽

Sungjoo Lee ◽

Jeonghoon Lee ◽

Won Chul Cha ◽

Kyunga Kim

Keyword(s):

Machine Learning ◽

Emergency Department ◽

Cardiac Arrest ◽

Prediction Model ◽

Prediction Models ◽

Characteristic Curve ◽

Machine Learning Algorithms ◽

Clinical Usefulness ◽

Class Imbalance Problem ◽

Data Set

BACKGROUND The development and application of clinical prediction models using machine learning in clinical decision support systems is attracting increasing attention. OBJECTIVE The aims of this study were to develop a prediction model for cardiac arrest in the emergency department (ED) using machine learning and sequential characteristics and to validate its clinical usefulness. METHODS This retrospective study was conducted with ED patients at a tertiary academic hospital who suffered cardiac arrest. To resolve the class imbalance problem, sampling was performed using propensity score matching. The data set was chronologically allocated to a development cohort (years 2013 to 2016) and a validation cohort (year 2017). We trained three machine learning algorithms with repeated 10-fold cross-validation. RESULTS The main performance parameters were the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). The random forest algorithm (AUROC 0.97; AUPRC 0.86) outperformed the recurrent neural network (AUROC 0.95; AUPRC 0.82) and the logistic regression algorithm (AUROC 0.92; AUPRC=0.72). The performance of the model was maintained over time, with the AUROC remaining at least 80% across the monitored time points during the 24 hours before event occurrence. CONCLUSIONS We developed a prediction model of cardiac arrest in the ED using machine learning and sequential characteristics. The model was validated for clinical usefulness by chronological visualization focused on clinical usability.

Download Full-text

A Novel Ensemble Stacking Classification of Genetic Variations Using Machine Learning Algorithms

International Journal of Image and Graphics ◽

10.1142/s0219467823500158 ◽

2021 ◽

Author(s):

Jahnavi Yeturu ◽

Poongothai Elango ◽

S. P. Raja ◽

P. Nagendra Kumar

Keyword(s):

Machine Learning ◽

Heart Diseases ◽

Learning Algorithms ◽

Genetic Mutation ◽

Machine Learning Algorithms ◽

Support Vector ◽

Genetic Mutations ◽

Validation Data ◽

Data Set

Genetics is the clinical review of congenital mutation, where the principal advantage of analyzing genetic mutation of humans is the exploration, analysis, interpretation and description of the genetic transmitted and inherited effect of several diseases such as cancer, diabetes and heart diseases. Cancer is the most troublesome and disordered affliction as the proportion of cancer sufferers is growing massively. Identification and discrimination of the mutations that impart to the enlargement of tumor from the unbiased mutations is difficult, as majority tumors of cancer are able to exercise genetic mutations. The genetic mutations are systematized and categorized to sort the cancer by way of medical observations and considering clinical studies. At the present time, genetic mutations are being annotated and these interpretations are being accomplished either manually or using the existing primary algorithms. Evaluation and classification of each and every individual genetic mutation was basically predicated on evidence from documented content built on medical literature. Consequently, as a means to build genetic mutations, basically, depending on the clinical evidences persists a challenging task. There exist various algorithms such as one hot encoding technique is used to derive features from genes and their variations, TF-IDF is used to extract features from the clinical text data. In order to increase the accuracy of the classification, machine learning algorithms such as support vector machine, logistic regression, Naive Bayes, etc., are experimented. A stacking model classifier has been developed to increase the accuracy. The proposed stacking model classifier has obtained the log loss 0.8436 and 0.8572 for cross-validation data set and test data set, respectively. By the experimentation, it has been proved that the proposed stacking model classifier outperforms the existing algorithms in terms of log loss. Basically, minimum log loss refers to the efficient model. Here the log loss has been reduced to less than 1 by using the proposed stacking model classifier. The performance of these algorithms can be gauged on the basis of the various measures like multi-class log loss.

Download Full-text

Performance of Machine Learning Algorithms and Diversity in Data

MATEC Web of Conferences ◽

10.1051/matecconf/201821004019 ◽

2018 ◽

Vol 210 ◽

pp. 04019 ◽

Cited By ~ 1

Author(s):

Hyontai SUG

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Real World ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Training Data ◽

Real World Data ◽

Random Data ◽

Data Set ◽

World Data

Recent world events in go games between human and artificial intelligence called AlphaGo showed the big advancement in machine learning technologies. While AlphaGo was trained using real world data, AlphaGo Zero was trained using massive random data, and the fact that AlphaGo Zero won AlphaGo completely revealed that diversity and size in training data is important for better performance for the machine learning algorithms, especially in deep learning algorithms of neural networks. On the other hand, artificial neural networks and decision trees are widely accepted machine learning algorithms because of their robustness in errors and comprehensibility respectively. In this paper in order to prove that diversity and size in data are important factors for better performance of machine learning algorithms empirically, the two representative algorithms are used for experiment. A real world data set called breast tissue was chosen, because the data set consists of real numbers that is very good property for artificial random data generation. The result of the experiment proved the fact that the diversity and size of data are very important factors for better performance.

Download Full-text