Data-driven diagnosis of spinal abnormalities using feature selection and machine learning algorithms.
Ontology highlight
ABSTRACT:
SUBMITTER: Raihan-Al-Masud M
PROVIDER: S-EPMC7004343 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:An accurate step length estimation can provide valuable information to different applications such as indoor positioning systems or it can be helpful when analyzing the gait of a user, which can then be used to detect various gait impairments that lead to a reduced step length (caused by e.g., Parkinson's disease or multiple sclerosis). In this paper, we focus on the estimation of the step length using machine learning techniques that could be used in an indoor positioning system. Previous step length algorithms tried to model the length of a step based on measurements from the accelerometer and some tuneable (user-specific) parameters. Machine-learning-based step length estimation algorithms eliminate these parameters to be tuned. Instead, to adapt these algorithms to different users, it suffices to provide examples of the length of multiple steps for different persons to the machine learning algorithm, so that in the training phase the algorithm can learn to predict the step length for different users. Until now, these machine learning algorithms were trained with features that were chosen intuitively. In this paper, we consider a systematic feature selection algorithm to be able to determine the features from a large collection of features, resulting in the best performance. This resulted in a step length estimator with a mean absolute error of 3.48 cm for a known test person and 4.19 cm for an unknown test person, while current state-of-the-art machine-learning-based step length estimators resulted in a mean absolute error of 4.94 cm and 6.27 cm for respectively a known and unknown test person.
| S-EPMC7038475 | biostudies-literature
Project description:IntroductionCardiotocography (CTG) consists of two biophysical signals that are fetal heart rate (FHR) and uterine contraction (UC). In this research area, the computerized systems are usually utilized to provide more objective and repeatable results.Materials and methodsFeature selection algorithms are of great importance regarding the computerized systems to not only reduce the dimension of feature set but also to reveal the most relevant features without losing too much information. In this paper, three filters and two wrappers feature selection methods and machine learning models, which are artificial neural network (ANN), k-nearest neighbor (kNN), decision tree (DT), and support vector machine (SVM), are evaluated on a high dimensional feature set obtained from an open-access CTU-UHB intrapartum CTG database. The signals are divided into two classes as normal and hypoxic considering umbilical artery pH value (pH?<?7.20) measured after delivery. A comprehensive diagnostic feature set forming the features obtained from morphological, linear, nonlinear, time-frequency and image-based time-frequency domains is generated first. Then, combinations of the feature selection algorithms and machine learning models are evaluated to achieve the most effective features as well as high classification performance.ResultsThe experimental results show that it is possible to achieve better classification performance using lower dimensional feature set that comprises of more related features, instead of the high-dimensional feature set. The most informative feature subset was generated by considering the frequency of selection of the features by feature selection algorithms. As a result, the most efficient results were produced by selected only 12 relevant features instead of a full feature set consisting of 30 diagnostic indices and SVM model. Sensitivity and specificity were achieved as 77.40% and 93.86%, respectively.ConclusionConsequently, the evaluation of multiple feature selection algorithms resulted in achieving the best results.
| S-EPMC6702252 | biostudies-literature
Project description:BackgroundStudying the relationships between rapeseed seed yield (SY) and its yield-related traits can assist rapeseed breeders in the efficient indirect selection of high-yielding varieties. However, since the conventional and linear methods cannot interpret the complicated relations between SY and other traits, employing advanced machine learning algorithms is inevitable. Our main goal was to find the best combination of machine learning algorithms and feature selection methods to maximize the efficiency of indirect selection for rapeseed SY.ResultsTo achieve that, twenty-five regression-based machine learning algorithms and six feature selection methods were employed. SY and yield-related data from twenty rapeseed genotypes were collected from field experiments over a period of 2 years (2019-2021). Root mean square error (RMSE), mean absolute error (MAE), and determination coefficient (R2) were used to evaluate the performance of the algorithms. The best performance with all fifteen measured traits as inputs was achieved by the Nu-support vector regression algorithm with quadratic polynomial kernel function (R2 = 0.860, RMSE = 0.266, MAE = 0.210). The multilayer perceptron neural network algorithm with identity activation function (MLPNN-Identity) using three traits obtained from stepwise and backward selection methods appeared to be the most efficient combination of algorithms and feature selection methods (R2 = 0.843, RMSE = 0.283, MAE = 0.224). Feature selection suggested that the set of pods per plant and days to physiological maturity along with plant height or first pod height from the ground are the most influential traits in predicting rapeseed SY.ConclusionThe results of this study showed that MLPNN-Identity along with stepwise and backward selection methods can provide a robust combination to accurately predict the SY using fewer traits and therefore help optimize and accelerate SY breeding programs of rapeseed.
| S-EPMC10273667 | biostudies-literature
Project description:Ransomware-related cyber-attacks have been on the rise over the last decade, disturbing organizations considerably. Developing new and better ways to detect this type of malware is necessary. This research applies dynamic analysis and machine learning to identify the ever-evolving ransomware signatures using selected dynamic features. Since most of the attributes are shared by diverse ransomware-affected samples, our study can be used for detecting current and even new variants of the threat. This research has the following objectives: (1) Execute experiments with encryptor and locker ransomware combined with goodware to generate JSON files with dynamic parameters using a sandbox. (2) Analyze and select the most relevant and non-redundant dynamic features for identifying encryptor and locker ransomware from goodware. (3) Generate and make public a dynamic features dataset that includes these selected parameters for samples of different artifacts. (4) Apply the dynamic feature dataset to obtain models with machine learning algorithms. Five platforms, 20 ransomware, and 20 goodware artifacts were evaluated. The final feature dataset is composed of 2000 registers of 50 characteristics each. This dataset allows for a machine learning detection with a 10-fold cross-evaluation with an average accuracy superior to 0.99 for gradient boosted regression trees, random forest, and neural networks.
| S-EPMC9920393 | biostudies-literature
Project description:Background and objectiveAccurate and fast diagnosis of rheumatic diseases affecting the hands is essential for further treatment decisions. Fluorescence optical imaging (FOI) visualizes inflammation-induced impaired microcirculation by increasing signal intensity, resulting in different image features. This analysis aimed to find specific image features in FOI that might be important for accurately diagnosing different rheumatic diseases.Patients and methodsFOI images of the hands of patients with different types of rheumatic diseases, such as rheumatoid arthritis (RA), osteoarthritis (OA), and connective tissue diseases (CTD), were assessed in a reading of 20 different image features in three phases of the contrast agent dynamics, yielding 60 different features for each patient. The readings were analyzed for mutual differential diagnosis of the three diseases (One-vs-One) and each disease in all data (One-vs-Rest). In the first step, statistical tools and machine-learning-based methods were applied to reveal the importance rankings of the features, that is, to find features that contribute most to the model-based classification. In the second step machine learning with a stepwise increasing number of features was applied, sequentially adding at each step the most crucial remaining feature to extract a minimized subset that yields the highest diagnostic accuracy.ResultsIn total, n = 605 FOI of both hands were analyzed (n = 235 with RA, n = 229 with OA, and n = 141 with CTD). All classification problems showed maximum accuracy with a reduced set of image features. For RA-vs.-OA, five features were needed for high accuracy. For RA-vs.-CTD ten, OA-vs.-CTD sixteen, RA-vs.-Rest five, OA-vs.-Rest eleven, and CTD-vs-Rest fifteen, features were needed, respectively. For all problems, the final importance ranking of the features with respect to the contrast agent dynamics was determined.ConclusionsWith the presented investigations, the set of features in FOI examinations relevant to the differential diagnosis of the selected rheumatic diseases could be remarkably reduced, providing helpful information for the physician.
| S-EPMC10475553 | biostudies-literature
Project description:Utilizing historical clinical datasets to guide future treatment choices is beneficial for patients and physicians. Machine learning and feature selection algorithms (namely, Fisher's discriminant ratio, Kruskal-Wallis' analysis, and Relief-F) have been combined in this research to analyse a SEER database containing clinical features from de-identified thyroid cancer patients. The data covered 34 unique clinical variables such as patients' age at diagnosis or information regarding lymph nodes, which were employed to build various novel classifiers to distinguish patients that lived for over 10 years since diagnosis, from those who did not survive at least five years. By properly optimizing supervised neural networks, specifically multilayer perceptrons, using data from large groups of thyroid cancer patients (between 6,756 and 20,344 for different models), we demonstrate that unspecialized and existing medical recording can be reliably turned into power of prediction to help doctors make informed and optimized treatment decisions, as distinguishing patients in terms of prognosis has been achieved with 94.5% accuracy. We also envisage the potential of applying our machine learning strategy to other diseases and purposes such as in designing clinical trials for unmasking the maximum benefits and minimizing risks associated with new drug candidates on given populations.
| S-EPMC7083829 | biostudies-literature
Project description:To solve major limitations in algorithms for the metabolite-based prediction of psychiatric phenotypes, a novel prediction model for depressive symptoms based on nonlinear feature selection machine learning, the Hilbert-Schmidt independence criterion least absolute shrinkage and selection operator (HSIC Lasso) algorithm, was developed and applied to a metabolomic dataset with the largest sample size to date. In total, 897 population-based subjects were recruited from the communities affected by the Great East Japan Earthquake; 306 metabolite features (37 metabolites identified by nuclear magnetic resonance measurements and 269 characterized metabolites based on the intensities from mass spectrometry) were utilized to build prediction models for depressive symptoms as evaluated by the Center for Epidemiologic Studies-Depression Scale (CES-D). The nested fivefold cross-validation was used for developing and evaluating the prediction models. The HSIC Lasso-based prediction model showed better predictive power than the other prediction models, including Lasso, support vector machine, partial least squares, random forest, and neural network. L-leucine, 3-hydroxyisobutyrate, and gamma-linolenyl carnitine frequently contributed to the prediction. We have demonstrated that the HSIC Lasso-based prediction model integrating nonlinear feature selection showed improved predictive power for depressive symptoms based on metabolome data as well as on risk metabolites based on nonlinear statistics in the Japanese population. Further studies should use HSIC Lasso-based prediction models with different ethnicities to investigate the generality of each risk metabolite for predicting depressive symptoms.
| S-EPMC7237664 | biostudies-literature
Project description:Keratoconus is a noninflammatory disease characterized by thinning and bulging of the cornea, generally appearing during adolescence and slowly progressing, causing vision impairment. However, the detection of keratoconus remains difficult in the early stages of the disease because the patient does not feel any pain. Therefore, the development of a method for detecting this disease based on machine and deep learning methods is necessary for early detection in order to provide the appropriate treatment as early as possible to patients. Thus, the objective of this work is to determine the most relevant parameters with respect to the different classifiers used for keratoconus classification based on the keratoconus dataset of Harvard Dataverse. A total of 446 parameters are analyzed out of 3162 observations by 11 different feature selection algorithms. Obtained results showed that sequential forward selection (SFS) method provided a subset of 10 most relevant variables, thus, generating the highest classification performance by the application of random forest (RF) classifier, with an accuracy of 98% and 95% considering 2 and 4 keratoconus classes, respectively. Found classification accuracy applying RF classifier on the selected variables using SFS method achieves the accuracy obtained using all features of the original dataset.
| S-EPMC8610665 | biostudies-literature
Project description:BackgroundThe Centers for Disease Control and Prevention identify antibiotic prescribing stewardship as the most important action to combat increasing antibiotic resistance. Clinicians balance broad empiric antibiotic coverage vs. precision coverage targeting only the most likely pathogens. We investigate the utility of machine learning-based clinical decision support for antibiotic prescribing stewardship.MethodsIn this retrospective multi-site study, we developed machine learning models that predict antibiotic susceptibility patterns (personalized antibiograms) using electronic health record data of 8342 infections from Stanford emergency departments and 15,806 uncomplicated urinary tract infections from Massachusetts General Hospital and Brigham & Women's Hospital in Boston. We assessed the trade-off between broad-spectrum and precise antibiotic prescribing using linear programming.ResultsWe find in Stanford data that personalized antibiograms reallocate clinician antibiotic selections with a coverage rate (fraction of infections covered by treatment) of 85.9%; similar to clinician performance (84.3% p = 0.11). In the Boston dataset, the personalized antibiograms coverage rate is 90.4%; a significant improvement over clinicians (88.1% p < 0.0001). Personalized antibiograms achieve similar coverage to the clinician benchmark with narrower antibiotics. With Stanford data, personalized antibiograms maintain clinician coverage rates while narrowing 69% of empiric vancomycin+piperacillin/tazobactam prescriptions to piperacillin/tazobactam. In the Boston dataset, personalized antibiograms maintain clinician coverage rates while narrowing 48% of ciprofloxacin to trimethoprim/sulfamethoxazole.ConclusionsPrecision empiric antibiotic prescribing with personalized antibiograms could improve patient safety and antibiotic stewardship by reducing unnecessary use of broad-spectrum antibiotics that breed a growing tide of resistant organisms.
| S-EPMC9053259 | biostudies-literature
Project description:BackgroundElectronic decision support systems could reduce the use of inappropriate or ineffective empirical antibiotics. We assessed the accuracy of an open-source machine-learning algorithm trained in predicting antibiotic resistance for three Gram-negative bacterial species isolated from patients' blood and urine within 48 h of hospital admission.MethodsThis retrospective, observational study used routine clinical information collected between January 2010 and October 2016 in Birmingham, UK. Patients from whose blood or urine cultures Escherichia coli, Klebsiella pneumoniae or Pseudomonas aeruginosa was isolated were identified. Their demographic, microbiology and prescribing data were used to train an open-source machine-learning algorithm-XGBoost-in predicting resistance to co-amoxiclav and piperacillin/tazobactam. Multivariate analysis was performed to identify predictors of resistance and create a point-scoring tool. The performance of both methods was compared with that of the original prescribers.ResultsThere were 15 695 admissions. The AUC of the receiver operating characteristic curve for the point-scoring tools ranged from 0.61 to 0.67, and performed no better than medical staff in the selection of appropriate antibiotics. The machine-learning system performed statistically but marginally better (AUC 0.70) and could have reduced the use of unnecessary broad-spectrum antibiotics by as much as 40% among those given co-amoxiclav, piperacillin/tazobactam or carbapenems. A validation study is required.ConclusionsMachine-learning algorithms have the potential to help clinicians predict antimicrobial resistance in patients found to have a Gram-negative infection of blood or urine. Prospective studies are required to assess performance in an unselected patient cohort, understand the acceptability of such systems to clinicians and patients, and assess the impact on patient outcome.
| S-EPMC7443728 | biostudies-literature