Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Machine learning.”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,711 records · Page 95Linked to original sources
PubMed1993

The effect of the articulator settings on the cusp inclines as measured by a coordinate measuring machine.

PURPOSE: The purpose of the study was to learn the effect of changes in the articulator settings on the cusp angles during working, nonworking, and protrusive movements; the purpose was also to determine the ability of the coordinate measuring machine to measure the movements. MATERIALS AND METHODS: The condylar angles and the anterior guide angles on a Hanau 96H2 articulator (Teledyne Hanau Corp, Buffalo, NY) were varied; 432 working, nonworking, and protrusive cusp angles were measured at the first molar by a coordinate measuring machine. RESULTS: The data from the coordinate measuring machine was used to produce formulas. The formulas were used to calculate the working, nonworking, and protrusive cusp angles that will occur as a result of 72 different articulator settings. CONCLUSIONS: The coordinate measuring machine is useful for making measurements of articulator movements. Additional research may measure the movements of other articulators or compare articulators (such as the arcon and nonarcon).

Dental Articulators↗
PubMedDate not supplied

Detection and classification of organophosphate nerve agent simulants using support vector machines with multiarray sensors.

The need for rapid and accurate detection systems is expanding and the utilization of cross-reactive sensor arrays to detect chemical warfare agents in conjunction with novel computational techniques may prove to be a potential solution to this challenge. We have investigated the detection, prediction, and classification of various organophosphate (OP) nerve agent simulants using sensor arrays with a novel learning scheme known as support vector machines (SVMs). The OPs tested include parathion, malathion, dichlorvos, trichlorfon, paraoxon, and diazinon. A new data reduction software program was written in MATLAB V. 6.1 to extract steady-state and kinetic data from the sensor arrays. The program also creates training sets by mixing and randomly sorting any combination of data categories into both positive and negative cases. The resulting signals were fed into SVM software for "pairwise" and "one" vs all classification. Experimental results for this new paradigm show a significant increase in classification accuracy when compared to artificial neural networks (ANNs). Three kernels, the S2000, the polynomial, and the Gaussian radial basis function (RBF), were tested and compared to the ANN. The following measures of performance were considered in the pairwise classification: receiver operating curve (ROC) Az indices, specificities, and positive predictive values (PPVs). The ROC Az) values, specifities, and PPVs increases ranged from 5% to 25%, 108% to 204%, and 13% to 54%, respectively, in all OP pairs studied when compared to the ANN baseline. Dichlorvos, trichlorfon, and paraoxon were perfectly predicted. Positive prediction for malathion was 95%.

Journal Article↗
PubMedDate not supplied

Local irritation/corrosion testing strategies: extending a decision support system by applying self-learning classifiers.

Procedures have been established and tested for the extension of a decision support system (DSS) for the prediction of the local irritation/corrosion potential of chemicals by using self-learning classifiers. The different approaches (decision trees, distances examinations in a multidimensional space, k-nearest-neighbour method) have been implemented, tested and evaluated independently. A combination of all of the established extension approaches was also developed and tested. Self-learning classifiers are constructed "automatically" by a computer, i.e. they are not derived by a human expert, and thus they can be constructed with minimal effort. The classifiers presented here extend the existing DSS in a manner that increased significantly the predictive power of the extended system. However, automatically calculated results of self-learning classifiers are produced by a machine, and a machine is incapable of explaining the toxicological relevance of the results obtained. Thus, these results must be accepted, despite an inability to prove their reliability. Only the mathematical correctness of the method and the prediction rates for suitable test cases can lend some credibility to predictions produced by a computer calculating on a self-learning basis. This may not be adequate for regulatory hazard assessment purposes.

Algorithms↗
PubMed2006

Building multiclass classifiers for remote homology detection and fold recognition.

BACKGROUND: Protein remote homology detection and fold recognition are central problems in computational biology. Supervised learning algorithms based on support vector machines are currently one of the most effective methods for solving these problems. These methods are primarily used to solve binary classification problems and they have not been extensively used to solve the more general multiclass remote homology prediction and fold recognition problems. RESULTS: We present a comprehensive evaluation of a number of methods for building SVM-based multiclass classification schemes in the context of the SCOP protein classification. These methods include schemes that directly build an SVM-based multiclass model, schemes that employ a second-level learning approach to combine the predictions generated by a set of binary SVM-based classifiers, and schemes that build and combine binary classifiers for various levels of the SCOP hierarchy beyond those defining the target classes. CONCLUSION: Analyzing the performance achieved by the different approaches on four different datasets we show that most of the proposed multiclass SVM-based classification approaches are quite effective in solving the remote homology prediction and fold recognition problems and that the schemes that use predictions from binary models constructed for ancestral categories within the SCOP hierarchy tend to not only lead to lower error rates but also reduce the number of errors in which a superfamily is assigned to an entirely different fold and a fold is predicted as being from a different SCOP class. Our results also show that the limited size of the training data makes it hard to learn complex second-level models, and that models of moderate complexity lead to consistently better results.

Algorithms↗
PubMed2025

Development and Validation an Integrated Deep Learning Model to Assist Eosinophilic Chronic Rhinosinusitis Diagnosis: A Multicenter Study.

BACKGROUND: The assessment of eosinophilic chronic rhinosinusitis (eCRS) lacks accurate non-invasive preoperative prediction methods, relying primarily on invasive histopathological sections. This study aims to use computed tomography (CT) images and clinical parameters to develop an integrated deep learning model for the preoperative identification of eCRS and further explore the biological basis of its predictions. METHODS: A total of 1098 patients with sinus CT images were included from two hospitals and were divided into training, internal, and external test sets. The region of interest of sinus lesions was manually outlined by an experienced radiologist. We utilized three deep learning models (3D-ResNet, 3D-Xception, and HR-Net) to extract features from CT images and calculate deep learning scores. The clinical signature and deep learning score were inputted into a support vector machine for classification. The receiver operating characteristic curve, sensitivity, specificity, and accuracy were used to evaluate the integrated deep learning model. Additionally, proteomic analysis was performed on 34 patients to explore the biological basis of the model's predictions. RESULTS: The area under the curve of the integrated deep learning model to predict eCRS was 0.851 (95% confidence interval [CI]: 0.77-0.93) and 0.821 (95% CI: 0.78-0.86) in the internal and external test sets. Proteomic analysis revealed that in patients predicted to be eCRS, 594 genes were dysregulated, and some of them were associated with pathways and biological processes such as chemokine signaling pathway. CONCLUSIONS: The proposed integrated deep learning model could effectively predict eCRS patients. This study provided a non-invasive way of identifying eCRS to facilitate personalized therapy, which will pave the way toward precision medicine for CRS.

Humans↗
PubMed2005

Emotion recognition through facial expression analysis based on a neurofuzzy network.

Extracting and validating emotional cues through analysis of users' facial expressions is of high importance for improving the level of interaction in man machine communication systems. Extraction of appropriate facial features and consequent recognition of the user's emotional state that can be robust to facial expression variations among different users is the topic of this paper. Facial animation parameters (FAPs) defined according to the ISO MPEG-4 standard are extracted by a robust facial analysis system, accompanied by appropriate confidence measures of the estimation accuracy. A novel neurofuzzy system is then created, based on rules that have been defined through analysis of FAP variations both at the discrete emotional space, as well as in the 2D continuous activation-evaluation one. The neurofuzzy system allows for further learning and adaptation to specific users' facial expression characteristics, measured though FAP estimation in real life application of the system, using analysis by clustering of the obtained FAP values. Experimental studies with emotionally expressive datasets, generated in the EC IST ERMIS project indicate the good performance and potential of the developed technologies.

Adaptation, Psychological↗
PubMedDate not supplied

Effect of molecular descriptor feature selection in support vector machine classification of pharmacokinetic and toxicological properties of chemical agents.

Statistical-learning methods have been developed for facilitating the prediction of pharmacokinetic and toxicological properties of chemical agents. These methods employ a variety of molecular descriptors to characterize structural and physicochemical properties of molecules. Some of these descriptors are specifically designed for the study of a particular type of properties or agents, and their use for other properties or agents might generate noise and affect the prediction accuracy of a statistical learning system. This work examines to what extent the reduction of this noise can improve the prediction accuracy of a statistical learning system. A feature selection method, recursive feature elimination (RFE), is used to automatically select molecular descriptors for support vector machines (SVM) prediction of P-glycoprotein substrates (P-gp), human intestinal absorption of molecules (HIA), and agents that cause torsades de pointes (TdP), a rare but serious side effect. RFE significantly reduces the number of descriptors for each of these properties thereby increasing the computational speed for their classification. The SVM prediction accuracies of P-gp and HIA are substantially increased and that of TdP remains unchanged by RFE. These prediction accuracies are comparable to those of earlier studies derived from a selective set of descriptors. Our study suggests that molecular feature selection is useful for improving the speed and, in some cases, the accuracy of statistical learning methods for the prediction of pharmacokinetic and toxicological properties of chemical agents.

Algorithms↗
PubMed2004

Prediction of the axillary lymph node status in mammary cancer on the basis of clinicopathological data and flow cytometry.

Axillary lymph node status is a major prognostic factor in mammary carcinoma. It is clinically desirable to predict the axillary lymph node status from data from the mammary cancer specimen. In the study, the axillary lymph node status, routine histological parameters and flow-cytometric data were retrospectively obtained from 1139 specimens of invasive mammary cancer. The ten variables: age, tumour type, tumour grade, tumour size, skin infiltration, lymphangiosis carcinomatosa, pT4 category, percentage of tumour cells in G2/M- and S-phases of the cell cycle, and ploidy index were considered as predictor variables, and the single variable lymph node metastasis pN (0 for pN0, or 1 for pN1 or pN2) was used as an output variable. A stepwise logistic regression analysis, with the axillary lymph node as a dependent variable, was used for feature selection. Only lymphangiosis carcinomatosa and tumour size proved to be significant as independent predictor variables; the other variables were non-contributory. Three paradigms with supervised learning rules (multilayer perceptron, learning vector quantisation and support vector machines) were used for the purpose of prediction. If any of these paradigms was used with the information from all ten input variables, 73% of cases could be correctly predicted, with specificity ranging from 82 to 84% and sensitivity ranging from 60 to 63%. If only the two significant input variables were used, lymphangiosis carcinomatosa and tumour diameter, the prediction accuracy was no worse. Nearly identical results were obtained by two different techniques of cross-validation (leave-one-out against ten-fold cross validation). It was concluded that: artificial neural networks can be used for risk stratification on the basis of routine data in individual cases of mammary cancer; and lymphangiosis carcinomatosa and tumour size are independent predictors of axillary lymph node metastasis in mammary cancer.

Algorithms↗
PubMed2005

[Mechatronic in functional endoscopic sinus surgery. First experiences with the daVinci Telemanipulatory System].

BACKGROUND: This study examines the advantages and disadvantages of a commercial telemanipulator system (daVinci, Intuitive Surgical, USA) with computer-guided instruments in functional endoscopic sinus surgery (FESS). METHODS: We performed five different surgical FESS steps on 14 anatomical preparation and compared them with conventional FESS. A total of 140 procedures were examined taking into account the following parameters: degrees of freedom (DOF), duration , learning curve, force feedback, human-machine-interface. RESULTS: Telemanipulatory instruments have more DOF available then conventional instrumentation in FESS. The average time consumed by configuration of the telemanipulator is around 9+/-2 min. Missing force feedback is evaluated mainly as a disadvantage of the telemanipulator. Scaling was evaluated as helpful. The ergonomic concept seems to be better than the conventional solution. DISCUSSION: Computer guided instruments showed better results for the available DOF of the instruments. The human-machine-interface is more adaptable and variable then in conventional instrumentation. Motion scaling and indexing are characteristics of the telemanipulator concept which are helpful for FESS in our study.

Clinical Competence↗
PubMed2004

Qualitative and quantitative analysis of the learning curve of a simulated surgical task on the da Vinci system.

BACKGROUND: Robotic telemanipulation systems provide solutions to the problems of less dexterity and visual constraints of minimally invasive surgery (MIS). However, their influence over surgeons' dexterity and learning curve needs to be assessed. We present motion analysis as an objective method to measure performance and learning progress.METHODS. Thirteen surgeons completed five synthetic small bowel anastomoses using the da Vinci system. Objective Structured Assessment of Technical Skills (OSATS) allowed qualitative analysis. Quantitative analysis used API software of the system to retrieve real-time robotic signal data of time, path length, and number of movements. Wilcoxon signed ranks test was used for statistical analysis. A p value <0.05 was considered significant.RESULTS. OSATS global scores were 18.6 points for the first attempt and 26 for the fifth attempt ( p < 0.02, Cronbach's alpha = 0.894). Paired data of motion analysis for attempts 1 vs 5 showed significant change: time taken 3507 sec and 2287 sec ( p < 0.008), total number of movements 2411 and 1387 ( p = 0.01), total path length 21,630 cm and 13,941 cm ( p = 0.01).CONCLUSIONS. A rapid learning curve to a competent level using the da Vinci system is possible aided by the system's intuitive motion. Motion analysis is a useful tool to measure performance in the da Vinci system compared to OSATS and time alone.

Anastomosis, Surgical↗
PubMed2004

An experimental comparison of 3-dimensional and 2-dimensional endoscopic systems in a model.

PURPOSE: This study compares the effect of new electronic display systems using endoscopic instruments on intrathoracal maneuvering and targeting under standardized conditions. A 2-dimensional (2-D) vision system is compared with 2 stereoscopic 3-dimensional (3-D) video technologies, called "shutter glasses," and the head-mounted display (HMD) system. METHODS: Fifteen participants with minor experience (<50 operations = beginners) and 15 participants with endoscopic experience (advanced) had to hit 12 electronically conducted wires in a thoracic spine model using 3 different systems (2-D video, 3-D shutter glasses, and 3-D HMD). The sequence was randomly alternated for each participant and repeated 3 times to eliminate the influence of training and concentration. RESULTS: The execution time with the 2-D system (mean time, 95.5 seconds) was shorter than with the HMD (mean time, 107 seconds; P =.001) or the Shutter system (mean time, 101 seconds; P =.002). No significant difference was seen between the 3-D systems (P =.153). The overall look of the missed targets showed statistically no difference between the 3 systems (P =.191). None of the 3 systems showed a statistically significant correlation between execution time and number of missed targets. Regarding the total number of missed targets for advanced and beginner groups, the head-mounted display system in the advanced group showed higher but not statistically significantly higher accuracy. CONCLUSIONS: Although the 3-D systems tested for endoscopic surgery did not accelerate the execution speed, the HMD system seems to increase the accuracy for endoscopically experienced surgeons.

Clinical Competence↗
PubMed2005

Emotion recognition in human-computer interaction.

In this paper, we outline the approach we have developed to construct an emotion-recognising system. It is based on guidance from psychological studies of emotion, as well as from the nature of emotion in its interaction with attention. A neural network architecture is constructed to be able to handle the fusion of different modalities (facial features, prosody and lexical content in speech). Results from the network are given and their implications discussed, as are implications for future direction for the research.

Attention↗
PubMed2001

A compatible chord code for inputting elements of Chinese characters.

A compatible chord code for inputting elements of Chinese characters (ECC) to computer was proposed. It capitalized on the graphic compatibility between ECC and chord combination of keys (CCK) on a single-handed chord keyboard with five keys. Experimental results showed that the proposed compatible chord code was better than a code that randomly mapped ECC onto CCK with respect to learning time and response time. Explicit indication of the graphic compatibility between ECC and CCK did not enhance memorizing the compatible code.

Adolescent↗
PubMed1998

Assessment of neuropsychological changes in patients with arteriovenous malformation (AVM) after radiosurgery.

PURPOSE: The purpose of this study was to investigate neuropsychological effects of radiosurgery in patients with cerebral arteriovenous malformation (AVM), with special focus on attention and memory. This report describes the study setup and presents the first results during a follow-up of up to 1 year. MATERIALS AND METHODS: Seventy-nine patients were studied before, acutely after radiosurgery, and during the regular follow-up (subacute phase: Weeks 6-12, chronic phase: Months 6-12). Radiosurgery was performed using a modified linear accelerator (minimum doses to the target volume: 15-22 Gy, median 20 Gy). Estimated whole brain dose was 0.5 to 2 Gy. Neuropsychological testing included assessment of general intelligence (Wechsler Adult Intelligence Scale), attention (modified Trail-Making Test A, Digit Symbol Test, D2 Test, Wiener Determination Machine) and memory (Rey Auditory Verbal Learning Test, Benton Visual Retention Test). During follow-up, alternate test versions were used. Neuropsychological deficits were defined as a test score of at least one standard deviation (SD) below the mean of the normal distribution. RESULTS: The pretherapeutic evaluation revealed marked deviations from the normal population; 24% had deficits in intelligence (range 23-31% in different subtests), attention (35%, 23-59%) and memory (48%, 31-61%). The overall percentage of aberrant results was reduced by 12% (memory) to 14% (attention) in the chronic phase up to 12 months after therapy. The improvement in test scores was significant (p < 0.05) in 3 of 4 subtests of attention functions. CONCLUSIONS: The acute tolerance of radiosurgery seems to be very good in these patients, showing no relevant increase in number of patients with neuropsychological deficits. Although the long-term follow-up needs to be further increased, our data indicate a tendency to slight improvement in the overall neuropsychological performance of AVM patients in the chronic phase after radiosurgery.

Adult↗
PubMed1992

Use of preferential inspection to define the viewing sphere and characteristic views of an arbitrary machined tool part.

Measurements were made of the way human subjects visually inspected an idealized machined tool part (a 'widget') while learning the three-dimensional shape of the object. Subjects were free to rotate the object about any axis. Inspection was not evenly distributed across all views. Subjects focused on views where the faces of the object were orthogonal to the line of sight and the edges of the object were aligned parallel or at right angles to the gravitational axis. These 'face' or 'plan' views were also the easiest for subjects to bring to mind in a mental imagery task. By contrast, when subjects were instructed to imagine the views displaying the most structural information they visualized views lying midway between face views.

Adolescent↗
PubMed2003

Ecological models of human performance based on affordance, emotion and intuition.

This paper proposes a complementary approach to Rasmussen's taxonomy of the human skill-, rule-, and knowledge-based performance models by combining the ecological concept of affordances with the neural concepts of human emotion and intuition. The classical cognitive engineering framework is extended through the neuro-ecological approach, including personal human attributes important in exercising control over the work environment. The proposed affordance-, emotion-, and intuition-based models correspond to the three types of human performance, namely: learning, adaptive and tuning control, respectively. The new framework is not a predictive model of the operator behaviour, but rather it describes the processes of neuro-ecological control of the human environment.

Cognition↗
PubMed2005

Profile-based direct kernels for remote homology detection and fold recognition.

MOTIVATION: Protein remote homology detection is a central problem in computational biology. Supervised learning algorithms based on support vector machines are currently one of the most effective methods for remote homology detection. The performance of these methods depends on how the protein sequences are modeled and on the method used to compute the kernel function between them. RESULTS: We introduce two classes of kernel functions that are constructed by combining sequence profiles with new and existing approaches for determining the similarity between pairs of protein sequences. These kernels are constructed directly from these explicit protein similarity measures and employ effective profile-to-profile scoring schemes for measuring the similarity between pairs of proteins. Experiments with remote homology detection and fold recognition problems show that these kernels are capable of producing results that are substantially better than those produced by all of the existing state-of-the-art SVM-based methods. In addition, the experiments show that these kernels, even when used in the absence of profiles, produce results that are better than those produced by existing non-profile-based schemes. AVAILABILITY: The programs for computing the various kernel functions are available on request from the authors.

Algorithms↗
PubMed2005

Data classification with radial basis function networks based on a novel kernel density estimation algorithm.

This paper presents a novel learning algorithm for efficient construction of the radial basis function (RBF) networks that can deliver the same level of accuracy as the support vector machines (SVMs) in data classification applications. The proposed learning algorithm works by constructing one RBF subnetwork to approximate the probability density function of each class of objects in the training data set. With respect to algorithm design, the main distinction of the proposed learning algorithm is the novel kernel density estimation algorithm that features an average time complexity of O(n log n), where n is the number of samples in the training data set. One important advantage of the proposed learning algorithm, in comparison with the SVM, is that the proposed learning algorithm generally takes far less time to construct a data classifier with an optimized parameter setting. This feature is of significance for many contemporary applications, in particular, for those applications in which new objects are continuously added into an already large database. Another desirable feature of the proposed learning algorithm is that the RBF networks constructed are capable of carrying out data classification with more than two classes of objects in one single run. In other words, unlike with the SVM, there is no need to resort to mechanisms such as one-against-one or one-against-all for handling datasets with more than two classes of objects. The comparison with SVM is of particular interest, because it has been shown in a number of recent studies that SVM generally are able to deliver higher classification accuracy than the other existing data classification algorithms. As the proposed learning algorithm is instance-based, the data reduction issue is also addressed in this paper. One interesting observation in this regard is that, for all three data sets used in data reduction experiments, the number of training samples remaining after a naive data reduction mechanism is applied is quite close to the number of support vectors identified by the SVM software. This paper also compares the performance of the RBF networks constructed with the proposed learning algorithm and those constructed with a conventional cluster-based learning algorithm. The most interesting observation learned is that, with respect to data classification, the distributions of training samples near the boundaries between different classes of objects carry more crucial information than the distributions of samples in the inner parts of the clusters.

Algorithms↗