SEARCH · PubMed Health

Results for “machine learning prediction”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 829 records · Page 46Linked to original sources

PubMed2006

Support vector analysis of color-Doppler images: a new approach for estimating indices of left ventricular function.

Reliable noninvasive estimators of global left ventricular (LV) chamber function remain unavailable. We have previously demonstrated a potential relationship between color-Doppler M-mode (CDMM) images and two basic indices of LV function: peak-systolic elastance (Emax) and the time-constant of LV relaxation (tau). Thus, we hypothesized that these two indices could be estimated noninvasively by adequate postprocessing of CDMM recordings. A semiparametric regression (SR) version of support vector machine (SVM) is here proposed for building a blind model, capable of analyzing CDMM images automatically, as well as complementary clinical information. Simultaneous invasive and Doppler tracings were obtained in nine mini-pigs in a high-fidelity experimental setup. The model was developed using a test and validation leave-one-out design. Reasonably acceptable prediction accuracy was obtained for both Emax (intraclass correlation coefficient Ric, = 0.81) and tau (Ric, = 0.61). For the first time, a quantitative, noninvasive estimation of cardiovascular indices is addressed by processing Doppler-echocardiography recordings using a learning-from-samples method.

Algorithms↗

PubMed2005

A cell proliferation signature is a marker of extremely poor outcome in a subpopulation of breast cancer patients.

Breast cancer comprises a group of distinct subtypes that despite having similar histologic appearances, have very different metastatic potentials. Being able to identify the biological driving force, even for a subset of patients, is crucially important given the large population of women diagnosed with breast cancer. Here, we show that within a subset of patients characterized by relatively high estrogen receptor expression for their age, the occurrence of metastases is strongly predicted by a homogeneous gene expression pattern almost entirely consisting of cell cycle genes (5-year odds ratio of metastasis, 24.0; 95% confidence interval, 6.0-95.5). Overexpression of this set of genes is clearly associated with an extremely poor outcome, with the 10-year metastasis-free probability being only 24% for the poor group, compared with 85% for the good group. In contrast, this gene expression pattern is much less correlated with the outcome in other patient subpopulations. The methods described here also illustrate the value of combining clinical variables, biological insight, and machine-learning to dissect biological complexity. Our work presented here may contribute a crucial step towards rational design of personalized treatment.

Age Factors↗

PubMed2026

Identification of NR4A2 as a Potential Predictive Biomarker for Atherosclerosis.

INTRODUCTION/OBJECTIVE: Atherosclerosis, a leading cause of death globally, is characterized by the buildup of immune cells and lipids in medium to large-sized arteries. However, its precise mechanism remains unclear. The purpose of this study is to explore innovative and reliable biomarkers as a viable approach for the identification and management of atherosclerosis. METHODS: The atherosclerosis-related datasets GSE100927 and GSE66360 were retrieved from the Gene Expression Omnibus (GEO) database. The Limma package in the R programming language was utilized, applying the criteria of |logFC| > 1 and P < 0.05. Subsequently, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed on the 127 identified DEGs using R. Machine learning techniques were then applied to these data to explore and pinpoint potential biomarkers. The diagnostic potential of these markers was assessed via Receiver Operating Characteristic (ROC) curve analysis. Finally, western blot, real-time quantitative PCR (qRT-PCR), and immunohistochemistry (IHC) were employed to confirm the key biomarkers. RESULTS: Our research indicated that a total of 127 DEGs linked to atherosclerosis were successfully identified. Through the application of machine learning methods, eight critical genes were highlighted. Among these, Nuclear Receptor Subfamily 4 Group A Member-2 (NR4A2) emerged as the most promising marker for further investigation. CIBERSORT analysis revealed that NR4A2 expression levels were significantly correlated with multiple immune cell types, including B cells, plasma cells, and macrophages. Additional validation experiments confirmed that NR4A2 expression was indeed elevated in atherosclerotic plaques, supporting its potential as a biomarker for atherosclerosis. CONCLUSION: Our study identified NR4A2 as a potential immune-related biomarker for the diagnosis and treatment of atherosclerosis.

Atherosclerosis↗

PubMed2006

Joint learning of gene functions--a Bayesian network model approach.

In this paper, we develop a machine learning system for determining gene functions from heterogeneous data sources using a Weighted Naive Bayesian network (WNB). The knowledge of gene functions is crucial for understanding many fundamental biological mechanisms such as regulatory pathways, cell cycles and diseases. Our major goal is to accurately infer functions of putative genes or Open Reading Frames (ORFs) from existing databases using computational methods. However, this task is intrinsically difficult since the underlying biological processes represent complex interactions of multiple entities. Therefore, many functional links would be missing when only one or two sources of data are used in the prediction. Our hypothesis is that integrating evidence from multiple and complementary sources could significantly improve the prediction accuracy. In this paper, our experimental results not only suggest that the above hypothesis is valid, but also provide guidelines for using the WNB system for data collection, training and predictions. The combined training data sets contain information from gene annotations, gene expressions, clustering outputs, keyword annotations, and sequence homology from public databases. The current system is trained and tested on the genes of budding yeast Saccharomyces cerevisiae. Our WNB model can also be used to analyze the contribution of each source of information toward the prediction performance through the weight training process. The contribution analysis could potentially lead to significant scientific discovery by facilitating the interpretation and understanding of the complex relationships between biological entities.

Artificial Intelligence↗

PubMed2006

Biomarkers that discriminate multiple myeloma patients with or without skeletal involvement detected using SELDI-TOF mass spectrometry and statistical and machine learning tools.

Multiple Myeloma (MM) is a severely debilitating neoplastic disease of B cell origin, with the primary source of morbidity and mortality associated with unrestrained bone destruction. Surface enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF MS) was used to screen for potential biomarkers indicative of skeletal involvement in patients with MM. Serum samples from 48 MM patients, 24 with more than three bone lesions and 24 with no evidence of bone lesions were fractionated and analyzed in duplicate using copper ion loaded immobilized metal affinity SELDI chip arrays. The spectra obtained were compiled, normalized, and mass peaks with mass-to-charge ratios (m/z) between 2000 and 20,000 Da identified. Peak information from all fractions was combined together and analyzed using univariate statistics, as well as a linear, partial least squares discriminant analysis (PLS-DA), and a non-linear, random forest (RF), classification algorithm. The PLS-DA model resulted in prediction accuracy between 96-100%, while the RF model was able to achieve a specificity and sensitivity of 87.5% each. Both models as well as multiple comparison adjusted univariate analysis identified a set of four peaks that were the most discriminating between the two groups of patients and hold promise as potential biomarkers for future diagnostic and/or therapeutic purposes.

Adult↗

PubMed2024

Evaluating the impact of modeling choices on the performance of integrated genetic and clinical models.

PURPOSE: The value of genetic information for improving the performance of clinical risk prediction models has yielded variable conclusions. Many methodological decisions have the potential to contribute to differential results. We performed multiple modeling experiments integrating clinical and demographic data from electronic health records with genetic data to understand which decisions may affect performance. METHODS: Clinical data in the form of structured diagnostic codes, medications, procedural codes, and demographics were extracted from 2 large independent health systems, and polygenic risk scores (PRS) were generated across all patients of European ancestry with genetic data in the corresponding biobanks. Crohn's disease was studied based on its substantial genetic component, established electronic health records-based definition, and sufficient prevalence for training and testing. We investigated the impact of choices regarding the PRS integration method, training sample, model complexity, and performance metrics. RESULTS: Overall, our results showed that including PRS resulted in higher performance, but this gain was only robust in situations with limited clinical information. We found consistent performance increases from more compute-intensive models, such as random forest, but the impact of other decisions varied by site. CONCLUSION: This work highlights the importance of considering methodological decision points in interpreting the impact of PRS on prediction performance in clinical models.

Humans↗

PubMed2004

Selection of patient samples and genes for outcome prediction.

Gene expression profiles with clinical outcome data enable monitoring of disease progression and prediction of patient survival at the molecular level. We present a new computational method for outcome prediction. Our idea is to use an informative subset of original training samples. This subset consists of only short-term survivors who died within a short period and long-term survivors who were still alive after a long follow-up time. These extreme training samples yield a clear platform to identify genes whose expression is related to survival. To find relevant genes, we combine two feature selection methods -- entropy measure and Wilcoxon rank sum test -- so that a set of sharp discriminating features are identified. The selected training samples and genes are then integrated by a support vector machine to build a prediction model, by which each validation sample is assigned a survival/relapse risk score for drawing Kaplan-Meier survival curves. We apply this method to two data sets: diffuse large-B-cell lymphoma (DLBCL) and primary lung adenocarcinoma. In both cases, patients in high and low risk groups stratified by our risk scores are clearly distinguishable. We also compare our risk scores to some clinical factors, such as International Prognostic Index score for DLBCL analysis and tumor stage information for lung adenocarcinoma. Our results indicate that gene expression profiles combined with carefully chosen learning algorithms can predict patient survival for certain diseases.

Biomarkers, Tumor↗

PubMed2000

Detecting predictors of new-born survival by fuzzy sets based machine learning system.

Machine learning system based on fuzzy sets was used for detecting predictors of new-born survival within the first 15 days after birth. The system processed real-life medical data of 566 new-borns; 528 survived and were classified as "alive", the remaining 38 did not survive and were classified as "died". The state of each new-born was described by values of 112 attributes. The system detected five of the attributes as the best predictors for survival (asphyxia, apnoea, birth weight, reanimation and gestation age). To evaluate are the selected attributes relevant for prediction, the following procedure was used: 566 new-borns were divided into two groups by random selection; 396 (70%) randomly selected new-borns formed the learning group, the remaining 170 new-borns formed the test group. The system acquired prediction knowledge by processing data of the learning group new-borns. Using the knowledge thus acquired, the system predicted survival for each new-born from the test group several times, each time using another set of attributes: once, using all 112 attributes; once, using attributes detected by the system as the best predictors; once, using remaining attributes without the best predictors. After the predictions for all new-borns from the test group had been finished, classification accuracy, sensitivity (accuracy for "alive") and specificity (accuracy for "died") were calculated as measures of prediction success with particular sets of attributes. The results have shown that the best prognostic accuracies were achieved when prediction was done using those attributes which the system detected as the best predictors for new-born survival.

Artificial Intelligence↗

PubMed2005

Support-vector-machine classification of linear functional motifs in proteins.

Our algorithm predicts short linear functional motifs in proteins using only sequence information. Statistical models for short linear functional motifs in proteins are built using the database of short sequence fragments taken from proteins in the current release of the Swiss-Prot database. Those segments are confirmed by experiments to have single-residue post-translational modification. The sensitivities of the classification for various types of short linear motifs are in the range of 70%. The query protein sequence is dissected into short overlapping fragments. All segments are represented as vectors. Each vector is then classified by a machine learning algorithm (Support Vector Machine) as potentially modifiable or not. The resulting list of plausible post-translational sites in the query protein is returned to the user. We also present a study of the human protein kinase C family as a biological application of our method.

Databases, Genetic↗

PubMed2005

Learning yeast gene functions from heterogeneous sources of data using hybrid weighted Bayesian networks.

We developed a machine learning system for determining gene functions from heterogeneous sources of data sets using a Weighted Naive Bayesian Network (WNB). The knowledge of gene functions is crucial for understanding many fundamental biological mechanisms such as regulatory pathways, cell cycles and diseases. Our major goal is to accurately infer functions of putative genes or ORFs (Open Reading Frames) from existing databases using computational methods. However, this task is intrinsically difficult since the underlying biological processes represent complex interactions of multiple entities. Therefore many functional links would be missing when only one or two source of data is used in the prediction. Our hypothesis is that integrating evidence from multiple and complementary sources could significantly improve the prediction accuracy. In this paper, our experimental results not only suggest that the above hypothesis is valid, but also provide guidelines for using the WNB system for data collection, training and predictions. The combined training data sets contain information from gene annotations, gene expressions, clustering outputs, keyword annotations and sequence homology from public databases. The current system is trained and tested on the genes of budding yeast Saccharomyces cerevisiae. Our WNB model can also be used to analyze the contribution of each source of information toward the prediction performance through the weight training process. The contribution analysis could potentially lead to significant scientific discovery by facilitating the interpretation and understanding of the complex relationships between biological entities.

Artificial Intelligence↗

PubMed2000

Neural networks predict protein folding and structure: artificial intelligence faces biomolecular complexity.

In the genomic era DNA sequencing is increasing our knowledge of the molecular structure of genetic codes from bacteria to man at a hyperbolic rate. Billions of nucleotides and millions of aminoacids are already filling the electronic files of the data bases presently available, which contain a tremendous amount of information on the most biologically relevant macromolecules, such as DNA, RNA and proteins. The most urgent problem originates from the need to single out the relevant information amidst a wealth of general features. Intelligent tools are therefore needed to optimise the search. Data mining for sequence analysis in biotechnology has been substantially aided by the development of new powerful methods borrowed from the machine learning approach. In this paper we discuss the application of artificial feedforward neural networks to deal with some fundamental problems tied with the folding process and the structure-function relationship in proteins.

Databases, Factual↗

PubMed2005

A novel statistical ligand-binding site predictor: application to ATP-binding sites.

Structural genomics initiatives are leading to rapid growth in newly determined protein 3D structures, the functional characterization of which may still be inadequate. As an attempt to provide insights into the possible roles of the emerging proteins whose structures are available and/or to complement biochemical research, a variety of computational methods have been developed for the screening and prediction of ligand-binding sites in raw structural data, including statistical pattern classification techniques. In this paper, we report a novel statistical descriptor (the Oriented Shell Model) for protein ligand-binding sites, which utilizes the distance and angular position distribution of various structural and physicochemical features present in immediate proximity to the center of a binding site. Using the support vector machine (SVM) as the classifier, our model identified 69% of the ATP-binding sites in whole-protein scanning tests and in eukaryotic proteins the accuracy is particularly high. We propose that this feature extraction and machine learning procedure can screen out ligand-binding-capable protein candidates and can yield valuable biochemical information for individual proteins.

Adenosine Triphosphate↗

PubMed2002

Maximum entropy modeling for mining patient medication status from free text.

Using a classification scheme of patient medication status we sought to recognize and categorize medications mentioned in the unrestricted text of clinical documents generated in clinical practice. The categories refer to the patient's status with respect to the medication such as discontinuation, start or initiation, and continuation of a given medication. This categorization is performed with a machine learning technique, Maximum Entropy (ME), that is well suited to incorporating heterogeneous sources of information necessary for classifying patient's medication status. We use hand labeled training data to generate ME models and test 5 different training feature sets. Our results show that the most optimal feature set includes a combination of the following: two words preceding and following the mention of the drug, the subject of the sentence in which the drug mention occurs, the 2 words following the subject, and a binary feature vector of lexicalized semantic cues indicative of medication status or its change. The average predictive power of a model trained on these features is approximately 89%.

Artificial Intelligence↗

PubMed2000

Optimal amnesic probabilistic automata or how to learn and classify proteins in linear time and space.

Statistical modeling of sequences is a central paradigm of machine learning that finds multiple uses in computational molecular biology and many other domains. The probabilistic automata typically built in these contexts are subtended by uniform, fixed-memory Markov models. In practice, such automata tend to be unnecessarily bulky and computationally imposing both during their synthesis and use. Recently, D. Ron, Y. Singer, and N. Tishby built much more compact, tree-shaped variants of probabilistic automata under the assumption of an underlying Markov process of variable memory length. These variants, called Probabilistic Suffix Trees (PSTs) were subsequently adapted by G. Bejerano and G. Yona and applied successfully to learning and prediction of protein families. The process of learning the automaton from a given training set S of sequences requires theta(Ln2) worst-case time, where n is the total length of the sequences in S and L is the length of a longest substring of S to be considered for a candidate state in the automaton. Once the automaton is built, predicting the likelihood of a query sequence of m characters may cost time theta(m2) in the worst case. The main contribution of this paper is to introduce automata equivalent to PSTs but having the following properties: Learning the automaton, for any L, takes O (n) time. Prediction of a string of m symbols by the automaton takes O (m) time. Along the way, the paper presents an evolving learning scheme and addresses notions of empirical probability and related efficient computation, which is a by-product possibly of more general interest.

Algorithms↗

PubMedDate not supplied

Detecting blickets: how young children use information about novel causal powers in categorization and induction.

Three studies explored whether and when children could categorize objects on the basis of a novel underlying causal power. To test this we constructed a "blicket detector," a machine that lit up and played music when certain objects were placed on it. First, 2-, 3- and 4-year-old children saw that an object labeled as a "blicket" would set off the machine. In a categorization task, other objects were demonstrated on the machine. Some set it off and some did not. Children were asked to say which objects were "blickets." In an induction task, other objects were or were not labeled as "blickets." Children had to predict which objects would have the causal power to set off the machine. The causal power could conflict with perceptual properties of the object, such as color and shape. In an association task the object was associated with the machine's lighting up but did not cause it to light up. Even the youngest children sometimes used the causal power to determine the object's name rather than using its perceptual properties and sometimes used the object's name rather than its perceptual properties to predict the object's causal powers. Children rarely categorized the object on the basis of the associated event. Young children also sometimes made interesting memory errors-they incorrectly reported that objects with the same perceptual features had had the same causal power. These studies demonstrate that even very young children will easily and swiftly learn about a new causal power of an object and spontaneously use that information in classifying and naming the object.

Age Factors↗

PubMed2002

Real-time computing without stable states: a new framework for neural computation based on perturbations.

A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrate-and-fire neurons in real time. We propose a new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks. It does not require a task-dependent construction of neural circuits. Instead, it is based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry. It is shown that the inherent transient dynamics of the high-dimensional dynamical system formed by a sufficiently large and heterogeneous neural circuit may serve as universal analog fading memory. Readout neurons can learn to extract in real time from the current state of such recurrent neural circuit information about current and past inputs that may be needed for diverse tasks. Stable internal states are not required for giving a stable output, since transient internal states can be transformed by readout neurons into stable target outputs due to the high dimensionality of the dynamical system. Our approach is based on a rigorous computational model, the liquid state machine, that, unlike Turing machines, does not require sequential transitions between well-defined discrete internal states. It is supported, as the Turing machine is, by rigorous mathematical results that predict universal computational power under idealized conditions, but for the biologically more realistic scenario of real-time processing of time-varying inputs. Our approach provides new perspectives for the interpretation of neural coding, the design of experiments and data analysis in neurophysiology, and the solution of problems in robotics and neurotechnology.

Action Potentials↗

PubMed2005

Analysis of alcoholism data using support vector machines.

A supervised learning method, support vector machine, was used to analyze the microsatellite marker dataset of the Collaborative Study on the Genetics of Alcoholism Problem 1 for the Genetic Analysis Workshop 14. Twelve binary-valued phenotype variables were chosen for analyses using the markers from all autosomal chromosomes. Using various polynomial kernel functions of the support vector machine and randomly divided genome regions, we were able to observe the association of some marker sets with the chosen phenotypes and thus reduce the size of the dataset. The successful classifications established with the chosen support vector machine kernel function had high levels of correctness for each prediction, e.g., 96% in the fourfold cross-validations. However, owing to the limited sample data, we were not able to test the predictions of the classifiers in the new sample data.

Alcoholism↗

PubMed2000

Bounds on error expectation for support vector machines.

We introduce the concept of span of support vectors (SV) and show that the generalization ability of support vector machines (SVM) depends on this new geometrical concept. We prove that the value of the span is always smaller (and can be much smaller) than the diameter of the smallest sphere containing the support vectors, used in previous bounds (Vapnik, 1998). We also demonstrate experimentally that the prediction of the test error given by the span is very accurate and has direct application in model selection (choice of the optimal parameters of the SVM).

Learning↗