Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Classification Algorithms”

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 235 records · Page 13Linked to original sources
PubMed1977

Influence of population on the classification of ECG-VCG's using linear regression techniques.

This paper describes the influence of different populations on statistical multivariate classification rules and classification results where the word "population" refers only to the frequency of diagnoses to be expected, the so-called prior probabilities. Using linear regression as a multivariate classification technique and six groups consisting of five pathological conditions and normals as test data, it has been shown: (a) That the population influences to a great extent the selection of the best ECG-VCG measurements for the classification rule. (b) That a mismatch of the populations in the learning and test sets can considerably decrease the number of correct classifications. (c) That a certain correction of the mismatch can be achieved when the prior probabilities in the learning and test sets are known, Further, the paper discusses the change of prior probabilities over the years at the Variety Club Heart Hospital in the University of Minnesota and its effect on the performance of the classification algorithm which has been used.

Electrocardiography↗
PubMed1996

A new approach to differential diagnosis of diseases.

The main goal of this paper is to show the usefulness of the logic-combinatory approach in pattern recognition theory for developing auxiliary criteria for differential medical diagnosis, based on the methodology presented by Heathfield et al. (J Biomed Eng 13 (1991) 51-57). Firstly, we propose a change in the characterization base, from disease characterization to patient characterization then, we suggest a k-valued treatment for variables which allows us to assign them values in a wider range in order to represent different degrees in symptom manifestations. Secondly, the methodology proposed is based on Testor Theory. This theory allows us to obtain the minimum combination of features (symptoms) and the set of features combination equally discriminant (typical testors) among the diseases considered. Then, applying some classification algorithm that uses typical testors, physicians will have more making differential flexibility diagnosis.

Algorithms↗
PubMed1991

Automated feature detection in digital images of skin.

This paper presents a new approach to the detection of cutaneous features such as pigmented moles, pores and hair in digital images. We show that by considering the digitized image to be a 3-D terrain with brightness being height, common skin features appear as 'pits' in the terrain. Pits contain a great deal of information about local features in a form that can be easily extracted and analyzed. Pigmented lesions of clinical interest typically have pit characteristics which can be used to separate them from other features. We show empirically that, by creating a statistical database, on the average over 99% of pits can be classified correctly after only a few training images are established for a subject. When attempting to detect pigmented lesions, mean sensitivity ranges from 78% to 98%, depending on imaging conditions and the classification algorithm used. Using image compression, the speed of this screening technique is shown to be increased by a factor of 4 without loss of sensitivity.

Algorithms↗
PubMed2005

Discriminating nevus and melanoma on paraffin-embedded skin biopsies using FTIR microspectroscopy.

FTIR microspectroscopy, in combination with cluster analysis, has been used to characterise skin tissues, in order to discriminate cancerous from non-cancerous ones. The main objective of this in vitro study was to demonstrate the applicability of infrared spectral imaging to separate, on paraffinised biopsies, pigmented nevi (benign skin lesions) from melanomas (malignant skin lesions). Infrared spectra were collected from paraffin-embedded samples of nevi and melanomas, without deparaffinisation. Despite the important contribution of the paraffin in these spectra, it was possible to find meaningful and discriminating spectral regions. Spectral imaging was first performed to localize different skin layers (dermis and epidermis). Spectra extracted from the images were subjected to hierarchical classification algorithm, which allowed the discrimination of melanomas from the nevi, using selected spectral windows that correspond to vibrations of DNA and melanin content. The diversity of skin lesions and direct accessibility to the skin make this organ an interesting field of investigation using this technique.

Biopsy↗
PubMed2006

Identifying DNA splice sites using hypernetworks with artificial molecular evolution.

Identifying DNA splice sites is a main task of gene hunting. We introduce the hyper-network architecture as a novel method for finding DNA splice sites. The hypernetwork architecture is a biologically inspired information processing system composed of networks of molecules forming cells, and a number of cells forming a tissue or organism. Its learning is based on molecular evolution. DNA examples taken from GenBank were translated into binary strings and fed into a hypernetwork for training. We performed experiments to explore the generalization performance of hypernetwork learning in this data set by two-fold cross validation. The hypernetwork generalization performance was comparable to well known classification algorithms. With the best hypernetwork obtained, including local information and heuristic rules, we built a system (HyperExon) to obtain splice site candidates. The HyperExon system outperformed leading splice recognition systems in the list of sequences tested.

Algorithms↗
PubMed2005

GASepo-a software solution for quantitative analysis of digital images in Epo doping control.

A software has been developed that is aimed at quantitative analysis of images acquired by isoelectric focusing and double blotting procedures used for recombinant erythropoietin doping control. It represents a unified and easy-to-use tool for Epo doping experts in WADA accredited laboratories. It is based on image segmentation philosophy that enables identification of individual bands whose characteristics are needed for evaluation of the Epo doping positivity criteria. Several modules implemented in the GASepo software include an original know how, in particular, the method of robust calculation of the cut-off line, band segmentation and classification algorithms. GASepo is being used in several doping control laboratories worldwide.

Algorithms↗
PubMed2026

Meta-PseU: A meta-classifier for robust prediction of RNA pseudouridine modification sites from long sequences.

BACKGROUND AND OBJECTIVES: Pseudouridine (Ψ) represents one of the most abundant and conserved RNA modifications. Ψ provides an additional hydrogen-bond donor that enhances RNA structural stability and modulates translation. It participates in diverse biological processes, including RNA-protein interactions, splicing, translational control, and stress responses. Aberrant pseudouridylation is implicated in cancer, neurodegenerative disorders, and autoimmune diseases. Despite its biological importance, experimental identification of Ψ sites remains time-consuming and costly, limiting the feasibility of transcriptome-wide profiling. Computational approaches have therefore become essential complements to experimental techniques. However, state-of-the-art machine-learning and deep-learning predictors often suffer from limited generalizability due to small training datasets. To overcome these issues, we aim at constructing new long-sequence datasets and developing a novel Ψ site predictor. METHODS: New long-sequence datasets were constructed as benchmarks for RNA Ψ-site prediction. The Ψ modification sites in RMBase 3.0 were mapped to the reference genomes across three species of human, mouse, and yeast, and the RNA sequences with a length of 201 were generated by extending the upstream and downstream from the mapped, central sites. To eliminate sequence redundancy, the sequences were clustered using CD-HIT with a 70% sequence identity threshold. We developed Meta-PseU, a logistic regression-based meta-classifier that considered 118 machine learning and deep learning classifiers. The datasets and programs are freely accessible at https://github.com/kuratahiroyuki/MetaPseU. RESULTS: By optimizing model configuration, we proposed the Meta-PseU model stacking 32 machine learning and deep learning classifiers out of 118 classifiers. Meta-PseU substantially improved model generalizability, overcoming a key limitation of existing approaches. It greatly outperformed state-of-the-art predictors and achieved increasing accuracy with increasing sequence length. CONCLUSIONS: Long-sequence datasets were newly constructed as benchmarks for RNA Ψ-site prediction. Meta-PseU offers a new framework for robust Ψ-site identification by using long sequences.

Pseudouridine↗
PubMed2005

GEMS: a system for automated cancer diagnosis and biomarker discovery from microarray gene expression data.

The success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (gene expression model selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. In this paper we present a preliminary evaluation of the system with five new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org.

Algorithms↗
PubMed2005

Prospective recruitment of patients with congestive heart failure using an ad-hoc binary classifier.

This paper addresses a very specific problem of identifying patients diagnosed with a specific condition for potential recruitment in a clinical trial or an epidemiological study. We present a simple machine learning method for identifying patients diagnosed with congestive heart failure and other related conditions by automatically classifying clinical notes dictated at Mayo Clinic. This method relies on an automatic classifier trained on comparable amounts of positive and negative samples of clinical notes previously categorized by human experts. The documents are represented as feature vectors, where features are a mix of demographic information as well as single words and concept mappings to MeSH and HICDA classification systems. We compare two simple and efficient classification algorithms (Naïve Bayes and Perceptron) and a baseline term spotting method with respect to their accuracy and recall on positive samples. Depending on the test set, we find that Naïve Bayes yields better recall on positive samples (95 vs. 86%) but worse accuracy than Perceptron (57 vs. 65%). Both algorithms perform better than the baseline with recall on positive samples of 71% and accuracy of 54%.

Artificial Intelligence↗
PubMed2004

Online prediction of self-paced hand-movements from subthalamic activity using neural networks in Parkinson's disease.

The significance of local field potential (LFP) activity in the subthalamic nucleus (STN) of patients with Parkinson's disease is unclear. Here we show that it is possible to predict self-paced hand-movements from the oscillatory nature of the STN LFP on a trial-by-trial basis. To this end we used a neural networks' classification algorithm on features representing different measures of spectral activity. Our experiments were simulated to process online LFP signal recordings collected beforehand from macroelectrodes implanted in STN. With spectral features extracted via wavelet transformation, we were able to predict a voluntary hand-movement's onset with 95% sensitivity and 77% specificity. Most predictions were made over a second in advance of the movement. We conclude that oscillatory LFP activity in STN is directly or indirectly related to processes involved in motor preparation. The ability to predict movement in real-time may open up several experimental and therapeutic possibilities.

Action Potentials↗
PubMed2026

Predicting ACL injury risk in athletes: A systematic review of machine learning-based models.

BACKGROUND: Early ACL injury risk identification in athletes is essential. This systematic review examines machine learning (ML) models for predicting ACL injuries, evaluating their methodological quality, performance, and reliability. METHOD: A comprehensive electronic search was conducted across PubMed, Scopus, Web of Science, and IEEE Xplore databases, supplemented by Google Scholar for grey literature, covering articles published between January 1, 2015, and August 30, 2025. Eligible studies were appraised using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST) for methodological quality and risk of bias, and the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines for quality of evidence. RESULTS: Ten studies were included. PROBAST showed eight studies had moderate risk of bias and two low risk. TRIPOD found only two studies met quality criteria. ML models included logistic regression (n = 5), support vector machines (n = 4), k-nearest neighbor (n = 3), decision trees (n = 3), random forests (n = 5), neural networks (n = 2), linear discriminant analysis (n = 1), and pre-trained CNNs (n = 1). AUC ranged from 0.63 to 0.98. Accuracy (reported in six studies) ranged from 26% to 95%; however, these values should be interpreted with caution due to the absence of confidence intervals, lack of class imbalance handling, and limited external validation across studies. Tree-based ensemble methods such as random forest achieved competitive accuracy (74-86%), while SVM, a non-ensemble classifier, reported accuracy ranging from 71% to 95%; however, the highest values were obtained in studies with notably small sample sizes (n = 12 to n = 39), raising concerns about overfitting and generalizability. CONCLUSION: Current ML algorithms show promise for identifying athletes at high ACL injury risk and detecting relevant risk factors. Although study quality was generally satisfactory, future research should prioritize external validation and model interpretability to support clinical translation.

Humans↗
PubMed2026

Stage-Independent Real-Time Subtype Classification and Comprehensive Biopsy Profiling of Urothelial Carcinomas by the Lund Taxonomy System.

Bladder cancer is a heterogeneous malignancy with diverse clinical outcomes, and conventional pathological assessment alone is insufficient to capture its underlying biology. Gene expression profiling can stratify tumors into molecular subtypes with prognostic and predictive potential, but the reliability of transcriptomic classification and its clinical utility remains to be established. The translational/observational UROSCANSEQ study (ISRCTN15459149) prospectively evaluates RNA-based Lund Taxonomy (LundTax) molecular subtype classification in a clinical setting. Among 784 consecutive biopsies collected between 2018 and 2022, RNA sequencing was successful for 90% of all biopsies, encompassing 662 bladder cancer patients with a stage distribution of 48% Ta, 27% T1, 24% ≥T2, and 1% CIS. We demonstrate that the LundTax subtype classification algorithm, applied to individual samples, accurately identifies cancer cell phenotypes with characteristic gene and protein expression patterns in a manner robust to RNA quality, data preprocessing strategies, and batch effects, supporting its clinical feasibility across both non-muscle-invasive and muscle-invasive disease. We further extend the LundTax framework by incorporating single-sample molecular risk scores reflecting tumor grade, proliferation, and progression risk, as well as tumor microenvironment signatures. Both risk scores and overall immune and stromal content in biopsies were significantly associated with an increased risk of clinical progression in noninvasive disease. In a separate analysis of the relative cellular composition of the tumor microenvironment, however, only the fraction of natural killer cells remained significant. Together, the expanded LundTax system provides a comprehensive molecular portrait of individual tumor biopsies. By explicitly separating cancer cell-intrinsic phenotypes, prognostic indexes, and microenvironmental signals, the framework minimizes biological confounding and establishes a strong foundation for future studies evaluating clinical outcomes and treatment responses.

Humans↗
PubMed2003

Prediction of total cerebral tissue volumes in normal appearing brain from sub-sampled segmentation volumes.

The need for anatomical coverage and multi-spectral information must be balanced against examination and processing time to ensure high-quality, feasible imaging protocols for clinical research of cerebral development in normal-appearing brains. The focus of this study was to create and assess models to estimate total cerebral volumes of gray matter, white matter, and cerebrospinal fluid (CSF) from anatomically defined sub-samples of full clinical examinations. Pediatric patients (18F, 11M; aged 1.7 to 18.7, median 5.2 years) underwent a clinical imaging protocol consisting of 3 mm contiguous T1-, T2-, PD-, and FLAIR-weighted images after obtaining informed consent. Magnetic resonance imaging (MRI) sets were registered, RF-corrected, and then analyzed with a hybrid neural network segmentation and classification algorithm to identify normal brain parenchyma. The correlation between the image subsets and the total cerebral volumes of gray matter, white matter and CSF were examined through linear regression analyses. Five sub-sampled sets were defined and assessed in each patient to produce estimation models which were all significantly correlated (p < 0.001) with the total cerebral volumes of gray matter, white matter, and CSF. Volumes were estimated from as little as a single representative slice requiring minimal processing time, 27 min, but with an average estimation error of approximately 6%. Larger sub-samples of approximately three-quarters of the full cerebral volume required much more processing time, 2 h and 4 min, but produced estimates with an average error less than 2%. This study demonstrated that investigators can choose the amount of cerebrum sampled to optimize the acquisition and processing time against the degree of accuracy needed in the total cerebral volume estimates.

Adolescent↗
PubMedDate not supplied

New hybrid count- and geometry-based method for quantification of left ventricular volumes and ejection fraction from ECG-gated SPECT: methodology and validation.

BACKGROUND: We have previously developed a new method for quantitative assessment of left ventricular (LV) volumes and ejection fraction (EF) from electrocardiography-gated single photon emission computed tomography (SPECT). The aims of this study were to present the methodology, to validate the gated SPECT cardiac quantification (GSCQ) method in phantoms and patients, and to determine normal values of LVEF. METHODS AND RESULTS: A simple thresholding technique was used to generate binary images from nongated SPECT images. The K-means cluster classification algorithm was used to separate the LV region from non-LV regions on the binary images. A count- and geometry-based algorithm was applied to define endocardial and epicardial boundaries for calculation of LV volumes and LVEF. Overall correlation between GSCQ-quantified volumes and actual phantom volumes was good ( r = 0.97 and standard error of estimation (SEE) = 9.99 mL for normal phantoms, r = 0.99 and SEE = 6.97 mL for phantoms with defects). In patient studies, LVEF derived by GSCQ from SPECT and from equilibrium radionuclide angiography also showed good correlation ( r = 0.90 and SEE = 6.2%). The lower limit of normal LVEF from 8-frame gated SPECT by use of GSCQ was 45%. Quantification of LVEF by the GSCQ method was highly producible and was not significantly affected by the presence of myocardial perfusion defects or intense gastrointestinal activity. CONCLUSIONS: The GSCQ method provides reliable and consistent assessments of LV volumes and EF. This methodology is less affected by intense gastrointestinal activity than other methods.

Adult↗
PubMed2006

Beyond mind-reading: multi-voxel pattern analysis of fMRI data.

A key challenge for cognitive neuroscience is determining how mental representations map onto patterns of neural activity. Recently, researchers have started to address this question by applying sophisticated pattern-classification algorithms to distributed (multi-voxel) patterns of functional MRI data, with the goal of decoding the information that is represented in the subject's brain at a particular point in time. This multi-voxel pattern analysis (MVPA) approach has led to several impressive feats of mind reading. More importantly, MVPA methods constitute a useful new tool for advancing our understanding of neural information processing. We review how researchers are using MVPA methods to characterize neural coding and information processing in domains ranging from visual perception to memory search.

Algorithms↗
PubMed2004

Patient-specific seizure onset detection.

This article presents an automated, patient-specific method for the detection of epileptic seizure onset from noninvasive electroencephalography. We adopt a patient-specific approach to exploit the consistency of an individual patient's seizure and nonseizure electroencephalograms. Our method uses a wavelet decomposition to construct a feature vector that captures the morphology and spatial distribution of an electroencephalographic epoch, and then determines whether that vector is representative of a patient's seizure or nonseizure electroencephalogram using the support vector machine classification algorithm. Our completely automated method was tested on noninvasive electroencephalograms from 36 pediatric subjects suffering from a variety of seizure types. It detected 131 of 139 seizure events within 8.0+/-3.2 seconds of electrographic onset, and declared 15 false detections in 60 hours of clinical electroencephalography. Our patient-specific method can be used to initiate delay-sensitive clinical procedures following seizure onset, for example, the injection of a functional imaging radiotracer.

Algorithms↗
PubMed2004

Evaluation of in vivo endoscopic autofluorescence spectroscopy in gastric cancer.

BACKGROUND: The aim of this study was to evaluate light-induced autofluorescence spectroscopy for the in vivo diagnosis of gastric cancer. METHODS: A total of 344 endogenous fluorescence spectra were obtained from normal (164) and cancerous gastric mucosa (180) in 15 patients with pure adenocarcinoma and in 16 patients with gastric cancer containing signet-ring cells. A special light source capable of delivering either white or violet-blue light for the excitation of tissue autofluorescence via the endoscope was used. Endogenous fluorescence spectra emitted by the tissue were collected with a fiberoptic probe and analyzed with a spectrograph. RESULTS: Gastric adenocarcinoma exhibits specific changes in the emitted fluorescence spectra as compared with normal gastric mucosa. By algorithmic classification of the spectra, a sensitivity of 84%, specificity of 87%, a likelihood ratio for a positive test of 6.5 and for a negative test of 0.18 were obtained for the diagnosis of pure adenocarcinoma of the stomach. However, gastric cancer with signet-ring cells exhibits great variation in emitted autofluorescence spectra as compared with normal mucosa. The sensitivity for the diagnosis of all carcinomas containing signet-ring cells was 55%, specificity 85%, the likelihood ratio for a positive test was 3.7 and for a negative test, 0.53. The diagnostic value decreases with increasing numbers of signet-ring cells and tumor grade. CONCLUSIONS: Light-induced autofluorescence spectroscopy is a new and promising bio-optical technique for the endoscopic in vivo diagnosis of gastric adenocarcinoma. The poor diagnostic accuracy for signet-ring cell carcinoma may be explained by the diffuse and frequent submucosal growth of this tumor and the presence of collagen fibers.

Adenocarcinoma↗
PubMed2002

Using machine vision to analyze and classify Caenorhabditis elegans behavioral phenotypes quantitatively.

Mutants with abnormal patterns of locomotion, also known as uncoordinated (Unc) mutants, have facilitated the genetic dissection of many important aspects of nervous system function and development in the nematode Caenorhabditis elegans. Although a large number of distinct classes of Unc mutants can be distinguished by an experienced observer, precise quantitative definitions of these classes have not been available. Here we describe a new approach for using automatically-acquired image data to quantify the locomotion patterns of wild-type and mutant worms. We designed an automated tracking and imaging system capable of following an individual animal for long time periods and saving a time-coded series of digital images representing its motion and body posture over the course of the recording. We have also devised methods for measuring specific features from these image data that can be used by the classification and regression tree classification algorithm to reliably identify the behavioral patterns of specific mutant types. Ultimately, these tools should make it possible to evaluate with quantitative precision the behavioral phenotypes of novel mutants, gene knockout lines, or pharmacological treatments.

Algorithms↗