SEARCH · PubMed Health

Results for “Feature selection”

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 199 records · Page 11Linked to original sources

PubMed1993

Comparison of spectral techniques for computer-assisted classification of spectra of heart sounds in patients with porcine bioprosthetic valves.

The diagnostic performance of two spectral techniques (the fast Fourier transform, FFT, and autoregressive modelling, ARM) combined with four windowing functions (rectangular, Hanning, Hamming, and sine-cosine) and two classifiers (Bayes and nearest neighbour) to detect valvular degeneration was evaluated in a group of 95 patients. Forty-seven patients had a porcine bioprosthetic valve inserted in the aortic position and 48 patients had a porcine bioprosthetic valve inserted in the mitral position. Among the aortic valves, 24 were normal and 23 were degenerated whereas among the mitral valves, 19 were normal and 29 were degenerated. The aortic and mitral valves were analysed separately. For each type of valve, 21 features were extracted from the spectra of the valve closure sounds to train and test the performance of four pattern recognition systems by using the leave-one-out method. The discriminant properties of all feature combinations between two and five among the 21 features selected were evaluated. Results show that the FFT combined to the nearest neighbour classifier provided the best performances: 87 per cent of correct classifications (CCs) for aortic valves when using the Hanning or the Hamming window and 94 per cent of CCs for mitral valves when using the rectangular window. The best performances obtained with the ARM were 81 per cent of CCs for the aortic valves (nearest neighbour classifier and the Hanning or the Hamming window) and 92 per cent of CCs for the mitral valves (nearest neighbour classifier and the Hamming window or the Bayes classifier and the Hanning or the Hamming window).

Aortic Valve↗

PubMedDate not supplied

Serum extravasation and cytoskeletal alterations following traumatic brain injury in rats. Comparison of lateral fluid percussion and cortical impact models.

Disruption of the blood-brain barrier (BBB) and neuronal cytoskeletal damage were evaluated in two commonly used rat models of traumatic brain injury. Adult rats received a lateral cortical impact (CI) or lateral fluid percussion (FP) injury of mild or moderate severity or a sham procedure. Six hours after trauma, the brains were removed and analyzed with immunocytochemical techniques for alterations in the serum protein, IgG, and the cytoskeletal protein, microtubule-associated protein 2 (MAP2). Both models induced profound alterations in these proteins in the ipsilateral cortex and hippocampus compared to sham-injured controls. Following an injury of moderate severity, the CI injury resulted in greater IgG extravasation in the cortex and hippocampus than the FP injury. Conversely, after a mild injury, IgG extravasation in the hippocampus was greater for FP than CI. All of the animals in the CI group and most of the FP group showed a loss of MAP2 in the hippocampus. The specific subregions within the cortex and hippocampus that were affected by the injury varied between models, despite having identical impact sites. These data demonstrate that there are both similarities and differences between a CI and FP injury on vascular and neuronal cystoskeletal integrity, which should be considered when utilizing these animal models to study selected features of human head injury.

Animals↗

PubMed2025

Digital Immunophenotyping of Lung Atypical Carcinoids and Large Cell Neuroendocrine Carcinomas Identifies Three Subtypes With Specific Tumor-Immune Microenvironment Features.

Atypical carcinoids (ACs) and large cell neuroendocrine carcinomas (LCNECs) are defined by the WHO as intermediate- and high-grade lung neuroendocrine neoplasms, respectively, based on morphological criteria; however, treatment strategies remain debated. Given the emerging role of the tumor microenvironment (TME) and tumor-infiltrating lymphocytes (TILs) in cancer prognosis and therapy response, this study aimed to characterize the immune landscape of ACs and LCNECs comprehensively. Immunohistochemistry for T-cell markers (CD3, CD8), immune checkpoints (PD-1, PD-L1), HLA molecules (HLA-DR, HLA-I), and fibroblasts (α-SMA) was performed on a re-evaluated cohort of 56 ACs and 104 LCNECs. Digital image analysis quantified intra-tumor (iTILs) and stromal (sTILs) CD3 and CD8 TILs in the whole slide and in specific tumor regions (invasive margin [IM] and central tumor [CT]). LCNECs exhibited significantly higher stromal T-cell infiltration, immune checkpoint expression, and HLA compared to ACs (p < 0.001), while α-SMA was more prominent in ACs. No ACs showed PD-L1 tumor expression. Digital quantification confirmed greater iTILs and sTILs in LCNECs across all regions, with moderate concordance to manual counts. Interestingly, TIL parameters were higher at the IM than in the CT (p < 0.001). Using Boruta feature selection algorithm, Principal Component Analysis and Hierarchical Clustering, three patient clusters were identified: Cluster 1 (mainly ACs, low TILs, favorable prognosis), Cluster 2 (mixed histology, intermediate TILs, moderate prognosis), and Cluster 3 (mostly LCNECs, high TILs, poor prognosis), with distinct TME marker profiles. PD-L1 tumor expression was strongly linked to Cluster 3. These findings suggest that ACs and LCNECs may be stratified into three distinct immune clusters, highlighting the heterogeneity of their tumor microenvironment and providing a rationale for further translational studies.

Humans↗

PubMed1992

On AR modelling for MEG spectral estimation, data compression and classification.

The use of the autoregressive (AR) model for magnetoencephalogram (MEG) processing is examined and compared to other methods. Spectral estimation, classification and data compression of MEG signals are studied. In application to spectral estimation the AR model is compared to the classical modified periodogram method. Also, AR modelling appears to perform very successfully when used for the classification of normal and epileptic MEG signals. Finally, the 17:1 to 23:1 data compression achieved by AR modelling, along with the above-mentioned advantages, render it suitable for storage applications. For comparison, the method of feature selection via orthogonal expansion is used as a tool to achieve data reduction. It is seen that while effective, this is less drastic than the compression of data volume achieved by AR modelling.

Brain Mapping↗

PubMed1976

Dynamic decision models for clinical diagnosis.

A unified approach to clinical decision-making is presented. This combines partially observable Markovian decision processes (Markov or semi-Markov) with cause-effect models as a probabilistic representation of the diagnostic process. Pattern recognition techniques are used in a first stage of system state identification. This new class of dynamic models has a direct application to medical diagnosis and treatment and specific physiological examples are emphasised. The methodology is given for combining the patient state of health, the clinician's state of knowledge of the cause-effect representation from the observation space (measurements), feature selection using pattern recognition techniques and, finally, the treatment decisions with which to restore the patient to a more desirable state of health. A cost functional for the decision process has then to be optimised according to some pre-assigned objective function (social return from the patient state of health or treatment cost for the patient), when the process has an infinite time horizon.

Computers↗

PubMed1985

Becoming a nurse: the ethical perspective.

This paper examines selected features of neophyte nursing students' approach to the moral dimension of their future practice. It argues that rapid changes in medical technology and in social perceptions of morality necessitate a critical examination of the content, sequence and methods of introductory ethics education in nursing. It suggests that greater emphasis should be placed upon individual moral development; and that Codes of Ethics and Bills of Rights should be presented as ideal statements, to serve as guides in assessing the ethical situation of the client. Some reactions of students are reported.

Curriculum↗

PubMed1988

Evoked potential estimates of the time course of adaptation and recovery to counterphase gratings.

Scalp-recorded evoked potentials (VEP) were sequentially sampled in humans during adaptation to and recovery from prolonged viewing of counterphase sinusoidal grating targets. The sum of the power at the first and second harmonics of the Fourier-transformed VEP components was found to decrease during adaptation and increase during recovery. Time constants (T) for the adaptation and recovery processes as estimated from exponential functions ranged from 2.9 to 19 sec, varying non-monotonically with the spatial frequency and contrast of the stimulus. The observed T values are shorter than those reported in psychophysical studies of adaptation but overlap estimates derived from single cell studies. An unexpected finding was the occurrence of a 3-6 sec delay in the appearance of the maximum VEP response after the onset of the adaptation stimulus. The delay occurred in all subjects and at all spatial frequencies when moderate to high adapting contrasts (e.g. greater than 0.2) were used. The data support a feature-selective, multi-channel lateral inhibitory model of spatial vision and suggest the presence of tonic inhibition between the channels.

Adaptation, Ocular↗

PubMed1993

Post-reactivation cocaine administration facilitates later acquisition of an avoidance response in rats.

We previously demonstrated that cocaine administered immediately prior to a reactivation episode comprised of re-exposure to selected features of the original fear-conditioning session alters subsequent memory retrieval or reconsolidation. In the present study we determined that, similar to pre-reactivation administration, post-reactivation administration of cocaine also alters memory retrieval or reorganization, as measured by subsequent conditioned performance. The dose-response function for this effect of cocaine was U-shaped; maximal enhancement of subsequent avoidance performance was produced by a 7.5 mg/kg i.p. dose of cocaine. Because a dose of lidocaine equimolar to the effective cocaine dose was found not to alter subsequent conditioned performance, the effect of cocaine on memory processing most likely is not attributable to its local anesthetic properties.

Anesthetics, Local↗

PubMed1986

BMDP program for piecewise linear regression.

Piecewise linear regression has potentially broad applications in medical data analysis as well as other types of regression. Various kinds of algorithms have been proposed for finding optimum piecewise linear regressions. This paper presents a BMDP program for obtaining near optimum piecewise linear regression equations. An idea intrinsic to the method is that restricting parameter space to a discrete set makes the difficult problems become standard problems. Any software having the variable selection feature in the multiple linear regression can be used to apply the method.

Computers↗

PubMedDate not supplied

Beneficial effects of nicotine administered prior to a delayed matching-to-sample task in young and aged monkeys.

Our earlier studies have demonstrated that administration of low micrograms/kg doses of nicotine to young adult monkeys prior to a delayed matching-to-sample (DMTS) task resulted in a centrally mediated improvement in performance of the task, particularly when delay intervals which most greatly challenged the animal's capabilities were involved. The present study confirmed these findings using a completely computer driven and automated procedure. In addition, performance on the DMTS was observed to be enhanced when animals were again tested 24 h after the dose of nicotine. Further analysis of the data indicated that the majority of enhancement to nicotine could be accounted for by a greatly increased performance at the least preferred stimulus color. Position preference (left vs. right stimulus) was not a factor in nicotine-induced enhancement. Two aged monkeys (34 years old Macaca mulatta) were significantly more difficult to train in the DMTS task and their longest delay capabilities were significantly shorter than the young animals (Macaca fascicularis). Nevertheless, the aged animals were essentially similar in most respects in their responses to nicotine administration. These data are consistent with a role for central nicotinic systems in memory performance and with the ability of nicotine to produce enhancement of selective features of mnemonic strategy in young and old monkeys. Furthermore, it is possible that either model, the aged animal, or the young animal stressed to his mnemonic capability may provide a good model for learning and memory disorders in humans.

Aging↗

PubMed1986

Lung collagen and elastin after ozone exposure in vitamin B-6-deficient rats.

The effects of vitamin B-6 deficiency and ozone exposure on selected features of connective tissue metabolism in lung were investigated in groups of weanling male rats fed one of three diets: B-6-supplemented, fed ad lib; B-6-deficient, fed ad lib; or B-6-supplemented, restricted to the food intake of deficient rats for 5 weeks. Also, perinatal rat pups were studied that were nursed from dams fed one of the 3 diets from parturition to day 15 of lactation. During the final week of each experiment, half of the rats in each of the groups were exposed to 0.64 ppm of ozone (23.5 h per day). The collagen and elastin content, collagen synthesis rate, total protein synthesis rate, and lysyloxidase activity of lungs were measured. Perinatal pups rendered vitamin B-6-deficient were particularly sensitive to ozone exposure (65% died as compared to fewer than 5% of the ad lib or food-restricted controls). When L-proline incorporation into collagen and total protein was investigated using lung minces, food restriction and B-6-deficiency resulted in about one-half the incorporation normally observed. Total lung lysyl oxidase activity was also decreased in B-6-deficient and food-restricted rats compared to B-6-supplemented rats fed ad lib. Exposure to ozone resulted in increased lysyl oxidase activity and collagen synthesis in lungs from B-6-supplemented rats, but such responses were not observed in B-6-deficient or food-restricted (FR) rats exposed to ozone.

Aging↗

PubMedDate not supplied

Skin cancer recognition by computer vision.

Automatic detection of several features characteristic of basal cell epitheliomas is described. The features selected for this feasibility study are semitranslucency, telangiectasia, ulcer, crust, and tumor border. Image processing methods used in this study include frequency analysis of the Fourier transform of the image, the Sun-Wee texture analysis algorithm, and several other image analysis techniques suitable for skin photographs. This image analysis software is designed for use with AI/DERM, an expert system that models diagnosis of skin tumors by dermatologists.

Basal Cell Carcinoma↗

PubMed1996

Sleep classification in infants by decision tree-based neural networks.

This paper presents an AI-based approach to automatic sleep stage scoring. The system TBNN (Tree-Based Neural Network) uses a decision-tree generator to provide knowledge that defines the architecture of a backpropagation neural network, including feature selection and initialisation of the weights. The case study reports a successful application to the data from polygraphic all-night sleep of 8 babies aged 6 months. The teaching input was provided by a medical expert in accordance with the rules of Guilleminault and Souquet. The performance of TBNN is compared with 5 other methods and the results are discussed.

Artificial Intelligence↗

PubMed2026

Applications of quantum AI in brain disorder diagnosis: A systematic review.

BACKGROUND AND OBJECTIVE: Brain disorder diagnosis and prediction remain challenging because neuroimaging, electrophysiological, behavioral, and multimodal data are high-dimensional, noisy, heterogeneous, and limited by small clinical cohorts. This systematic review synthesised applications of quantum artificial intelligence (QAI) for brain disorder diagnosis, prediction, detection, and monitoring. METHODS: Following PRISMA guidelines, studies published from 2016 to 13 January 2026 were retrieved from Scopus, Web of Science, and IEEE Xplore. After screening, 36 studies met the eligibility criteria and were qualitatively analysed according to disorder category, data modality, QAI method, implementation setting, validation strategy, and performance. RESULTS: At the broader disease-group level, neurodegenerative disorders were the most frequently investigated, followed by mental health and psychiatric disorders. At the individual level, Parkinson's disease and schizophrenia were the leading applications, followed by depression, anxiety, Alzheimer's disease, and stress-related tasks. MRI-based modalities were the most frequently used data source, followed by multimodal data and EEG. Methodologically, primary QAI approaches were dominated by quantum neural and QDL architectures, followed by quantum-inspired optimization or feature-selection methods and quantum-kernel/conventional QML classifiers. Qiskit/IBM Quantum and PennyLane were the most frequently reported quantum software frameworks. However, most studies relied on simulators, classical quantum-inspired implementations, or unclear implementation settings, with limited real-hardware evaluation. CONCLUSIONS: QAI shows emerging potential for brain disorder analysis, particularly through hybrid quantum-classical learning, quantum neural architectures, quantum-kernel methods, and quantum-inspired optimization. Nevertheless, current evidence remains preliminary and requires larger datasets, subject-level and external validation, fair classical benchmarking, noise-resilient circuits, real quantum hardware evaluation, explainability, and clinical validation.

Humans↗

PubMed2026

Development and validation of a comprehensive prognostic model for 28-day ICU mortality in non-traumatic subarachnoid hemorrhage: an analysis based on the MIMIC-IV database.

BACKGROUND: Due to the complex pathophysiology of non-traumatic subarachnoid hemorrhage (SAH), accurate risk prediction remains a challenge. Our aim is to develop and validate a comprehensive prognostic model that integrates demographic characteristics, vital signs, laboratory parameters, and more, to provide clinical decision-making support in real-world practice. METHODS: We conducted a retrospective cohort study of 785 Non-traumatic subarachnoid hemorrhage patients. The cohort was randomly divided into a training set (n = 549) and a validation set (n = 236). Feature selection was performed using LASSO regression, followed by backward stepwise Cox regression for optimization. A nomogram was constructed based on independent predictive factors, and model performance was assessed using discrimination, calibration, and decision curve analysis. To prevent immortal-time bias, all predictors were anchored to a fixed early (first-24-hour) measurement window, treatment variables were modelled as binary indicators rather than cumulative exposures, and a five-model sensitivity analysis with baseline-severity adjustment was performed. RESULTS: The development of our model followed a systematic approach: first, 15 potential predictive factors were selected via LASSO regression, which were then refined to 12 independent predictors using backward stepwise Cox regression. The final predictive factors included: Ventilation, AHT, Nimodipine 60 mg, Age, SAPS.II, Input amount, Calcium total, Platelet count, White blood cells, Anion gap, pH, and Chloride. The integrated model demonstrated excellent predictive ability for 7-day, 14-day, and 21-day mortality in both the training set (AUC: 0.972, 0.934, 0.898) and the validation set (AUC: 0.968, 0.948, 0.911). Calibration curves and decision curve analysis confirmed the model's reliability and clinical utility across different time points. We constructed a nomogram for individualized risk prediction. Univariate Kaplan-Meier survival analysis demonstrated significant stratification of survival outcomes by each predictor, while restricted cubic spline analysis revealed non-linear relationships between continuous variables and mortality risk. Random survival forest analysis identified the top three predictive factors (Nimodipine 60 mg, Ventilation, AHT) and compared them with our full 12-variable model, confirming superior performance of the integrated model at all time points. At the 28-day primary endpoint, the model achieved a time-dependent AUC of 0.898 (training) and 0.904 (validation); after restricting predictors to the early baseline window, the leakage-controlled model retained good discrimination (validation C-index 0.803). CONCLUSIONS: Our ICU 28-day mortality prognosis model demonstrated robust performance in predicting ICU 28-day mortality in non-traumatic subarachnoid hemorrhage. The model, through the nomogram, provides individualized risk assessment, aiding clinical decision-making and patient stratification.

Humans↗

PubMed2026

Integrated salivary proteomic and metabolomic analyses reveal molecular characterization and novel biomarker panels of chronic obstructive pulmonary disease.

Chronic obstructive pulmonary disease (COPD) is a respiratory disorder characterized by chronic inflammation, oxidative stress, and metabolic dysregulation. The lack of convenient and easily-accessible non-invasive diagnostic approaches remains a major clinical challenge. This study applied an integrated saliva-based proteomic and untargeted metabolomic strategy to identify potential biomarkers for COPD classification. Comprehensive multi-omics analyses identified 225 differentially abundant proteins and 60 differentially abundant metabolites between patients with COPD and healthy controls, including 24 biologically relevant endogenous metabolites. Functional enrichment analyses revealed pronounced dysregulation of mitochondrial energy metabolism, redox homeostasis, lipid remodeling, and inflammatory-related pathways in COPD. By integrating salivary proteomic and metabolomic biomarkers, a stepwise feature selection combined with LASSO logistic regression was used to construct diagnostic models, yielding an optimized biomarker panel consisting of 11 proteins and 2 endogenous metabolites. This integrated model achieved excellent diagnostic performance, with an area under the ROC curve of 0.96. Collectively, these findings demonstrate that integrated salivary proteomic and metabolomic profiling provides a robust, non-invasive approach for COPD classification and offers a promising foundation for the development of biosensor-based diagnostic platforms and early disease detection. SIGNIFICANCE: Chronic obstructive pulmonary disease (COPD) remains a major global health burden. Current diagnostic approaches rely largely on spirometry and clinical assessment, which are limited in sensitivity for early-stage disease and unsuitable for large-scale screening. This study employs an integrated saliva-based proteomic and metabolomic strategy to identify non-invasive biomarkers for COPD classification. Our findings reveal coordinated dysregulation of mitochondrial energy metabolism, redox homeostasis, and lipid remodeling in COPD, highlighting the interconnected roles of metabolic reprogramming, oxidative stress, and inflammation in disease pathophysiology. Notably, a robust diagnostic panel comprising 11 proteins and 2 endogenous metabolites was established, achieving excellent classification performance (AUC of 0.96). To our knowledge, the integrated application of salivary proteomics and metabolomics for COPD diagnosis remains largely unexplored, underscoring the significance and translational potential of our findings.

Humans↗

PubMed2026

Multiomics Integration Identifies a Molecular Subtype of Intrahepatic Cholangiocarcinoma With Enhanced Benefit From Adjuvant Therapy.

Intrahepatic cholangiocarcinoma (iCCA) is a molecularly heterogeneous liver cancer with a poor prognosis. Improved stratification is needed to guide postoperative therapy. In this study, we applied integrative multiomics analysis to classify iCCA and identify biomarkers predictive of adjuvant treatment benefit. Using publicly available datasets (including whole exome sequencing, RNA sequencing, proteomics, and phosphoproteomics from FU-iCCA cohort and a transcriptomic cohort GSE244807), we defined 3 robust molecular subtypes of iCCA. These subtypes exhibited distinct genomic alterations, pathway activation, and immune microenvironments, with significant differences in overall survival (OS). Through protein-protein interaction network analysis and consensus feature selection using 10 clustering algorithms, we prioritized 8 marker genes distinguishing the subtypes. A Cox proportional-hazards model constructed from these markers stratified patients into high- and low-risk groups. High-risk iCCA, characterized by elevated expression of markers such as CLDN18, MUC1, and MUC5AC, had significantly worse OS in the absence of adjuvant therapy. Notably, in an independent validation of 174 patients with iCCA who underwent resection (single-center cohort), high expression of any of these 3 markers were associated with markedly prolonged OS in patients who received adjuvant chemotherapy or chemoembolization, compared with those who did not. In contrast, marker-negative patients showed no clear benefit from adjuvant therapy. In conclusion, our multiomics approach identified a high-risk, mucin-enriched subtype of iCCA. CLDN18, MUC1, and MUC5AC emerge as candidate predictive biomarkers for adjuvant chemotherapy benefit in iCCA, warranting prospective validation to improve personalized postoperative management.

Humans↗

PubMed2026

Unveiling the power of TIIC: A prognostic tool for esophageal adenocarcinoma.

BACKGROUND: Esophageal adenocarcinoma (EAC) remains a lethal malignancy with limited prognostic tools for guiding immunotherapy. Tumor-infiltrating immune cells (TIICs) play a critical role in EAC prognosis and treatment response. METHODS: We integrated single-cell RNA sequencing and bulk transcriptome data from TCGA and GEO databases. TIIC-specific RNAs were identified via tissue specificity index calculation combined with machine learning feature selection. Twenty machine learning algorithms were benchmarked to construct an optimal TIIC signature score (TIIC-Score) based on the comprehensive C-index. Immunotherapy response, genomic mutation, and copy number variation were analyzed. Summary-data-based Mendelian randomization (SMR) and two-sample Mendelian randomization (MR) were performed to explore genetic associations. Core prognostic TIIC-related genes were functionally validated in esophageal cancer cell lines through loss-of-function assays. RESULTS: The TIIC-Score demonstrated robust prognostic value for 1-, 2-, and 3-year overall survival across multiple cohorts, outperforming 22 published models. High TIIC-Score was associated with poor survival and increased chromosomal instability. Mutation profiling revealed high frequencies of TP53 (78.2%), TTN (48.7%), and SYNE1 (30.8%). MR analysis identified a significant association between gastro-oesophageal reflux and EAC risk at SNP rs8130507. Functionally, CCNI was upregulated in esophageal cancer cells, and its knockdown suppressed malignant phenotypes while promoting apoptosis, supporting its pro-tumorigenic role. CONCLUSION: The TIIC-Score provides a novel prognostic framework for EAC that effectively stratifies patient risk and may help identify individuals most likely to benefit from immunotherapy.

Esophageal adenocarcinoma↗