Colorectal cancer remains a major health burden, and its early detection is crucial for effective treatment. This study investigates the use of a handheld Raman spectrometer in combination with machine learning to classify colorectal tissue samples collected during colonoscopy. A dataset of 330 spectra from 155 participants was preprocessed using a standardized pipeline, and multiple classification models were trained to distinguish between healthy and pathological tissue. Due to the strong class imbalance and limited data size, a custom grid search approach was implemented to optimize both model hyperparameters and preprocessing parameters. Unlike standard GridSearchCV, our method prioritized balanced accuracy on the test set to reduce bias toward the dominant class. Among the tested classifiers, the Decision Tree (DT) and Support Vector Classifier (SVC) achieved the highest balanced accuracy (71.77% for DT and 70.77% for SVC), outperforming models trained using traditional methods. These results demonstrate the potential of Raman spectroscopy as a rapid, non-destructive screening tool and highlight the importance of tailored model selection strategies in biomedical applications. While this study is based on a limited dataset, it serves as a promising step toward more robust classification models and supports the feasibility of this approach for future clinical validation.
- Keywords
- Balanced accuracy, Colorectal cancer, Machine learning, Preprocessing pipeline, Raman spectroscopy, Spectral classification,
- MeSH
- Colorectal Neoplasms * diagnosis diagnostic imaging MeSH
- Middle Aged MeSH
- Humans MeSH
- Spectrum Analysis, Raman * methods MeSH
- Decision Trees MeSH
- Machine Learning * MeSH
- Support Vector Machine MeSH
- Check Tag
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
Infertility has emerged as a significant public health concern, with assisted reproductive technology (ART) is a last-resort treatment option. However, ART's efficacy is limited by significant financial cost and physical discomfort. The aim of this study is to build Machine learning (ML) decision-support models to predict the optimal range of embryo numbers to transfer, using data from infertile couples identified through literature reviews. Binary classification models were developed to classify cases into two groups: those transferring two or fewer embryos and those transferring three or four. Four popular ML algorithms were used, including random forest (RF), logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN), considering seven criteria: the woman's age, sperm origin, the developmental qualities of four potential embryos, infertility duration, assessment of the woman, morphological qualities of the four best embryos on the day of transfer, and number of oocytes extracted. The stratified 3-fold cross-validation results show that the SVM model obtained the highest average accuracy (95.83%) and demonstrated the best overall performance, closely followed by the ANN and LR models with an average accuracy equal to 91.67%. The RF model achieved a slightly lower average accuracy (88.89%), which demonstrated the lowest variability. Testing on a new dataset revealed all models performed well, with ANN and SVM models classified all test set instances correctly, while the RF and LR models achieved 91.68% accuracy. These results highlight the superior generalization and effectiveness of the ANN and SVM models in guiding ART decisions.
- Keywords
- Artificial neural network, assisted reproductive technology, embryo transfer, infertility, multi-criteria decision aiding, number of embryos,
- MeSH
- Reproductive Techniques, Assisted * MeSH
- Adult MeSH
- Infertility * therapy MeSH
- Humans MeSH
- Neural Networks, Computer MeSH
- Embryo Transfer * MeSH
- Machine Learning * MeSH
- Support Vector Machine MeSH
- Pregnancy MeSH
- Check Tag
- Adult MeSH
- Humans MeSH
- Male MeSH
- Pregnancy MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
Crop classification during the early stages is challenging because of the striking similarity in spectral and texture features among various crops. To improve classification accuracy, this study proposes a novel fusion-based deep learning approach. The approach integrates textural and spectral features from a fused dataset generated by merging Landsat 8-9 and Sentinel-2A data using the Gram-Schmidt fusion approach. The textural features were extracted using the multi-patch Gray Level Co-occurrence Matrix (GLCM) technique. The spectral features, namely the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI), were obtained using the spectral index method. The five machine learning methods (deep neural network, 1D convolutional neural network, decision tree, support vector machine, and random forest) were trained using textural and spectral parameters to develop classifiers. The proposed approach achieves promising results using deep neural network (DNN), with an accuracy of 0.89, precision of 0.88, recall of 0.91, and F1-score of 0.90. These results demonstrate the effectiveness of the fusion-based deep learning approach in enhancing classification accuracy for early-stage crops.
- Keywords
- Crop classification, Deep learning, Early-stage crop, Feature integration, Image fusion, Multi-patch GLCM,
- MeSH
- Deep Learning MeSH
- Environmental Monitoring * methods MeSH
- Neural Networks, Computer MeSH
- Satellite Imagery * MeSH
- Machine Learning * MeSH
- Support Vector Machine MeSH
- Crops, Agricultural * classification growth & development MeSH
- Publication type
- Journal Article MeSH
Flow cytometry immunophenotyping is critical for the diagnostic classification of mature/peripheral B-cell neoplasms/B-cell chronic lymphoproliferative disorders (B-CLPD). Quantitative driven classification approaches applied to multiparameter flow cytometry immunophenotypic data can be used to extract maximum information from a multidimensional space created by individual parameters (e.g., immunophenotypic markers), for highly accurate and automated classification of individual patient (sample) data. Here, we developed and compared five diagnostic classification algorithms, based on a large set of EuroFlow multicentric flow cytometry data files from a cohort 659 B-CLPD patients. These included automatic population separators based on Principal Component Analysis (PCA), Canonical Variate Analysis (CVA), Neighbourhood Component Analysis (NCA), Support Vector Machine algorithms (SVM) and a variant of the CA(Canonical Analysis) algorithm, in which the number of SDs (Standard Deviations) varied for each of the comparisons of different pairs of diseases (CA-vSD). All five classification approaches are based on direct prospective interrogation of individual B-CLPD patients against the EuroFlow flow cytometry B-CLPD database composed of tumor B-cells of 659 individual patients stained in an identical way and classified a priori by the World Health Organization (WHO) criteria into nine diagnostic categories. Each classification approach was evaluated in parallel in terms of accuracy (% properly classified cases), precision (multiple or single diagnosis/case) and coverage (% cases with a proposed diagnosis). Overall, average rates of correct diagnosis (for the nine B-CLPD diagnostic entities) of between 58.9 % and 90.6 % were obtained with the five algorithms, with variable percentages of cases being either misclassified (4.1 %-14.0 %) or unclassifiable (0.3 %-37.0 %). Automatic population separators based on CA, SVM and PCA showed a high average level of correctness (90.6 %, 86.8 %, and 86.0 %, respectively). Nevertheless, this was at the expense of proposing a considerable number of multiple diagnoses for a significant proportion of the test cases (54.5 %, 53.5 %, and 49.6 %, respectively). The CA-vSD algorithm generated the smaller average misclassification rate (4.1 %), but with 37.0 % of cases for which no diagnosis was proposed. In contrast, the NCA algorithm left only 2.7 % of cases without an associated diagnosis but misclassified 14.0 %. Among correctly classified cases (83.3 % of total), 91.2 % had a single proposed diagnosis, 8.6 % had two possible diagnoses, and 0.2 % had three. We demonstrate that the proposed AI algorithms provide an acceptable level of accuracy for the diagnostic classification of B-CLPD patients and, in general, surpass other algorithms reported in the literature.
- MeSH
- Algorithms MeSH
- B-Lymphocytes * pathology MeSH
- Immunophenotyping * methods MeSH
- Middle Aged MeSH
- Humans MeSH
- Lymphoproliferative Disorders * diagnosis classification MeSH
- Flow Cytometry * methods MeSH
- Aged MeSH
- Support Vector Machine MeSH
- Check Tag
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Comparative Study MeSH
Accurate segmentation of biomedical time-series, such as intracardiac electrograms, is vital for understanding physiological states and supporting clinical interventions. Traditional rule-based and feature engineering approaches often struggle with complex clinical patterns and noise. Recent deep learning advancements offer solutions, showing various benefits and drawbacks in segmentation tasks. This study evaluates five segmentation algorithms, from traditional rule-based methods to advanced deep learning models, using a unique clinical dataset of intracardiac signals from 100 patients. We compared a rule-based method, a support vector machine (SVM), fully convolutional semantic neural network (UNet), region proposal network (Faster R-CNN), and recurrent neural network for electrocardiographic signals (DENS-ECG). Notably, Faster R-CNN has never been applied to 1D signals segmentation before. Each model underwent Bayesian optimization to minimize hyperparameter bias. Results indicated that deep learning models outperformed traditional methods, with UNet achieving the highest segmentation score of 88.9 % (root mean square errors for onset and offset of 8.43 ms and 7.49 ms), closely followed by DENS-ECG at 87.8 %. Faster R-CNN and SVM showed moderate performance, while the rule-based method had the lowest accuracy (77.7 %). UNet and DENS-ECG excelled in capturing detailed features and handling noise, highlighting their potential for clinical application. Despite greater computational demands, their superior performance and diagnostic potential support further exploration in biomedical time-series analysis.
- Keywords
- DENS-ECG, Electrophysiology Study, Faster R-CNN, Rule-based Delineation, Support Vector Machines, Time-series Segmentation, U-Net,
- MeSH
- Algorithms MeSH
- Bayes Theorem MeSH
- Deep Learning MeSH
- Electrocardiography * methods MeSH
- Humans MeSH
- Neural Networks, Computer MeSH
- Signal Processing, Computer-Assisted * MeSH
- Support Vector Machine MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
Long QT syndrome (LQTS) presents a group of inheritable channelopathies with prolonged ventricular repolarization, leading to syncope, ventricular tachycardia, and sudden death. Differentiating LQTS genotypes is crucial for targeted management and treatment, yet conventional genetic testing remains costly and time-consuming. This study aims to improve the distinction between LQTS genotypes, particularly LQT3, through a novel electrocardiogram (ECG)-based approach. Patients with LQT3 are at elevated risk due to arrhythmia triggers associated with rest and sleep. Employing a database of genotyped long QT syndrome E-HOL-03-0480-013 ECG signals, we introduced two innovative parameterization techniques-area under the ECG curve and wave transformation into the unit circle-to classify LQT3 against LQT1 and LQT2 genotypes. Our methodology utilized single-lead ECG data with a 200 Hz sampling frequency. The support vector machine (SVM) model demonstrated the ability to discriminate LQT3 with a recall of 90% and a precision of 81%, achieving an F1-score of 0.85. This parameterization offers a potential substitute for genetic testing and is practical for low frequencies. These single-lead ECG data could enhance smartwatches' functionality and similar cardiovascular monitoring applications. The results underscore the viability of ECG morphology-based genotype classification, promising a significant step towards streamlined diagnosis and improved patient care in LQTS.
- Keywords
- LQT3 discrimination, electrocardiogram classification, electrocardiogram parameterization, long QT syndrome, support vector machine classification,
- MeSH
- Adult MeSH
- Electrocardiography * methods MeSH
- Genotype MeSH
- Humans MeSH
- Machine Learning * MeSH
- Support Vector Machine MeSH
- Long QT Syndrome * genetics diagnosis physiopathology MeSH
- Check Tag
- Adult MeSH
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Comparative Study MeSH
Sensing rice drought stress is crucial for agriculture, and chlorophyll a fluorescence (ChlF) is often used. However, existing techniques usually rely on defined feature points on the OJIP induction curve, which ignores the rich physiological information in the entire curve. Independent Component Analysis (ICA) can effectively preserve independent features, making it suitable for capturing drought-induced physiological changes. This study applies ICA and Support Vector Machine (SVM) to classify drought levels using the entire OJIP curve. The results show that the 20-dimensional ChlF features obtained by ICA provide superior classification performance, with Accuracy, Precision, Recall, F1-score, and Kappa coefficient improving by 18.15%, 0.18, 0.17, 0.17, and 0.22, respectively, compared to the entire curve. This work provides a rice drought stress levels determination method and highlights the importance of applying dimension reduction methods for ChlF analysis. This work is expected to enhance stress detection using ChlF.
- Keywords
- chlorophyll a fluorescence, dimension reduction, drought, rice,
- MeSH
- Principal Component Analysis MeSH
- Chlorophyll A * metabolism MeSH
- Chlorophyll * metabolism MeSH
- Fluorescence MeSH
- Stress, Physiological * MeSH
- Droughts * MeSH
- Oryza * physiology metabolism MeSH
- Support Vector Machine MeSH
- Publication type
- Journal Article MeSH
- Names of Substances
- Chlorophyll A * MeSH
- Chlorophyll * MeSH
Early detection of malignant thyroid nodules is crucial for effective treatment, but traditional diagnostic methods face challenges such as variability in expert opinions and limited integration of advanced imaging techniques. This prospective cohort study investigates a novel multimodal approach, integrating traditional methods with advanced machine learning techniques. We studied 181 patients who underwent fine-needle aspiration (FNA) biopsy, each contributing one nodule, resulting in a total of 181 nodules for our analysis. Data collection included sex, age, and ultrasound imaging, which incorporated elastography. Features extracted from these images included Thyroid Imaging Reporting and Data System (TIRADS) scores, elastography parameters, and radiomic features. The pathological results based on the FNA biopsy, provided by the pathologists, served as our gold standard for nodule classification. Our methodology, termed ELTIRADS, combines these features with interpretable machine learning techniques. Performance evaluation showed that a Support Vector Machine (SVM) classifier using TIRADS, elastography data, and radiomic features achieved high accuracy (0.92), with sensitivity (0.89), specificity (0.94), precision (0.89), and F1 score (0.89). To enhance interpretability, we used hierarchical clustering, shapley additive explanations (SHAP), and partial dependence plots (PDP). This combined approach holds promise for enhancing the accuracy of thyroid nodule malignancy detection, thereby contributing to advancements in personalized and precision medicine in the field of thyroid cancer research.
- Keywords
- Elastography, Hierarchical clustering, Interpretable machine learning, Nodule classification, Radiomics,
- MeSH
- Adult MeSH
- Elasticity Imaging Techniques * methods MeSH
- Middle Aged MeSH
- Humans MeSH
- Thyroid Neoplasms diagnostic imaging pathology MeSH
- Prospective Studies MeSH
- Radiomics MeSH
- Aged MeSH
- Machine Learning * MeSH
- Support Vector Machine MeSH
- Biopsy, Fine-Needle MeSH
- Thyroid Nodule * diagnostic imaging classification pathology diagnosis MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
Lung carcinoma remains the leading cause of cancer death worldwide. The tactic to change this unfortunate rate may be a timely and rapid diagnostic, which may in many cases improve patient prognosis. In our study, we focus on the comparison of two novel methods of rapid lung carcinoma diagnostics, label-free in vivo and ex vivo Raman spectroscopy of the epithelial tissue, and assess their feasibility in clinical practice. As these techniques are sensitive not only to the basic molecular composition of the analyzed sample but also to the secondary structure of large biomolecules, such as tissue proteins, they represent suitable candidate methods for epithelial cancer diagnostics. During routine bronchoscopy, we collected 78 in vivo Raman spectra of normal and cancerous lung tissue and 37 samples of endobronchial pathologies, which were subsequently analyzed ex vivo. Using machine learning techniques, namely principal component analysis (PCA) and support vector machines (SVM), we were able to reach 87.2% (95% CI, 79.8-94.6%) and 100.0% (95% CI, 92.1-100.0%) of diagnostic accuracy for in vivo and ex vivo setup, respectively. Although the ex vivo approach provided superior results, the rapidity of in vivo Raman spectroscopy might become unmatchable in the acceleration of the diagnostic process.
- Keywords
- Endoscopy, Ex vivo diagnostics, In vivo diagnostics, Lung cancer, Machine learning, Optical biopsy, Raman spectroscopy,
- MeSH
- Principal Component Analysis * MeSH
- Middle Aged MeSH
- Humans MeSH
- Lung Neoplasms * diagnosis pathology MeSH
- Spectrum Analysis, Raman * methods MeSH
- Aged MeSH
- Support Vector Machine MeSH
- Check Tag
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
Individual physiotherapy is crucial in treating patients with various pain and health issues, and significantly impacts abdominal surgical outcomes and further medical problems. Recent technological and artificial intelligent advancements have equipped healthcare professionals with innovative tools, such as sensor systems and telemedicine equipment, offering groundbreaking opportunities to monitor and analyze patients' physical activity. This paper investigates the potential applications of mobile accelerometers in evaluating the symmetry of specific rehabilitation exercises using a dataset of 1280 tests on 16 individuals in the age range between 8 and 75 years. A comprehensive computational methodology is introduced, incorporating traditional digital signal processing, feature extraction in both time and transform domains, and advanced classification techniques. The study employs a range of machine learning methods, including support vector machines, Bayesian analysis, and neural networks, to evaluate the balance of various physical activities. The proposed approach achieved a high classification accuracy of 90.6% in distinguishing between left- and right-side motion patterns by employing features from both the time and frequency domains using a two-layer neural network. These findings demonstrate promising applications of precise monitoring of rehabilitation exercises to increase the probability of successful surgical recovery, highlighting the potential to significantly enhance patient care and treatment outcomes.
- Keywords
- abdominal wall repair, accelerometers, computational intelligence, machine learning, motion symmetry, physical activity monitoring, rehabilitation,
- MeSH
- Accelerometry * methods MeSH
- Bayes Theorem MeSH
- Exercise physiology MeSH
- Child MeSH
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Adolescent MeSH
- Young Adult MeSH
- Mobile Applications MeSH
- Neural Networks, Computer * MeSH
- Signal Processing, Computer-Assisted MeSH
- Aged MeSH
- Machine Learning MeSH
- Support Vector Machine MeSH
- Check Tag
- Child MeSH
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Adolescent MeSH
- Young Adult MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH