Radial Basis Function Support Vector Machine Research Articles

Machine learning approaches to debris flow susceptibility analyses in the Yunnan section of the Nujiang River Basin.

The Yunnan section of the Nujiang River (YNR) Basin in the alpine-valley area is one of the most critical areas of debris flow in China. We analyzed the applicability of three machine learning algorithms to model of susceptibility to debris flow-Random Forest (RF), the linear kernel support vector machine (Linear SVM), and the radial basis function support vector machine (RBFSVM)-and compared 20 factors to determine the dominant controlling in debris flow occurrence in the region. We found that (1) RF outperformed RBFSVM and Linear SVM in terms of accuracy, (2) topographic conditions were prerequisites, and geology, precipitation, vegetation, and anthropogenic influence were critical to forming debris flows. Also, the relative elevation difference was the most prominent evaluation factor of debris flow susceptibility, and (3) susceptibility maps based on RF's debris flow susceptibility (DFS) showed that zones with very high susceptibility were distributed along the mainstream of the Nujiang River. These findings provide methodological guidance and reference for improvement of DFS assessment. It enriches the content of DFS studies in the alpine-valley areas.

Support Vector Machine Approaches for Tumor Classification and Survival Prediction in Cancer Patients: A Multi-Omics Data Analysis

This study examines the viability of Support Vector Machine (SVM) calculations in tumour classification and survival forecast utilizing multi-omics information investigation in cancer patients. Leveraging a comprehensive dataset comprising genomic, transcriptomic, proteomic, and metabolomics profiles from assorted cancer sorts, we compared four SVM variations: Direct SVM, Polynomial SVM, Radial Basis Function (RBF) SVM, and Sigmoid SVM. Results illustrated that the RBF SVM calculation displayed predominant execution in tumour classification, accomplishing an exactness of 92%, with accuracy, review, and F1 score values of 91%, 94%, and 92% respectively. For survival forecast, the RBF SVM too beat other variations with a concordance file (C-Index) of 78%. These discoveries highlight the potential of SVM approaches in leveraging multi-omics information to move forward with cancer determination and forecast. Our consideration contributes to the developing body of research in machine learning-based cancer investigation and underscores the significance of coordination of different atomic datasets for personalized oncology.

Rapid and non-invasive detection of cystic echinococcosis in sheep based on serum fluorescence spectrum combined with machine learning algorithms.

Cystic echinococcosis (CE) is a grievous zoonotic parasitic disease. Currently, the traditional technology of screening CE is laborious and expensive, developing an innovative technology is urgent. In this study, we combined serum fluorescence spectroscopy with machine learning algorithms to develop an innovative screening technique to diagnose CE in sheep. Serum fluorescence spectra of Echinococcus granulosus sensu stricto-infected group (n = 63) and uninfected E. granulosus s.s. group (n = 60) under excitation at 405 nm were recorded. The linear support vector machine (Linear SVM), Quadratic SVM, medium radial basis function (RBF) SVM, K-nearest neighbor (KNN), and principal component analysis-linear discriminant analysis (PCA-LDA) were used to analyze the spectra data. The results showed that Quadratic SVM had the great classification capacity, its sensitivity, specificity, and accuracy were 85.0%, 93.8%, and 88.9%, respectively. In short, serum fluorescence spectroscopy combined with Quadratic SVM algorithm has great potential in the innovative diagnosis of CE in sheep.

Combination of spectral and textural features of hyperspectral imaging for the authentication of the diet supplied to fattening cattle

This study explored the potential of hyperspectral imaging in the near infrared region (NIR-HSI) as a non-destructive and rapid tool to discriminate among two beef fattening diets. For that purpose, a feeding trial was carried out with a total of 24 purebred Pirenaica calves. Twelve of them were fed barley and straw (BS) while 11 animals were finished on vegetable by-products (VBPR). When comparing the reference measurements of the meat coming from those animals, only the total collagen ratio expressed the feeding effect (p-value<0.05). To undertake the authentication procedure, two discrimination approaches were run: partial least squares discriminant analysis (PLS-DA) and radial basis function-support vector machine (RBF-SVM). To precisely extract spectral and textural information from the lean portion of the meat steaks, various techniques were executed, such as principal component (PC) images, competitive adaptive reweighted sampling (CARS) for selecting optimal wavelengths, and gray-level-co-occurrence matrix (GLCM). After hyperspectral imaging and the combination of their own texture features, samples were classified according to feeding diet with an overall accuracy of 72.92% for PLS-DA and 80.56% for RBF-SVM. So, the potential of using HSI technology to authenticate the meat obtained from beef supplied a diet based on circular economy techniques was made in evidence.

Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification.

The integration of artificial intelligence (AI) in diagnosing diabetic retinopathy, a major contributor to global vision impairment, is becoming increasingly pronounced. Notably, the detection of vision-threatening diabetic retinopathy (VTDR) has been significantly fortified through automated techniques. Traditionally, the reliance on manual analysis of retinal images, albeit slow and error-prone, constituted the conventional approach. Addressing this, our study introduces a novel methodology that amplifies the robustness and precision of the detection process. This is complemented by the groundbreaking Hierarchical Block Attention (HBA) and HBA-U-Net architecture, which notably propel attention mechanisms in image segmentation. This innovative model refines image processing without imposing excessive computational demands by honing in on individual pixel intricacies, spatial relationships, and channel-specific attention. Building upon this innovation, our proposed method employs a multi-stage strategy encompassing data pre-processing, feature extraction via a hybrid CNN-SVD model, and classification employing an amalgamation of Improved Support Vector Machine-Radial Basis Function (ISVM-RBF), DT, and KNN techniques. Rigorously tested on the IDRiD dataset classified into five severity tiers, the hybrid model yields remarkable performance, achieving a 99.18% accuracy, 98.15% sensitivity, and 100% specificity in VTDR detection, thus surpassing existing methods. These results underscore a more potent avenue for diagnosing and addressing this crucial ocular condition while underscoring AI's transformative potential in medical care, particularly in ophthalmology.

Comparing Texture Analysis of Apparent Diffusion Coefficient MRI in Hepatocellular Adenoma and Hepatocellular Carcinoma.

This study aimed to assess the effectiveness of using MRI-apparent diffusion coefficient (ADC) map-driven radiomics to differentiate between hepatocellular adenoma (HCA) and hepatocellular carcinoma (HCC) features. The study involved 55 patients with liver tumors (20 with HCA and 35 with HCC), featuring 106 lesions equally distributed between hepatic carcinoma and hepatic adenoma who underwent texture analysis on ADC map MR images. The analysis identified several imaging features that significantly differed between the HCA and HCC groups. Four classification models were compared for distinguishing HCA from HCC including linear support vector machine (linear-SVM), radial basis function SVM (RBF-SVM), random forest (RF), and k-nearest neighbor (KNN). The k-nearest neighbor (KNN) classifierdisplayed the top accuracy (0.89) and specificity (0.90). Linear-SVM and KNN classifiers showcased the leading sensitivity (0.88) for both, with the KNN classifier achieving the highest precision (0.9). In comparison, the conventional interpretation had lower sensitivity (70.1%) and specificity (77.9%). The study found that utilizing ADC maps for texture analysis in MR images is a viable method to differentiate HCA from HCC, yielding promising results in identified texture features.

Machine learning based on SEER database to predict distant metastasis of thyroid cancer.

Distant metastasis of thyroid cancer often indicates poor prognosis, and it is important to identify patients who have developed distant metastasis or are at high risk as early as possible. This paper aimed to predict distant metastasis of thyroid cancer through the construction of machine learning models to provide a reference for clinical diagnosis and treatment. Data on demographic and clinicopathological characteristics of thyroid cancer patients between 2010 and 2015 were extracted from the National Institutes of Health (NIH) Surveillance, Epidemiology, and End Results (SEER) database. Our research used univariate and multivariate logistic models to screen independent risk factors, respectively. Decision Trees (DT), ElasticNet (ENET), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Multilayer Perceptron (MLP), Radial Basis Function Support Vector Machine (RBFSVM) and seven machine learning models were compared and evaluated by the following metrics: the area under receiver operating characteristic curve (AUC), calibration curve, decision curve analysis (DCA), sensitivity(also called recall), specificity, precision, accuracy and F1 score. Interpretable machine learning was used to identify possible correlation between variables and distant metastasis. Independent risk factors for distant metastasis, including age, gender, race, marital status, histological type, capsular invasion, and number of lymph nodes metastases were screened by multifactorial regression analysis. Among the seven machine learning algorithms, RF was the best algorithm, with an AUC of 0.948, sensitivity of 0.919, accuracy of 0.845, and F1 score of 0.886 in the training set, and an AUC of 0.960, sensitivity of 0.929, accuracy of 0.906, and F1 score of 0.908 in the test set. The machine learning model constructed in this study helps in the early diagnosis of distant thyroid metastases and helps physicians to make better decisions and medical interventions.

Transfer-Ensemble Learning: A Novel Approach for Mapping Urban Land Use/Cover of the Indian Metropolitans

Land use and land cover (LULC) classification plays a significant role in the analysis of climate change, evidence-based policies, and urban and regional planning. For example, updated and detailed information on land use in urban areas is highly needed to monitor and evaluate urban development plans. Machine learning (ML) algorithms, and particularly ensemble ML models support transferability and efficiency in mapping land uses. Generalization, model consistency, and efficiency are essential requirements for implementing such algorithms. The transfer-ensemble learning approach is increasingly used due to its efficiency. However, it is rarely investigated for mapping complex urban LULC in Global South cities, such as India. The main objective of this study is to assess the performance of machine and ensemble-transfer learning algorithms to map the LULC of two metropolitan cities of India using Landsat 5 TM, 2011, and DMSP-OLS nightlight, 2013. This study used classical ML algorithms, such as Support Vector Machine-Radial Basis Function (SVM-RBF), SVM-Linear, and Random Forest (RF). A total of 480 samples were collected to classify six LULC types. The samples were split into training and validation sets with a 65:35 ratio for the training, parameter tuning, and validation of the ML algorithms. The result shows that RF has the highest accuracy (94.43%) of individual models, as compared to SVM-RBF (85.07%) and SVM-Linear (91.99%). Overall, the ensemble model-4 produces the highest accuracy (94.84%) compared to other ensemble models for the Kolkata metropolitan area. In transfer learning, the pre-trained ensemble model-4 achieved the highest accuracy (80.75%) compared to other pre-trained ensemble models for Delhi. This study provides innovative guidelines for selecting a robust ML algorithm to map urban LULC at the metropolitan scale to support urban sustainability.

Detection of Diabetes through Microarray Genes with Enhancement of Classifiers Performance.

Diabetes is a life-threatening, non-communicable disease. Diabetes mellitus is a prevalent chronic disease with a significant global impact. The timely detection of diabetes in patients is necessary for an effective treatment. The primary objective of this study is to propose a novel approach for identifying type II diabetes mellitus using microarray gene data. Specifically, our research focuses on the performance enhancement of methods for detecting diabetes. Four different Dimensionality Reduction techniques, Detrend Fluctuation Analysis (DFA), the Chi-square probability density function (Chi2pdf), the Firefly algorithm, and Cuckoo Search, are used to reduce high dimensional data. Metaheuristic algorithms like Particle Swarm Optimization (PSO) and Harmonic Search (HS) are used for feature selection. Seven classifiers, Non-Linear Regression (NLR), Linear Regression (LR), Logistics Regression (LoR), Gaussian Mixture Model (GMM), Bayesian Linear Discriminant Classifier (BLDC), Softmax Discriminant Classifier (SDC), and Support Vector Machine-Radial Basis Function (SVM-RBF), are utilized to classify the diabetic and non-diabetic classes. The classifiers' performances are analyzed through parameters such as accuracy, recall, precision, F1 score, error rate, Matthews Correlation Coefficient (MCC), Jaccard metric, and kappa. The SVM (RBF) classifier with the Chi2pdf Dimensionality Reduction technique with a PSO feature selection method attained a high accuracy of 91% with a Kappa of 0.7961, outperforming all of the other classifiers.

Classification of white blood cells based on modified U‐Net and SVM

SummaryManual investigation of blood cell count is sometimes erroneous due to interoperability error, fatigue error, requiring expert skill and time consuming too. In particular, investigation of white blood cell (WBC) gains importance in identifying diseases like leukemia, leukopenia, etc. WBC does not possess regular structure because they move throughout the blood stream and hence analyzing WBC and its types for structure and shape is quite challenging. To aid in hematology, this work provides classification of WBC classification based on modified U‐Net and support vector machines (SVM). A modified U‐Net architecture is developed to segment WBC followed by feature extraction and classification by radial basis function‐support vector machine (RBF‐SVM). Experiments indicated that the modified U Net segmentation can detect the WBC nucleus with a dice similarity coefficient of 0.972. The proposed U‐Net‐SVM can recognize WBCs in Raabin‐WBC, LISC, and BCCD datasets with an accuracy of 99.45%, 98.62%, and 98.81%, respectively. Further investigation on leukemia dataset, ALL‐IDB2, revealed an accuracy of 99.42% with 100% sensitivity and specificity. The proposed model can be used to investigate WBCs and hence provide a great support to the hematologists in analyzing the blood smear for various disease identifications.

FUEL INCREASE SENTIMENT ANALYSIS USING SUPPORT VECTOR MACHINE WITH PARTICLE SWARM OPTIMIZATION AND GENETIC ALGORITHM AS FEATURE SELECTION

BBM, or fuel oil, is one of the essential needs of the Indonesian people. The government's policy regarding the increase in fuel prices raises many opinions from the public. Twitter is one of the social media that Indonesian people often use to express opinions on a topic. In this study, sentiment analysis was carried out on public opinion regarding the fuel price increase policy from Twitter social media. This research is expected to help determine public opinion regarding the fuel price increase policy with positive, neutral and negative sentiments. The sentiment analysis method used is the Support Vector Machine (SVM) classification algorithm. The results of the accuracy of SVM were compared with accuracy by adding a feature selection process. The Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) algorithms are used for the feature selection method. After several experiments using the three methods, the SVM method with the Radial Basis Function (RBF) kernel produced the best accuracy of 71.2%. The combination of the SVM method with the RBF and PSO kernels obtained an accuracy of 68.84%, and the combination of the RBF and GA kernel SVM methods obtained an accuracy of 69.52%.

Sugarbeet Seed Germination Prediction Using Hyperspectral Imaging Information Fusion.

Germination rate is important for seed selection and planting and quality. In this study, hyperspectral image technology integrated with germination tests was applied for feature association analysis and germination performance prediction of sugarbeet seeds. In this study, we proposed a nondestructive prediction method for sugarbeet seed germination. Sugarbeet seed was studied, and hyperspectral imaging (HIS) performed by binarization, morphology, and contour extraction was applied as a nondestructive and accurate technique to achieve single seed image segmentation. Comparative analysis of nine spectral pretreatment methods, SNV + 1D was used to process the average spectrum of sugarbeet seeds. Fourteen characteristic wavelengths were obtained by the Kullback-Leibler (KL) divergence, as the spectral characteristics of sugarbeet seeds. Principal component analysis (PCA) and material properties verified the validity of the extracted characteristic wavelengths. It was extracted of six image features of the hyperspectral image of a single seed obtained based on the gray-level co-occurrence matrix (GLCM). The spectral features, image features, and fusion features were used to establish partial least squares discriminant analysis (PLS-DA), CatBoost, and support vector machine radial-basis function (SVM-RBF) models respectively to predict the germination. The results showed that the prediction effect of fusion features was better than spectral features and image features. By comparing other models, the prediction results of the CatBoost model accuracy were up to 93.52%. The results indicated that, based on HSI and fusion features, the prediction of germinating sugarbeet seeds was more accurate and nondestructive.

Prediction of dengue cases using the attention-based long short-term memory (LSTM) approach

This research proposes a 'temporal attention' addition for long-short term memory (LSTM) models for dengue prediction. The number of monthly dengue cases was collected for each of five Malaysian states i.e. Selangor, Kelantan, Johor, Pulau Pinang, and Melaka from 2011 to 2016. Climatic, demographic, geographic and temporal attributes were used as covariates. The proposed LSTM models with temporal attention was compared with several benchmark models including a linear support vector machine (LSVM), a radial basis function support vector machine (RBFSVM), a decision tree (DT), a shallow neural network (SANN) and a deep neural network (D-ANN). In addition, experiments were conducted to analyze the impact of look-back settings on each model performance. The results showed that the attention LSTM (A-LSTM) model performed best, with the stacked, attention LSTM (SA-LSTM) one in second place. The LSTM and stacked LSTM (S-LSTM) models performed almost identically but with the accuracy improved by the attention mechanism was added. Indeed, they were both found to be superior to the benchmark models mentioned above. The best results were obtained when all attributes were included in the model. The four models (LSTM, S-LSTM, A-LSTM and SA-LSTM) were able to accurately predict dengue presence 1-6 months ahead. Our findings provide a more accurate dengue prediction model than previously used, with the prospect of also applying this approach in other geographic areas.

IMPROVING DIGITAL SIGNATURE VERIFICATION ACCURACY THROUGH SUPPORT VECTOR MACHINE LEARNING: A COMPARATIVE STUDY

Digital signatures are widely used in electronic documents, and their verification is crucial to ensure document authenticity and security. However, digital signature verification can be challenging, especially when dealing with large amounts of data. In this paper, we present a comparative study of three Support Vector Machine (SVM) based methods for improving digital signature verification accuracy. We used a dataset of 10,000 digital signatures and compared the performance of linear SVM, polynomial SVM, and radial basis function (RBF) SVM. Our results showed that all three SVM-based methods improved the accuracy of digital signature verification compared to traditional methods. The RBF SVM method was found to be the most effective method for improving accuracy, with an accuracy of 98%.

Label-free surface-enhanced Raman spectroscopy of serum with machine-learning algorithms for gallbladder cancer diagnosis

Gallbladder cancer (GBC) is a rare but frequently fatal biliary tract malignancy that is typically discovered when it is already advanced. In this study, we investigated a novel technique for the quick and non-invasive diagnosis of GBC based on serum surface-enhanced Raman spectroscopy (SERS). SERS spectra of serum from 41 patients with GBC and 72 normal subjects were recorded. Principal component analysis-linear discriminant analysis (PCA-LDA), and PCA-support vector machine (PCA-SVM), Linear SVM and Gaussian radial basis function-SVM (RBF-SVM) algorithms were used to establish the classification models, respectively. When the Linear SVM was used, the overall diagnostic accuracy for classifying the two groups could achieve 97.1%, and when RBF-SVM was used, the diagnostic sensitivity of GBC was 100%. The results demonstrated that SERS combination with a machine learning algorithm is a promising candidate to be one of the diagnostic tools for GBC in the future.

Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices

Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, which can progress from simple steatosis to advanced cirrhosis and hepatocellular carcinoma. Clinical diagnosis of NAFLD is crucial in the early stages of the disease. The main aim of this study was to apply machine learning (ML) methods to identify significant classifiers of NAFLD using body composition and anthropometric variables. A cross-sectional study was carried out among 513 individuals aged 13 years old or above in Iran. Anthropometric and body composition measurements were performed manually using body composition analyzer InBody 270. Hepatic steatosis and fibrosis were determined using a Fibroscan. ML methods including k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Radial Basis Function (RBF) SVM, Gaussian Process (GP), Random Forest (RF), Neural Network (NN), Adaboost and Naïve Bayes were examined for model performance and to identify anthropometric and body composition predictors of fatty liver disease. RF generated the most accurate model for fatty liver (presence of any stage), steatosis stages and fibrosis stages with 82%, 52% and 57% accuracy, respectively. Abdomen circumference, waist circumference, chest circumference, trunk fat and body mass index were among the most important variables contributing to fatty liver disease. ML-based prediction of NAFLD using anthropometric and body composition data can assist clinicians in decision making. ML-based systems provide opportunities for NAFLD screening and early diagnosis, especially in population-level and remote areas.

Differentiation of NaCl, NaOH, and β-Phenylethylamine Using Ultraviolet Spectroscopy and Improved Adaptive Artificial Bee Colony Combined with BP-ANN Algorithm.

The aim of this study is to enhance the classification performance of the back-propagation-artificial neural network (BP-ANN) algorithm for NaCl, NaOH, β-phenylethylamine (PEA), and their mixture, as well as to avoid the defects of the artificial bee colony (ABC) algorithm such as prematurity and local optimization. In this paper, a method that combined an improved adaptive artificial bee colony (IAABC) algorithm and BP-ANN algorithm was proposed. This method improved the ABC algorithm by adding an adaptive local search factor and mutation factor; meanwhile, it can enhance the abilities of the global optimization and local search of the ABC algorithm and avoid prematurity. The extracted score vectors of the principal component of the ultraviolet (UV) spectrum were used as the input variable of the BP-ANN algorithm. The IAABC algorithm was used to optimize the weight and threshold of the BP-ANN algorithm, and the iterative algorithm was repeated until the output accuracy was reached. The output variable was the classification results of NaCl, NaOH, PEA, and the mixture. Meanwhile, the proposed IAABC-BP-ANN algorithm was compared with discriminant analysis (DA), sigmaid-support vector machine (SVM), radial basis function-SVM (RBF-SVM), BP-ANN, and ABC-BP-ANN. Then, the above algorithms were used to classify NaCl, NaOH, PEA, and the mixture, respectively. In the experiment, four indicators, accuracy, recall, precision, and F-score, were used as the evaluation criteria. In addition, the regression equation parameters of the mixture for the testing set were obtained by BP-ANN, ABC-BP-ANN, and IAABC-BP-ANN models. All of the results showed that IAABC-BP-ANN exhibits better performance than other algorithms. Therefore, IAABC-BP-ANN combined with UV spectroscopy is a potential identification tool for the detection of NaCl, NaOH, PEA, and the mixture.

Applying a nomogram based on preoperative CT to predict early recurrence of laryngeal squamous cell carcinoma after surgery.

To identify the value of a computed tomography (CT)-based radiomics model to predict probability of early recurrence (ER) in patients diagnosed with laryngeal squamous cell carcinoma (LSCC) after surgery. Pre-operative CT scans of 140 LSCC patients treated by surgery are reviewed and selected. These patients are randomly split into the training set (n = 97) and test set (n = 43). The regions of interest of each patient were delineated manually by two senior radiologists. Radiomics features are extracted from CT images acquired in non-enhanced, arterial, and venous phases. Variance threshold, one-way ANOVA, and least absolute shrinkage and selection operator algorithm are used for feature selection. Then, radiomics models are built with five algorithms namely, k-nearest neighbor (KNN), logistic regression (LR), linear support vector machine (LSVM), radial basis function SVM (RSVM), and polynomial SVM (PSVM). Clinical factors are selected using univariate and multivariate logistic regressions. Last, a radiomics nomogram incorporating the radiomics signature and clinical factors is built to predict ER and its efficiency is evaluated by receiver operating characteristic (ROC) curve and calibration curve. Decision curve analysis (DCA) is also used to evaluate clinical usefulness. Four features are remarkably associated with ER in patients with LSCC. Applying to test set, the area under the ROC curves (AUCs) of KNN, LR, LSVM, RSVM, and PSVM are 0.936, 0.855, 0.845, 0.829, and 0.794, respectively. The radiomics nomogram shows better discrimination (with AUC: 0.939, 95% CI: 0.867-0.989) than the best radiomics model and the clinical model. Predicted and actual ERs in the calibration curves are in good agreement. DCA shows that the radiomics nomogram is clinically useful. The radiomics nomogram, as a noninvasive prediction tool, exhibits favorable performance for ER prediction of LSCC patients after surgery.

Improved Parkinsonian tremor quantification based on automatic label modification and SVM with RBF kernel

Objective. The quantitative assessment of Parkinsonian tremor, e.g. (0, 1, 2, 3, 4) according to the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale, is crucial for treating Parkinson’s disease. However, the tremor amplitude constantly fluctuates due to environmental and psychological effects on the patient. In clinical practice, clinicians assess the tremor severity for a short duration, whereas manual tremor labeling relies on the clinician’s physician experience. Therefore, automatic tremor quantification based on wearable inertial sensors and machine learning algorithms is affected by the manual labels of clinicians. In this study, an automatic modification method for the labels judged by clinicians is presented to improve Parkinsonian tremor quantitation. Approach. For the severe overlapping of dynamic feature range between different severities, an outlier modification algorithm (PCA-IQR) based on the combination of principal component analysis and interquartile range statistic rule is proposed to learn the blurred borders between different severity scores, thereby optimizing the labels. Afterward, according to the modified feature vectors, a support vector machine (SVM) with a radial basis function (RBF) kernel is proposed to classify the tremor severity. The classifier models of SVM with RBF kernel, k-nearest neighbors, and SVM with the linear kernel are compared. Main results. Experimental results show that the proposed method has high classification performance and excellent model generalization ability for tremor quantitation (accuracy: 97.93%, precision: 97.96%, sensitivity: 97.93%, F1-score: 97.94%). Significance. The proposed method may not only provide valuable assistance for clinicians to assess the tremor severity accurately, but also provides self-monitoring for patients at home and improve the assessment skills of clinicians.

P264 Machine learning can accurately predict development of Inflammatory Bowel Disease

Abstract Background Prediction of inflammatory bowel disease (IBD) development is the subject of intense study. We have previously shown that significant changes occur in routine laboratory tests in the 5 years preceding IBD diagnosis. Using routinely collected laboratory results, we developed machine learning models to predict development of IBD. Methods We extracted data from the electronic medical records of Maccabi Health Services and included patients with IBD ≥ 16 years of age with a minimum of 5 years follow up and an age and sex matched healthy cohort. The outcome measured was entry into the IBD registry. The study population was split into training and validation cohorts and using laboratory values in the 5 years prior to IBD diagnosis as features, we assessed the performance of supervised learning models and performed interpretability analysis with unsupervised dimensionality reduction. Results 5643 patients with IBD and 17199 healthy people were included in this study. 3039 (53.8%) had Crohn’s disease (CD), 2322 (41.1%) ulcerative colitis (UC) and 282 (5%) indeterminate colitis. The mean age of the IBD and healthy cohorts at study inclusion was 39.3 ± 16.5 and 38.5 ± 15.6 years, respectively. Weighted nearest neighbour imputation was used to correct for data missingness. Unsupervised Uniform Manifold Approximation Projection dimensionality reduction correctly separated the cohort into healthy and IBD clusters (Figure 1A). Furthermore, this algorithm identified two distinct groups correlating to CD or UC diagnosis (Figure 1B). Supervised learning models, namely neural net (AUC 0.95), linear support vector machine (SVM) (AUC 0.93), radial basis function SVM (AUC 0.85) and logistic regression (AUC 0.93) models, accurately predicted IBD diagnosis (Figure 2). These models were repeated without C-reactive protein and the predictive value was not significantly changed. Moreover, we excluded data in the 2 years preceding IBD diagnosis to determine whether model performance was reduced and the predictive value remained the same. Interestingly, using only data from 3-5 years preceding IBD diagnosis, the model could better distinguish between CD and UC (Figure 3). Conclusion In this study, machine learning models could accurately predict a diagnosis of IBD using laboratory data from the 5 years preceding IBD diagnosis. Prospective studies are needed to test these models in a real world setting.