Establishment of a Lung Cancer Discriminative Model Based on an Optimized Support Vector Machine Algorithm and Study of Key Targets of Wogonin in Lung Cancer

An optimized support vector machine model was used to construct a lung cancer diagnosis model based on serological indicators, and a molecular regulation model of Wogonin, a component of Scutellaria baicalensis, was established. Serological indexes of patients were collected, the grid search method was used to identify the optimal penalty coefficient C and parameter g of the support vector machine model, and the benign and malignant auxiliary diagnosis model of isolated pulmonary nodules based on serological indicators was established. The regulatory network and key targets of Wogonin in lung cancer were analyzed by network pharmacology, and key targets were detected by western blot. The relationship between serological susceptibility genes and key targets of Wogonin was established, and the signaling pathway of Wogonin regulating lung cancer was constructed. After support vector machine parameter optimization (C = 90.597, g = 32), the accuracy of the model was 90.8333%, with nine false positives and two false negative cases. Ontology functional analysis of 67 common genes between Wogonin targets and lung cancer–related genes showed that the targets were associated with biological processes involved in peptidye-serine modification and regulation of protein kinase B signaling; cell components in the membrane raft and chromosomal region; and molecular function in protein serine/threonine kinase activity and heme binding. Kyoto Encyclopedia of Genes and Genomes analysis showed that the regulation pathways involved the PI3K-Akt signaling pathway, ERBB signaling pathway, and EGFR tyrosine kinase inhibitor resistance. In vitro analyses using lung cancer cells showed that Wogonin led to significantly increased levels of cleaved caspase-3 and Bad and significantly decreased Bcl-2 expression in a concentration-dependent manner. ErbB4 expression also significantly decreased in lung cancer cells after treatment with Wogonin. A regulatory network of Wogonin regulating lung cancer cell apoptosis was constructed, including the participation of serological susceptibility genes. There is a certain regulatory effect between the serological indexes that can be used in the diagnosis of lung cancer and the key targets of Chinese herbal medicine treatment of lung cancer, which provides a new idea for the diagnosis, treatment and prognosis of clinical lung cancer.

Application of Artificial Intelligence-Based Classifiers to Predict the Outcome Measures and Stone-Free Status Following Percutaneous Nephrolithotomy for Staghorn Calculi: Cross-Validation of Data and Estimation of Accuracy

Objective: To develop a decision support system (DSS) for the prediction of the postoperative outcome of a kidney stone treatment procedure, particularly percutaneous nephrolithotomy (PCNL) to serve as a promising tool to provide counseling before an operation. Materials and Methods: The overall procedure includes data collection and prediction model development. Pre-/postoperative variables of 100 patients with staghorn calculus, who underwent PCNL, were collected. For feature vector, variables and categories including patient history variables, kidney stone parameters, and laboratory data were considered. The prediction model was developed using machine learning techniques, which include dimensionality reduction and supervised classification. Multiple classifier scheme was used for prediction. The derived DSS was evaluated by running the leave-one-patient-out cross-validation approach on the data set. Results: The system provided favorable accuracy (81%) in predicting the outcome of a treatment procedure. Performance in predicting the stone-free rate with the Minimum Redundancy Maximum Relevance feature (MRMR) treatment extracting top 3 features using Random Forest (RF) was 67%, with MRMR treatment extracting top 5 features using RF was 63%, and with MRMR treatment extracting top 10 features using Decision Tree was 62%. The statistical significance using standard error between the best area under the curves (AUCs) obtained from the Linear Discriminant Analysis (LDA) and MRMR. The results obtained from the LDA approach (0.81 AUC) was statistically significant (p = 0.027, z = 2.21) from the MRMR (0.64 AUC) (p = 0.05). Conclusion: The promising results of the developed DSS could be used in assisting urologists to provide counseling, predict a surgical outcome, and ultimately choose an appropriate surgical treatment for removing kidney stones.

An artificial intelligence-based clinical decision support system for large kidney stone treatment

A decision support system (DSS) was developed to predict postoperative outcome of a kidney stone treatment procedure, particularly percutaneous nephrolithotomy (PCNL). The system can serve as a promising tool to provide counseling before an operation. The overall procedure includes data collection and prediction model development. Pre/postoperative variables of 254 patients were collected. For feature vector, we used 26 variables from three categories including patient history variables, kidney stone parameters, and laboratory data. The prediction model was developed using machine learning techniques, which includes dimensionality reduction and supervised classification. A novel method based on the combination of sequential forward selection and Fisher's discriminant analysis was developed to reduce the dimensionality of the feature space and to improve the performance of the system. Multiple classifier scheme was used for prediction. The derived DSS was evaluated by running leave-one-patient-out cross-validation approach on the dataset. The system provided favorable accuracy (94.8%) in predicting the outcome of a treatment procedure. The system also correctly estimated 85.2% of the cases that required stent placement after the removal of a stone. In predicting whether the patient might require a blood transfusion during the surgery or not, the system predicted 95.0% of the cases correctly. The results are promising and show that the developed DSS could be used in assisting urologists to provide counseling, predict a surgical outcome, and ultimately choose an appropriate surgical treatment for removing kidney stones.

Cross Comparison of Motor Unit Potential Features Used in EMG Signal Decomposition

Feature extraction is an important step of resolving an electromyographic (EMG) signal into its component motor unit potential trains, commonly known as EMG decomposition. Until now, different features have been used to represent motor unit potentials (MUPs) and improve decomposition processing time and accuracy, but a major limitation is that no systematic comparison of these features exists. In an EMG decomposition system, like any pattern recognition system, the features used for representing MUPs play an important role in the overall performance of the system. A cross comparison of the feature extraction methods used in EMG signal decomposition can assist in choosing the best features for representing MUPs and ultimately may improve EMG decomposition results. This paper presents a survey and cross comparison of these feature extraction methods. Decomposability index, classification accuracy of a -nearest neighbors classifier, and class-feature mutual information were employed for evaluating the discriminative power of various feature extraction techniques commonly used in the literature including time domain, morphological, frequency domain, and discrete wavelets. In terms of data, 45 simulated and 82 real EMG signals were used. Results showed that among time domain features, the first derivative of time samples exhibit the best separability. For morphological features, slope analysis provided the most discriminative power. Discrete Fourier transform coefficients offered the best separability among frequency domain features. However, neither morphological nor frequency domain techniques outperformed time domain features. The detail 4 coefficients in a discrete wavelets decomposition exceeded in evaluation measures when compared with other feature extraction techniques. Using principal component analysis slightly improved the results, but it is time consuming. Overall, considering computation time and discriminative ability, the first derivative of time samples might be efficient in representing MUPs in EMG decomposition and there is no need for sophisticated feature extraction methods.

Exact inter-discharge interval distribution of motor unit firing patterns with gamma model

Inter-discharge interval distribution modeling of the motor unit firing pattern plays an important role in electromyographic decomposition and the statistical analysis of firing patterns. When modeling firing patterns obtained from automatic procedures, false positives and false negatives can be taken into account to enhance performance in estimating firing pattern statistics. Available models of this type, however, are only approximate and use Gaussian distributions, which are not strictly suitable for modeling renewal point processes. In this paper, the theory of point processes is used to derive an exact solution to the distribution when a gamma distribution is used to model the physiological firing pattern. Besides being exact, the solution provides a way to model the skewness of the inter-discharge distribution, and this may make it possible to obtain a better fit with available experimental data. In order to demonstrate potential applications of the model, we use it to obtain a maximum likelihood estimator of firing pattern statistics. Our tests found this estimator to be reliable over a wide range of firing conditions, whether dealing with real or simulated firing patterns, the proposed solution had better agreement than other models.

Graphical Abstract

Inter-discharge interval distribution of motor unit firing patterns with detection errors

Inter-discharge interval (IDI) distribution analysis of motor unit firing patterns is a valuable tool in EMG decomposition and analysis. However, the firing pattern obtained by EMG decomposition may have detection errors: false positives (incorrectly classified firings) and false negatives (missed firings). In this paper, the mathematical derivation of an IDI distribution model that accommodates false positives and false negatives of the detection process is presented. An approximation of the general model to adapt to specific EMG decomposition conditions is also presented. To illustrate the usefulness of the model, the obtained distribution is used to derive the maximum likelihood estimates of the statistics of motor unit firing patterns, the IDI mean and standard deviation, and estimates of the false negative and false positive ratios. Results obtained from simulation experiments and tests with real motor unit firing patterns show an enhanced estimation performance when compared to previously available algorithms. Goodness-of-fit tests applied to estimations for real data corrupted with false positives showed that the model-driven estimations fitted the uncorrupted data better than EFE estimations: 82% versus 52% not rejectable, respectively, when false positives were about 10% of IDIs. With about 5% false positives, the not rejectable estimations were 85% versus 70%.

Transparent muscle characterization using quantitative electromyography: different binarization mappings

Evaluation of patients with suspected neuromuscular disorders is typically based on qualitative visual and auditory assessment of needle detected eletromyographic (EMG) signals; the resulting muscle characterization is subjective and highly dependent on the skill and experience of the examiner. Quantitative electromyography (QEMG) techniques were developed to extract motor unit potential trains (MUPTs) from needle detected EMG signals, and estimate features capturing motor unit potential (MUP) morphology and quantifying morphological consistency across MUPs belonging to the same MUPT. The aim of this study is to improve available methods for obtaining transparent muscle characterizations from features obtained using QEMG techniques. More specifically, we investigate the following. 1) Can the use of binarization mappings improve muscle categorization accuracies of transparent methods? 2) What are the appropriate binarization mappings in terms of accuracy and transparency? Results from four different sets of examined limb muscles (342 muscles in total) demonstrate that four out of the 10 investigated binarization mappings based on transparent characterization methods outperformed the multi-class characterizers based on Gaussian mixture models (GMM) and the corresponding binarization mappings based on GMM. This suggests that the use of an appropriate binarization mapping can overcome the decrease in categorization accuracy associated with quantizing MUPT features, which is necessary to obtain transparent characterizations. This performance gain can be attributed to the use of more relevant features and tuned quantization to obtain more specific binary characterizations.

Maximum likelihood estimation of motor unit firing pattern statistics

Estimation of motor unit firing pattern statistics is a valuable method in physiological studies and a key procedure in electromyographic (EMG) decomposition algorithms. However, if any firings within the pattern are undetected or missed during the decomposition process, the estimation procedure can be disrupted. In order to provide an optimal solution, we present a maximum likelihood estimator of EMG firing pattern statistics, taking into account that some firings may be undetected. A model of the inter-discharge interval (IDI) probability density function with missing firings has been employed to derive the maximum likelihood estimator of the mean and standard deviation of the IDIs. Actual calculation of the maximum likelihood solution has been obtained by means of numerical optimization. The proposed estimator has been evaluated and compared to other previously developed algorithms by means of simulation experiments and has been tested on real signals. The new estimator was found to be robust and reliable in diverse conditions: IDI distributions with a high coefficient of variance or considerable skewness. Moreover, the proposed estimator outperforms previous algorithms both in simulated and real conditions.

Decomposition of intramuscular EMG signals using a knowledge -based certainty classifier algorithm

An automated system for resolving an intramuscular electromyographic (EMG) signal into its constituent motor unit potential trains (MUPTs) is presented. The system is intended mainly for clinical applications where several physiological parameters for each motor unit (MU), such as the motor unit potential (MUP) template and mean firing rate, are required. The system decomposes an EMG signal off-line by filtering the signal, detecting MUPs, and then grouping the detected MUPs using a clustering and a supervised classification algorithm. Both the clustering and supervised classification algorithms use MUP shape and MU firing pattern information to group MUPs into several MUPTs. Clustering is partially based on the K-means clustering algorithm. Supervised classification is implemented using a certainty-based classifier technique that employs a knowledge-based system to merge trains, detect and correct invalid trains, as well as adjust the assignment threshold for each train. The accuracy (93.2%±5.5%), assignment rate (93.9%±2.6%), and error in estimating the number of MUPTs (0.3±0.5) achieved for 10 simulated EMG signals comprised of 3-11 MUPTs are encouraging for using the system for decomposing various EMG signals.

Prediction of lung tumor types based on protein attributes by machine learning algorithms

Early diagnosis of lung cancers and distinction between the tumor types (Small Cell Lung Cancer (SCLC) and Non-Small Cell Lung Cancer (NSCLC) are very important to increase the survival rate of patients. Herein, we propose a diagnostic system based on sequence-derived structural and physicochemical attributes of proteins that involved in both types of tumors via feature extraction, feature selection and prediction models. 1497 proteins attributes computed and important features selected by 12 attribute weighting models and finally machine learning models consist of seven SVM models, three ANN models and two NB models applied on original database and newly created ones from attribute weighting models; models accuracies calculated through 10-fold cross and wrapper validation (just for SVM algorithms). In line with our previous findings, dipeptide composition, autocorrelation and distribution descriptor were the most important protein features selected by bioinformatics tools. The algorithms performances in lung cancer tumor type prediction increased when they applied on datasets created by attribute weighting models rather than original dataset. Wrapper-Validation performed better than X-Validation; the best cancer type prediction resulted from SVM and SVM Linear models (82%). The best accuracy of ANN gained when Neural Net model applied on SVM dataset (88%). This is the first report suggesting that the combination of protein features and attribute weighting models with machine learning algorithms can be effectively used to predict the type of lung cancer tumors (SCLC and NSCLC).

EMG signal decomposition using motor unit potential train validity

A system to resolve an intramuscular electromyographic (EMG) signal into its component motor unit potential trains (MUPTs) is presented. The system is intended mainly for clinical applications where several physiological parameters of motor units (MUs), such as their motor unit potential (MUP) templates and mean firing rates, are of interest. The system filters an EMG signal, detects MUPs, and clusters and classifies the detected MUPs into MUPTs. Clustering is partially based on the K-means algorithm, and the supervised classification is implemented using a certainty-based algorithm. Both clustering and supervised classification algorithms use MUP shape and MU firing pattern information along with signal dependent assignment criteria to obtain robust performance across a variety of EMG signals. During classification, the validity of extracted MUPTs are determined using several supervised classifiers; invalid trains are corrected and the assignment threshold for each train is adjusted based on the estimated validity (i.e., adaptive classification). Performance of the developed system in terms of accuracy (A(c)), assignment rate (A(r)), correct classification rate (CC(r)) , and the error in estimating the number of MUPTs represented in the set of detected MUPs (E(NMUPTs)) was evaluated using 32 simulated and 30 real EMG signals comprised of 3-11 and 3-15 MUPTs, respectively. The developed system, with average CC(r) of 86.4% for simulated and 96.4% for real data, outperformed a previously developed EMG decomposition system, with average CC(r) of 71.6% and 89.7% for simulated and real data, by 14.7% and 6.7%, respectively. In terms of E(NMUPTs), the new system, with average E(NMUPTs) of 0.3 and 0.2 for simulated and real data respectively, was better able to estimate the number of MUPTs represented in a set of detected MUPs than the previous system, with average E(NMUPTs) of 2.2 and 0.8 for simulated and real data respectively. For both the simulated and real data used, variations in A(c), A(r), and E(NMUPTs) for the newly developed system were lower than for the previous system, which demonstrates that the new system can successfully adjust the assignment criteria based on the characteristics of a given signal to achieve robust performance across a wide variety of EMG signals, which is of paramount importance for successfully promoting the clinical application of EMG signal decomposition techniques.