Artif Intell Med - White box radial basis function classifiers with component selection for clinical prediction models.

Tópicos

{ model(2341) predict(2261) use(1141) }
{ featur(3375) classif(2383) classifi(1994) }
{ visual(1396) interact(850) tool(830) }
{ method(2212) result(1239) propos(1039) }
{ imag(1947) propos(1133) code(1026) }
{ case(1353) use(1143) diagnosi(1136) }
{ implement(1333) system(1263) develop(1122) }
{ network(2748) neural(1063) input(814) }
{ problem(2511) optim(1539) algorithm(950) }
{ can(981) present(881) function(850) }
{ patient(2315) diseas(1263) diabet(1191) }
{ learn(2355) train(1041) set(1003) }
{ howev(809) still(633) remain(590) }
{ process(1125) use(805) approach(778) }
{ measur(2081) correl(1212) valu(896) }
{ take(945) account(800) differ(722) }
{ care(1570) inform(1187) nurs(1089) }
{ perform(999) metric(946) measur(919) }
{ research(1085) discuss(1038) issu(1018) }
{ medic(1828) order(1363) alert(1069) }
{ activ(1452) weight(1219) physic(1104) }
{ method(1557) propos(1049) approach(1037) }
{ data(1714) softwar(1251) tool(1186) }
{ search(2224) databas(1162) retriev(909) }
{ compound(1573) activ(1297) structur(1058) }
{ model(3480) simul(1196) paramet(876) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ first(2504) two(1366) second(1323) }
{ structur(1116) can(940) graph(676) }
{ cancer(2502) breast(956) screen(824) }
{ use(976) code(926) identifi(902) }
{ model(3404) distribut(989) bayesian(671) }
{ method(1219) similar(1157) match(930) }
{ framework(1458) process(801) describ(734) }
{ concept(1167) ontolog(924) domain(897) }
{ clinic(1479) use(1117) guidelin(835) }
{ general(901) number(790) one(736) }
{ risk(3053) factor(974) diseas(938) }
{ studi(1119) effect(1106) posit(819) }
{ health(3367) inform(1360) care(1135) }
{ activ(1138) subject(705) human(624) }
{ use(1733) differ(960) four(931) }
{ decis(3086) make(1611) patient(1517) }
{ can(774) often(719) complex(702) }
{ data(1737) use(1416) pattern(1282) }
{ inform(2794) health(2639) internet(1427) }
{ system(1976) rule(880) can(841) }
{ imag(1057) registr(996) error(939) }
{ bind(1733) structur(1185) ligand(1036) }
{ sequenc(1873) structur(1644) protein(1328) }
{ imag(2830) propos(1344) filter(1198) }
{ imag(2675) segment(2577) method(1081) }
{ studi(2440) review(1878) systemat(933) }
{ motion(1329) object(1292) video(1091) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ error(1145) method(1030) estim(1020) }
{ chang(1828) time(1643) increas(1301) }
{ algorithm(1844) comput(1787) effici(935) }
{ extract(1171) text(1153) clinic(932) }
{ design(1359) user(1324) use(1319) }
{ control(1307) perform(991) simul(935) }
{ model(2220) cell(1177) simul(1124) }
{ method(984) reconstruct(947) comput(926) }
{ featur(1941) imag(1645) propos(1176) }
{ data(3963) clinic(1234) research(1004) }
{ studi(1410) differ(1259) use(1210) }
{ system(1050) medic(1026) inform(1018) }
{ import(1318) role(1303) understand(862) }
{ perform(1367) use(1326) method(1137) }
{ blood(1257) pressur(1144) flow(957) }
{ spatial(1525) area(1432) region(1030) }
{ record(1888) medic(1808) patient(1693) }
{ monitor(1329) mobil(1314) devic(1160) }
{ ehr(2073) health(1662) electron(1139) }
{ state(1844) use(1261) util(961) }
{ research(1218) medic(880) student(794) }
{ patient(2837) hospit(1953) medic(668) }
{ model(2656) set(1616) predict(1553) }
{ data(2317) use(1299) case(1017) }
{ age(1611) year(1155) adult(843) }
{ signal(2180) analysi(812) frequenc(800) }
{ sampl(1606) size(1419) use(1276) }
{ gene(2352) biolog(1181) express(1162) }
{ data(3008) multipl(1320) sourc(1022) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ use(2086) technolog(871) perceiv(783) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ high(1669) rate(1365) level(1280) }
{ drug(1928) target(777) effect(648) }
{ result(1111) use(1088) new(759) }
{ survey(1388) particip(1329) question(1065) }
{ estim(2440) model(1874) function(577) }
{ method(1969) cluster(1462) data(1082) }
{ detect(2391) sensit(1101) algorithm(908) }

Resumo

JECTIVE: To propose a new flexible and sparse classifier that results in interpretable decision support systems.METHODS: Support vector machines (SVMs) for classification are very powerful methods to obtain classifiers for complex problems. Although the performance of these methods is consistently high and non-linearities and interactions between variables can be handled efficiently when using non-linear kernels such as the radial basis function (RBF) kernel, their use in domains where interpretability is an issue is hampered by their lack of transparency. Many feature selection algorithms have been developed to allow for some interpretation but the impact of the different input variables on the prediction still remains unclear. Alternative models using additive kernels are restricted to main effects, reducing their usefulness in many applications. This paper proposes a new approach to expand the RBF kernel into interpretable and visualizable components, including main and two-way interaction effects. In order to obtain a sparse model representation, an iterative l1-regularized parametric model using the interpretable components as inputs is proposed.RESULTS: Results on toy problems illustrate the ability of the method to select the correct contributions and an improved performance over standard RBF classifiers in the presence of irrelevant input variables. For a 10-dimensional x-or problem, an SVM using the standard RBF kernel obtains an area under the receiver operating characteristic curve (AUC) of 0.947, whereas the proposed method achieves an AUC of 0.997. The latter additionally identifies the relevant components. In a second 10-dimensional artificial problem, the underlying class probability follows a logistic regression model. An SVM with the RBF kernel results in an AUC of 0.975, as apposed to 0.994 for the presented method. The proposed method is applied to two benchmark datasets: the Pima Indian diabetes and the Wisconsin Breast Cancer dataset. The AUC is in both cases comparable to those of the standard method (0.826 versus 0.826 and 0.990 versus 0.996) and those reported in the literature. The selected components are consistent with different approaches reported in other work. However, this method is able to visualize the effect of each of the components, allowing for interpretation of the learned logic by experts in the application domain.CONCLUSIONS: This work proposes a new method to obtain flexible and sparse risk prediction models. The proposed method performs as well as a support vector machine using the standard RBF kernel, but has the additional advantage that the resulting model can be interpreted by experts in the application domain.

Resumo Limpo

jectiv propos new flexibl spars classifi result interpret decis support systemsmethod support vector machin svms classif power method obtain classifi complex problem although perform method consist high nonlinear interact variabl can handl effici use nonlinear kernel radial basi function rbf kernel use domain interpret issu hamper lack transpar mani featur select algorithm develop allow interpret impact differ input variabl predict still remain unclear altern model use addit kernel restrict main effect reduc use mani applic paper propos new approach expand rbf kernel interpret visualiz compon includ main twoway interact effect order obtain spars model represent iter lregular parametr model use interpret compon input proposedresult result toy problem illustr abil method select correct contribut improv perform standard rbf classifi presenc irrelev input variabl dimension xor problem svm use standard rbf kernel obtain area receiv oper characterist curv auc wherea propos method achiev auc latter addit identifi relev compon second dimension artifici problem under class probabl follow logist regress model svm rbf kernel result auc appos present method propos method appli two benchmark dataset pima indian diabet wisconsin breast cancer dataset auc case compar standard method versus versus report literatur select compon consist differ approach report work howev method abl visual effect compon allow interpret learn logic expert applic domainconclus work propos new method obtain flexibl spars risk predict model propos method perform well support vector machin use standard rbf kernel addit advantag result model can interpret expert applic domain

Resumos Similares

Comput Methods Programs Biomed - Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines. ( 0,760191653423724 )
Comput Methods Programs Biomed - ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform. ( 0,721989334296452 )
BMC Med Inform Decis Mak - A three-step approach for the derivation and validation of high-performing predictive models using an operational dataset: congestive heart failure readmission case study. ( 0,693949813840835 )
IEEE J Biomed Health Inform - Classification of color images of dermatological ulcers. ( 0,690982364886723 )
Methods Inf Med - An experimental evaluation of boosting methods for classification. ( 0,686560054048806 )
Comput Methods Programs Biomed - Recurrence predictive models for patients with hepatocellular carcinoma after radiofrequency ablation using support vector machines with feature selection methods. ( 0,684166516594453 )
J Med Syst - Diagnosing breast masses in digital mammography using feature selection and ensemble methods. ( 0,678767428613273 )
AMIA Annu Symp Proc - Decision path models for patient-specific modeling of patient outcomes. ( 0,673230540201671 )
Comput. Biol. Med. - Pre-operative prediction of surgical morbidity in children: comparison of five statistical models. ( 0,666638471534239 )
IEEE Trans Vis Comput Graph - A Subdivision-Based Representation for Vector Image Editing. ( 0,663237695693794 )
Comput Methods Programs Biomed - Comparative evaluation of support vector machines for computer aided diagnosis of lung cancer in CT based on a multi-dimensional data set. ( 0,657055155801512 )
Comput Math Methods Med - An efficient diagnosis system for Parkinson's disease using kernel-based extreme learning machine with subtractive clustering features weighting approach. ( 0,653045671425993 )
J Am Med Inform Assoc - Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy. ( 0,643481054589997 )
J. Comput. Biol. - Prediction of siRNA potency using sparse logistic regression. ( 0,643194987788117 )
Comput Methods Programs Biomed - Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis. ( 0,643181861330138 )
J Biomed Inform - An empirical approach to model selection through validation for censored survival data. ( 0,640395237027436 )
J Med Syst - A new approach: role of data mining in prediction of survival of burn patients. ( 0,639980084233212 )
BMC Med Inform Decis Mak - Predicting disease risks from highly imbalanced data using random forest. ( 0,639515695790383 )
Comput Math Methods Med - Iterative reweighted noninteger norm regularizing SVM for gene expression data classification. ( 0,634646647034518 )
Comput. Biol. Med. - A modular approach to computer-aided auscultation: analysis and parametric characterization of murmur acoustic qualities. ( 0,633412678931883 )
IEEE J Biomed Health Inform - Novel fractal feature-based multiclass glaucoma detection and progression prediction. ( 0,630301551077356 )
Artif Intell Med - eXiT*CBR: A framework for case-based medical diagnosis development and experimentation. ( 0,627814844671409 )
BMC Med Inform Decis Mak - Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes. ( 0,626344344998023 )
AMIA Annu Symp Proc - Application of Bayesian logistic regression to mining biomedical data. ( 0,62205559186571 )
Med Decis Making - A comparison of methods for converting DCE values onto the full health-dead QALY scale. ( 0,620775354475302 )
Artif Intell Med - Improving the Mann-Whitney statistical test for feature selection: an approach in breast cancer diagnosis on mammography. ( 0,618608390411233 )
Comput Biol Chem - Using ensemble methods to deal with imbalanced data in predicting protein-protein interactions. ( 0,61745270208555 )
IEEE Trans Image Process - Efficient image classification via multiple rank regression. ( 0,616984518605833 )
J Digit Imaging - Computer-aided detection of architectural distortion in prior mammograms of interval cancer. ( 0,616183920495878 )
J Med Syst - An intelligent system for lung cancer diagnosis using a new genetic algorithm based feature selection method. ( 0,607198446018306 )
Comput. Biol. Med. - Breast-cancer identification using HMM-fuzzy approach. ( 0,605670827054657 )
J Biomed Inform - Statistical process control for validating a classification tree model for predicting mortality--a novel approach towards temporal validation. ( 0,604384085280829 )
IEEE J Biomed Health Inform - Computer-aided staging of lymphoma patients with FDG PET/CT imaging based on textural information. ( 0,60252514105416 )
Int J Med Inform - Artificial intelligence techniques applied to the development of a decision-support system for diagnosing celiac disease. ( 0,601842803163758 )
J Med Syst - A three-stage expert system based on support vector machines for thyroid disease diagnosis. ( 0,595617520761944 )
Comput Math Methods Med - Knee joint vibration signal analysis with matching pursuit decomposition and dynamic weighted classifier fusion. ( 0,59500308745354 )
J Med Syst - Comparison of artificial neural networks with logistic regression for detection of obesity. ( 0,59384726665822 )
J Am Med Inform Assoc - An improved model for predicting postoperative nausea and vomiting in ambulatory surgery patients using physician-modifiable risk factors. ( 0,593641652042269 )
J Am Med Inform Assoc - Word sense disambiguation in the clinical domain: a comparison of knowledge-rich and knowledge-poor unsupervised methods. ( 0,593084325300044 )
Comput Methods Programs Biomed - An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms. ( 0,592918798199959 )
Comput Biol Chem - newDNA-Prot: Prediction of DNA-binding proteins by employing support vector machine and a comprehensive sequence representation. ( 0,592902818465949 )
Neural Comput - An extension of the receiver operating characteristic curve and AUC-optimal classification. ( 0,591887106219916 )
Artif Intell Med - Comparative analysis of a-priori and a-posteriori dietary patterns using state-of-the-art classification algorithms: a case/case-control study. ( 0,589978851845064 )
Methods Inf Med - Classification of postural profiles among mouth-breathing children by learning vector quantization. ( 0,589475751912508 )
Comput Math Methods Med - Modified logistic regression models using gene coexpression and clinical features to predict prostate cancer progression. ( 0,58864804618391 )
Med Biol Eng Comput - Mortality prediction of rats in acute hemorrhagic shock using machine learning techniques. ( 0,58490501173539 )
BMC Med Inform Decis Mak - Artificial neural network models for prediction of cardiovascular autonomic dysfunction in general Chinese population. ( 0,580973767614899 )
AMIA Annu Symp Proc - Clinical risk prediction by exploring high-order feature correlations. ( 0,580027413055262 )
J Am Med Inform Assoc - Applying active learning to supervised word sense disambiguation in MEDLINE. ( 0,579293875458123 )
Comput. Biol. Med. - A knowledge-driven probabilistic framework for the prediction of protein-protein interaction networks. ( 0,578533592452378 )
Comput Methods Programs Biomed - Single stage and multistage classification models for the prediction of liver fibrosis degree in patients with chronic hepatitis C infection. ( 0,578250759587867 )
IEEE Trans Vis Comput Graph - The Generalized Sensitivity Scatterplot. ( 0,577493876809675 )
J Biomed Inform - Not just data: a method for improving prediction with knowledge. ( 0,577355672728566 )
J Med Syst - Effective automated prediction of vertebral column pathologies based on logistic model tree with SMOTE preprocessing. ( 0,577018069234741 )
Spat Spatiotemporal Epidemiol - Assessment of land use factors associated with dengue cases in Malaysia using Boosted Regression Trees. ( 0,575684941324585 )
J Biomed Inform - Boosting performance of gene mention tagging system by hybrid methods. ( 0,571998905916027 )
BMC Med Inform Decis Mak - Mining geriatric assessment data for in-patient fall prediction models and high-risk subgroups. ( 0,571563213027623 )
Artif Intell Med - Predicting the need for CT imaging in children with minor head injury using an ensemble of Naive Bayes classifiers. ( 0,568721066298198 )
J Med Syst - An integrated index for the identification of diabetic retinopathy stages using texture parameters. ( 0,568385727931148 )
J Am Med Inform Assoc - Computer-aided diagnosis of pneumonia in patients with chronic obstructive pulmonary disease. ( 0,566569825400187 )
BMC Med Inform Decis Mak - A novel differential diagnostic model based on multiple biological parameters for immunoglobulin A nephropathy. ( 0,566338372313869 )
Comput Math Methods Med - Determination of fetal state from cardiotocogram using LS-SVM with particle swarm optimization and binary decision tree. ( 0,566233444106757 )
Comput. Biol. Med. - Prediction of pre-miRNA with multiple stem-loops using pruning algorithm. ( 0,565816888021876 )
Comput Methods Programs Biomed - Computer-aided diagnosis of breast masses using quantified BI-RADS findings. ( 0,565252573445916 )
BMC Med Inform Decis Mak - Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning. ( 0,565192741804439 )
J Am Med Inform Assoc - A comparative analysis of methods for predicting clinical outcomes using high-dimensional genomic datasets. ( 0,565047396680653 )
Comput Methods Programs Biomed - Classification of normal and epileptic seizure EEG signals using wavelet transform, phase-space reconstruction, and Euclidean distance. ( 0,564114613328033 )
J Med Syst - Classification of normal and diseased liver shapes based on Spherical Harmonics coefficients. ( 0,564080476343341 )
J Chem Inf Model - Predictive toxicology modeling: protocols for exploring hERG classification and Tetrahymena pyriformis end point predictions. ( 0,563742074255039 )
Comput. Biol. Med. - Statistical model based 3D shape prediction of postoperative trunks for non-invasive scoliosis surgery planning. ( 0,563268563978332 )
J Med Syst - Applying cybernetic technology to diagnose human pulmonary sounds. ( 0,563045271229317 )
J Biomed Inform - Data mining methods for classification of Medium-Chain Acyl-CoA dehydrogenase deficiency (MCADD) using non-derivatized tandem MS neonatal screening data. ( 0,562567621082087 )
Appl Clin Inform - Comparing predictions made by a prediction model, clinical score, and physicians: pediatric asthma exacerbations in the emergency department. ( 0,560108747504236 )
Neural Comput - Adaptive classification on brain-computer interfaces using reinforcement signals. ( 0,559580914589575 )
Comput Methods Programs Biomed - Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering. ( 0,558362383953574 )
Comput Math Methods Med - SNP selection in genome-wide association studies via penalized support vector machine with MAX test. ( 0,555532018868772 )
IEEE Trans Vis Comput Graph - Beautification of Design Sketches Using Trainable Stroke Clustering and Curve Fitting. ( 0,555496014993417 )
Brief. Bioinformatics - Class-imbalanced classifiers for high-dimensional data. ( 0,554700006095813 )
Comput Math Methods Med - Multivoxel pattern analysis for FMRI data: a review. ( 0,553246674200371 )
BMC Med Inform Decis Mak - Evaluation of prediction models for the staging of prostate cancer. ( 0,55163220722259 )
J Biomed Inform - Partial least squares and logistic regression random-effects estimates for gene selection in supervised classification of gene expression data. ( 0,551367113795639 )
J Biomed Inform - Decision-making model for early diagnosis of congestive heart failure using rough set and decision tree approaches. ( 0,550716658990204 )
J Am Med Inform Assoc - Predicting complications of percutaneous coronary intervention using a novel support vector method. ( 0,550598840790143 )
AMIA Annu Symp Proc - Automatic annotation of radiological observations in liver CT images. ( 0,550502419012095 )
AMIA Annu Symp Proc - Predicting Surgical Risk: How Much Data is Enough? ( 0,549207380861417 )
Artif Intell Med - Instance-based classifiers applied to medical databases: diagnosis and knowledge extraction. ( 0,548807607841072 )
Brief. Bioinformatics - Caveats and pitfalls of ROC analysis in clinical microarray research (and how to avoid them). ( 0,548798052650228 )
J Med Syst - Support vector machine based diagnostic system for breast cancer using swarm intelligence. ( 0,548496403307172 )
IEEE Trans Image Process - Network-based H.264/AVC whole frame loss visibility model and frame dropping methods. ( 0,546899166318167 )
AMIA Annu Symp Proc - ICDA: a platform for Intelligent Care Delivery Analytics. ( 0,54678479962987 )
J Clin Monit Comput - Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery. ( 0,546304948741154 )
J Chem Inf Model - Two new parameters based on distances in a receiver operating characteristic chart for the selection of classification models. ( 0,545581232358769 )
Artif Intell Med - A modified artificial immune system based pattern recognition approach--an application to clinical diagnostics. ( 0,545395046992625 )
IEEE Trans Pattern Anal Mach Intell - The Spike-and-Slab RBM and Extensions to Discrete and Sparse Data Distributions. ( 0,544822991614894 )
J Biomed Inform - A medical diagnostic tool based on radial basis function classifiers and evolutionary simulated annealing. ( 0,544178153041881 )
J Med Syst - SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease. ( 0,543678798927928 )
Brief. Bioinformatics - Critical assessment of high-throughput standalone methods for secondary structure prediction. ( 0,542670143309097 )
Lifetime Data Anal - Understanding increments in model performance metrics. ( 0,542660386341903 )
J Am Med Inform Assoc - A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data. ( 0,542539718567808 )
Comput Methods Programs Biomed - Design of fuzzy classifier for diabetes disease using Modified Artificial Bee Colony algorithm. ( 0,541612270821373 )