Artif Intell Med - Cost-sensitive case-based reasoning using a genetic algorithm: application to medical diagnosis.

Tópicos

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

Resumo

JECTIVE: The paper studies the new learning technique called cost-sensitive case-based reasoning (CSCBR) incorporating unequal misclassification cost into CBR model. Conventional CBR is now considered as a suitable technique for diagnosis, prognosis and prescription in medicine. However it lacks the ability to reflect asymmetric misclassification and often assumes that the cost of a positive diagnosis (an illness) as a negative one (no illness) is the same with that of the opposite situation. Thus, the objective of this research is to overcome the limitation of conventional CBR and encourage applying CBR to many real world medical cases associated with costs of asymmetric misclassification errors.METHODS: The main idea involves adjusting the optimal cut-off classification point for classifying the absence or presence of diseases and the cut-off distance point for selecting optimal neighbors within search spaces based on similarity distribution. These steps are dynamically adapted to new target cases using a genetic algorithm. We apply this proposed method to five real medical datasets and compare the results with two other cost-sensitive learning methods-C5.0 and CART.RESULTS: Our finding shows that the total misclassification cost of CSCBR is lower than other cost-sensitive methods in many cases. Even though the genetic algorithm has limitations in terms of unstable results and over-fitting training data, CSCBR results with GA are better overall than those of other methods. Also the paired t-test results indicate that the total misclassification cost of CSCBR is significantly less than C5.0 and CART for several datasets.CONCLUSION: We have proposed a new CBR method called cost-sensitive case-based reasoning (CSCBR) that can incorporate unequal misclassification costs into CBR and optimize the number of neighbors dynamically using a genetic algorithm. It is meaningful not only for introducing the concept of cost-sensitive learning to CBR, but also for encouraging the use of CBR in the medical area. The result shows that the total misclassification costs of CSCBR do not increase in arithmetic progression as the cost of false absence increases arithmetically, thus it is cost-sensitive. We also show that total misclassification costs of CSCBR are the lowest among all methods in four datasets out of five and the result is statistically significant in many cases. The limitation of our proposed CSCBR is confined to classify binary cases for minimizing misclassification cost because our proposed CSCBR is originally designed to classify binary case. Our future work extends this method for multi-classification which can classify more than two groups.

Resumo Limpo

jectiv paper studi new learn techniqu call costsensit casebas reason cscbr incorpor unequ misclassif cost cbr model convent cbr now consid suitabl techniqu diagnosi prognosi prescript medicin howev lack abil reflect asymmetr misclassif often assum cost posit diagnosi ill negat one ill opposit situat thus object research overcom limit convent cbr encourag appli cbr mani real world medic case associ cost asymmetr misclassif errorsmethod main idea involv adjust optim cutoff classif point classifi absenc presenc diseas cutoff distanc point select optim neighbor within search space base similar distribut step dynam adapt new target case use genet algorithm appli propos method five real medic dataset compar result two costsensit learn methodsc cartresult find show total misclassif cost cscbr lower costsensit method mani case even though genet algorithm limit term unstabl result overfit train data cscbr result ga better overal method also pair ttest result indic total misclassif cost cscbr signific less c cart sever datasetsconclus propos new cbr method call costsensit casebas reason cscbr can incorpor unequ misclassif cost cbr optim number neighbor dynam use genet algorithm meaning introduc concept costsensit learn cbr also encourag use cbr medic area result show total misclassif cost cscbr increas arithmet progress cost fals absenc increas arithmet thus costsensit also show total misclassif cost cscbr lowest among method four dataset five result statist signific mani case limit propos cscbr confin classifi binari case minim misclassif cost propos cscbr origin design classifi binari case futur work extend method multiclassif can classifi two group

Resumos Similares

IEEE Trans Image Process - Flexible Image Similarity Computation Using Hyper-Spatial Matching. ( 0,606618073890257 )
IEEE Trans Neural Netw Learn Syst - Discriminative embedded clustering: a framework for grouping high-dimensional data. ( 0,593202024323391 )
Methods Inf Med - The evolution of boosting algorithms. From machine learning to statistical modelling. ( 0,569766624250587 )
Artif Intell Med - Improved cosine similarity measures of simplified neutrosophic sets for medical diagnoses. ( 0,561565815507557 )
IEEE Trans Pattern Anal Mach Intell - Exemplar-Based Colour Constancy and Multiple Illumination. ( 0,556893683003723 )
Neural Comput - Deep, big, simple neural nets for handwritten digit recognition. ( 0,555225232023058 )
Med Decis Making - How much should we pay for a new HIV diagnosis? A mathematical model of HIV screening in US clinical settings. ( 0,555205947079045 )
IEEE Trans Image Process - Transferring boosted detectors towards viewpoint and scene adaptiveness. ( 0,55120191496041 )
Comput Methods Programs Biomed - Evaluation of different distortion correction methods and interpolation techniques for an automated classification of celiac disease. ( 0,53992367780316 )
Comput Methods Programs Biomed - Computer-aided diagnosis system: a Bayesian hybrid classification method. ( 0,533831087920305 )
IEEE Trans Neural Netw Learn Syst - Incremental Generalized Discriminative Common Vectors for Image Classification. ( 0,532504997889465 )
IEEE Trans Pattern Anal Mach Intell - Joint Histogram Based Cost Aggregation for Stereo Matching. ( 0,532428165526886 )
Comput. Biol. Med. - Hangman BCI: an unsupervised adaptive self-paced Brain-Computer Interface for playing games. ( 0,524221162005712 )
IEEE Trans Image Process - Multiple-kernel, multiple-instance similarity features for efficient visual object detection. ( 0,523425829890483 )
Comput Math Methods Med - Energy preserved sampling for compressed sensing MRI. ( 0,521785786594334 )
J. Comput. Biol. - Optimization of combinatorial mutagenesis. ( 0,521597147771711 )
Artif Intell Med - Evolving fuzzy medical diagnosis of Pima Indians diabetes and of dermatological diseases. ( 0,520600291420034 )
Comput. Biol. Med. - A bilateral analysis scheme for false positive reduction in mammogram mass detection. ( 0,519368511386394 )
J Chem Inf Model - Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. ( 0,518560337848519 )
Artif Intell Med - Automatic classification of epilepsy types using ontology-based and genetics-based machine learning. ( 0,516757624013444 )
Med Biol Eng Comput - Probabilistic neural network approach for the detection of SAHS from overnight pulse oximetry. ( 0,515412495060124 )
Artif Intell Med - Multi-marker tagging single nucleotide polymorphism selection using estimation of distribution algorithms. ( 0,513973698582195 )
Int J Neural Syst - Aggregation of sparse linear discriminant analyses for event-related potential classification in brain-computer interface. ( 0,512934791480752 )
J Med Syst - Cost and performance: complements for improvement. ( 0,511747847784382 )
IEEE Trans Image Process - Reducing the complexity of the N-FINDR algorithm for hyperspectral image analysis. ( 0,511317796381927 )
IEEE J Biomed Health Inform - Multiple kernel learning in the primal for multimodal Alzheimer's disease classification. ( 0,510861735829652 )
Comput Methods Programs Biomed - Hybridization between multi-objective genetic algorithm and support vector machine for feature selection in walker-assisted gait. ( 0,510124854347917 )
J Telemed Telecare - Cost-utility analysis of a telehealth programme for patients with severe chronic obstructive pulmonary disease treated with long-term oxygen therapy. ( 0,509783317645493 )
IEEE Trans Image Process - Label transfer by measuring compactness. ( 0,505925504518686 )
J Biomed Inform - A medical diagnostic tool based on radial basis function classifiers and evolutionary simulated annealing. ( 0,503910980578714 )
J Integr Bioinform - Towards a classification approach using meta-biclustering: impact of discretization in the analysis of expression time series. ( 0,50373946460238 )
Comput Math Methods Med - Mixed-norm regularization for brain decoding. ( 0,502166050634005 )
Med Biol Eng Comput - Extended Gabor approach applied to classification of emphysematous patterns in computed tomography. ( 0,501314551539082 )
Artif Intell Med - A multi-module case-based biofeedback system for stress treatment. ( 0,499964437002137 )
J Biomed Inform - Learning Bayesian networks for clinical time series analysis. ( 0,498922180251187 )
IEEE Trans Image Process - User-assisted ink-bleed reduction. ( 0,497907362396624 )
IEEE Trans Image Process - Decomposition-based transfer distance metric learning for image classification. ( 0,497695969758168 )
Artif Intell Med - A decision support system for cost-effective diagnosis. ( 0,497515404565407 )
J Biomed Inform - Evaluation of matched control algorithms in EHR-based phenotyping studies: a case study of inflammatory bowel disease comorbidities. ( 0,49571105299464 )
J Chem Inf Model - Large-scale learning of structure-activity relationships using a linear support vector machine and problem-specific metrics. ( 0,495367196392431 )
Artif Intell Med - An implicit approach to deal with periodically repeated medical data. ( 0,493621490481893 )
Comput. Biol. Med. - Fractal features for localization of temporal lobe epileptic foci using SPECT imaging. ( 0,492352996020025 )
Med Decis Making - Simulation of quality-adjusted survival in chronic diseases: an application in type 2 diabetes. ( 0,491689669345842 )
J Chem Inf Model - Classifying large chemical data sets: using a regularized potential function method. ( 0,490535667026609 )
J Am Med Inform Assoc - Missing values in deduplication of electronic patient data. ( 0,489563978615079 )
J Biomed Inform - Implementing ReliefF filters to extract meaningful features from genetic lifetime datasets. ( 0,488843420353503 )
IEEE Trans Image Process - Shape-based normalized cuts using spectral relaxation for biomedical segmentation. ( 0,488482317465184 )
Int J Med Robot - Robotic system with sweeping palpation and needle biopsy for prostate cancer diagnosis. ( 0,487012949828869 )
J. Comput. Biol. - Phylogeny construction with rigid gapped motifs. ( 0,486053579764545 )
Comput Methods Programs Biomed - Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering. ( 0,485650230105035 )
Med Decis Making - Societal preferences for distributive justice in the allocation of health care resources: a latent class discrete choice experiment. ( 0,484762906113673 )
Neural Comput - Refined rademacher chaos complexity bounds with applications to the multikernel learning problem. ( 0,484468101212371 )
J Am Med Inform Assoc - Cost-effectiveness of a shared computerized decision support system for diabetes linked to electronic medical records. ( 0,483165364265452 )
Comput. Biol. Med. - Modeling and prediction of peptide drift times in ion mobility spectrometry using sequence-based and structure-based approaches. ( 0,481957997853834 )
Neural Comput - Divergence-based vector quantization. ( 0,481542386139608 )
Comput. Biol. Med. - Identification of epilepsy stages from ECoG using genetic programming classifiers. ( 0,480799962284027 )
Med Decis Making - Nutritional policy changes in the supplemental nutrition assistance program: a microsimulation and cost-effectiveness analysis. ( 0,480651564277943 )
Comput. Biol. Med. - Robust prediction of protein subcellular localization combining PCA and WSVMs. ( 0,479192841793134 )
AMIA Annu Symp Proc - SNOMED CT Saves Keystrokes: Quantifying Semantic Autocompletion. ( 0,478396106600786 )
J Telemed Telecare - Teleconsultation: changes in technology and costs over a 12-year period. ( 0,478072525527718 )
J Am Med Inform Assoc - Applying active learning to supervised word sense disambiguation in MEDLINE. ( 0,477875202751509 )
J Biomed Inform - Automatic detection of patients with invasive fungal disease from free-text computed tomography (CT) scans. ( 0,477610425216675 )
IEEE Trans Image Process - Modeling IrisCode and its variants as convex polyhedral cones and its security implications. ( 0,476586896226443 )
J Am Med Inform Assoc - Practical implementation of an existing smoking detection pipeline and reduced support vector machine training corpus requirements. ( 0,475928318695088 )
IEEE Trans Pattern Anal Mach Intell - Automatic Generation of Co-Embeddings from Relational Data with Adaptive Shaping. ( 0,475736107274148 )
Neural Comput - Bayesian sparse partial least squares. ( 0,475195835840582 )
J Integr Bioinform - On the parameter optimization of Support Vector Machines for binary classification. ( 0,474044388575082 )
IEEE Trans Image Process - A uniform grid structure to speed up example-based photometric stereo. ( 0,472801290268461 )
IEEE Trans Image Process - Real-time object tracking via online discriminative feature selection. ( 0,471979077389887 )
J Med Syst - A neuro-fuzzy identification of ECG beats. ( 0,471034684499277 )
J Biomed Inform - Identifying well-formed biomedical phrases in MEDLINE? text. ( 0,469968669799652 )
IEEE Trans Pattern Anal Mach Intell - Learning with Box Kernels. ( 0,468760857998975 )
Neural Comput - Parameter learning for alpha integration. ( 0,468394741860486 )
J Chem Inf Model - Classifying molecules using a sparse probabilistic kernel binary classifier. ( 0,468253540672452 )
Med Decis Making - Opportunity cost of funding drugs for rare diseases: the cost-effectiveness of eculizumab in paroxysmal nocturnal hemoglobinuria. ( 0,467385075579378 )
J. Comput. Biol. - Separating significant matches from spurious matches in DNA sequences. ( 0,466704458031402 )
IEEE Trans Image Process - A Unified Methodology for Computing Accurate Quaternion Color Moments and Moment Invariants. ( 0,466612843114208 )
BMC Med Inform Decis Mak - On the efficacy of per-relation basis performance evaluation for PPI extraction and a high-precision rule-based approach. ( 0,466580310225168 )
Comput Methods Programs Biomed - Design of fuzzy classifier for diabetes disease using Modified Artificial Bee Colony algorithm. ( 0,466445579291994 )
J. Comput. Biol. - Determining protein structures from NOESY distance constraints by semidefinite programming. ( 0,46582735652389 )
J Chem Inf Model - ReactionMap: an efficient atom-mapping algorithm for chemical reactions. ( 0,465658117243508 )
Comput. Biol. Med. - Relabeling algorithm for retrieval of noisy instances and improving prediction quality. ( 0,465212605538104 )
Comput. Biol. Med. - Classification and retrieval on macroinvertebrate image databases. ( 0,464292135560591 )
Artif Intell Med - A Markov decision process approach to multi-category patient scheduling in a diagnostic facility. ( 0,464092776554372 )
Med Biol Eng Comput - Single-trial classification of antagonistic oxyhemoglobin responses during mental arithmetic. ( 0,46379874462094 )
J Chem Inf Model - A binary ant colony optimization classifier for molecular activities. ( 0,463571810913027 )
Artif Intell Med - Evolutionary-driven support vector machines for determining the degree of liver fibrosis in chronic hepatitis C. ( 0,463476300923519 )
J Biomed Inform - Multi-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms. ( 0,463424812320533 )
Artif Intell Med - Suppressed fuzzy-soft learning vector quantization for MRI segmentation. ( 0,46304527268492 )
IEEE Trans Image Process - Implicit polynomial representation through a fast fitting error estimation. ( 0,462620408004508 )
BMC Med Inform Decis Mak - Learning to improve medical decision making from imbalanced data without a priori cost. ( 0,462056776825044 )
IEEE Trans Pattern Anal Mach Intell - Identifying Rare and Subtle Behaviours: A Weakly Supervised Joint Topic Model. ( 0,461568423953316 )
Comput. Biol. Med. - Event-based progression detection strategies using scanning laser polarimetry images of the human retina. ( 0,461253718810754 )
AMIA Annu Symp Proc - Dissimilarities in the Logical Modeling of Apparently Similar Concepts in SNOMED CT. ( 0,461103527005013 )
Comput Math Methods Med - Objectifying facial expressivity assessment of Parkinson's patients: preliminary study. ( 0,460730577652085 )
Med Decis Making - Evaluation of markers and risk prediction models: overview of relationships between NRI and decision-analytic measures. ( 0,459793577808279 )
IEEE Trans Image Process - Fast bilateral filter with arbitrary range and domain kernels. ( 0,459372819806592 )
Healthc (Amst) - Measuring the value of process improvement initiatives in a preoperative assessment center using time-driven activity-based costing. ( 0,459368391611596 )
IEEE Trans Neural Netw Learn Syst - On recursive edit distance kernels with application to time series classification. ( 0,459304056980978 )
IEEE Trans Image Process - Robust weighted graph transformation matching for rigid and nonrigid image registration. ( 0,458632019147592 )