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.


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


CKGROUND: The aim of this study was to propose an analytical approach to develop high-performing predictive models for congestive heart failure (CHF) readmission using an operational dataset with incomplete records and changing data over time.METHODS: Our analytical approach involves three steps: pre-processing, systematic model development, and risk factor analysis. For pre-processing, variables that were absent in >50% of records were removed. Moreover, the dataset was divided into a validation dataset and derivation datasets which were separated into three temporal subsets based on changes to the data over time. For systematic model development, using the different temporal datasets and the remaining explanatory variables, the models were developed by combining the use of various (i) statistical analyses to explore the relationships between the validation and the derivation datasets; (ii) adjustment methods for handling missing values; (iii) classifiers; (iv) feature selection methods; and (iv) discretization methods. We then selected the best derivation dataset and the models with the highest predictive performance. For risk factor analysis, factors in the highest-performing predictive models were analyzed and ranked using (i) statistical analyses of the best derivation dataset, (ii) feature rankers, and (iii) a newly developed algorithm to categorize risk factors as being strong, regular, or weak.RESULTS: The analysis dataset consisted of 2,787 CHF hospitalizations at University of Utah Health Care from January 2003 to June 2013. In this study, we used the complete-case analysis and mean-based imputation adjustment methods; the wrapper subset feature selection method; and four ranking strategies based on information gain, gain ratio, symmetrical uncertainty, and wrapper subset feature evaluators. The best-performing models resulted from the use of a complete-case analysis derivation dataset combined with the Class-Attribute Contingency Coefficient discretization method and a voting classifier which averaged the results of multi-nominal logistic regression and voting feature intervals classifiers. Of 42 final model risk factors, discharge disposition, discretized age, and indicators of anemia were the most significant. This model achieved a c-statistic of 86.8%.CONCLUSION: The proposed three-step analytical approach enhanced predictive model performance for CHF readmissions. It could potentially be leveraged to improve predictive model performance in other areas of clinical medicine.

Resumo Limpo

ckground aim studi propos analyt approach develop highperform predict model congest heart failur chf readmiss use oper dataset incomplet record chang data timemethod analyt approach involv three step preprocess systemat model develop risk factor analysi preprocess variabl absent record remov moreov dataset divid valid dataset deriv dataset separ three tempor subset base chang data time systemat model develop use differ tempor dataset remain explanatori variabl model develop combin use various statist analys explor relationship valid deriv dataset ii adjust method handl miss valu iii classifi iv featur select method iv discret method select best deriv dataset model highest predict perform risk factor analysi factor highestperform predict model analyz rank use statist analys best deriv dataset ii featur ranker iii newli develop algorithm categor risk factor strong regular weakresult analysi dataset consist chf hospit univers utah health care januari june studi use completecas analysi meanbas imput adjust method wrapper subset featur select method four rank strategi base inform gain gain ratio symmetr uncertainti wrapper subset featur evalu bestperform model result use completecas analysi deriv dataset combin classattribut conting coeffici discret method vote classifi averag result multinomin logist regress vote featur interv classifi final model risk factor discharg disposit discret age indic anemia signific model achiev cstatist conclus propos threestep analyt approach enhanc predict model perform chf readmiss potenti leverag improv predict model perform area clinic medicin

Resumos Similares

J Am Med Inform Assoc - An improved model for predicting postoperative nausea and vomiting in ambulatory surgery patients using physician-modifiable risk factors. ( 0,877951711306165 )
Appl Clin Inform - Comparing predictions made by a prediction model, clinical score, and physicians: pediatric asthma exacerbations in the emergency department. ( 0,877816290143579 )
BMC Med Inform Decis Mak - Artificial neural network models for prediction of cardiovascular autonomic dysfunction in general Chinese population. ( 0,87597979436875 )
IEEE J Biomed Health Inform - The effect of sample age and prediction resolution on myocardial infarction risk prediction. ( 0,83512175196293 )
Lifetime Data Anal - Understanding increments in model performance metrics. ( 0,834092205383434 )
Comput. Biol. Med. - A ternary model of decompression sickness in rats. ( 0,833971261288391 )
J. Comput. Biol. - Prediction of siRNA potency using sparse logistic regression. ( 0,833294448639006 )
Comput Math Methods Med - Modified logistic regression models using gene coexpression and clinical features to predict prostate cancer progression. ( 0,832364259808825 )
Med Decis Making - Application of an artificial neural network to predict postinduction hypotension during general anesthesia. ( 0,831501062011233 )
Comput Methods Programs Biomed - Recurrence predictive models for patients with hepatocellular carcinoma after radiofrequency ablation using support vector machines with feature selection methods. ( 0,827224570126138 )
J Biomed Inform - Decision-making model for early diagnosis of congestive heart failure using rough set and decision tree approaches. ( 0,824934352846413 )
J Biomed Inform - Partial least squares and logistic regression random-effects estimates for gene selection in supervised classification of gene expression data. ( 0,815846391770562 )
Int J Med Inform - Application of data mining to the identification of critical factors in patient falls using a web-based reporting system. ( 0,815406719315162 )
J Clin Monit Comput - Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery. ( 0,813603375036002 )
J Med Syst - Classifying hospitals as mortality outliers: logistic versus hierarchical logistic models. ( 0,810639641591768 )
J Med Syst - Effective automated prediction of vertebral column pathologies based on logistic model tree with SMOTE preprocessing. ( 0,803695180560664 )
J Biomed Inform - Statistical process control for validating a classification tree model for predicting mortality--a novel approach towards temporal validation. ( 0,802889167791783 )
BMC Med Inform Decis Mak - Evaluation of prediction models for the staging of prostate cancer. ( 0,799737551408935 )
Comput Math Methods Med - Variable selection in ROC regression. ( 0,799473490186444 )
Comput. Biol. Med. - Pre-operative prediction of surgical morbidity in children: comparison of five statistical models. ( 0,799448885839481 )
Comput Methods Programs Biomed - Single stage and multistage classification models for the prediction of liver fibrosis degree in patients with chronic hepatitis C infection. ( 0,794325598515106 )
Med Decis Making - A comparison of methods for converting DCE values onto the full health-dead QALY scale. ( 0,789586434132349 )
AMIA Annu Symp Proc - Predicting Surgical Risk: How Much Data is Enough? ( 0,781085732611732 )
Comput. Biol. Med. - A knowledge-driven probabilistic framework for the prediction of protein-protein interaction networks. ( 0,775289201046546 )
Appl Clin Inform - Exploring the value of clinical data standards to predict hospitalization of home care patients. ( 0,773009376798095 )
Spat Spatiotemporal Epidemiol - Assessment of land use factors associated with dengue cases in Malaysia using Boosted Regression Trees. ( 0,771937367191304 )
Comput Math Methods Med - Prediction of BP reactivity to talking using hybrid soft computing approaches. ( 0,771816006801279 )
Neural Comput - An extension of the receiver operating characteristic curve and AUC-optimal classification. ( 0,771322612178094 )
Int J Health Geogr - Prediction of high-risk areas for visceral leishmaniasis using socioeconomic indicators and remote sensing data. ( 0,771007334257054 )
J Chem Inf Model - Two new parameters based on distances in a receiver operating characteristic chart for the selection of classification models. ( 0,770727677464372 )
BMC Med Inform Decis Mak - Use of outcomes to evaluate surveillance systems for bioterrorist attacks. ( 0,769599057094216 )
BMC Med Inform Decis Mak - Bayesian predictors of very poor health related quality of life and mortality in patients with COPD. ( 0,769481951683328 )
BMC Med Inform Decis Mak - Mining geriatric assessment data for in-patient fall prediction models and high-risk subgroups. ( 0,768268398924056 )
Comput Methods Programs Biomed - Development of a daily mortality probability prediction model from Intensive Care Unit patients using a discrete-time event history analysis. ( 0,766719336883654 )
J Biomed Inform - An empirical approach to model selection through validation for censored survival data. ( 0,764766437087267 )
BMC Med Inform Decis Mak - Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning. ( 0,763949298321606 )
Med Decis Making - Performance profiling in primary care: does the choice of statistical model matter? ( 0,758563916602216 )
J Chem Inf Model - Are bigger data sets better for machine learning? Fusing single-point and dual-event dose response data for Mycobacterium tuberculosis. ( 0,756084997386984 )
IEEE Trans Image Process - Network-based H.264/AVC whole frame loss visibility model and frame dropping methods. ( 0,752266499574566 )
Comput Math Methods Med - Iterative reweighted noninteger norm regularizing SVM for gene expression data classification. ( 0,751003447465466 )
BMC Med Inform Decis Mak - Computerized prediction of intensive care unit discharge after cardiac surgery: development and validation of a Gaussian processes model. ( 0,749221842786523 )
Comput Biol Chem - Using ensemble methods to deal with imbalanced data in predicting protein-protein interactions. ( 0,747642174366939 )
Comput Methods Programs Biomed - Prediction of postprandial blood glucose under uncertainty and intra-patient variability in type 1 diabetes: a comparative study of three interval models. ( 0,746011009160974 )
Med Decis Making - Lehmann family of ROC curves. ( 0,745669438388512 )
J Med Syst - A new approach: role of data mining in prediction of survival of burn patients. ( 0,741847344053439 )
AMIA Annu Symp Proc - Clinical risk prediction by exploring high-order feature correlations. ( 0,740875883903297 )
Med Decis Making - Development of inpatient risk stratification models of acute kidney injury for use in electronic health records. ( 0,733080500167771 )
Med Decis Making - Adaptation of clinical prediction models for application in local settings. ( 0,729621411248908 )
Methods Inf Med - Limited sampling strategies to estimate the area under the concentration-time curve. Biases and a proposed more accurate method. ( 0,727463587135968 )
IEEE J Biomed Health Inform - Novel fractal feature-based multiclass glaucoma detection and progression prediction. ( 0,726622101877696 )
AMIA Annu Symp Proc - Development and implementation of a real-time 30-day readmission predictive model. ( 0,726440056597772 )
Med Decis Making - Performance of a mathematical model to forecast lives saved from HIV treatment expansion in resource-limited settings. ( 0,725842231867221 )
J Biomed Inform - Not just data: a method for improving prediction with knowledge. ( 0,724565529402809 )
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. ( 0,723264248243927 )
J Med Syst - Comparison of artificial neural networks with logistic regression for detection of obesity. ( 0,722961715705528 )
BMC Med Inform Decis Mak - Prediction of axillary lymph node metastasis in primary breast cancer patients using a decision tree-based model. ( 0,720584855411039 )
J Am Med Inform Assoc - Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy. ( 0,7196175806396 )
Brief. Bioinformatics - Caveats and pitfalls of ROC analysis in clinical microarray research (and how to avoid them). ( 0,717772444545241 )
Methods Inf Med - An experimental evaluation of boosting methods for classification. ( 0,715748699721089 )
BMC Med Inform Decis Mak - Prediction of adverse cardiac events in emergency department patients with chest pain using machine learning for variable selection. ( 0,714238432259277 )
Comput Methods Programs Biomed - Exploring an optimal vector autoregressive model for multi-channel pulmonary sound data. ( 0,714052609152816 )
Med Biol Eng Comput - Mortality prediction of rats in acute hemorrhagic shock using machine learning techniques. ( 0,712015200490836 )
Med Biol Eng Comput - System identification of the mechanomyogram from single motor units during voluntary isometric contraction. ( 0,710209578960109 )
Spat Spatiotemporal Epidemiol - Modeling habitat suitability for occurrence of highly pathogenic avian influenza virus H5N1 in domestic poultry in Asia: a spatial multicriteria decision analysis approach. ( 0,708749307862342 )
J Am Med Inform Assoc - A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data. ( 0,708471600849256 )
J Biomed Inform - Prediction of influenza vaccination outcome by neural networks and logistic regression. ( 0,706732947281917 )
AMIA Annu Symp Proc - Decision path models for patient-specific modeling of patient outcomes. ( 0,705959486358649 )
Comput Methods Programs Biomed - Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines. ( 0,704715605520377 )
Artif Intell Med - Machine learning for improved pathological staging of prostate cancer: a performance comparison on a range of classifiers. ( 0,703438007860963 )
J Med Syst - Diagnosing breast masses in digital mammography using feature selection and ensemble methods. ( 0,70095805344616 )
Methods Inf Med - Classification of postural profiles among mouth-breathing children by learning vector quantization. ( 0,697240888868259 )
Artif Intell Med - White box radial basis function classifiers with component selection for clinical prediction models. ( 0,693949813840835 )
Int J Health Geogr - Assessing the effects of variables and background selection on the capture of the tick climate niche. ( 0,692233975853883 )
AMIA Annu Symp Proc - Developing predictive models using electronic medical records: challenges and pitfalls. ( 0,688034452240159 )
J Am Med Inform Assoc - From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system. ( 0,68779393135863 )
J Biomed Inform - The effects of data sources, cohort selection, and outcome definition on a predictive model of risk of thirty-day hospital readmissions. ( 0,687127478200169 )
Artif Intell Med - Prediction of human major histocompatibility complex class II binding peptides by continuous kernel discrimination method. ( 0,683180759877223 )
J Chem Inf Model - Predictive toxicology modeling: protocols for exploring hERG classification and Tetrahymena pyriformis end point predictions. ( 0,681060811860401 )
Brief. Bioinformatics - Adjusting confounders in ranking biomarkers: a model-based ROC approach. ( 0,681053772011139 )
BMC Med Inform Decis Mak - Decision curve analysis revisited: overall net benefit, relationships to ROC curve analysis, and application to case-control studies. ( 0,680543764274767 )
J Chem Inf Model - Ligand efficiency-based support vector regression models for predicting bioactivities of ligands to drug target proteins. ( 0,678711121771822 )
Lifetime Data Anal - Estimating improvement in prediction with matched case-control designs. ( 0,673843743787042 )
IEEE J Biomed Health Inform - Prediction of periventricular leukomalacia occurrence in neonates after heart surgery. ( 0,672387205080975 )
Med Decis Making - Constructing proper ROCs from ordinal response data using weighted power functions. ( 0,67025803658014 )
J Clin Monit Comput - Complex signals bioinformatics: evaluation of heart rate characteristics monitoring as a novel risk marker for neonatal sepsis. ( 0,668575127084527 )
Methods Inf Med - Sensor-based fall risk assessment--an expert 'to go'. ( 0,66811762059242 )
Artif Intell Med - Predicting patient survival after liver transplantation using evolutionary multi-objective artificial neural networks. ( 0,665165123321051 )
Artif Intell Med - Predicting the need for CT imaging in children with minor head injury using an ensemble of Naive Bayes classifiers. ( 0,662978494780487 )
Comput Math Methods Med - An efficient diagnosis system for Parkinson's disease using kernel-based extreme learning machine with subtractive clustering features weighting approach. ( 0,65982266331333 )
Comput Biol Chem - An ensemble method for prediction of conformational B-cell epitopes from antigen sequences. ( 0,659098634902701 )
BMC Med Inform Decis Mak - A novel differential diagnostic model based on multiple biological parameters for immunoglobulin A nephropathy. ( 0,65806273864961 )
Artif Intell Med - Machine learning of clinical performance in a pancreatic cancer database. ( 0,65656734515294 )
Med Biol Eng Comput - A dynamic Bayesian network for estimating the risk of falls from real gait data. ( 0,654900775110658 )
Health Informatics J - Development of an automated model to predict the risk of elderly emergency medical admissions within a month following an index hospital visit: a Hong Kong experience. ( 0,65476106580704 )
J Digit Imaging - Computer-aided detection of architectural distortion in prior mammograms of interval cancer. ( 0,65420597729744 )
J Am Med Inform Assoc - Supervised embedding of textual predictors with applications in clinical diagnostics for pediatric cardiology. ( 0,649978292010409 )
J Am Med Inform Assoc - Word sense disambiguation in the clinical domain: a comparison of knowledge-rich and knowledge-poor unsupervised methods. ( 0,648708576543937 )
AMIA Annu Symp Proc - Application of Bayesian logistic regression to mining biomedical data. ( 0,647823811907277 )
Comput. Biol. Med. - Statistical model based 3D shape prediction of postoperative trunks for non-invasive scoliosis surgery planning. ( 0,646472786183533 )
Med Decis Making - Contrasting two frameworks for ROC analysis of ordinal ratings. ( 0,645819263473154 )