BMC Med Inform Decis Mak - Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records.

Tópicos

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

Resumo

CKGROUND: Distinguishing cases from non-cases in free-text electronic medical records is an important initial step in observational epidemiological studies, but manual record validation is time-consuming and cumbersome. We compared different approaches to develop an automatic case identification system with high sensitivity to assist manual annotators.METHODS: We used four different machine-learning algorithms to build case identification systems for two data sets, one comprising hepatobiliary disease patients, the other acute renal failure patients. To improve the sensitivity of the systems, we varied the imbalance ratio between positive cases and negative cases using under- and over-sampling techniques, and applied cost-sensitive learning with various misclassification costs.RESULTS: For the hepatobiliary data set, we obtained a high sensitivity of 0.95 (on a par with manual annotators, as compared to 0.91 for a baseline classifier) with specificity 0.56. For the acute renal failure data set, sensitivity increased from 0.69 to 0.89, with specificity 0.59. Performance differences between the various machine-learning algorithms were not large. Classifiers performed best when trained on data sets with imbalance ratio below 10.CONCLUSIONS: We were able to achieve high sensitivity with moderate specificity for automatic case identification on two data sets of electronic medical records. Such a high-sensitive case identification system can be used as a pre-filter to significantly reduce the burden of manual record validation.

Resumo Limpo

ckground distinguish case noncas freetext electron medic record import initi step observ epidemiolog studi manual record valid timeconsum cumbersom compar differ approach develop automat case identif system high sensit assist manual annotatorsmethod use four differ machinelearn algorithm build case identif system two data set one compris hepatobiliari diseas patient acut renal failur patient improv sensit system vari imbal ratio posit case negat case use oversampl techniqu appli costsensit learn various misclassif costsresult hepatobiliari data set obtain high sensit par manual annot compar baselin classifi specif acut renal failur data set sensit increas specif perform differ various machinelearn algorithm larg classifi perform best train data set imbal ratio conclus abl achiev high sensit moder specif automat case identif two data set electron medic record highsensit case identif system can use prefilt signific reduc burden manual record valid

Resumos Similares

Int J Neural Syst - Automated seizure detection using EKG. ( 0,684158881199194 )
J Biomed Inform - Improving record linkage performance in the presence of missing linkage data. ( 0,679321816499104 )
AMIA Annu Symp Proc - Development and validation of an electronic phenotyping algorithm for chronic kidney disease. ( 0,673515097853183 )
J Med Syst - Utilization of electronic medical records to build a detection model for surveillance of healthcare-associated urinary tract infections. ( 0,657762153396043 )
AMIA Annu Symp Proc - I am Not Dead Yet: Identification of False-Positive Matches to Death Master File. ( 0,652748799746545 )
Appl Clin Inform - Towards prevention of acute syndromes: electronic identification of at-risk patients during hospital admission. ( 0,632407917930586 )
J Biomed Inform - Automation of a high risk medication regime algorithm in a home health care population. ( 0,629788666617202 )
J Med Syst - Automatic detection of the existence of subarachnoid hemorrhage from clinical CT images. ( 0,628264292894466 )
BMC Med Inform Decis Mak - Predicting out of intensive care unit cardiopulmonary arrest or death using electronic medical record data. ( 0,624569161616727 )
BMC Med Inform Decis Mak - Outbreak detection algorithms for seasonal disease data: a case study using Ross River virus disease. ( 0,617336850758483 )
BMC Med Inform Decis Mak - De-identification of primary care electronic medical records free-text data in Ontario, Canada. ( 0,616531464551834 )
J Am Med Inform Assoc - Finding falls in ambulatory care clinical documents using statistical text mining. ( 0,612415689196752 )
Comput. Biol. Med. - Informatics can identify systemic sclerosis (SSc) patients at risk for scleroderma renal crisis. ( 0,606680329549866 )
J Am Med Inform Assoc - A benchmark comparison of deterministic and probabilistic methods for defining manual review datasets in duplicate records reconciliation. ( 0,603682866376144 )
IEEE J Biomed Health Inform - Automatic identification and classification of muscle spasms in long-term EMG recordings. ( 0,598419017520372 )
Brief. Bioinformatics - An empirical assessment of validation practices for molecular classifiers. ( 0,596908191902256 )
BMC Med Inform Decis Mak - Evaluation of syndromic algorithms for detecting patients with potentially transmissible infectious diseases based on computerised emergency-department data. ( 0,596759587892976 )
J Am Med Inform Assoc - Automatic identification of methotrexate-induced liver toxicity in patients with rheumatoid arthritis from the electronic medical record. ( 0,59343582950009 )
AMIA Annu Symp Proc - A Weighty Problem: Identification, Characteristics and Risk Factors for Errors in EMR Data. ( 0,592857144493796 )
Int J Comput Assist Radiol Surg - Hybrid method for the detection of pulmonary nodules using positron emission tomography/computed tomography: a preliminary study. ( 0,591386918652738 )
J Am Med Inform Assoc - Adjusting outbreak detection algorithms for surveillance during epidemic and non-epidemic periods. ( 0,589778129953859 )
Int J Med Inform - Using electronic medical records to determine the diagnosis of clinical depression. ( 0,58821225373213 )
Artif Intell Med - Automatic detection of epileptic seizures on the intra-cranial electroencephalogram of rats using reservoir computing. ( 0,587620404081227 )
J Am Med Inform Assoc - A framework for assessing patient crossover and health information exchange value. ( 0,587072135405174 )
Comput. Biol. Med. - Myocardial border detection from ventriculograms using support vector machines and real-coded genetic algorithms. ( 0,58633420955239 )
J Am Med Inform Assoc - A taste of individualized medicine: physicians' reactions to automated genetic interpretations. ( 0,572130322636168 )
J Am Med Inform Assoc - Use of computerized algorithm to identify individuals in need of testing for celiac disease. ( 0,565557786906576 )
Appl Clin Inform - Retrospective derivation and validation of a search algorithm to identify emergent endotracheal intubations in the intensive care unit. ( 0,563433961577359 )
J Clin Monit Comput - Pulse oximetry saturation patterns detect repetitive reductions in airflow. ( 0,562397675707284 )
Int J Neural Syst - Kernel collaborative representation-based automatic seizure detection in intracranial EEG. ( 0,56239489906206 )
Comput. Biol. Med. - Synergistic combination of clinical and imaging features predicts abnormal imaging patterns of pulmonary infections. ( 0,561871289086637 )
Med Biol Eng Comput - Quasi real-time gait event detection using shank-attached gyroscopes. ( 0,561539734309764 )
BMC Med Inform Decis Mak - Derivation and validation of a search algorithm to retrospectively identify mechanical ventilation initiation in the intensive care unit. ( 0,560878252218722 )
AMIA Annu Symp Proc - Who said it? Establishing professional attribution among authors of Veterans' Electronic Health Records. ( 0,560142689405045 )
Comput. Biol. Med. - A user-operated test of suprathreshold acuity in noise for adult hearing screening: The SUN (Speech Understanding in Noise) test. ( 0,558185653054355 )
Int J Med Inform - Implementation and expansion of an electronic medical record for HIV care and treatment in Haiti: an assessment of system use and the impact of large-scale disruptions. ( 0,55758437996169 )
J Chem Inf Model - A multiscale simulation system for the prediction of drug-induced cardiotoxicity. ( 0,554948205511631 )
IEEE Trans Pattern Anal Mach Intell - Online Learning and Sequential Anomaly Detection in Trajectories. ( 0,553976142167386 )
BMC Med Inform Decis Mak - Optimal strategy for linkage of datasets containing a statistical linkage key and datasets with full personal identifiers. ( 0,551856502494886 )
AMIA Annu Symp Proc - Automatic Prediction of Conversion from Mild Cognitive Impairment to Probable Alzheimer's Disease using Structural Magnetic Resonance Imaging. ( 0,551490575230602 )
Int J Comput Assist Radiol Surg - Rapid image recognition of body parts scanned in computed tomography datasets. ( 0,547901746117111 )
J Clin Monit Comput - Detection of endobronchial intubation by monitoring the CO2 level above the endotracheal cuff. ( 0,547349784773707 )
Med Biol Eng Comput - Application of the RIMARC algorithm to a large data set of action potentials and clinical parameters for risk prediction of atrial fibrillation. ( 0,546432766442959 )
J Am Med Inform Assoc - Syndromic surveillance for health information system failures: a feasibility study. ( 0,546259863302721 )
AMIA Annu Symp Proc - Toward a two-tier clinical warning system for hospitalized patients. ( 0,544061257250232 )
BMC Med Inform Decis Mak - Implementation of automated reporting of estimated glomerular filtration rate among Veterans Affairs laboratories: a retrospective study. ( 0,543341053403794 )
J Am Med Inform Assoc - Phenotyping for patient safety: algorithm development for electronic health record based automated adverse event and medical error detection in neonatal intensive care. ( 0,542904331494397 )
J Telemed Telecare - Diabetic retinopathy screening using tele-ophthalmology in a primary care setting. ( 0,541942917941632 )
AMIA Annu Symp Proc - Computer surveillance of patients at high risk for and with venous thromboembolism. ( 0,540123389098186 )
AMIA Annu Symp Proc - Mining echocardiography workflows for disease discriminative patterns. ( 0,535407129039269 )
Int J Comput Assist Radiol Surg - Combination of computer-aided detection algorithms for automatic lung nodule identification. ( 0,534132108642651 )
BMC Med Inform Decis Mak - Improved de-identification of physician notes through integrative modeling of both public and private medical text. ( 0,532443703123212 )
Comput. Biol. Med. - Automated detection of the osseous acetabular rim using three-dimensional models of the pelvis. ( 0,531662818856335 )
Int J Comput Assist Radiol Surg - Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer. ( 0,53153180960077 )
AMIA Annu Symp Proc - Analysis of medication and indication occurrences in clinical notes. ( 0,531251423322121 )
J Biomed Inform - Predictive combinations of monitor alarms preceding in-hospital code blue events. ( 0,529939668775205 )
IEEE Trans Pattern Anal Mach Intell - Robust Text Detection in Natural Scene Images. ( 0,528073734148862 )
AMIA Annu Symp Proc - Type 2 diabetes risk forecasting from EMR data using machine learning. ( 0,527345398614012 )
J Chem Inf Model - Applicability domain based on ensemble learning in classification and regression analyses. ( 0,524763386929334 )
BMC Med Inform Decis Mak - Developing model-based algorithms to identify screening colonoscopies using administrative health databases. ( 0,521686259748235 )
J Med Syst - Field programmable gate array based fuzzy neural signal processing system for differential diagnosis of QRS complex tachycardia and tachyarrhythmia in noisy ECG signals. ( 0,520795513511847 )
Methods Inf Med - Reliable blood pressure self-measurement in the obstetric waiting room. ( 0,519405846769674 )
BMC Med Inform Decis Mak - Is it possible to identify cases of coronary artery bypass graft postoperative surgical site infection accurately from claims data? ( 0,518916176918101 )
Comput Methods Programs Biomed - Fetal phonocardiography--past and future possibilities. ( 0,518321829649875 )
Comput Methods Programs Biomed - Automated pulmonary nodule detection based on three-dimensional shape-based feature descriptor. ( 0,518168747417367 )
J Med Syst - Applying ontology techniques to develop a medication history search and alert system in department of nuclear medicine. ( 0,515851304939845 )
BMC Med Inform Decis Mak - Manual and automated methods for identifying potentially preventable readmissions: a comparison in a large healthcare system. ( 0,515431758244478 )
Telemed J E Health - Data integrity module for data quality assurance within an e-health system in sub-Saharan Africa. ( 0,512685286039473 )
IEEE Trans Image Process - Chromaticity space for illuminant invariant recognition. ( 0,512080059070155 )
Comput Methods Programs Biomed - Blood vessel segmentation methodologies in retinal images--a survey. ( 0,511825153650351 )
Comput Methods Programs Biomed - Modeling the glucose regulatory system in extreme preterm infants. ( 0,51151130083538 )
Comput Math Methods Med - Hypovigilance detection for UCAV operators based on a hidden Markov model. ( 0,510227791571804 )
J Med Syst - Automated screening of arrhythmia using wavelet based machine learning techniques. ( 0,50994774356986 )
Comput Methods Programs Biomed - Development of a model-based clinical sepsis biomarker for critically ill patients. ( 0,509755640120867 )
AMIA Annu Symp Proc - A prototype knowledge base and SMART app to facilitate organization of patient medications by clinical problems. ( 0,509415763875008 )
Int J Comput Assist Radiol Surg - Automated measurement of mandibular cortical width on dental panoramic radiographs. ( 0,508978172096467 )
AMIA Annu Symp Proc - Comparing content coverage in medical curriculum to trainee-authored clinical notes. ( 0,508800955581504 )
Artif Intell Med - Fuzzy model identification of dengue epidemic in Colombia based on multiresolution analysis. ( 0,507568414728717 )
Int J Comput Assist Radiol Surg - Detection and quantification of intracerebral and intraventricular hemorrhage from computed tomography images with adaptive thresholding and case-based reasoning. ( 0,506006373744173 )
IEEE J Biomed Health Inform - Automatic annotation of seismocardiogram with high-frequency precordial accelerations. ( 0,505767203402043 )
J. Med. Internet Res. - FluBreaks: early epidemic detection from Google flu trends. ( 0,504358031746252 )
Int J Comput Assist Radiol Surg - Computer-aided focal liver lesion detection. ( 0,504140531272149 )
J Am Med Inform Assoc - Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network. ( 0,503180472790516 )
Comput Methods Programs Biomed - Unsupervised skin lesions border detection via two-dimensional image analysis. ( 0,503161087657513 )
J Clin Monit Comput - Detection of respiratory compromise by acoustic monitoring, capnography, and brain function monitoring during monitored anesthesia care. ( 0,50186856047757 )
AMIA Annu Symp Proc - Validation and enhancement of a computable medication indication resource (MEDI) using a large practice-based dataset. ( 0,501578655133702 )
AMIA Annu Symp Proc - Predicting the dengue incidence in Singapore using univariate time series models. ( 0,500485109618703 )
Comput Methods Programs Biomed - An associative memory approach to medical decision support systems. ( 0,499160120940062 )
J Am Med Inform Assoc - Use of electronic medical records differs by specialty and office settings. ( 0,498622693775396 )
Comput Methods Programs Biomed - Identification of intestinal wall abnormalities and ischemia by modeling spatial uncertainty in computed tomography imaging findings. ( 0,498170581215223 )
Comput Methods Programs Biomed - Fall detection for multiple pedestrians using depth image processing technique. ( 0,497801975481279 )
Comput Methods Programs Biomed - Automated detection of microaneurysms using scale-adapted blob analysis and semi-supervised learning. ( 0,494485640239745 )
Comput. Biol. Med. - CNV detection method optimized for high-resolution arrayCGH by normality test. ( 0,493991442698607 )
IEEE J Biomed Health Inform - Fast and adaptive detection of pulmonary nodules in thoracic CT images using a hierarchical vector quantization scheme. ( 0,493415463305072 )
Comput Methods Programs Biomed - Accurate detection of blood vessels improves the detection of exudates in color fundus images. ( 0,492874646273612 )
Artif Intell Med - A machine learning-based approach to prognostic analysis of thoracic transplantations. ( 0,491204692562117 )
Comput Methods Programs Biomed - Automated detection of exudates and macula for grading of diabetic macular edema. ( 0,490052691761493 )
AMIA Annu Symp Proc - Methods for identifying suicide or suicidal ideation in EHRs. ( 0,48971110170674 )
Med Biol Eng Comput - Automated detection of perinatal hypoxia using time-frequency-based heart rate variability features. ( 0,489390469063547 )
BMC Med Inform Decis Mak - Automated systems to identify relevant documents in product risk management. ( 0,489191655284808 )