J Biomed Inform - Limestone: high-throughput candidate phenotype generation via tensor factorization.

Tópicos

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

Resumo

The rapidly increasing availability of electronic health records (EHRs) from multiple heterogeneous sources has spearheaded the adoption of data-driven approaches for improved clinical research, decision making, prognosis, and patient management. Unfortunately, EHR data do not always directly and reliably map to medical concepts that clinical researchers need or use. Some recent studies have focused on EHR-derived phenotyping, which aims at mapping the EHR data to specific medical concepts; however, most of these approaches require labor intensive supervision from experienced clinical professionals. Furthermore, existing approaches are often disease-centric and specialized to the idiosyncrasies of the information technology and/or business practices of a single healthcare organization. In this paper, we propose Limestone, a nonnegative tensor factorization method to derive phenotype candidates with virtually no human supervision. Limestone represents the data source interactions naturally using tensors (a generalization of matrices). In particular, we investigate the interaction of diagnoses and medications among patients. The resulting tensor factors are reported as phenotype candidates that automatically reveal patient clusters on specific diagnoses and medications. Using the proposed method, multiple phenotypes can be identified simultaneously from data. We demonstrate the capability of Limestone on a cohort of 31,815 patient records from the Geisinger Health System. The dataset spans 7years of longitudinal patient records and was initially constructed for a heart failure onset prediction study. Our experiments demonstrate the robustness, stability, and the conciseness of Limestone-derived phenotypes. Our results show that using only 40 phenotypes, we can outperform the original 640 features (169 diagnosis categories and 471 medication types) to achieve an area under the receiver operator characteristic curve (AUC) of 0.720 (95% CI 0.715 to 0.725). Moreover, in consultation with a medical expert, we confirmed 82% of the top 50 candidates automatically extracted by Limestone are clinically meaningful.

Resumo Limpo

rapid increas avail electron health record ehr multipl heterogen sourc spearhead adopt datadriven approach improv clinic research decis make prognosi patient manag unfortun ehr data alway direct reliabl map medic concept clinic research need use recent studi focus ehrderiv phenotyp aim map ehr data specif medic concept howev approach requir labor intens supervis experienc clinic profession furthermor exist approach often diseasecentr special idiosyncrasi inform technolog andor busi practic singl healthcar organ paper propos limeston nonneg tensor factor method deriv phenotyp candid virtual human supervis limeston repres data sourc interact natur use tensor general matric particular investig interact diagnos medic among patient result tensor factor report phenotyp candid automat reveal patient cluster specif diagnos medic use propos method multipl phenotyp can identifi simultan data demonstr capabl limeston cohort patient record geising health system dataset span year longitudin patient record initi construct heart failur onset predict studi experi demonstr robust stabil concis limestonederiv phenotyp result show use phenotyp can outperform origin featur diagnosi categori medic type achiev area receiv oper characterist curv auc ci moreov consult medic expert confirm top candid automat extract limeston clinic meaning

Resumos Similares

J Integr Bioinform - Integrating phenotypic data for depression. ( 0,622769120305366 )
Brief. Bioinformatics - Mathematics and evolutionary biology make bioinformatics education comprehensible. ( 0,609876329708385 )
Comput Methods Programs Biomed - The O3-Vet project: integration of a standard nomenclature of clinical terms in a veterinary electronic medical record for veterinary hospitals. ( 0,580444528485568 )
J Integr Bioinform - Noise tolerance of multiple classifier systems in data integration-based gene function prediction. ( 0,573125111647978 )
J Integr Bioinform - BioNetLink - an architecture for working with network data. ( 0,56666948218672 )
J Am Med Inform Assoc - Genetic data and electronic health records: a discussion of ethical, logistical and technological considerations. ( 0,561290391701251 )
AMIA Annu Symp Proc - Managing Medical Vocabulary Updates in a Clinical Data Warehouse: An RxNorm Case Study. ( 0,560512883068671 )
J Biomed Inform - Federated Aggregate Cohort Estimator (FACE): an easy to deploy, vendor neutral, multi-institutional cohort query architecture. ( 0,555057729005881 )
J Clin Monit Comput - Design and implementation of a hospital wide waveform capture system. ( 0,553223298171574 )
AMIA Annu Symp Proc - Semantic interoperability of Health Risk Assessments. ( 0,546599184496826 )
Appl Clin Inform - The false security of blind dates: chrononymization's lack of impact on data privacy of laboratory data. ( 0,543231282939378 )
J Biomed Inform - DSGeo: software tools for cross-platform analysis of gene expression data in GEO. ( 0,54055513151202 )
Med Biol Eng Comput - Remote physiological and GPS data processing in evaluation of physical activities. ( 0,536701389299879 )
IEEE Trans Vis Comput Graph - Joint Contour Nets. ( 0,534207224296495 )
Neural Comput - On criticality in high-dimensional data. ( 0,533366155648074 )
IEEE Trans Image Process - Multimodal graph-based reranking for web image search. ( 0,531885083436448 )
Appl Clin Inform - Measures of user experience in a streptococcal pharyngitis and pneumonia clinical decision support tools. ( 0,529805243023771 )
J Am Med Inform Assoc - Using the CER Hub to ensure data quality in a multi-institution smoking cessation study. ( 0,523302071910594 )
Brief. Bioinformatics - Teaching the bioinformatics of signaling networks: an integrated approach to facilitate multi-disciplinary learning. ( 0,522838844351107 )
Brief. Bioinformatics - A first course in computing with applications to biology. ( 0,522000580141701 )
Brief. Bioinformatics - Social pathway annotation: extensions of the systems biology metabolic modelling assistant. ( 0,521351970235885 )
J Chem Inf Model - Heterogeneous classifier fusion for ligand-based virtual screening: or, how decision making by committee can be a good thing. ( 0,52061772217406 )
Appl Clin Inform - Design of a medication reconciliation application: facilitating clinician-focused decision making with data from multiple sources. ( 0,516178159671139 )
Appl Clin Inform - Medical student appraisal: electronic resources for inpatient pre-rounding. ( 0,514749011421461 )
Comput Math Methods Med - The number of candidate variants in exome sequencing for Mendelian disease under no genetic heterogeneity. ( 0,513063107834256 )
Brief. Bioinformatics - Bayesian inference for genomic imprinting underlying developmental characteristics. ( 0,51083517140783 )
J Am Med Inform Assoc - An informatics approach to medication adherence assessment and improvement using clinical, billing, and patient-entered data. ( 0,510794515841616 )
J Biomed Inform - Harmonization and semantic annotation of data dictionaries from the Pharmacogenomics Research Network: a case study. ( 0,509427832297274 )
J Biomed Inform - Using aggregated, de-identified electronic health record data for multivariate pharmacosurveillance: a case study of azathioprine. ( 0,50794398587647 )
J Med Syst - Medical students' expectations towards an implementation of a family medicine textbook as a comprehensive app in Germany. ( 0,507837642931594 )
Artif Intell Med - An implicit approach to deal with periodically repeated medical data. ( 0,507393896544817 )
AMIA Annu Symp Proc - Improving Clinical Data Integrity by using Data Adjudication Techniques for Data Received through a Health Information Exchange (HIE). ( 0,50716585838364 )
Comput Math Methods Med - BioTCM-SE: a semantic search engine for the information retrieval of modern biology and traditional Chinese medicine. ( 0,50426138658327 )
AMIA Annu Symp Proc - Piloting a deceased subject integrated data repository and protecting privacy of relatives. ( 0,503891847992238 )
Artif Intell Med - Multiple kernel learning in protein-protein interaction extraction from biomedical literature. ( 0,503826367941584 )
Comput Methods Programs Biomed - Computer simulation of the activity of the elderly person living independently in a Health Smart Home. ( 0,503609318198233 )
Int J Med Inform - Using a web-based orthopaedic clinic in the curricular teaching of a German university hospital: analysis of learning effect, student usage and reception. ( 0,50346043373882 )
J Am Med Inform Assoc - 'N-of-1-pathways' unveils personal deregulated mechanisms from a single pair of RNA-Seq samples: towards precision medicine. ( 0,500885492436164 )
J Telemed Telecare - Telemedicine for retinal care in developing nations: the ORBIS Cyber-Sight programme, 2003-2011. ( 0,500063807902741 )
J. Med. Internet Res. - Crowdsourcing black market prices for prescription opioids. ( 0,498938006722621 )
AMIA Annu Symp Proc - Graphical methods for reducing, visualizing and analyzing large data sets using hierarchical terminologies. ( 0,498621192195982 )
J. Comput. Biol. - Bayesian blind source separation for data with network structure. ( 0,495767838561295 )
J Biomed Inform - Practical approach to determine sample size for building logistic prediction models using high-throughput data. ( 0,495672815290779 )
J. Comput. Biol. - Prediction of rare single-nucleotide causative mutations for muscular diseases in pooled next-generation sequencing experiments. ( 0,494833205190463 )
J Biomed Inform - Procurement of shared data instruments for Research Electronic Data Capture (REDCap). ( 0,493448403423442 )
Perspect Health Inf Manag - ICD-10-CM/PCS: transferring knowledge from ICD-9-CM. ( 0,49177761138527 )
AMIA Annu Symp Proc - Development and validation of an electronic phenotyping algorithm for chronic kidney disease. ( 0,491192447454448 )
J Am Med Inform Assoc - R engine cell: integrating R into the i2b2 software infrastructure. ( 0,489542258606246 )
AMIA Annu Symp Proc - Oncoshare: lessons learned from building an integrated multi-institutional database for comparative effectiveness research. ( 0,488566551317496 )
Wiley Interdiscip Rev Syst Biol Med - The virtual liver: a multidisciplinary, multilevel challenge for systems biology. ( 0,488135598521986 )
J Am Med Inform Assoc - Leveraging biodiversity knowledge for potential phyto-therapeutic applications. ( 0,486917918395908 )
Comput Methods Programs Biomed - Medical faculties educational network: multidimensional quality assessment. ( 0,486821998700501 )
Inform Health Soc Care - Medical decision-making inspired from aerospace multisensor data fusion concepts. ( 0,486179181127982 )
Health Informatics J - Does use of computer technology for perinatal data collection influence data quality? ( 0,485717685728629 )
Brief. Bioinformatics - Broader incorporation of bioinformatics in education: opportunities and challenges. ( 0,484444123595657 )
J. Med. Internet Res. - Promoting business and entrepreneurial awareness in health care professionals: lessons from venture capital panels at medicine 2.0 conferences. ( 0,483786720726049 )
AMIA Annu Symp Proc - Lessons learned in replicating data-driven experiments in multiple medical systems and patient populations. ( 0,483711346927862 )
J Integr Bioinform - Quality controls in integrative approaches to detect errors and inconsistencies in biological databases. ( 0,482154279005483 )
J Med Syst - Modeling paradigms for medical diagnostic decision support: a survey and future directions. ( 0,481896140545463 )
J Integr Bioinform - Coex-Rank: An approach incorporating co-expression information for combined analysis of microarray data. ( 0,48186266747041 )
Health Info Libr J - Health librarians: developing professional competence through a 'legitimate peripheral participation' model. ( 0,481458306814501 )
Brief. Bioinformatics - Bioinformatics and systems biology: bridging the gap between heterogeneous student backgrounds. ( 0,480543058817608 )
AMIA Annu Symp Proc - Implementation of a platform dedicated to the biomedical analysis terminologies management. ( 0,480174364751175 )
BMC Med Inform Decis Mak - A multiscale and multiparametric approach for modeling the progression of oral cancer. ( 0,478316896464213 )
IEEE J Biomed Health Inform - Integrative clustering by nonnegative matrix factorization can reveal coherent functional groups from gene profile data. ( 0,476329850007745 )
J. Med. Internet Res. - Massive open online courses on health and medicine: review. ( 0,476324824741875 )
AMIA Annu Symp Proc - Using Anchors to Estimate Clinical State without Labeled Data. ( 0,476167556042408 )
BMC Med Inform Decis Mak - Evaluation of data completeness in the electronic health record for the purpose of patient recruitment into clinical trials: a retrospective analysis of element presence. ( 0,475943634674041 )
Brief. Bioinformatics - Network biology methods integrating biological data for translational science. ( 0,475015805582021 )
J. Med. Internet Res. - Interactive algorithms for teaching and learning acute medicine in the network of medical faculties MEFANET. ( 0,474846815897914 )
Sci Data - Genomes and phenomes of a population of outbred rats and its progenitors. ( 0,474728533288048 )
AMIA Annu Symp Proc - MEDCIS: Multi-Modality Epilepsy Data Capture and Integration System. ( 0,474441123001191 )
J Chem Inf Model - Analysis of commercial and public bioactivity databases. ( 0,474419545613305 )
Comput Biol Chem - The complex task of choosing a de novo assembly: lessons from fungal genomes. ( 0,474029638671103 )
Inform Health Soc Care - Medical informatics across Europe: analysis of medical informatics scientific output in 33 European countries. ( 0,473983057260012 )
Med Decis Making - Predictive Modeling of Implantation Outcome in an In Vitro Fertilization Setting: An Application of Machine Learning Methods. ( 0,47388768103776 )
Comput Biol Chem - Meta-analysis of microarray data: The case of imatinib resistance in chronic myelogenous leukemia. ( 0,473691944793641 )
Perspect Health Inf Manag - Using an audience response system (ARS) in a face-to-face and distance education CPT/HCPCS coding course. ( 0,473372964888362 )
J Am Med Inform Assoc - Portability of an algorithm to identify rheumatoid arthritis in electronic health records. ( 0,473279082217865 )
Brief. Bioinformatics - Biological feature validation of estimated gene interaction networks from microarray data: a case study on MYC in lymphomas. ( 0,473000699750769 )
Artif Intell Med - Detecting disease genes based on semi-supervised learning and protein-protein interaction networks. ( 0,471803363798303 )
Comput Biol Chem - Ped_Outlier software for automatic identification of within-family outliers. ( 0,471568150669209 )
AMIA Annu Symp Proc - Learning medical diagnosis models from multiple experts. ( 0,47082055479568 )
J Am Med Inform Assoc - CAPriCORN: Chicago Area Patient-Centered Outcomes Research Network. ( 0,470786487366711 )
Telemed J E Health - Enabling the mission through trans-atlantic remote mentored musculoskeletal ultrasound: case report of a portable hand-carried tele-ultrasound system for medical relief missions. ( 0,470208047628433 )
Int J Med Inform - Application of a low-cost web-based simulation to improve students' practical skills in medical education. ( 0,470177909359926 )
Brief. Bioinformatics - A practical guide for the functional annotation of genetic variations using SNPnexus. ( 0,469900357129401 )
Health Info Libr J - What type of leader am I?: a training needs analysis of health library and information managers. ( 0,469673642626142 )
AMIA Annu Symp Proc - Developing an online and in-person HIT workforce training program using a team-based learning approach. ( 0,469427009995883 )
Med Biol Eng Comput - Size matters: MEG empirical and simulation study on source localization of the earliest visual activity in the occipital cortex. ( 0,469333696748406 )
Health Info Libr J - A bibliometric analysis of the clinical development of drugs in Norway for the year 2000. ( 0,469200978096479 )
Appl Clin Inform - Interest in health information exchange in ambulatory care: a statewide survey. ( 0,468680918870747 )
Telemed J E Health - Telepresent intubation supervision is as effective as in-person supervision of procedurally naive operators. ( 0,468637723507324 )
Comput. Biol. Med. - Identification of epilepsy stages from ECoG using genetic programming classifiers. ( 0,468223817853765 )
Health Info Libr J - The academic librarian as co-investigator on an interprofessional primary research team: a case study. ( 0,467683492970034 )
IEEE Trans Image Process - Retina verification system based on biometric graph matching. ( 0,467579243063098 )
J Biomed Inform - Complementary ensemble clustering of biomedical data. ( 0,467345207986397 )
Wiley Interdiscip Rev Syst Biol Med - Complexity and the reductionism-holism debate in systems biology. ( 0,467335733742974 )
Res Synth Methods - Exploration of heterogeneity in distributed research network drug safety analyses. ( 0,466305597242574 )
Wiley Interdiscip Rev Syst Biol Med - Using systems approaches to address challenges for clinical implementation of pharmacogenomics. ( 0,464646508219299 )