ライフサイエンスコーパス: EHR

1 EHR audit log data can provide insights into strategies

2 EHR data from a large health care database spanning 15 y

3 EHR data on more than 112,000 participants from 34 sites

4 EHR documentation consists largely of imported text, is

5 EHR identified 472 IE discharges (430 of these were capt

6 EHR review of 342 G+ individuals predicted to have 1 MCV

7 EHR-AF (C index, 0.808 [95% CI, 0.807-0.809]) demonstrat

8 EHR-AF demonstrates predictive accuracy for incident AF

9 A strategy that limited clinicians to 1 EHR patient record open compared with a strategy that al

10 The top 4 EHR vendors accounted for 50% of attestations by ophthal

11 with patients on the following 3 activities: EHR use, conversation, and examination.

12 ly validated an electronic health record AF (EHR-AF) score in IBM Explorys Life Sciences, a multi-ins

13 cumentation behaviors changed 1 decade after EHR adoption.

14 re risks of GDM in the temporally aggregated EHRs.

15 ularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data

16 is supported, rather than controlled, by an EHR intervention.

17 The authors developed an EHR-based algorithm and demonstrated that it had excelle

18 As an example, an EHR-based intervention to improve communication and time

19 otechnical changes were made to implement an EHR-related intervention to improve patient safety, why

20 were randomly assigned in a 1:1 ratio to an EHR configuration limiting to 1 patient record open at a

21 Time stamps from the medical record and EHR audit log were analyzed to measure the length of tim

22 time with patients during office visits, and EHR use requires a substantial portion of that time.

23 ted death determined from automated data and EHRs; and (5) recurrent HZ identified from a cohort init

24 de the natural integration of PSEVs into any EHR machine-learning platform, provide a key step toward

25 cy for incident AF using readily ascertained EHR data.

26 An automated EHR extraction identified a cohort of patients at the Un

27 poor medication adherence than an automated EHR pull alone but was limited by the small number of pa

28 Because EHR software, configuration, and local context differ co

29 models showed a positive association between EHR use and billing level and a negative association bet

30 ing level and a negative association between EHR use per encounter and clinic volume.

31 The proportion of attestations by EHR vendor was calculated using all attestations for eac

32 We compared EHR-AF to existing scores including CHARGE-AF (Cohorts f

33 sis-3) criteria for objective and consistent EHR-based surveillance.

34 ethods investments that are needed to curate EHR data toward research quality and to integrate comple

35 ks), over the existing state-of-the-art deep EHR models.

36 ataset containing statistically deidentified EHR data for over 21 million individuals (Explorys Datas

37 d a transition from mostly locally developed EHRs to commercial systems.

38 nts across hospitals despite their different EHR systems.

39 isorder, and Quebec Congenital Heart Disease EHR datasets.

40 anosmia/dysgeusia, constitutes the earliest EHR-derived signature of COVID-19.

41 h played a critical role in developing early EHR prototypes and demonstrating their value to justify

42 asks involving different modalities (ECG/EEG/EHR), required level of characterization (abnormality de

43 caling up curation throughput, thus enabling EHR-powered early disease diagnosis.

44 Epic EHR software (Epic Systems Corporation) is currently one

45 AF teledermatology workflows within the Epic EHR system.

46 ould be easily integrated within an existing EHR system.

47 orkflow within the Epic system, the existing EHR system of Parkland Health and Hospital System (Dalla

48 to be essential in the next phase: expanding EHR-based interventions and maximizing their role in cre

49 hysicians invest in these clinically focused EHR functions.

50 e spent on each of the 13 clinically focused EHR functions.

51 enables reporting of patient safety-focused EHR-based interventions while accounting for the multifa

52 suggest RWOV should be further developed for EHR-related NLP.

53 ses a methodological reporting framework for EHR interventions targeting patient safety and builds on

54 gth of time required by ophthalmologists for EHR use.

55 total time required by ophthalmologists for EHR use.

56 icle provides additional recommendations for EHR-based research.

57 xamine ophthalmologist time requirements for EHR use.

58 Linear mixed models found EHR time per office visit was 31.9+/-0.2% (P < 0.001) gr

59 ated clinic workflow timings calculated from EHR timestamps and the simulation models based on them w

60 n physician examination time calculated from EHR timestamps was 13.8+/-8.2 minutes and was not statis

61 potential predictors of HIV risk drawn from EHR data from 2007-15 at Atrius Health, an ambulatory gr

62 ed aggregated and longitudinal features from EHR.

63 raction of ophthalmic surgical outcomes from EHR to answer key clinical questions on a large scale.

64 general-purpose patient representation from EHR data that facilitates clinical predictive modeling.

65 Simulation models based on big data from EHRs can test clinic changes before real-life implementa

66 ETTING, AND PARTICIPANTS: Clinical data from EHRs were linked with CGP results for 28 998 patients fr

67 This study linking diagnoses from EHRs to claims data collected valid information on PAR m

68 ; and clinical characteristics gathered from EHRs.

69 extract clinically relevant information from EHRs.

70 Furthermore, EHR confidence and acceptance improved from 40% to 90%.

71 eported poor adherence and 6.1% (n = 45) had EHR documentation of poor adherence (P < .0001).

72 y 41% of hospitals in the United States have EHR from outside providers or sources when treating a pa

73 S information from a large mental healthcare EHR data resource at the South London and Maudsley NHS F

74 plex symptomatic data from mental healthcare EHRs using NLP to facilitate further analyses of these c

75 nt was associated with decreased after-hours EHR use in a cohort of 139 academic ophthalmologists.

76 However, EHRs present several modeling challenges, including high

77 in some degree of bias and become encoded in EHR data.

78 re (65,720) and from discoveries reported in EHR analysis studies (only 10, manually extracted); and

79 There is variability in EHR use patterns among ophthalmologists.

80 es and patient characteristics documented in EHRs of a large healthcare network over the last two dec

81 lity improvement and safety interventions in EHRs is still conducted at a single site, in a single EH

82 occurrence of diagnoses and prescriptions in EHRs as a third-order tensor, and decomposed it using th

83 We included EHRs of all patients aged 15 years or older with at leas

84 or studying complex interventions, including EHR interventions.

85 PatientExploreR can incorporate EHR data from any institution that employs the CDM for u

86 However, extending analyses to incorporate EHR and biobank-based analyses will require careful cons

87 Increased EHR adoption across various clinical settings and the es

88 with approved access to their institutional EHR can use this package.

89 Integrating these models into EHRs to alert providers about patients who might benefit

90 otype and phenotype data from biobank-linked EHRs for polygenic risk prediction.

91 Longitudinal EHR data, commonly available in clinical settings, can b

92 Median EHR time per office visit in 2006 was 4.2 minutes (inter

93 ommon data model (CDM) could accelerate more EHR-based research by making the data more accessible to

94 o further ease data sharing across multisite EHR data networks.

95 linician consensus review of 2,700 narrative EHR notes (from 520 patients), supplemented by state dea

96 n (HBsAg) testing were identified by a novel EHR-based population health tool.

97 ) systems can be configured to deliver novel EHR interventions that influence clinical decision makin

98 ease of 1.7 minutes (95% CI, -4.3 to 1.0) of EHR use time per encounter for ophthalmologists with hig

99 is article describes 4 potential benefits of EHR-based research: improving clinical decisions, suppor

100 t designed for the unique characteristics of EHR.

101 hat interfaces with a relational database of EHR data in the Observational Medical Outcomes Partnersh

102 rves to inform how to coevolve the design of EHR systems and organizational decisions about processes

103 into strategies for optimizing efficiency of EHR use.

104 s clinical settings and the establishment of EHR-linked population-based biobanks provide unprecedent

105 Nevertheless, evaluators of EHR-based innovations can choose reporting guidelines th

106 tion, effectiveness, and generalizability of EHR-based interventions needed to effectively reduce pre

107 At the present time, the majority of EHR content is unstructured and locked into proprietary

108 However, the heterogeneous nature of EHR data brings forth many practical challenges along ev

109 tual factors that may affect the outcomes of EHR implementations, such as attitudes toward implementa

110 l considerations will improve the quality of EHR-based observational studies.

111 Data and safety monitoring for RCTs of EHR interventions should be conducted to guide instituti

112 In designing RCTs of EHR interventions, one should carefully consider the uni

113 es, and opportunities for standardization of EHR interventions in multisite studies and describes fle

114 e innovation lifecycle, multisite studies of EHR interventions are critical for generalizability.

115 Trials of EHR interventions should be reviewed by an institutional

116 erations for reporting on flexible trials of EHR interventions, including sharing details of the proc

117 tentional weight loss of at least 5%, use of EHR tools plus coaching resulted in less weight regain t

118 l haplotypes, and demonstrate the utility of EHR data in evolutionary analyses.

119 Analyses of EHRs in >2.6 million Vanderbilt subjects revealed signif

120 Augmented curation of EHRs suggests that only a minority of COVID(pos) patient

121 of eligible professionals attesting to MU of EHRs. Ophthalmologists were more likely to remain in the

122 research is needed to fulfill the promise of EHRs to not only store information but also support the

123 determined from automated data and review of EHRs; (5) Recurrent HZ identified from a cohort initiall

124 ] plus organizational changes) from those of EHRs alone.

125 While adoption and use of EHRs are incentivized by the federal government in the U

126 me on direct clinical face time and 37.0% on EHR and desk work.

127 y ophthalmologists directly with patients on EHR use, conversation, and examination as well as total

128 ayment systems, user training, and roles) on EHR implementation projects.

129 (27% of the examination time) were spent on EHR use, 4.7 (4.2) minutes (42%) on conversation, and 3.

130 Future studies should optimise EHR-based HIV risk prediction tools and evaluate their e

131 communication with providers (19, 37.3%) or EHR messaging (11, 21.6%).

132 the goal to optimize the workflow within our EHR, improve operative room metrics and user satisfactio

133 nal DTI prediction and large-scale patients' EHRs-based clinical corroboration has high potential in

134 Here, we show that MLCs can query EHRs in a manner similar to the hypothetico-deductive re

135 e the effect of an electronic health record (EHR) alert on chronic hepatitis B (CHB) screening among

136 oped and tested an electronic health record (EHR) algorithm to identify children with glomerular dise

137 using longitudinal electronic health record (EHR) and genetic data.

138 Large-scale use of electronic health record (EHR) data can help to understand phenotypes in a scalabl

139 ective analysis of electronic health record (EHR) data from 50,515 adult primary care patients was co

140 registry based on electronic health record (EHR) data from participating university hospitals.

141 e second leveraged electronic health record (EHR) data from the Vanderbilt University Medical Center

142 notype analyses on Electronic Health Record (EHR) data have recently drawn benefits across many areas

143 ome sequencing and electronic health record (EHR) data of 50,726 individuals were used to assess the

144 iverse and massive electronic health record (EHR) data remains challenging.

145 13; n = 1,847,165) electronic health record (EHR) data sets.

146 interest in using electronic health record (EHR) data to assess quality of care, the accuracy of suc

147 This study uses electronic health record (EHR) data to evaluate differences in central line-associ

148 lgorithm that uses electronic health record (EHR) data to identify individuals at increased risk for

149 computer science, electronic health record (EHR) data, and more affordable high-throughput genomics,

150 extracted from the Electronic Health Record (EHR) database of 150 patients to characterize the lung t

151 study, we combined electronic health record (EHR) derived phenotypes and genotype information to cond

152 modeling into the electronic health record (EHR) has been challenging, as complex models increase th

153 e interrogated the electronic health record (EHR) information of >1.3 million adults from the Geising

154 from unstructured electronic health record (EHR) provider notes is integral to advancing precision m

155 n the CHOP unified electronic health record (EHR) system (July 1, 2010, to June 30, 2014) were select

156 Electronic health record (EHR) systems can be configured to deliver novel EHR inte

157 Adoption of Electronic Health Record (EHR) systems has led to collection of massive healthcare

158 Electronic health record (EHR) systems have transformed the practice of medicine.

159 cant investment in electronic health record (EHR) systems in the United States.

160 ical data from the electronic health record (EHR) systems of diverse hospitals.

161 monly available in electronic health record (EHR) systems, can be used to predict patients' future ri

162 ied the sources of electronic health record (EHR) text documentation in ophthalmology progress notes.

163 ds displayed in an electronic health record (EHR) to 1 at a time, although little evidence supports t

164 odification of the electronic health record (EHR) to include FBSE as a recommended preventive service

165 data from hospital Electronic Health Record (EHR) to State Uniform Hospital Discharge Data Set (UHDDS

166 Using 81 electronic health record (EHR) variables, we applied least absolute shrinkage and

167 surements from the electronic health record (EHR) was 75-96% sensitive and 91%-96% specific.

168 Electronic health record (EHR)-based AF risk prediction may facilitate efficient d

169 icant predictor of electronic health record (EHR)-based estimates of 10-year survival probability in

170 Electronic health record (EHR)-based interventions to improve patient safety are c

171 he availability of electronic health record (EHR)-based phenotypes allows for genome-wide association

172 largest PheWASs on electronic health record (EHR)-derived phenotypes across 38,682 unrelated samples

173 By contrasting Electronic Health Record (EHR)-derived symptoms of COVID-19-positive (COVID(pos);

174 to BioVU, a large electronic health record (EHR)-linked biobank at Vanderbilt University Medical Cen

175 phic data from the electronic health record (EHR).

176 e phenotypes from electronic health records (EHR) and genotypes across millions of individuals, this

177 Electronic health records (EHR) are rich heterogeneous collections of patient healt

178 unt values in the electronic health records (EHR) of 45 068 patients with idiopathic pulmonary fibros

179 Electronic health records (EHR) represent a rich resource for conducting observatio

180 duction model for electronic health records (EHR), capable of simultaneously predicting the likelihoo

181 measurements and electronic health records (EHR), manual interpretation for differential diagnosis h

182 pread adoption of electronic health records (EHRs) and a transition from mostly locally developed EHR

183 atients by mining electronic health records (EHRs) and linked blood donor data.

184 Electronic health records (EHRs) are an increasingly important source of real-world

185 Increasingly, electronic health records (EHRs) are being linked to patient genetic data in bioban

186 Electronic health records (EHRs) are now widely adopted in the United States, but h

187 Electronic health records (EHRs) are quickly becoming omnipresent in healthcare, bu

188 Electronic health records (EHRs) are ubiquitous yet still evolving, resulting in a

189 wide adoption of electronic health records (EHRs) by ophthalmologists, there are widespread concerns

190 Electronic health records (EHRs) contain information on each feature of this triad.

191 -control study of electronic health records (EHRs) data of 73,099,850 unique patients, of whom 12,030

192 heterogeneity in electronic health records (EHRs) discard pertinent information.

193 ng lncRNAs and/or electronic health records (EHRs) from clinically diagnosed PTB patients and non-TB

194 or sites such as electronic health records (EHRs) from multiple healthcare systems and have drawn in

195 Wide adoption of electronic health records (EHRs) has raised the expectation that data obtained duri

196 secondary use of electronic health records (EHRs) in early pregnancy.

197 d other data with electronic health records (EHRs) in the United States and elsewhere.

198 portals to access electronic health records (EHRs) in the United States, but only 15% to 30% of patie

199 le abstraction of electronic health records (EHRs) of 600 incident patients 2011-2015; (3) HZ-related

200 le abstraction of electronic health records (EHRs) of 600 incident patients from 2011-2015; (3) HZ-re

201 and diseases and electronic health records (EHRs) of 72 million patients, we developed a novel integ

202 bridge this gap, Electronic Health Records (EHRs) of individual patients are connected to a heteroge

203 ion from paper to electronic health records (EHRs) over the past decade has been characterized by pro

204 (NLP) applied to Electronic Health Records (EHRs) presents an opportunity to create large datasets t

205 a using patients' electronic health records (EHRs) remain sparse.

206 s within existing electronic health records (EHRs) should be the standard for large health care organ

207 ata captured from electronic health records (EHRs) to address pressing medical questions, but gaps re

208 iders spend using electronic health records (EHRs) to support the care delivery process is a concern

209 Electronic health records (EHRs) were reviewed for individuals harboring P/LP varia

210 cal data, such as Electronic Health Records (EHRs), and in this case, may either correspond to new kn

211 ioVU) with linked electronic health records (EHRs), including Illumina Expanded Multi-Ethnic Global A

212 h questionnaires, electronic health records (EHRs), physical measurements, the use of digital health

213 Using Electronic Health Records (EHRs), we identified in 2010 two cohorts of PAR patients

214 from free text in electronic health records (EHRs).

215 H (which involves electronic health records [EHRs] plus organizational changes) from those of EHRs al

216 National perspective regarding EHRs.

217 The Safety-related EHR Research (SAFER) Reporting Framework enables reporti

218 data from a large health care organization's EHR between 2000 and 2013, we determined the prevalence

219 physician and hospital do not share the same EHR. Information blocking, now prohibited by federal law

220 Of the scores, EHR-AF demonstrated the best calibration to incident AF

221 imes and progress note length from secondary EHR data.

222 2016, and December 31, 2018, using secondary EHR data and a follow-up manual review of a random sampl

223 till conducted at a single site, in a single EHR.

224 am) incorporated these three lncRNAs and six EHRs (age, hemoglobin, weight loss, low-grade fever, cal

225 Structured EHR data of 385 POAG patients from a single academic ins

226 als predicted to have 1 MCVD with sufficient EHR data revealed that 52 had been given the relevant cl

227 To facilitate a learning health system, EHRs must contain clinically meaningful structured data

228 xtracts data from the corneal exam free-text EHR field.

229 coaching resulted in less weight regain than EHR tools alone.

230 owever, physicians have raised concerns that EHR time requirements have negatively affected their pro

231 and reporting CDS studies to: 1) ensure that EHR data to inform the CDS are available; 2) choose deci

232 The findings also suggest that EHR-based clinical data provide more objective estimates

233 3.3+/-7.3 minutes; P = 0.7), suggesting that EHR timestamps are accurate.

234 The EHR has become integral to perioperative care.

235 The EHR IHD phenotype was most strongly correlated with ARIC

236 The EHR IHD risk profile differed from ARIC and indicates th

237 The EHR tools included weight, diet, and physical activity t

238 The EHR-based case-control studies identified that the presc

239 imates between the ARIC risk factors and the EHR IHD were modestly linearly correlated with hazards r

240 rted poor adherence was compared between the EHR extraction and text parsing identification using a F

241 correctly identified as not eligible by the EHR data (specificity).

242 ew) and who were classified correctly by the EHR data as passing (sensitivity).

243 onstruct and export patient cohorts from the EHR for analysis with other software.

244 t parsing tool that abstracted data from the EHR was used to search for combinations of the following

245 od allergy and intolerance documented in the EHR allergy module.

246 Existing systemic data in the EHR has some predictive value in identifying POAG patien

247 imization users agreed to proficiency in the EHR system, this improved to 70% post-optimization.

248 Concussion visits in the EHR were defined based on International Classification o

249 documented by the treating physician in the EHR), and clinical benefit rate (fraction of patients wi

250 In the EHR, we found that patients taking both ceftriaxone and

251 enome-wide association study (PheWAS) in the EHR-linked BioVU biobank, we show that reduced genetical

252 cal notes, and eye examination fields in the EHR.

253 may lend itself well to integration into the EHR without sacrificing the performance seen in more com

254 y computational assessment components of the EHR intervention, such as a predictive algorithm used to

255 analyzing the full phenotypic breadth of the EHR, computerized risk screening approaches may enhance

256 rimination and clinical net benefit than the EHR model.

257 r studying food allergy, suggesting that the EHR's allergy module has the potential to be used for cl

258 months of personalized coaching through the EHR patient portal, with 24 scheduled contacts.

259 ther an informatics algorithm applied to the EHR could electronically identify patients with AERD.

260 d describes the changes necessary to use the EHR to build a learning health system.

261 ard clinical practice or who did not use the EHR were excluded.

262 We calculated time spent using the EHR associated with each individual office visit using E

263 al ophthalmologist spent 3.7 hours using the EHR for a full day of clinic: 2.1 hours during examinati

264 of use, providers spend more time using the EHR for an office visit, generate longer notes, and clos

265 ) total ophthalmologist time spent using the EHR was 10.8 (5.0) minutes per encounter (range, 5.8-28.

266 rns about the amount of time spent using the EHR.

267 ment of automated risk prediction within the EHR based on systemic data to assist with clinical decis

268 tance of each SPOKE node for any code in the EHRs.

269 For each patient, the EHRs were linked to corresponding claims data with MRU a

270 loped an informatics algorithm to search the EHRs of patients aged 18 years and older from the Partne

271 inherited lipodystrophies and examined their EHR for comorbidities associated with lipodystrophy.

272 g higher rates of patient engagement through EHR portals will require paying more attention to the ne

273 Participants were randomly assigned to EHR tools (tracking group) versus EHR tools plus coachin

274 ter-hours work each night, devoted mostly to EHR tasks.

275 Considerations unique to EHR-based studies include assessment of the accuracy of

276 We used EHR data from 231 patients with glomerular disorders at

277 on) is currently one of the most widely used EHR system in the United States, and development of a su

278 ic and Nextgen were the most frequently used EHRs for attestation by ophthalmologists.

279 e (1.91 using CHA(2)DS(2)-VASc to 2.58 using EHR-AF).

280 se 1.85 using CHA(2)DS(2)-VASc to 2.88 using EHR-AF), stroke (1.61 using C(2)HEST to 1.92 using CHARG

281 f 1 pediatric ophthalmologist's clinic using EHR timestamp data, which was used to develop a scheduli

282 n subgroup analyses, AF discrimination using EHR-AF was lower in individuals with stroke (C index, 0.

283 oke electronic quality measures (eQMs) using EHR data.

284 Lastly, it presents an approach for using EHR data and clinical prediction to generate quantitativ

285 Prediction models using EHR data can identify patients at high risk of HIV acqui

286 l also apply to observational research using EHR data, and these are well addressed in prior literatu

287 ated with each individual office visit using EHR audit logs and determined chart closure times and pr

288 cy of top repositioned drug candidates using EHRs of over 72 million patients.

289 6 minutes and 14 seconds per encounter using EHRs, with chart review (33%), documentation (24%), and

290 istribution of time spent by providers using EHRs varies greatly within specialty.

291 o examine how the amount of time spent using EHRs as well as related documentation behaviors changed

292 The time spent using EHRs to support care delivery constitutes a large portio

293 ssigned to EHR tools (tracking group) versus EHR tools plus coaching (coaching group).

294 to integrate complementary data sources when EHR data alone are insufficient for research goals.

295 xible software that interfaces directly with EHR data structured around a common data model (CDM) cou

296 r future research on patient engagement with EHR data through patient portals, These studies mostly i

297 ndependent sample of 18 498 individuals with EHR data to conduct a PheWAS with.

298 study to apply machine learning models with EHRs to predict GDM, which will facilitate personalized

299 Healthcare systems with EHRs should consider using electronic data to evaluate c

300 illustrate potential biases inherent within EHR analyses, how these may be compounded across time an