Automated detection of substance use information from electronic health records for a pediatric population.
Ontology highlight
ABSTRACT: Objective
Substance use screening in adolescence is unstandardized and often documented in clinical notes, rather than in structured electronic health records (EHRs). The objective of this study was to integrate logic rules with state-of-the-art natural language processing (NLP) and machine learning technologies to detect substance use information from both structured and unstructured EHR data.Materials and methods
Pediatric patients (10-20 years of age) with any encounter between July 1, 2012, and October 31, 2017, were included (n = 3890 patients; 19 478 encounters). EHR data were extracted at each encounter, manually reviewed for substance use (alcohol, tobacco, marijuana, opiate, any use), and coded as lifetime use, current use, or family use. Logic rules mapped structured EHR indicators to screening results. A knowledge-based NLP system and a deep learning model detected substance use information from unstructured clinical narratives. System performance was evaluated using positive predictive value, sensitivity, negative predictive value, specificity, and area under the receiver-operating characteristic curve (AUC).Results
The dataset included 17 235 structured indicators and 27 141 clinical narratives. Manual review of clinical narratives captured 94.0% of positive screening results, while structured EHR data captured 22.0%. Logic rules detected screening results from structured data with 1.0 and 0.99 for sensitivity and specificity, respectively. The knowledge-based system detected substance use information from clinical narratives with 0.86, 0.79, and 0.88 for AUC, sensitivity, and specificity, respectively. The deep learning model further improved detection capacity, achieving 0.88, 0.81, and 0.85 for AUC, sensitivity, and specificity, respectively. Finally, integrating predictions from structured and unstructured data achieved high detection capacity across all cases (0.96, 0.85, and 0.87 for AUC, sensitivity, and specificity, respectively).Conclusions
It is feasible to detect substance use screening and results among pediatric patients using logic rules, NLP, and machine learning technologies.
SUBMITTER: Ni Y
PROVIDER: S-EPMC8449626 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveLarge electronic health record (EHR) datasets are increasingly used to facilitate research on growth, but measurement and recording errors can lead to biased results. We developed and tested an automated method for identifying implausible values in pediatric EHR growth data.Materials and methodsUsing deidentified data from 46 primary care sites, we developed an algorithm to identify weight and height values that should be excluded from analysis, including implausible values and values that were recorded repeatedly without remeasurement. The foundation of the algorithm is a comparison of each measurement, expressed as a standard deviation score, with a weighted moving average of a child's other measurements. We evaluated the performance of the algorithm by (1) comparing its results with the judgment of physician reviewers for a stratified random selection of 400 measurements and (2) evaluating its accuracy in a dataset with simulated errors.ResultsOf 2 000 595 growth measurements from 280 610 patients 1 to 21 years old, 3.8% of weight and 4.5% of height values were identified as implausible or excluded for other reasons. The proportion excluded varied widely by primary care site. The automated method had a sensitivity of 97% (95% confidence interval [CI], 94-99%) and a specificity of 90% (95% CI, 85-94%) for identifying implausible values compared to physician judgment, and identified 95% (weight) and 98% (height) of simulated errors.Discussion and conclusionThis automated, flexible, and validated method for preparing large datasets will facilitate the use of pediatric EHR growth datasets for research.
| S-EPMC7651915 | biostudies-literature
Project description:Background: Drug-induced coagulopathy (DIC) is a severe adverse reaction and has become a significantly increased clinical problem in children. It is crucial to the detection of the DIC safety signal for drug post-marketing scientific supervision purposes. Therefore, this study aimed to detect potential signals for DIC in children using the routine electronic medical record (EMR) data. Methods: This study extracted EMR data from Beijing Children's Hospital between 2009 and 2020. A two-stage modeling method was developed to detect the signal of DIC. We calculated the crude incidence by mining cases of coagulopathy to select the potential suspected drugs; then, propensity score-matched retrospective cohorts of specific screened drugs from the first stage were constructed and estimated the odds ratio (OR) and 95% confidence interval (CI) using conditional logistic regression models. The current literature evidence was used to assess the novelty of the signal. Results:In the study, from a total of 340 drugs, 22 drugs were initially screened as potentially inducing coagulopathy. In total, we identified 19 positive DIC associations. Of these, potential DIC risk of omeprazole (OR: 2.23, 95% CI: 1.88-2.65), chlorpheniramine (OR:3.04, 95% CI:2.56-3.60), and salbutamol sulfate (OR:1.36, 95% CI:1.07-1.73) were three new DIC signals in both children and adults. Twelve associations between coagulopathy and drugs, meropenem (OR: 3.38, 95% CI: 2.72-4.20), cefoperazone sulbactam (OR: 2.80, 95% CI: 2.30-3.41), fluconazole (OR: 2.11, 95% CI: 1.71-2.59), voriconazole (OR: 2.82, 95% CI: 2.20-3.61), ambroxol hydrochloride (OR: 2.12, 95% CI: 1.74-2.58), furosemide (OR: 2.36, 95% CI: 2.08-2.67), iodixanol (OR: 2.21, 95% CI: 1.72-2.85), cefamandole (OR: 1.82, 95% CI: 1.56-2.13), ceftizoxime (OR: 1.95, 95% CI: 1.44-2.63), ceftriaxone (OR: 1.95, 95% CI: 1.44-2.63), latamoxef sodium (OR: 1.76, 95% CI: 1.49-2.07), and sulfamethoxazole (OR: 1.29, 95% CI: 1.01-1.64), were considered as new signals in children. Conclusion: The two-stage algorithm developed in our study to detect safety signals of DIC found nineteen signals of DIC, including twelve new signals in a pediatric population. However, these safety signals of DIC need to be confirmed by further studies based on population study and mechanism research.
| S-EPMC9348591 | biostudies-literature
Project description:BACKGROUND:Adverse events in health care entail substantial burdens to health care systems, institutions, and patients. Retrospective trigger tools are often manually applied to detect AEs, although automated approaches using electronic health records may offer real-time adverse event detection, allowing timely corrective interventions. OBJECTIVE:The aim of this systematic review was to describe current study methods and challenges regarding the use of automatic trigger tool-based adverse event detection methods in electronic health records. In addition, we aimed to appraise the applied studies' designs and to synthesize estimates of adverse event prevalence and diagnostic test accuracy of automatic detection methods using manual trigger tool as a reference standard. METHODS:PubMed, EMBASE, CINAHL, and the Cochrane Library were queried. We included observational studies, applying trigger tools in acute care settings, and excluded studies using nonhospital and outpatient settings. Eligible articles were divided into diagnostic test accuracy studies and prevalence studies. We derived the study prevalence and estimates for the positive predictive value. We assessed bias risks and applicability concerns using Quality Assessment tool for Diagnostic Accuracy Studies-2 (QUADAS-2) for diagnostic test accuracy studies and an in-house developed tool for prevalence studies. RESULTS:A total of 11 studies met all criteria: 2 concerned diagnostic test accuracy and 9 prevalence. We judged several studies to be at high bias risks for their automated detection method, definition of outcomes, and type of statistical analyses. Across all the 11 studies, adverse event prevalence ranged from 0% to 17.9%, with a median of 0.8%. The positive predictive value of all triggers to detect adverse events ranged from 0% to 100% across studies, with a median of 40%. Some triggers had wide ranging positive predictive value values: (1) in 6 studies, hypoglycemia had a positive predictive value ranging from 15.8% to 60%; (2) in 5 studies, naloxone had a positive predictive value ranging from 20% to 91%; (3) in 4 studies, flumazenil had a positive predictive value ranging from 38.9% to 83.3%; and (4) in 4 studies, protamine had a positive predictive value ranging from 0% to 60%. We were unable to determine the adverse event prevalence, positive predictive value, preventability, and severity in 40.4%, 10.5%, 71.1%, and 68.4% of the studies, respectively. These studies did not report the overall number of records analyzed, triggers, or adverse events; or the studies did not conduct the analysis. CONCLUSIONS:We observed broad interstudy variation in reported adverse event prevalence and positive predictive value. The lack of sufficiently described methods led to difficulties regarding interpretation. To improve quality, we see the need for a set of recommendations to endorse optimal use of research designs and adequate reporting of future adverse event detection studies.
| S-EPMC6000482 | biostudies-literature
Project description:Electronic health records (EHRs) are an important source of data for detection of adverse drug reactions (ADRs). However, adverse events are frequently due not to medications but to the patients' underlying conditions. Mining to detect ADRs from EHR data must account for confounders. We developed an automated method using natural-language processing (NLP) and a knowledge source to differentiate cases in which the patient's disease is responsible for the event rather than a drug. Our method was applied to 199,920 hospitalization records, concentrating on two serious ADRs: rhabdomyolysis (n = 687) and agranulocytosis (n = 772). Our method automatically identified 75% of the cases, those with disease etiology. The sensitivity and specificity were 93.8% (confidence interval: 88.9-96.7%) and 91.8% (confidence interval: 84.0-96.2%), respectively. The method resulted in considerable saving of time: for every 1 h spent in development, there was a saving of at least 20 h in manual review. The review of the remaining 25% of the cases therefore became more feasible, allowing us to identify the medications that had caused the ADRs.
| S-EPMC3685297 | biostudies-literature
Project description:BACKGROUND: Previous studies regarding the use of information technologies (IT) specifically among pediatricians and other physicians who treat children are lacking. As such, the objective of this study is to examine the use of electronic health record (EHR) systems and other IT applications among pediatricians and other child health providers (CHPs) in Florida. METHODS: We focus on pediatricians and other CHPs who responded to a state-wide physician survey of IT use. CHPs included general pediatricians, pediatric sub-specialists, and family physicians who self-reported a practice composition of at least 20% children. We compared general pediatricians to other CHPs and all CHPs (including pediatricians) to other physicians with respect to computer and internet availability, and to the use of personal digital assistants and EHRs. Those with an EHR were also compared regarding the availability of key functions available in their system. Statistical analyses included chi-square analysis and logistic regression models which controlled for numerous factors. RESULTS: A total of 4,203 surveys (28.2% response) including 1,021 CHPs, were returned. General pediatricians (13.7%) were significantly less likely to be using an EHR than both CHP family physicians (26.1%) and pediatric sub-specialists (29.6%; p < .001). In multivariate analysis, only general pediatricians were significantly less likely than other physicians to indicate the use of an EHR system (OR = .43; 95% C.I. = .29 - .64). Overall, CHPs were less likely to have key functions available in their EHR system including electronic prescribing (53.3% vs. 61.9%; p = .028), and electronic order entry (47.7% vs. 57.2%; p = .017) among others. General pediatricians and pediatric sub-specialists frequently lagged behind CHP family physicians with respect to key EHR functions. In contrast, CHPs had growth charts (51.3% vs. 24.0%; p < .001) and weight-based dosing functions (35.5% vs.22.7%; p < .001) more frequently than others. CONCLUSION: Physicians caring for children, and especially pediatricians, in Florida, are significantly slower than other doctors to adopt EHRs, and important electronic patient safety functionalities, into their office practices.
| S-EPMC1552060 | biostudies-literature
Project description:BackgroundGrowth chart recording is a key component of pediatric care. EHR systems could provide several growth charting functionalities compared to paper methods. To our knowledge, there has been no U.S. study exploring clinicians' perceptions and practices related to recording of growth parameters as they adapt to electronic methods.ObjectivesTo explore clinician practices regarding recording growth parameters as they adapt to electronic health records (EHR) and to investigate clinician perceptions of electronic growth charting using EHR.MethodsAn online survey of pediatricians and family practitioners in Kentucky inquiring about EHR usage, specifically use of growth charting with EHR, was conducted.ResultsForty-six percent of respondents utilized EHRs, with pediatricians lagging family practitioners, and academic pediatricians lagging non-academicians. There was no consensus on EHR platforms being used. Almost a third of those who used EHR did not utilize electronic growth charting. Clinicians using EHR reported that electronic growth charts would improve clinician satisfaction and clinical efficiency as well as parent satisfaction and parent education. Only 12% of respondents provided copies of growth charts to parents at the end of their visit and discussed growth parameters with parents, with clinicians using EHR more likely to engage in these activities than non-EHR users.ConclusionAlthough Kentucky clinicians continue to slowly adopt EHRs, clinician perceptions and practices reflect enduring barriers to widespread use of electronic growth charting in pediatric and family practice. However, our results suggest that electronic growth charting has important benefits for both clinicians and patients, and greater adoption is expected as EHRs become standard across health care systems.
| S-EPMC3613041 | biostudies-literature
Project description:BackgroundSubstance use disorders (SUD) elevate the risk for COVID-19 hospitalization, but studies are inconsistent on the relationship of SUD to COVID-19 mortality.MethodsVeterans Health Administration (VHA) patients treated in 2019 and evaluated in 2020 for COVID-19 (n=5,556,315), of whom 62,303 (1.1%) tested positive for COVID-19 (COVID-19+). Outcomes were COVID-19+ by 11/01/20, hospitalization, ICU admission, or death within 60 days of a positive test. Main predictors were any ICD-10-CM SUDs, with substance-specific SUDs (cannabis, cocaine, opioid, stimulant, sedative) explored individually. Logistic regression produced unadjusted and covariate-adjusted odds ratios (OR; aOR).ResultsAmong COVID-19+ patients, 19.25% were hospitalized, 7.71% admitted to ICU, and 5.84% died. In unadjusted models, any SUD and all substance-specific SUDs except cannabis use disorder were associated with COVID-19+(ORs=1.06-1.85); adjusted models produced similar results. Any SUD and all substance-specific SUDs were associated with hospitalization (aORs: 1.24-1.91). Any SUD, cocaine and opioid disorder were associated with ICU admission in unadjusted but not adjusted models. Any SUD, cannabis, cocaine, and stimulant disorders were inversely associated with mortality in unadjusted models (OR=0.27-0.46). After adjustment, associations with mortality were no longer significant. In ad hoc analyses, adjusted odds of mortality were lower among the 49.9% of COVID-19+ patients with SUD who had SUD treatment in 2019, but not among those without such treatment.ConclusionsIn VHA patients, SUDs are associated with COVID-19 hospitalization but not COVID-19 mortality. SUD treatment may provide closer monitoring of care, ensuring that these patients received needed medical attention, enabling them to ultimately survive serious illness.
| S-EPMC8891118 | biostudies-literature
Project description:BackgroundAs the availability of interoperable electronic health records (iEHRs) or health information exchanges (HIEs) continues to increase, there is greater need and opportunity to assess the current evidence base on what works and what does not regarding the adoption, use, and impact of iEHRs.ObjectiveThe purpose of this project is to assess the international evidence base on the adoption, use, and impact of iEHRs.MethodsWe conducted a systematic review, searching multiple databases-MEDLINE, Embase, and the Cumulative Index to Nursing and Allied Health Literature (CINAHL)-with supplemental searches conducted in Google Scholar and grey literature sources (ie, Google, Grey Literature Report, and OpenGrey). All searches were conducted in January and February 2017. Articles were eligible for inclusion if they were published in English, were published from 2006 to 2017, and were either an original research study or a literature review. In order to be included, articles needed to focus on iEHRs and HIEs across multiple health care settings, as well as on the impact and effectiveness of iEHR adoption and use.ResultsWe included 130 articles in the synthesis (113 primary studies, 86.9%; 17 reviews, 13.1%), with the majority focused on the United States (88/130, 67.7%). The primary studies focused on a wide range of health care settings; the three most prevalent settings studied included acute care (59/113, 52.2%), primary care (44/113, 38.9%), and emergency departments (34/113, 30.1%). We identified 29 distinct measurement items in the 113 primary studies that were linked to 522 specific measurement outcomes. Productivity and quality were the two evaluation dimensions that received the most attention, accounting for 14 of 29 (48%) measurement items and 306 of 522 (58.6%) measurement outcomes identified. Overall, the majority of the 522 measurement outcomes were positive (298/522, 57.1%). We also identified 17 reviews on iEHR use and impact, 6 (35%) that focused on barriers and facilitators to adoption and implementation and 11 (65%) that focused on benefits and impacts, with the more recent reviews finding little generalizable evidence of benefit and impact.ConclusionsThis review captures the status of an evolving and active field focused on the use and impact of iEHRs. While the overall findings suggest many positive impacts, the quality of the primary studies were not evaluated systematically. When broken down by specific measurement item, the results directed attention both to measurement outcomes that were consistently positive and others that were mostly negative or equivocal.
| S-EPMC6592487 | biostudies-literature
Project description:BackgroundHealth information technology (HIT) certification and meaningful use are interventions encouraging the adoption of electronic health records (EHRs) in the USA. However, these initiatives also constitute a significant intervention which will change the structure of the EHR market.ObjectiveTo describe quantitatively recent changes to both the demand and supply sides of the EHR market.Materials and methodsA cohort of 3447 of hospitals from the HIMSS Analytics Database (2006-10) was created. Using hospital referral regions to define the local market, we determined the percentage of hospitals using paper records, the number of vendors, and local EHR vendor competition using the Herfindahl-Hirschman Index. Changes over time were assessed using a series of regression equations and geographic information systems analyses.ResultsOverall, there was movement away from paper records, upward trends in the number of EHR vendors, and greater competition. However, changes differed according to hospital size and region of the country. Changes were greatest for small hospitals, whereas competition and the number of vendors did not change dramatically for large hospitals.DiscussionThe EHR market is changing most dramatically for those least equipped to handle broad technological transformation, which underscores the need for continued targeted support. Furthermore, wide variations across the nation indicate a continued role for states in the support of EHR utilization.ConclusionThe structure of the EHR market is undergoing substantial changes as desired by the proponents and architects of HIT certification and meaningful use. However, these transformations are not uniform for all hospitals or all the country.
| S-EPMC3638173 | biostudies-literature
Project description:BackgroundAlcohol misuse is an important cause of premature disability and death. While clinicians are recommended to ask patients about alcohol use and provide brief interventions and specialist referral, this is poorly implemented in routine practice. We undertook a national consultation to ascertain the appropriateness of proposed standards for recording information about alcohol use in electronic health records (EHRs) in the UK and to identify potential barriers and facilitators to their implementation in practice.MethodsA wide range of stakeholders in the UK were consulted about the appropriateness of proposed information standards for recording alcohol use in EHRs via a multi-disciplinary stakeholder workshop and online survey. Responses to the survey were thematically analysed using the Consolidated Framework for Implementation Research.ResultsThirty-one stakeholders participated in the workshop and 100 in the online survey. This included patients and carers, healthcare professionals, researchers, public health specialists, informaticians, and clinical information system suppliers. There was broad consensus that the Alcohol Use Disorders Identification Test (AUDIT) and AUDIT-Consumption (AUDIT-C) questionnaires were appropriate standards for recording alcohol use in EHRs but that the standards should also address interventions for alcohol misuse. Stakeholders reported a number of factors that might influence implementation of the standards, including having clear care pathways and an implementation guide, sharing information about alcohol use between health service providers, adequately resourcing the implementation process, integrating alcohol screening with existing clinical pathways, having good clinical information systems and IT infrastructure, providing financial incentives, having sufficient training for healthcare workers, and clinical leadership and engagement. Implementation of the standards would need to ensure patients are not stigmatised and that patient confidentiality is robustly maintained.ConclusionsA wide range of stakeholders agreed that use of AUDIT-C and AUDIT are appropriate standards for recording alcohol use in EHRs in addition to recording interventions for alcohol misuse. The findings of this consultation will be used to develop an appropriate information model and implementation guide. Further research is needed to pilot the standards in primary and secondary care.
| S-EPMC5992754 | biostudies-literature