Dataset Information

Identification of acute myocardial infarction from electronic healthcare records using different disease coding systems: a validation study in three European countries.

ABSTRACT:

Objective

To evaluate positive predictive value (PPV) of different disease codes and free text in identifying acute myocardial infarction (AMI) from electronic healthcare records (EHRs).

Design

Validation study of cases of AMI identified from general practitioner records and hospital discharge diagnoses using free text and codes from the International Classification of Primary Care (ICPC), International Classification of Diseases 9th revision-clinical modification (ICD9-CM) and ICD-10th revision (ICD-10).

Setting

Population-based databases comprising routinely collected data from primary care in Italy and the Netherlands and from secondary care in Denmark from 1996 to 2009.

Participants

A total of 4 034 232 individuals with 22 428 883 person-years of follow-up contributed to the data, from which 42 774 potential AMI cases were identified. A random sample of 800 cases was subsequently obtained for validation.

Main outcome measures

PPVs were calculated overall and for each code/free text. 'Best-case scenario' and 'worst-case scenario' PPVs were calculated, the latter taking into account non-retrievable/non-assessable cases. We further assessed the effects of AMI misclassification on estimates of risk during drug exposure.

Results

Records of 748 cases (93.5% of sample) were retrieved. ICD-10 codes had a 'best-case scenario' PPV of 100% while ICD9-CM codes had a PPV of 96.6% (95% CI 93.2% to 99.9%). ICPC codes had a 'best-case scenario' PPV of 75% (95% CI 67.4% to 82.6%) and free text had PPV ranging from 20% to 60%. Corresponding PPVs in the 'worst-case scenario' all decreased. Use of codes with lower PPV generally resulted in small changes in AMI risk during drug exposure, but codes with higher PPV resulted in attenuation of risk for positive associations.

Conclusions

ICD9-CM and ICD-10 codes have good PPV in identifying AMI from EHRs; strategies are necessary to further optimise utility of ICPC codes and free-text search. Use of specific AMI disease codes in estimation of risk during drug exposure may lead to small but significant changes and at the expense of decreased precision.

SUBMITTER: Coloma PM

PROVIDER: S-EPMC3686251 | biostudies-literature | 2013 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of acute myocardial infarction from electronic healthcare records using different disease coding systems: a validation study in three European countries.

Coloma Preciosa M PM Valkhoff Vera E VE Mazzaglia Giampiero G Nielsson Malene Schou MS Pedersen Lars L Molokhia Mariam M Mosseveld Mees M Morabito Paolo P Schuemie Martijn J MJ van der Lei Johan J Sturkenboom Miriam M Trifirò Gianluca G

BMJ open 20130620 6

<h4>Objective</h4>To evaluate positive predictive value (PPV) of different disease codes and free text in identifying acute myocardial infarction (AMI) from electronic healthcare records (EHRs).<h4>Design</h4>Validation study of cases of AMI identified from general practitioner records and hospital discharge diagnoses using free text and codes from the International Classification of Primary Care (ICPC), International Classification of Diseases 9th revision-clinical modification (ICD9-CM) and IC ...[more]

PMID: 23794587

Similar Datasets

Project description:BackgroundDrug-related adverse events remain an important cause of morbidity and mortality and impose huge burden on healthcare costs. Routinely collected electronic healthcare data give a good snapshot of how drugs are being used in 'real-world' settings.ObjectiveTo describe a strategy that identifies potentially drug-induced acute myocardial infarction (AMI) from a large international healthcare data network.MethodsPost-marketing safety surveillance was conducted in seven population-based healthcare databases in three countries (Denmark, Italy, and the Netherlands) using anonymised demographic, clinical, and prescription/dispensing data representing 21,171,291 individuals with 154,474,063 person-years of follow-up in the period 1996-2010. Primary care physicians' medical records and administrative claims containing reimbursements for filled prescriptions, laboratory tests, and hospitalisations were evaluated using a three-tier triage system of detection, filtering, and substantiation that generated a list of drugs potentially associated with AMI. Outcome of interest was statistically significant increased risk of AMI during drug exposure that has not been previously described in current literature and is biologically plausible.ResultsOverall, 163 drugs were identified to be associated with increased risk of AMI during preliminary screening. Of these, 124 drugs were eliminated after adjustment for possible bias and confounding. With subsequent application of criteria for novelty and biological plausibility, association with AMI remained for nine drugs ('prime suspects'): azithromycin; erythromycin; roxithromycin; metoclopramide; cisapride; domperidone; betamethasone; fluconazole; and megestrol acetate.LimitationsAlthough global health status, co-morbidities, and time-invariant factors were adjusted for, residual confounding cannot be ruled out.ConclusionA strategy to identify potentially drug-induced AMI from electronic healthcare data has been proposed that takes into account not only statistical association, but also public health relevance, novelty, and biological plausibility. Although this strategy needs to be further evaluated using other healthcare data sources, the list of 'prime suspects' makes a good starting point for further clinical, laboratory, and epidemiologic investigation.

Project description:ObjectivesTo investigate whether the use and timing of prescription of β blockers in patients with chronic obstructive pulmonary disease (COPD) having a first myocardial infarction was associated with survival and to identify factors related to their use.DesignPopulation based cohort study in England.SettingUK national registry of myocardial infarction (Myocardial Ischaemia National Audit Project (MINAP)) linked to the General Practice Research Database (GPRD), 2003-11.ParticipantsPatients with COPD with a first myocardial infarction in 1 January 2003 to 31 December 2008 as recorded in MINAP, who had no previous evidence of myocardial infarction in their GPRD or MINAP record. Data were provided by the Cardiovascular Disease Research using Linked Bespoke studies and Electronic Health Records (CALIBER) group at University College London.Main outcome measureCox proportional hazards ratio for mortality after myocardial infarction in patients with COPD in those prescribed β blockers or not, corrected for covariates including age, sex, smoking status, drugs, comorbidities, type of myocardial infarction, and severity of infarct.ResultsAmong 1063 patients with COPD, treatment with β blockers started during the hospital admission for myocardial infarction was associated with substantial survival benefits (fully adjusted hazard ratio 0.50, 95% confidence interval 0.36 to 0.69; P<0.001; median follow-up time 2.9 years). Patients already taking a β blocker before their myocardial infarction also had a survival benefit (0.59, 0.44 to 0.79; P<0.001). Similar results were obtained with propensity scores as an alternative method to adjust for differences between those prescribed and not prescribed β blockers. With follow-up started from date of discharge from hospital, the effect size was slightly attenuated but there was a similar protective effect of treatment with β blockers started during hospital admission for myocardial infarction (0.64, 0.44 to 0.94; P=0.02).ConclusionsThe use of β blockers started either at the time of hospital admission for myocardial infarction or before a myocardial infarction is associated with improved survival after myocardial infarction in patients with COPD.RegistrationNCT01335672.

Project description:BackgroundThe widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention.ObjectiveWe aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI).MethodsMedical concepts, including patients' age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score.ResultsCompared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice.ConclusionsThe introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

Project description:BackgroundEvaluation is a challenging but necessary part of the development cycle of clinical information systems like the electronic medical records (EMR) system. It is believed that such evaluations should include multiple perspectives, be comparative and employ both qualitative and quantitative methods. Self-administered questionnaires are frequently used as a quantitative evaluation method in medical informatics, but very few validated questionnaires address clinical use of EMR systems.MethodsWe have developed a task-oriented questionnaire for evaluating EMR systems from the clinician's perspective. The key feature of the questionnaire is a list of 24 general clinical tasks. It is applicable to physicians of most specialties and covers essential parts of their information-oriented work. The task list appears in two separate sections, about EMR use and task performance using the EMR, respectively. By combining these sections, the evaluator may estimate the potential impact of the EMR system on health care delivery. The results may also be compared across time, site or vendor. This paper describes the development, performance and validation of the questionnaire. Its performance is shown in two demonstration studies (n = 219 and 80). Its content is validated in an interview study (n = 10), and its reliability is investigated in a test-retest study (n = 37) and a scaling study (n = 31).ResultsIn the interviews, the physicians found the general clinical tasks in the questionnaire relevant and comprehensible. The tasks were interpreted concordant to their definitions. However, the physicians found questions about tasks not explicitly or only partially supported by the EMR systems difficult to answer. The two demonstration studies provided unambiguous results and low percentages of missing responses. In addition, criterion validity was demonstrated for a majority of task-oriented questions. Their test-retest reliability was generally high, and the non-standard scale was found symmetric and ordinal.ConclusionThis questionnaire is relevant for clinical work and EMR systems, provides reliable and interpretable results, and may be used as part of any evaluation effort involving the clinician's perspective of an EMR system.

Dataset Information

Identification of acute myocardial infarction from electronic healthcare records using different disease coding systems: a validation study in three European countries.

Objective

Design

Setting

Participants

Main outcome measures

Results

Conclusions

Publications

Identification of acute myocardial infarction from electronic healthcare records using different disease coding systems: a validation study in three European countries.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets