Dose-Specific Adverse Drug Reaction Identification in Electronic Patient Records: Temporal Data Mining in an Inpatient Psychiatric Population

Abstract

BackgroundData collected for medical, filing and administrative purposes in electronic patient records (EPRs) represent a rich source of individualised clinical data, which has great potential for improved detection of patients experiencing adverse drug reactions (ADRs), across all approved drugs and across all indication areas.ObjectivesThe aim of this study was to take advantage of techniques for temporal data mining of EPRs in order to detect ADRs in a patient- and dose-specific manner.MethodsWe used a psychiatric hospital’s EPR system to investigate undesired drug effects. Within one workflow the method identified patient-specific adverse events (AEs) and links these to specific drugs and dosages in a temporal manner, based on integration of text mining results and structured data. The structured data contained precise information on drug identity, dosage and strength.ResultsWhen applying the method to the 3,394 patients in the cohort, we identified AEs linked with a drug in 2,402 patients (70.8 %). Of the 43,528 patient-specific drug substances prescribed, 14,736 (33.9 %) were linked with AEs. From these links we identified multiple ADRs (p < 0.05) and found them to occur at similar frequencies, as stated by the manufacturer and in the literature. We showed that drugs displaying similar ADR profiles share targets, and we compared submitted spontaneous AE reports with our findings. For nine of the ten most prescribed antipsychotics in the patient population, larger doses were prescribed to sedated patients than non-sedated patients; five patients exhibited a significant difference (p < 0.05). Finally, we present two cases (p < 0.05) identified by the workflow. The method identified the potentially fatal AE QT prolongation caused by methadone, and a non-described likely ADR between levomepromazine and nightmares found among the hundreds of identified novel links between drugs and AEs (p < 0.05).ConclusionsThe developed method can be used to extract dose-dependent ADR information from already collected EPR data. Large-scale AE extraction from EPRs may complement or even replace current drug safety monitoring methods in the future, reducing or eliminating manual reporting and enabling much faster ADR detection.Electronic supplementary materialThe online version of this article (doi:10.1007/s40264-014-0145-z) contains supplementary material, which is available to authorised users.

Big Data for Health

“…Mining EHRs is a valuable tool for improving clinical knowledge and supporting clinical research, for example, in discovering phenotype information [5]. Mining local information included in EHR data has already been proven to be effective for a wide range of healthcare challenges, such as disease management support [6], [7], pharmacovigilance [8], building models for predicting health risk assessment [9], [10], enhancing knowledge about survival rates [11], [12], therapeutic recommendation [11], [13], discovering comorbidities, and building support systems for the recruitment of patients for new clinical trials [14]. Most of this work focused on the analysis of very large multidimensional longitudinal patient data collected over many years.…”

Data Requirements for the Correct Identification of Medication Errors and Adverse Drug Events in Patients Presenting at an Emergency Department

“…In 1993 Cullen et al [37] coined the term "system failure" for ME attributable to missing patient data required for safe prescription and use of medication. These findings were later confirmed by Warrer [35] and Eriksson [32,33] while Schnurrer [12] stressed the continued need for the comprehensive assessment of all available patient data. Warrer [36] showed that "manual in-depth chart reviews" can ensure a high level of reliability in the detection of ADE.…”

“…The notion to make use of all available (i.e. most complete) patient data for the detection of ADE and for clinical decision support is not new [32][33][34][35][36]. The HELP hospital information system (Health Evaluation Through Logical Processing), introduced in 1967, pioneered the combination of all available patient data, i.e.…”

Proceedings of the Sixth International Workshop on Health Text Mining and Information Analysis

“…In a recent study (Henriksson et al, 2015a), information pertaining to ADEs -including named entities such as drugs and medical problems, as well as relations between them, i.e., whether one exists and whether it expresses, e.g., an indication or an ADE -were detected in clinical notes using machine learning; this approach, however, relies on the availability of data that has been manually labeled outside the clinical setting. There have also been efforts to combine information from the structured and unstructured sections of EHRs for ADE detection (Harpaz et al, 2010;Eriksson et al, 2014). In one of these (Henriksson et al, 2015b), heterogeneous types of clinical data, including free-text notes, were represented using distributional semantics, the use of which is also investigated in this study.…”