Abstract:Background: Adverse drug reactions and adverse drug events (ADEs) are major public health issues. Many different prospective tools for the automated detection of ADEs in hospital databases have been developed and evaluated. The objective of the present study was to evaluate an automated method for the retrospective detection of ADEs with hyperkalaemia during inpatient stays. Methods: We used a set of complex detection rules to take account of the patient's clinical and biological context and the chronological … Show more
“…Then, we combined laboratory test results and prescription of drugs with narrow indications (SPS, in this study) to improve comorbidity detection [ 24 ]. This result needs to be confirmed in other similar situations, to further validate the algorithm performance.…”
BackgroundMedical coding is used for a variety of activities, from observational studies to hospital billing. However, comorbidities tend to be under-reported by medical coders. The aim of this study was to develop an algorithm to detect comorbidities in electronic health records (EHR) by using a clinical data warehouse (CDW) and a knowledge database.MethodsWe enriched the Theriaque pharmaceutical database with the French national Comorbidities List to identify drugs associated with at least one major comorbid condition and diagnoses associated with a drug indication. Then, we compared the drug indications in the Theriaque database with the ICD-10 billing codes in EHR to detect potentially missing comorbidities based on drug prescriptions. Finally, we improved comorbidity detection by matching drug prescriptions and laboratory test results. We tested the obtained algorithm by using two retrospective datasets extracted from the Rennes University Hospital (RUH) CDW. The first dataset included all adult patients hospitalized in the ear, nose, throat (ENT) surgical ward between October and December 2014 (ENT dataset). The second included all adult patients hospitalized at RUH between January and February 2015 (general dataset). We reviewed medical records to find written evidence of the suggested comorbidities in current or past stays.ResultsAmong the 22,132 Common Units of Dispensation (CUD) codes present in the Theriaque database, 19,970 drugs (90.2%) were associated with one or several ICD-10 diagnoses, based on their indication, and 11,162 (50.4%) with at least one of the 4878 comorbidities from the comorbidity list. Among the 122 patients of the ENT dataset, 75.4% had at least one drug prescription without corresponding ICD-10 code. The comorbidity diagnoses suggested by the algorithm were confirmed in 44.6% of the cases. Among the 4312 patients of the general dataset, 68.4% had at least one drug prescription without corresponding ICD-10 code. The comorbidity diagnoses suggested by the algorithm were confirmed in 20.3% of reviewed cases.ConclusionsThis simple algorithm based on combining accessible and immediately reusable data from knowledge databases, drug prescriptions and laboratory test results can detect comorbidities.Electronic supplementary materialThe online version of this article (10.1186/s12911-018-0586-x) contains supplementary material, which is available to authorized users.
“…Then, we combined laboratory test results and prescription of drugs with narrow indications (SPS, in this study) to improve comorbidity detection [ 24 ]. This result needs to be confirmed in other similar situations, to further validate the algorithm performance.…”
BackgroundMedical coding is used for a variety of activities, from observational studies to hospital billing. However, comorbidities tend to be under-reported by medical coders. The aim of this study was to develop an algorithm to detect comorbidities in electronic health records (EHR) by using a clinical data warehouse (CDW) and a knowledge database.MethodsWe enriched the Theriaque pharmaceutical database with the French national Comorbidities List to identify drugs associated with at least one major comorbid condition and diagnoses associated with a drug indication. Then, we compared the drug indications in the Theriaque database with the ICD-10 billing codes in EHR to detect potentially missing comorbidities based on drug prescriptions. Finally, we improved comorbidity detection by matching drug prescriptions and laboratory test results. We tested the obtained algorithm by using two retrospective datasets extracted from the Rennes University Hospital (RUH) CDW. The first dataset included all adult patients hospitalized in the ear, nose, throat (ENT) surgical ward between October and December 2014 (ENT dataset). The second included all adult patients hospitalized at RUH between January and February 2015 (general dataset). We reviewed medical records to find written evidence of the suggested comorbidities in current or past stays.ResultsAmong the 22,132 Common Units of Dispensation (CUD) codes present in the Theriaque database, 19,970 drugs (90.2%) were associated with one or several ICD-10 diagnoses, based on their indication, and 11,162 (50.4%) with at least one of the 4878 comorbidities from the comorbidity list. Among the 122 patients of the ENT dataset, 75.4% had at least one drug prescription without corresponding ICD-10 code. The comorbidity diagnoses suggested by the algorithm were confirmed in 44.6% of the cases. Among the 4312 patients of the general dataset, 68.4% had at least one drug prescription without corresponding ICD-10 code. The comorbidity diagnoses suggested by the algorithm were confirmed in 20.3% of reviewed cases.ConclusionsThis simple algorithm based on combining accessible and immediately reusable data from knowledge databases, drug prescriptions and laboratory test results can detect comorbidities.Electronic supplementary materialThe online version of this article (10.1186/s12911-018-0586-x) contains supplementary material, which is available to authorized users.
“…Because the levels of serum potassium—defined as hyperkalemia—in the study varied, varying results were inevitable [ 12 ]. For this reason, we set the cutoff of hyperkalemia to two levels, 5.5 mEq/L and 6.0 mEq/L.…”
Introduction. In spite of the established importance of detecting angiotensin-converting enzyme inhibitor (ACEI) or angiotensin II receptor blocker- (ARB-) induced hyperkalemia, there have not been many studies on the time of its occurrence. Methods. We retrospectively analyzed electronic medical records to determine the onset time and incidence rate of hyperkalemia (
serum
potassium
>
5.5
mEq
/
L
or 6.0 mEq/L) among hospitalized patients newly started on a 15-day ACEI or ARB therapy. Results. Among 3101 hospitalized patients, hyperkalemia incidence was 0.5%–0.9% and 0.8%–2.1% in the ACEI and ARB groups, respectively. However, it was not significantly different among different ARB types. Hyperkalemia’s onset was distributed throughout 15 days, without any trend. Hyperkalemia incidence was 7.3 and 35.1 times higher at 5.5 mEq/L (
hazard
ratio
HR
=
7.31
,
95
%
confidence
interval
CI
=
4.19
–
12.76
,
p
<
0.001
) and 6.0 mEq/L (
HR
=
35.11
,
95
%
CI
=
8.25
–
149.52
,
p
<
0.001
), respectively, than the baseline creatinine level. Hyperkalemia incidence in patients with chronic renal failure was 5.7 and 9.2 times higher at 5.5 mEq/L (
HR
=
5.72
,
95
%
CI
=
3.24
–
10.12
,
p
<
0.001
) and 6.0 mEq/L (
HR
=
9.16
,
95
%
CI
=
4.02
–
20.88
,
p
<
0.001
), respectively. Conclusions. It is unlikely that it is necessary to monitor hyperkalemia immediately after administration of ACEI or ARB. However, when prescribed for patients with abnormal kidney function, clinicians should always consider the possibility of developing hyperkalemia.
“…In some studies, however, clinical measurements or lab tests from EHRs have been utilized for (adverse) event detection by representing them as time series [ 22 ], aggregating them into categorical variables [ 23 ], or representing them from multiple perspectives [ 24 ]. Other studies have used diagnoses and drugs instead [ 25 , 26 ], while these data types have also been used in conjunction for signaling ADEs, albeit only in a case study and on a very limited scale [ 27 ].…”
BackgroundThe digitization of healthcare data, resulting from the increasingly widespread adoption of electronic health records, has greatly facilitated its analysis by computational methods and thereby enabled large-scale secondary use thereof. This can be exploited to support public health activities such as pharmacovigilance, wherein the safety of drugs is monitored to inform regulatory decisions about sustained use. To that end, electronic health records have emerged as a potentially valuable data source, providing access to longitudinal observations of patient treatment and drug use. A nascent line of research concerns predictive modeling of healthcare data for the automatic detection of adverse drug events, which presents its own set of challenges: it is not yet clear how to represent the heterogeneous data types in a manner conducive to learning high-performing machine learning models.MethodsDatasets from an electronic health record database are used for learning predictive models with the purpose of detecting adverse drug events. The use and representation of two data types, as well as their combination, are studied: clinical codes, describing prescribed drugs and assigned diagnoses, and measurements. Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation.ResultsWithin each data type, combining multiple representations yields better predictive performance compared to using any single representation. The use of clinical codes for adverse drug event detection significantly outperforms the use of measurements; however, there is no significant difference over datasets between using only clinical codes and their combination with measurements. For certain adverse drug events, the combination does, however, outperform using only clinical codes. Feature selection leads to increased predictive performance for both data types, in isolation and combined.ConclusionsWe have demonstrated how machine learning can be applied to electronic health records for the purpose of detecting adverse drug events and proposed solutions to some of the challenges this presents, including how to represent the various data types. Overall, clinical codes are more useful than measurements and, in specific cases, it is beneficial to combine the two.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.