A Machine-Learning Algorithm to Optimise Automated Adverse Drug Reaction Detection from Clinical Coding

McMaster, Christopher; Liew, David; Keith, Claire; Aminian, Parnaz; Frauman, Albert G

doi:10.1007/s40264-018-00794-y

Cited by 30 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…electronic medical record, administrative data) to identify risk of adverse outcomes for drugs. For example, predicting opioid overdose risk on administrative data with opioid prescriptions using deep neural networks and GBM 34 , predict adverse drug reactions from ICD-10 codes using machine learning models 35 and comparing logistic regression with machine learning in predicting the risk of death from drug intoxication 36 . The AUC-ROC of the models from these studies ranged from 0.69 to 0.91.…”

Section: Discussionmentioning

confidence: 99%

Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data

Lü

Bennamoun

Ward

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Our aim was to investigate the usefulness of machine learning approaches on linked administrative health data at the population level in predicting older patients’ one-year risk of acute coronary syndrome and death following the use of non-steroidal anti-inflammatory drugs (NSAIDs). Patients from a Western Australian cardiovascular population who were supplied with NSAIDs between 1 Jan 2003 and 31 Dec 2004 were identified from Pharmaceutical Benefits Scheme data. Comorbidities from linked hospital admissions data and medication history were inputs. Admissions for acute coronary syndrome or death within one year from the first supply date were outputs. Machine learning classification methods were used to build models to predict ACS and death. Model performance was measured by the area under the receiver operating characteristic curve (AUC-ROC), sensitivity and specificity. There were 68,889 patients in the NSAIDs cohort with mean age 76 years and 54% were female. 1882 patients were admitted for acute coronary syndrome and 5405 patients died within one year after their first supply of NSAIDs. The multi-layer neural network, gradient boosting machine and support vector machine were applied to build various classification models. The gradient boosting machine achieved the best performance with an average AUC-ROC of 0.72 predicting ACS and 0.84 predicting death. Machine learning models applied to linked administrative data can potentially improve adverse outcome risk prediction. Further investigation of additional data and approaches are required to improve the performance for adverse outcome risk prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data

Lü

Bennamoun

Ward

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Better methods for using EHRs to extract information about ADE prevalence and drug safety in general are needed. 17 , 33 , 34 Therefore, better learning algorithms that can be applied to unstructured data as they exist in EHRs are required. 2 An approach to improve the performance of trigger tools could be to combine them with methods using a natural language processing (NLP) technique, 35 , 36 which would also enable examination of data from diverse clinical data management platforms.…”

Section: Discussionmentioning

confidence: 99%

Development and Implementation of an e-Trigger Tool for Adverse Drug Events in a Swiss University Hospital

Saghir¹,

Dimitriou²,

Schöler³

et al. 2021

DHPS

View full text Add to dashboard Cite

Purpose The purpose of the study was to develop and implement an institution-specific trigger tool based on the Institute for Healthcare Improvement medication module trigger tool (IHI MMTT) in order to detect and monitor ADEs. Methods We performed an investigator-driven, single-center study using retrospective and prospective patient data to develop (“development phase”) and implement (“implementation phase”) an efficient, institution-specific trigger tool based on the IHI MMTT. Complete medical data from 1008 patients hospitalized in 2018 were used in the development phase. ADEs were identified by chart review. The performance of two versions of the tool was assessed by comparing their sensitivities and specificities. Tool A employed only digitally extracted triggers (“e-trigger-tool”) while Tool B employed an additional manually extracted trigger. The superior tool – taking efficiency into account – was applied prospectively to 19–22 randomly chosen charts per month for 26 months during the implementation phase. Results In the development phase, 189 (19%) patients had ≥1 ADE (total 277 ADEs). The time needed to identify these ADEs was 15 minutes/chart. A total of 203 patients had ≥1 trigger (total 273 triggers – Tool B). The sensitivities and specificities of Tools A and B were 0.41 and 0.86, and 0.43 and 0.86, respectively. Tool A was more time-efficient than Tool B (4 vs 9 minutes/chart) and was therefore used in the implementation phase. During the 26-month implementation phase, 22 patients experienced trigger-identified ADEs and 529 did not. The median number of ADEs per 1000 patient days was 6 (range 0–13). Patients with at least one ADE had a mean hospital stay of 22.3 ± 19.7 days, compared to 8.0 ± 7.6 days for those without an ADE (p = 2.7×10 −14 ). Conclusion We developed and implemented an e-trigger tool that was specific and moderately sensitive, gave consistent results and required minimal resources.

show abstract

“…This can be explained by unawareness of clinicians about drug specific ADRs. Next to under detection, underreporting of ADRs is also a common problem, as well in adult clinical care, and could be improved with automated ADR detection systems (McMaster et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Precision Dosing of Doxapram in Preterm Infants Using Continuous Pharmacodynamic Data and Model-Based Pharmacokinetics: An Illustrative Case Series

et al. 2020

View full text Add to dashboard Cite

Conclusion: Real-time and non-invasive effect monitoring of drug therapy combined with model-based exposure provides relevant information to clinicians and can importantly improve therapy. The variability between and within patients emphasizes the importance of individual, objective evaluation of pharmacotherapy. These measurements, together with data on ADRs, allow for precision medicine in neonatology that should be brought to the bedside.

show abstract

A Machine-Learning Algorithm to Optimise Automated Adverse Drug Reaction Detection from Clinical Coding

Cited by 30 publications

References 15 publications

Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data

Machine learning risk prediction model for acute coronary syndrome and death from use of non-steroidal anti-inflammatory drugs in administrative data

Development and Implementation of an e-Trigger Tool for Adverse Drug Events in a Swiss University Hospital

Precision Dosing of Doxapram in Preterm Infants Using Continuous Pharmacodynamic Data and Model-Based Pharmacokinetics: An Illustrative Case Series

Contact Info

Product

Resources

About