Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources

Liang, Likeng; Hu, Jifa; Sun, Gang; Hong, Na; Wu, Ge; He, Yulong; Li, Yong; Hao, Tianyong; Liu, Li; Gong, Mengchun

doi:10.1007/s40264-022-01170-7

Cited by 18 publications

(9 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These findings are largely consistent with our disproportionality analyses of PRL-related adverse events with antipsychotics, which suggest that risperidone should be discontinued first in OLZ-treated patients with hyperprolactinemia, and that the use of aripiprazole may protect them from this adverse event. Therefore, our study has highlighted the feasibility of AI-based pharmacovigilance detection in resource-limited settings by extracting various sources of data recorded in the EHR ( 71 ). Compared with OLZ and other atypical antipsychotics, risperidone is more likely to cause hyperprolactinemia owing to its incomplete crossing of the BBB, where this results in higher occupancy by DA D 2 receptors in the pituitary gland than in the striatum ( 72 ).…”

Section: Discussionmentioning

confidence: 99%

Integrating machine learning with electronic health record data to facilitate detection of prolactin level and pharmacovigilance signals in olanzapine-treated patients

Zhu

Hu²,

Xiao³

et al. 2022

Front. Endocrinol.

View full text Add to dashboard Cite

Background and aimAvailable evidence suggests elevated serum prolactin (PRL) levels in olanzapine (OLZ)-treated patients with schizophrenia. However, machine learning (ML)-based comprehensive evaluations of the influence of pathophysiological and pharmacological factors on PRL levels in OLZ-treated patients are rare. We aimed to forecast the PRL level in OLZ-treated patients and mine pharmacovigilance information on PRL-related adverse events by integrating ML and electronic health record (EHR) data.MethodsData were extracted from an EHR system to construct an ML dataset in 672×384 matrix format after preprocessing, which was subsequently randomly divided into a derivation cohort for model development and a validation cohort for model validation (8:2). The eXtreme gradient boosting (XGBoost) algorithm was used to build the ML models, the importance of the features and predictive behaviors of which were illustrated by SHapley Additive exPlanations (SHAP)-based analyses. The sequential forward feature selection approach was used to generate the optimal feature subset. The co-administered drugs that might have influenced PRL levels during OLZ treatment as identified by SHAP analyses were then compared with evidence from disproportionality analyses by using OpenVigil FDA.ResultsThe 15 features that made the greatest contributions, as ranked by the mean (|SHAP value|), were identified as the optimal feature subset. The features were gender_male, co-administration of risperidone, age, co-administration of aripiprazole, concentration of aripiprazole, concentration of OLZ, progesterone, co-administration of sulpiride, creatine kinase, serum sodium, serum phosphorus, testosterone, platelet distribution width, α-L-fucosidase, and lipoprotein (a). The XGBoost model after feature selection delivered good performance on the validation cohort with a mean absolute error of 0.046, mean squared error of 0.0036, root-mean-squared error of 0.060, and mean relative error of 11%. Risperidone and aripiprazole exhibited the strongest associations with hyperprolactinemia and decreased blood PRL according to the disproportionality analyses, and both were identified as co-administered drugs that influenced PRL levels during OLZ treatment by SHAP analyses.ConclusionsMultiple pathophysiological and pharmacological confounders influence PRL levels associated with effective treatment and PRL-related side-effects in OLZ-treated patients. Our study highlights the feasibility of integration of ML and EHR data to facilitate the detection of PRL levels and pharmacovigilance signals in OLZ-treated patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrating machine learning with electronic health record data to facilitate detection of prolactin level and pharmacovigilance signals in olanzapine-treated patients

Zhu

Hu²,

Xiao³

et al. 2022

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence is already in use and can be a powerful tool when the data retrieved are in line with company internal standards and health authority requirements; however, technical challenges still exist. Lack of qualitative databases, weak technology, insufficient human resources and insufficient support from governments are just a few examples 46 . While current algorithms are not sufficient for complete automation, they can still be applied to improve efficiency, value and consistency if included into a system with human intelligence in control 47,48 …”

Section: Discussionmentioning

confidence: 99%

“…Lack of qualitative databases, weak technology, insufficient human resources and insufficient support from governments are just a few examples. 46 While current algorithms are not sufficient for complete automation, they can still be applied to improve efficiency, value and consistency if included into a system with human intelligence in control. 47,48 The value of mass media, social media and the Internet, as sources of case reports, has been debated and intensely investigated.…”

Section: Data Collectionmentioning

confidence: 99%

The evolution of pharmacovigilance ecosystems: Does Moore's law invite the use of Occam's razor?

Mueller

Lewis

Alexe

2022

Brit J Clinical Pharma

View full text Add to dashboard Cite

Aims Moore's law predicts the doubling of complexity of integrated circuits every 2 years; Kryder's corollary assumes a doubling of data storage every 13 months. With the increasing volume of legislation, pharmacovigilance systems today are inherently complex, and the emphasis has shifted from reactive (responding to emerging risks) to planned, active, risk‐proportionate approaches operating throughout the life cycle of medicines. Methods Exploration of the drivers for increasing complexity of pharmacovigilance systems, focusing on regulatory environment, data management and evaluation. Results Evaluation of postmarketing data plays an increasingly important role in pharmacovigilance. There is great interest on the part of all stakeholders in optimizing the use of these data. Innovative approaches, including pharmacogenetics and passive measures (sensors), will lead to increased complexity and volumes of data and inevitably to an increase in the volume of case reports. There is a multiplicity of regulations and guidelines on how to manage these data, with an inherent lack of harmonization. Conclusion We summarize the current characterization of safety data types, sources and the classification of these data. Using this benchmark, we discuss the future requirements of an effective pharmacovigilance ecosystem, keeping the principle of parsimony in mind. In this complex, continuously and rapidly changing environment, there is a need for a return to simplicity and pragmatism. The application of Occam's razor could help to support the rapid provision of new, affordable medicines with a positive benefit to risk profile.

show abstract

“…Similarly, probability scales, developed to help standardize assessment of causality for all adverse drug reactions [ 18 ] are one way to assign ADR predictability scores, but such tools still require advanced (and robust) collection capabilities. As Liang, et al point out, the quantity and quality of data directly affect the performance of AI, and there are particular challenges to implementing AI in limited-resource settings [ 19 ].…”

Section: Thinking Beyond the Status Quomentioning

confidence: 99%

Twenty-First Century Global ADR Management: A Need for Clarification, Redesign, and Coordinated Action

Louët¹,

Pitts

2022

Ther Innov Regul Sci

View full text Add to dashboard Cite

Adverse drug reactions (ADRs) are estimated to be between the fourth and sixth most common cause of death worldwide, taking their place among other prevalent causes of mortality such as heart disease, cancer, and stroke. ADRs impact a broad range of populations across a wide variety of global geography and demographics, with significant mortality and morbidity burden in vulnerable groups such as older people, pediatric populations, and individuals in low-income settings. Too large a share of medicines risk management remains limited to signal detection in big ADR databases (USFDA, EMA, WHO, etc.) This resource allocation is antiquated and applied statistical signal detection methodologies have reached their limits of usefulness. In addition, existing databases are designed for short-term reactions, closely related to medication use and, thus, can only partially assess important broader consequences across geography, time, and clinical relevance. There is an urgent need change the dynamic. We need to identify (earlier and more regularly) many of the important but often overlooked or missed ADRs. Rather than assigning blame, we need to identify the root causes of the problem so they can be clearly addressed and fixed. The public health implications are profound—particularly as we recognize the importance of predicting and mitigating the next pandemic. Consequently, medicines risk management must be integrated within a broader global public health vision. To accomplish this, we need to develop the new tools and methodologies critical to assessing these public health imperatives.

show abstract

Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources

Cited by 18 publications

References 58 publications

Integrating machine learning with electronic health record data to facilitate detection of prolactin level and pharmacovigilance signals in olanzapine-treated patients

Integrating machine learning with electronic health record data to facilitate detection of prolactin level and pharmacovigilance signals in olanzapine-treated patients

The evolution of pharmacovigilance ecosystems: Does Moore's law invite the use of Occam's razor?

Twenty-First Century Global ADR Management: A Need for Clarification, Redesign, and Coordinated Action

Contact Info

Product

Resources

About