Next Article in Journal
Improving Our Understanding and Practice of Antibiotic Prescribing: A Study on the Use of Social Norms Feedback Letters in Primary Care
Next Article in Special Issue
Assessment of the Toxicity of Quantum Dots through Biliometric Analysis
Previous Article in Journal
Firm Growth as a Driver of Sustainable Product Innovation: Mediation and Moderation Analysis. Evidence from Manufacturing Firms
Previous Article in Special Issue
Polydatin Beneficial Effects in Zebrafish Larvae Undergoing Multiple Stress Types
Article

Multi-Drug Featurization and Deep Learning Improve Patient-Specific Predictions of Adverse Events

1
Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA
2
Coral Genomics, Inc., 953 Indiana St., San Francisco, CA 94107, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Paul B. Tchounwou
Int. J. Environ. Res. Public Health 2021, 18(5), 2600; https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph18052600
Received: 12 January 2021 / Revised: 23 February 2021 / Accepted: 3 March 2021 / Published: 5 March 2021
(This article belongs to the Collection Predictive Toxicology)
While the clinical approval process is able to filter out medications whose utility does not offset their adverse drug reaction profile in humans, it is not well suited to characterizing lower frequency issues and idiosyncratic multi-drug interactions that can happen in real world diverse patient populations. With a growing abundance of real-world evidence databases containing hundreds of thousands of patient records, it is now feasible to build machine learning models that incorporate individual patient information to provide personalized adverse event predictions. In this study, we build models that integrate patient specific demographic, clinical, and genetic features (when available) with drug structure to predict adverse drug reactions. We develop an extensible graph convolutional approach to be able to integrate molecular effects from the variable number of medications a typical patient may be taking. Our model outperforms standard machine learning methods at the tasks of predicting hospitalization and death in the UK Biobank dataset yielding an R2 of 0.37 and an AUC of 0.90, respectively. We believe our model has potential for evaluating new therapeutic compounds for individualized toxicities in real world diverse populations. It can also be used to prioritize medications when there are multiple options being considered for treatment. View Full-Text
Keywords: adverse events; real world evidence; neural networks; graph convolution; FDA FAERS; UK Biobank adverse events; real world evidence; neural networks; graph convolution; FDA FAERS; UK Biobank
Show Figures

Figure 1

MDPI and ACS Style

Anastopoulos, I.N.; Herczeg, C.K.; Davis, K.N.; Dixit, A.C. Multi-Drug Featurization and Deep Learning Improve Patient-Specific Predictions of Adverse Events. Int. J. Environ. Res. Public Health 2021, 18, 2600. https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph18052600

AMA Style

Anastopoulos IN, Herczeg CK, Davis KN, Dixit AC. Multi-Drug Featurization and Deep Learning Improve Patient-Specific Predictions of Adverse Events. International Journal of Environmental Research and Public Health. 2021; 18(5):2600. https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph18052600

Chicago/Turabian Style

Anastopoulos, Ioannis N., Chloe K. Herczeg, Kasey N. Davis, and Atray C. Dixit 2021. "Multi-Drug Featurization and Deep Learning Improve Patient-Specific Predictions of Adverse Events" International Journal of Environmental Research and Public Health 18, no. 5: 2600. https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph18052600

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop