A Drug Recommendation System (Dr.S) for Cancer Cell Lines

Balvert, Marleen; Patoulidis, Georgios; Patti, A.J.; Deist, Timo M.; Eyler, Christine E.; Dutilh, Bas E.; Schönhuth, Alexander; Craft, David

doi:10.2139/ssrn.3551621

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Palanivinayagam and Sasikumar (2020) proposed a drug recommendation system aiming at minimizing potential side effects. Balvert et al (2019) conducted personalized drug prescription based on information from cancer cell lines by selecting the prediction model with the best performance for each drug. In a recent review paper, Romagnoli et al (2017) discussed the information needed for making clinical recommendations about potential drug–drug interactions.…”

Section: Research Backgroundmentioning

confidence: 99%

Bayesian multitask learning for medicine recommendation based on online patient reviews

2023

View full text Add to dashboard Cite

Motivation We propose a drug recommendation model that integrates information from both structured data (patient demographic information) and unstructured texts (patient reviews). It is based on multitask learning to predict review ratings of several satisfaction-related measures for a given medicine, where related tasks can learn from each other for prediction. The learned models can then be applied to new patients for drug recommendation. This is fundamentally different from most recommender systems in e-commerce, which do not work well for new customers (referred to as the cold-start problem). To extract information from review texts, we employ both topic modeling and sentiment analysis. We further incorporate variable selection into the model via Bayesian LASSO, which aims to filter out irrelevant features. To our best knowledge, this is the first Bayesian multitask learning method for ordinal responses. We are also the first to apply multitask learning to medicine recommendation. The sample code and data are made available at GitHub: Results We evaluate the proposed method on two sets of drug reviews involving 17 depression/high blood pressure related drugs. Overall, our method performs better than existing benchmark methods in terms of accuracy and AUC. It is effective even with a small sample size and only a few available features, and more robust to possible non-informative covariates. Due to our model explainability, insights generated from our model may work as a useful reference for doctors. In practice, however, a final decision should be carefully made by combining the information from the proposed recommender with doctors’ domain knowledge and past experience. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Research Backgroundmentioning

confidence: 99%