Untangling adverse drug reactions in polypharmacy: multifactor analysis partner

Datharsis, a University of Granada spin-off specialised in explainable data analysis, is looking to join a consortium as the partner responsible for data analysis, either leading the data analysis work package or contributing specific tasks.

Adverse drug reactions in patients on multiple medications are a textbook multifactor problem: drug combination, dose, duration, age, sex, renal and hepatic function, comorbidities and genetic background all act at once, and the interactions matter more than any single factor. Our methods (ASCA, vASCA and group-wise models) separate the effect of each factor and their interactions, and identify the variables behind each effect. For a personalised approach that clinicians and regulators must act on, a risk score nobody can explain is not enough.

What we offer:

• Design of observational and interventional studies on polypharmacy, including stratification and sample size

• Analysis of prescription, clinical, laboratory and real-world data, combined with omics or pharmacogenomic data where available

• Interpretable models that identify which patient profiles and which drug combinations carry the risk, and why

• Rigorous validation with cross-validation and permutation testing

• Reproducible, auditable, FAIR-aligned analysis pipelines

• Access to DathaSuite, our analysis platform, and training for consortium researchers

Our team’s methods are built for studies with several crossed factors, and have been applied in clinical, crop and ecotoxicology settings. See the documented cases.

We are looking for consortia with hospitals, primary care networks, pharmacovigilance groups or prescription registries that need a partner to analyse complex, multifactor data transparently.