The gold‐standard approach for modeling pharmacokinetic mediated drug–drug interactions is the use of physiologically‐based pharmacokinetic modeling and population pharmacokinetics. However, these models require extensive amounts of drug‐specific data generated from a wide variety of in vitro and in vivo models, which are later refined with clinical data and system‐specific parameters. Machine learning has the potential to be utilized for the prediction of drug–drug interactions much earlier in the drug discovery cycle, using inputs derived from, among others, chemical structure. This could lead to refined chemical designs in early drug discovery. Machine‐learning models have many advantages, such as the capacity to automate learning (increasing the speed and scalability of predictions), improved generalizability by learning from multicase historical data, and highlighting statistical and potentially clinically significant relationships between input variables. In contrast, the routinely used mechanistic models (physiologically‐based pharmacokinetic models and population pharmacokinetics) are currently considered more interpretable, reliable, and require a smaller sample size of data, although insights differ on a case‐by‐case basis. Therefore, they may be appropriate for later stages of drug–drug interaction assessment when more in vivo and clinical data are available. A combined approach of using mechanistic models to highlight features that can be used for training machine‐learning models may also be exploitable in the future to improve the performance of machine learning. In this review, we provide concepts, strategic considerations, and compare machine learning to mechanistic modeling for drug–drug interaction risk assessment across the stages of drug discovery and development.

Combination therapy or concomitant drug administration can be associated with pharmacokinetic drug–drug interactions, increasing the risk of adverse drug events and reduced drug efficacy. Thus far, machine‐learning models have been developed that can classify drug–drug interactions. However, to enable quantification of the pharmacokinetic effects of a drug–drug interaction, regression‐based machine learning should be explored. Therefore, this study investigated the use of regression‐based machine learning to predict changes in drug exposure caused by pharmacokinetic drug–drug interactions. Fold changes in exposure relative to substrate drug monotherapy were collected from 120 clinical drug–drug interaction studies extracted from the Washington Drug Interaction Database and SimCYP compound library files. Drug characteristics (features) were collected such as structure, physicochemical properties, in vitro pharmacokinetic properties, cytochrome P450 metabolic activity, and population characteristics. Three different regression‐based supervised machine‐learning models were then applied to the prediction task: random forest, elastic net, and support vector regressor. Model performance was evaluated using fivefold cross‐validation. Strongest performance was observed with support vector regression, with 78% of predictions within twofold of the observed exposure changes. The results show that changes in drug exposure can be predicted with reasonable accuracy using regression‐based machine‐learning models trained on data available early in drug discovery. This has potential applications in enabling earlier drug–drug interaction risk assessment for new drug candidates.

Introduction: To report with multi-modal imaging the clinical course of 3 patients with new-onset uveitis following treatment with etanercept. Methods: Retrospective case-note reviews were conducted of 3 patients previously established on etanercept who developed new-onset acute uveitis. Results and Discussion: Three patients were assessed with a mean age of 44.3 (43-47). Etanercept was indicated for the treatment of ankylosing spondylitis in two patients and psoriatic arthritis in 1 patient. Duration of etanercept treatment ranged from 7 to 10 years; however, in two cases, treatment recently changed to an etanercept biosimilar agent. Two patients were diagnosed with bilateral panuveitis and one patient had chronic relapsing anterior uveitis. Infection screen was negative in all three patients. 2 patients developed cystoid macular oedema as viewed on Spectral Domain OCT. Fundus fluorescein angiography was performed in one patient who demonstrated bilateral retinal vasculitis. All three patients were started on systemic and topical treatment. One patient received sub-tenon triamcinolone injection. Etanercept was discontinued for all patients. 1 of 3 patients lost vision at 7 months. 2 patients demonstrated long-term remission and one patient required intravitreal steroid implantation to stabilize an ongoing intraocular inflammation. Two patients who had complete remission were commenced on Adalimumab while the third patient was commenced on Secukinumab. Conclusion: The clinical course of uveitis developing paradoxically following etanercept treatment is variable. Multi-modal imaging is useful for the clinician that helps in diagnosing and monitoring associated macular oedema and retinal ischaemia. Cessation of etanercept and systemic corticosteroid treatment are often required to prevent ocular morbidity.