Data mining analyses for precision medicine in acromegaly

Context: Predicting which acromegaly patients could benefit from somatostatin receptor ligand (SRL) is crucial to avoid months of ineffective treatment for non-responding cases. Although many biomarkers linked to SRL response have been identified, there is no consensus criterion on how to assign pharmacologic treatment according to biomarker levels. Objective: Our aim is to provide better predictive tools for a more accurate acromegaly patient stratification regarding the ability to respond to SRL. Design and patients: Retrospective multicenter study of 71 acromegaly patients. Methods: We used advanced mathematical modelling and artificial intelligence to predict SRL response combining molecular and clinical information. Results: Different models of patient stratification were obtained regarding SRL response, with a much higher accuracy when the studied cohort is fragmented according to relevant clinical characteristics. Considering all the models, a patient stratification based on the extrasellar growth of the tumor, sex, age and the expression of E-cadherin, GHRL, IN1-GHRL, DRD2, SSTR5 and PEBP1 is proposed, with accuracies that stand between 71 to 95%. Furthermore, we show an association between extrasellar growth and high BMI for SRL non-responding patients. Conclusion. The use of data mining is necessary for implementation of personalized medicine in acromegaly and requires an interdisciplinary effort between computer science, mathematics, biology and medicine. This new methodology opens a door to more precise personalized medicine for acromegaly patients.