Major depressive disorder (MDD) is complex and multifactorial, posing a major challenge of tailoring the optimal medication for each patient. Current practice for MDD treatment mainly relies on trial and error, with an estimated 42–53% response rates for antidepressant use. Here, we sought to generate an accurate predictor of response to a panel of antidepressants and optimize treatment selection using a data-driven approach analyzing combinations of genetic, clinical, and demographic factors. We analyzed the response patterns of patients to three antidepressant medications in the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study, and employed state-of-the-art machine learning (ML) tools to generate a predictive algorithm. To validate our results, we assessed the algorithm’s capacity to predict individualized antidepressant responses on a separate set of 530 patients in STAR*D, consisting of 271 patients in a validation set and 259 patients in the final test set. This assessment yielded an average balanced accuracy rate of 72.3% (SD 8.1) and 70.1% (SD 6.8) across the different medications in the validation and test set, respectively (p < 0.01 for all models). To further validate our design scheme, we obtained data from the Pharmacogenomic Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS) of patients treated with citalopram, and applied the algorithm’s citalopram model. This external validation yielded highly similar results for STAR*D and PGRN-AMPS test sets, with a balanced accuracy of 60.5% and 61.3%, respectively (bothp’s < 0.01). These findings support the feasibility of using ML algorithms applied to large datasets with genetic, clinical, and demographic features to improve accuracy in antidepressant prescription.

Large amounts of expired and unused medications accumulate in households. This potentially exposes the public to hazards due to uncontrolled use of medications. Most of the expired or unused medications that accumulate in households (household medical waste) is thrown to the garbage or flushed down to the sewage, potentially contaminating waste-water, water resources and even drinking water. There is evidence that pharmaceutical active ingredients reach the environment, including food, however the risk to public health from low level exposure to pharmaceuticals in the environment is currently unknown. In Israel, there is no legislation regarding household medical waste collection and disposal. Furthermore, only less than 14 % of Israelis return unused medications to Health Maintenance Organization (HMO) pharmacies. In this study, we investigated world-wide approaches and programs for household medical waste collection and disposal. In many countries around the world there are programs for household medical waste collection. In many countries there is legislation to address the issue of household medical waste, and this waste is collected in hospitals, clinics, law enforcement agencies and pharmacies. Furthermore, in many countries, medication producers and pharmacies pay for the collection and destruction of household medical waste, following the “polluter pays” principle. Several approaches and methods should be considered in Israel: (a) legislation and regulation to enable a variety of institutes to collect household medical waste (b) implementing the “polluter pays” principle and enforcing medical products manufactures to pay for the collection and destruction of household medical waste. (c) Raising awareness of patients, pharmacists, and other medical health providers regarding the health and environmental risks in accumulation of drugs and throwing them to the garbage, sink or toilet. (d) Adding specific instructions regarding disposal of the drug, in the medication label and leaflet. (e) Examining incentives for returning medications to pharmacies. (f) Examining drug collection from deceased in retirement homes and hospitals.