Table 3.

Characteristics of included studies

Author, Year	Country	Aim	No. of used observations	Method of data analysis	Outcome
Keine et al. 2019 [24]	USA	Evaluating a precision medicine platform to identify a multitude of polypharmacy problems in people with dementia and mild Alzheimer’s disease through the creation of personalized, multidomain treatment plans	295 patients with a family history of Alzheimer’s disease or mild cognitive decline	Clinical decision support software (CDSS) with machine-learning algorithms	The system was able to identify a multitude of polypharmacy problems that individuals are currently facing.
Kadra et al. 2015 [25]	UK	Extracting antipsychotic polypharmacy data from structured and free-text fields in electronic health records	7201 patients with serious mental illness	Combination of natural language processing and a bespoke algorithm.	Individual instances of antipsychotic prescribing, 2 or more antipsychotics prescribed in any 6 week window; antipsychotic co-prescribing for 6 months
Duke et al. 2010 [26]	USA	Creating a decision support system tailored to the evaluation of adverse reactions in patients on multiple medications	16,340 unique drug and side-effect pairs, representing 250 common medications	A numeric score was assigned to reflect the strength of association between drug and effect. Based on this score, the system generates graphical adverse reaction maps for any user-selected combination of drugs.	This tool demonstrated a 60% reduction in time to complete a query (61 s vs. 155 s, p < 0.0001) with no decrease in accuracy