An algorithm that uses artificial intelligence systems to predict the ways that many drugs currently on the market, tested almost exclusively on men (for various reasons), can create unexpected problems for women.
The new mathematical formula is called AwareDX (acronym for Analyzing Women At Risk for Experiencing Drug toxicity) and has been developed by the Department of Biomedical Informatics at Columbia University in New York.
What is it exactly? “Women take longer to metabolize medications”, write the researchers in the scientific journal Cell, “and they experience twice the risk of developing adverse reactions compared with men.
Unfortunately, however, these sex differences have not yet been comprehensively understood”.
AwareDX was created for the exact purpose of trying to identify the possible weaknesses of certain types of medicines, and to prevent these in advance. The artificial intelligence system gets its information from FAERS (FDA Adverse Event Reporting System), a large pharmacovigilance archive in the United States, which contains reports on the adverse effects of drugs on the market, coming from consumers, healthcare workers and manufacturers, in the last 50 years.
AwareDX groups the data into sex-balanced subsets, before looking for patterns and trends. To improve the results, the algorithm then repeats the entire process 25 times. Thanks to AwareDX, the researchers were able to compile 20,000 potential different effects between men and women, identifying many of them through the FAERS data.
For example, they focused on a gene (an active DNA trait) called ABCB1, which, in the case of many drugs, affects how much a medicine can be used by the body and for how long. This gene is more active in men, and AwareDX identified two drugs (one against cholesterol and one antipsychotic) that produce adverse effects, depending on gender, due to the action of ABCB1.
“The most important thing for us”, explained Payal Chandak, one of the authors of the study, “is that not only do we have a database of adverse events, but we’ve shown that for some of these events, there is pre-existing knowledge of genetic differences between men and women”.
The researchers hope that the “insights” from AwareDX can help doctors to make more informed choices when prescribing drugs, especially to women.
But why are the majority of medicines tested only on men? “Clinical trials”, write the researchers in Patterns, “have historically been conducted in homogeneous patient populations (for example, white males).
Until 1993, the US Food and Drug Administration (FDA, the body that regulates and controls the use of drugs in the United States, editor’s note) designated women as a special sub-group of patients during clinical trials. A decade after this ‘designation’ was lifted, women remained severely under-represented in clinical trials”.
Men, in particular, are used in trials, because the male body is more stable than the female one. The menstrual cycle constantly changes a woman’s hormonal structure and influences a large number of biochemical reactions, depending on its different stages. A complete study ought to take all of this into account, but doing so would cost much more and would be more complex to manage.
Women, however, aren’t the only part of the population that is under-studied. Entire ethnic populations have been overlooked by research, because the majority of studies, especially in the field of cancer – as recently highlighted by Harold Varmus, winner of the Nobel Prize in Medicine – are carried out on white populations, failing to pay sufficient attention to other groups.
For this reason, Varmus has launched the Polyethnic-1000 project, together with the New York Genome Center, to try and change this situation.
