Researchers at Columbia University have developed AwareDX—Analysing Women At Risk for Experiencing Drug toXicity—a machine learning algorithm that identifies and predicts differences in adverse drug effects between men and women by analyzing 50 years’ worth of reports in an FDA database. The algorithm, described September 22 in the journal Patterns, automatically corrects for the biases in these data that stem from an overrepresentation of male subjects in clinical research trials.

Though men and women can have different responses to medications—the sleep aid Ambien, for example, metabolizes more slowly in women, causing next-day grogginess—even doctors may not know about these differences because most clinical trial data itself are biased toward men. This trickles down to impact prescribing guidelines, drug marketing, and ultimately, patients’ health.

“Pharma has a history of ignoring complex problems. Traditionally, clinical trials have not even included women in their studies. The old-fashioned way used to be to get a group of healthy guys together to give them the drug, make sure it didn’t kill them, and you’re off to the races. As a result, we have a lot less information about how women respond to drugs than men,” says Nicholas Tatonetti, an associate professor of biomedical informatics at Columbia University and a co-author on the paper. “We haven’t had the ability to evaluate these differences before, or even to quantify them.”

Tatonetti teamed up with one of his students—Payal Chandak, a senior biomedical informatics major at Columbia University and the other co-author on the paper. Together they developed AwareDX. Because it is a machine learning algorithm, AwareDX can automatically adjust for sex-based biases in a way that would take concerted effort to do manually.

“Machine learning is definitely a buzzword, but essentially the idea is to correct for these biases

Parkinson’s disease is most commonly treated with levodopa, a drug which alleviates the slowing of bodily movements, called bradykinesia, found in Parkinson’s disease patients.

But the benefits of levodopa wear off as the disease progresses. The relationship between its dosage and its effectiveness becomes fuzzy, and high doses can result in dyskinesia, which are involuntary and uncontrollable movements.

To better understand the underlying reasons behind these effects, researchers from the Université de Montréal, University of Bologna, and University of Ottawa created a model of the interactions between levodopa, dopamine, and the basal ganglia, an area of the brain that plays a crucial role in Parkinson’s disease. They discuss their findings in the journal Chaos.

“In Parkinson’s disease, the dopaminergic neurons of the basal ganglia are dying, which results in a lower concentration of dopamine. Levodopa is effective at the beginning of the disease, because it can be transformed into dopamine by the remaining dopaminergic neurons,” said Florence Véronneau-Veilleux, one of the authors. “However, at advanced stages of disease, there are not enough remaining dopaminergic neurons for levodopa to prevent symptoms.”

Once they confirmed the accuracy of their model by using it to predict behavior like modification of dopamine dynamics with neuron degeneration, the group used it to simulate a patient tapping their finger a few hours after taking levodopa, a clinical assessment of bradykinesia.

What they found verified suspicions about the progression of Parkinson’s disease. Eventually, as the brain loses more and more of its neurons, its dopamine concentration falls, and no amount of levodopa can compensate for this. This leads to a competition of effects, in which maintaining low levels of levodopa is not