Scientists can’t completely rely on the accuracy of discoveries made using machine-learning techniques, according to Rice University statistician Genevera Allen.

One of the most discussed sub categories of AI, machine learning is just about everywhere today. But scientists have warned that their predictions should be treated with a grain of salt until machine-learning systems are capable of assessing the uncertainty and reproducibility of their predictions.

Allen said that uncorroborated data-driven discoveries from recently published ML studies of cancer data are a good example.

“In precision medicine, it’s important to find groups of patients that have genomically similar profiles so you can develop drug therapies that are targeted to the specific genome for their disease,” she added. “People have applied machine learning to genomic data from clinical cohorts to find groups, or clusters, of patients with similar genomic profiles.

But there are cases where discoveries don’t produce corroborated results.

You may also like