Thanks to its ability to process large amounts of data, artificial intelligence (AI) has become an increasingly popular tool for solving complex problems over the past several decades.
As understanding of advanced computer algorithms grows, the range of AI-based techniques for the diagnosis, surgical treatment and monitoring of brain diseases keeps widening.
To assess the state-of-the-art in the use of AI for brain disease, a group of Italian researchers had recently conducted a systematic literature review, selecting 154 most cited papers out of a total of 2,696.
According to co-author on the paper Alice Segato, “[…] in recent years, thanks to the accumulation of relevant data and the development of increasingly effective algorithms, it has been possible to significantly increase the understanding of complex brain mechanisms.”
The paper demonstrates that, during the last decade, there’s been an exponential growth in the number of studies evaluating AI models as an assisting tool across multiple paradigms of brain care.
More specifically, the authors have identified eight key paradigms: “diagnosis with anatomical information, diagnosis with morphological information, diagnosis with connectivity information, candidate selection for surgical treatment, target definition for surgical treatment, trajectory definition for surgical treatment, modelling of tissue deformation for intra-operative assistance, and prediction of patient outcome for postoperative assessment”.
In addition, Segato and colleagues also emphasise the importance of using “explainable algorithms” that provide clear paths to solutions, rather than relying on “black box” algorithms which often do come to the right conclusion, but tend to operate in a way that’s almost impossible to understand.
“If humans are to accept algorithmic prescriptions or diagnosis, they need to trust them,” Segato said. “Researchers’ efforts are leading to the creation of increasingly sophisticated and interpretable algorithms, which could favour a more intensive use of ‘intelligent’ technologies in practical clinical contexts.”
The paper was published in the journal APL Bioengineering.