Deep learning to jointly analyze images and clinical data for disease detection
In recent years, computer-assisted diagnostic systems increasingly gained
interest through the use of deep learning techniques. Surely, the medical field could
be one of the best environments in which the power of the AI algorithms can be
tangible for everyone. Deep learning models can be useful to help radiologists elaborate
fast and even more accurate diagnosis or accelerate the triage systems in hospitals.
However, differently from other fields of works, the collaboration and co-work
between data scientists and physicians is crucial in order to achieve better performances.
With this work we show how it is possible to classify X-ray images through
a multi-input neural network that also considers clinical data. Indeed, the use of clinical
information together with the images allowed us to obtain better results than
those already present in the literature on the same data.