The role of machine learning in advancing precision medicine with feedback control

The capacity of machine-learning methods to handle large and com-plex datasets makes them suitable for applications in precision med-icine. Current methods automate data analysis and predict physio-logical outcomes of patients with various types of clinical data to inform treatment strategies. In this perspective, we propose ways in which machine learning can be leveraged even further to advance methods of optimizing patient treatment. Namely, machine learning can be used to expand applications of feedback control to direct the response of complex biological systems predictably and automati-cally. This paves the way for highly sophisticated treatments that continuously adapt to an individual patient's response. The ele-ments of control that can be improved using machine learning include sensor data analysis, modeling, and methods of reconfigur-ing the control algorithm "on the fly."We discuss the control chal-lenges unique to the analysis/control of complex biological systems, existing work, and areas that remain underdeveloped.