Classification of patient movement events captured with a 6-axis inertial sensor

Patient monitoring is an important part of the overall treatment plan for hospital in-patients. However, monitoring is often time consuming for hospital staff. Staff must either remain in a patient's room, check in on the patient with frequent intervals or remotely monitor the patient via video surveillance. Constant monitoring may be disruptive to the patient as he or she attempts to rest. Furthermore, all of these methods may be considered intrusive to the patient's privacy and time-consuming for hospital staff which may result in increased medical costs. To mitigate these issues, we propose an alternate method of patient monitoring wherein a high-sensitivity 6-axis accelerometer is attached to the patient's hospital bed. Using frequency-series analysis, we can extract relevant patterns for patient movement and train a classifier to identify movement patterns of the patient. Automated monitoring of the patient's movement frees up time for hospital staff. The system can be configured to immediately notify staff when certain events are detected, thereby directing resources to where they are needed most. Event identification accuracy of 90% for a 12-class problem space was achieved.