Allison Kang – BPUholdings.com
Background/Problem: High volume of dementia falls are a serious dilemma as reported by the Joint Commission. Every year, about one million patients fall within hospitals (AHRQ.gov). Forty percent of those falls result in injury. This affects a hospital’s reputation, financial burdens and increases the cost of care by approximately $14,000. A reoccurring factor to falls is due to inadequate supervision of staff. Current systems lack the ability to monitor falls and don’t have the intelligent technology to prevent future falls from happening.
Solution: SeVA, Senior Virtual Assistant, is an Artificial Emotional Intelligent (AEI) based platform with natural language processing to interact with patients, to provide continuous monitoring and ultimately – prevent falls. SeVA uses safe, pocketsize mmWave radar (mWR) sensors that can detect changes in a patient’s position. SeVA then initiates conversation with the patient to understand his/her needs; simultaneously, alerting medical staff during emergencies. SeVA will significantly impact and reduce administrative workload for medical staff by enabling more time for critical caretaking. The AEI technology will decrease the number of erroneous falls, allowing immediate patient care and critical support.
Licensing AEI technology to 1% of healthcare patients will generate $15 Million in annual revenue.
Method: The system consists of: SeVA Patient Room, mWR, SeVA Master Control, and a SeVA Server, with Internet. The mWR system detects physical movement (hand wave, standing, sitting) and then transmits this information to the SeVA Server. The Server activates the SeVA Patient Room App, which then initiates a conversation with the patient, synchronously alerting the nurse. The Server is able to manage multiple SeVA Patient Rooms congruently.
SeVA’s lab testing has shown a 90% accuracy for fall detection. The device is pending clinical trial for implementation in a large academic hospital. Phase demonstration of SeVA has received positive feedback from medical staff.