Most seniors fear falling more than disease. Hospitals fear falls also. Between 700,000 and 1 million patients fall in hospitals each year, according to the Agency for Healthcare Research and Quality.[i] Most patients who fall are not seriously injured, but the cost of one-third of falls resulting in a serious fall-related injury is more than $13,000, and the patient’s length of stay increases by an average of 6.27 days.[ii] In 2015, medical costs for falls in the U.S. totaled more than $50 billion.[iii]
Qventus, Inc., a Mountain View, California, technology startup is determined to reduce the number of falls in the hospital. The traditional method of prevention is to respond to a call button alarm. If you have spent any time in a hospital, you know the alarms are nearly continuous. It is impossible for the already busy nurses and aides to respond quickly to every alarm. Qventus is applying AI and machine learning to the problem.
The data used to build the software model includes call lights, bed alarms, electronic medical records, patient age, patient medications and when last administered, and the vitals last recorded by a nurse or aide. By applying machine learning technology to this assortment of data, the Qventus software can identify patterns. With enough historical data, the company believes it can accurately identify patients at high risk of a fall. The software would send a special alarm directly to an electronic badge worn by an appropriate nurse for quick response.
At one California hospital, use of the Qventus AI software has resulted in a 29% reduction in falls since 2014.[iv] Some large investors are believers in the Qventus vision, and have invested over $40 million in the company. The cash infusion will enable the company to expand significantly beyond the handful of hospitals it now has as customers.
[i] “Fall Prevention Toolkit Facilitates Customized Risk Assessment and Prevention Strategies, Reducing Inpatient Falls,” AHRQ Agency for Healthcare Research and Quality (2018), https://innovations.ahrq.gov/profiles/fall-prevention-toolkit-facilitates-customized-risk-assessment-and-prevention-strategies?id=3094
[ii] Lola Butcher, “The No-Fall Zone,” Hospitals & Health Networks (2013), https://www.hhnmag.com/articles/6404-Hospitals-work-to-prevent-patient-falls
[iii] Emma Ockerman, “AI Hospital Software Knows Who’s Going to Fall,” Bloomberg Businessweek (2018), https://www.bloomberg.com/news/articles/2018-06-21/ai-programs-fight-medical-alarm-fatigue-with-patient-fall-alerts
[iv] Ibid.
