Interrupted Time-Series Study for In-hospital Fall Reduction

The purpose of this study is to determine the effect of an Internet-of-Things bed fall solution when used in a hospital setting.

The study evaluates the SensableCare System for reducing bed falls. The SensableCare System will be used in three units of a hospital. It will be turned off for one month for the control group and then turned on the next month for the intervention group, repeating this sequence until the study concludes. To better inform the data analysis, the investigators collect baseline patient characteristics, fall risk scores, and the unit fall rate every month.

The SenableCare System: A pressure sensor pad is placed between the mattress surface and the bed sheet. The system lets nurses know how the patient is positioned in bed at the time of the alert, from which room number the alert is being generated, and informs other nurses when a patient is being assisted.

Using a predictive algorithm, the system can also monitor patient position in bed and send specific, customized alerts if nurses want to know when a patient begins to stir in bed, sits up in bed, attempts to leave the bed, or is already out of bed. When the system's software algorithm detects an increased probability of a bed exit, the system alerts the nursing staff via an app on mobile devices (i.e., smartphones) that nurses carry and via a dashboard at the nursing station. When the patient attempts to leave the bed, an audible message coming from a control box next to the patient's bed reminds the patient not to leave and that a nurse will arrive shortly. Concurrently, nurses receive alerts at a dashboard and through their smartphones via audible, vibratory, and visual alerts prompting a rapid response. Nurses respond to the alerts by tapping a control box in the patient room or returning the patient back to bed; this turns off alerts at the dashboard and on other nurses' smartphones.

Nurses can customize each individual patient's alert settings. Nurses receive bed leaving alerts when the System detects the patient is attempting to leave the bed or is out of the bed. Nurses may also choose to receive alerts when a patient is stirring after being still for >20 minutes and/or when a patient is sitting up in bed. Both the nurse and nurse aide responsible for an enrolled patient receive alerts directly through their smartphones via a real-time push notification. The charge nurse at the nursing station also receives alerts through the SensableCare app on the dashboard.

Standard medical care: A standard bed fall alarm or no alarm is used as standard medical care. The three trial units only have two bed fall alarms available for high fall risk patients. Those who do not consent to the study use this standard bed fall alarm or none at all. The standard bed fall alarm signals when a patient is exiting the bed via an audible alert. The nurses listen for the sound and go to the room to assist the patient.

Inclusion criteria

• inpatient
• consents to study (family members may sign on behalf of patients unable to consent)
• high fall risk patient (assessed fall risk score greater than or equal to 3 points

Exclusion criteria

• unable to cooperate
• under quarantine
• using special mattresses (cushion pad, air mattresses)