The Role of Wearable Devices in Reducing Fall Incidences in Hospitals

This report addresses the significant problem of patient falls in hospitals, a prevalent issue leading to injuries and increased healthcare costs. The report identifies the use of wearable devices, specifically those with accelerometers, as a potential solution. It reviews existing research supporting the efficacy of wearable technology in detecting and predicting falls, highlighting the importance of constant monitoring and timely alerts to healthcare personnel. The proposed plan involves using waist belts with accelerometers to detect movements indicative of a fall, triggering alerts to staff within a specific radius. The report acknowledges limitations, such as battery failure, but concludes that wearable accelerometers offer a promising strategy to improve fall detection, reduce response times, and enhance patient safety and independence. The report emphasizes the need for an interdisciplinary approach and the importance of personalized fall prevention strategies, concluding that wearable technology can be an effective tool in this effort.

Running head: HEALTH INFORMATION TECHNOLOGY
Wearable device to reduce falls in hospitals
Name of the Student
Name of the University
Author note

1HEALTH INFORMATION TECHNOLOGY
Introduction- Health technology is an umbrella term and refers to the implementation
of definite skills and knowledge in the form of vaccines, medicines, devices, systems and
procedures that are developed, with the aim of solving an existing health issue (Lehoux,
2014). The implementation of health technology helps in improving the quality of lives of the
people who receive healthcare services and typically encompass the usage of standardised
physical items, during care delivery. The effects of technology in the domain of health and
social care comprises of three major aspects namely, (i) quality of human life, (ii) world
economy, and (iii) healthcare related jobs (Khangura et al., 2014). Among the potential
benefits of health technology, reduction in rates of preventable death also counts, which in
turn improves patient wellbeing. This essay will elaborate on the implementation of wearable
devices for addressing a problem that is prevalent in the healthcare sector.
Problem identified- As per global estimates, every year roughly 700,000-1,000,000
individuals residing in the United States suffer from fall related accidents in hospital settings
(Centers for Disease Control and Prevention, 2017). Such falls have often been associated
with the occurrence of lacerations, fractures, and/or internal bleeding, thereby leading to an
increase in health care utilization. Such falls of patients are commonly defined as a form of
unplanned and sudden descent to a surface, or floor, with or without any major injury (Singh,
Okeke & Edwards, 2015). In addition, the Centres for Medicare & Medicaid Services (CMS)
does not provide any reimbursement to the hospitals for prevention and management of the
traumatic injuries that are encountered by a patient, during the hospitalisation period.
Healthcare staff employed in acute care hospitals most often displays a multifaceted
and potentially contradictory set of objectives when treating the patients. Hospice personnel
are primarily entitled with the duty of managing the problem that impelled the patient's
admission, in addition to keeping them safe, and helping them recover or maintain their

2HEALTH INFORMATION TECHNOLOGY
physical and mental function (Staggs, Mion & Shorr, 2014). This calls for the need of
balancing fall prevention against other priorities.
Time and again researchers have provided evidences for the common challenges that
are encountered by healthcare professionals during fall prevention. It has been found that fall
prevention technique implementation requires the adoption of an interdisciplinary care
approach. While specific portions of fall prevention care are extremely routinized, other
features must be personalised to meet the needs and risk profile of each patient (Koshmak,
Loutfi & Linden, 2016). Incidence of falls in hospitals cannot be reduced by nurses alone.
Rather, fall prevention would require the dynamic engagement of numerous persons, in
addition to the implementation of health technology. In addition, there are numerous
explanations for the substantial increase in rates of patient falls per patient days or per
discharge, and are certainly interrelated. Poor accident reporting systems, increased average
age of patients, more impairment, more rates of acutely ill patients, and heavy sedation are
some of the common factors that contribute to fall risks (Weil, 2015). In addition, less time is
often spent by the nursing personnel at the patient’s bedside, thus increasing fall rates.
Health technology- According to Zheng et al. (2014) wearable device or wearable
refer to smart electronic devices having microcontrollers that are primarily incorporated in
the garments, or worn by people in the form of accessories or implants. These devices
comprise of activity trackers that are a major component of Internet of Things and enable the
easy exchange of information, via the internet, with operators, manufacturers, and connected
devices, not necessarily requiring any human intervention. In addition, the wearable
technologies have also been associated with a reduction in the overall costs of hospitalisation
(Patel, Asch & Volpp, 2015). This is accomplished through constant monitoring of the patient
health indicators in various domains, following the integration of the devices with mobile
applications and telemedicine, to assemble medical Internet of Things. Recent evidences

3HEALTH INFORMATION TECHNOLOGY
support the growing interest in the usage of wearable, not only for the self-tracking of
individuals, but also their incorporation within health and wellness programs (Gao, Li & Luo,
2015). Taking into account the fact that prediction of fall risk is imperative for reducing
incidence of falls in hospitals, there is a need to implement the use of wearable by all
patients, who are at a moderate or high risk of falling. Evidences from a study suggested that
when compared to non-fallers, fallers performed worse in relation to test battery and the
application of wearable sensor data was associated with a 89.4% accuracy and 92.7%
sensitivity, thus confirming its role in identifying ‘at fall risk’ patients in hospital settings
(Qiu et al., 2018). Findings from another study also suggested that independent predictors of
patient falls are largely dependent on their frailty status and application of wearable
technology helps in constant monitoring of their physical activity and motor performance,
thus lowering the risks of falls (Mohler et al., 2016).
Danielsen, Olofsen and Bremdal (2016) also postulated that some of the major factors
that differentiated fallers from non-fallers were namely, step duration, gait speed, activity
level, multi-scale entropy, gait variability, and harmonic ratio. While formulating a fall risk
awareness protocol, they stated that presence of a vibration or sound in the wearable put on
the patient would send contextual data in the form of alarms to the personnel working in
alarm central that would notify the healthcare personnel, followed by immediate follow-up of
the patient to prevent the fall incidents. Efficacy of wearable devices in preventing fall onset
among people were also established in another study where wearable inertial measurement
units were able to effectively detect near-miss falls through a semi-supervised algorithm, with
86.4% accuracy and 75.9% recall rates, thus demonstrating the usefulness of the wearable
technology in fall prevention (Yang et al., 2016).
Proposed plan- Patients from the geriatric ward of a community hospital will be
selected after conducting a fall risk assessment and determining their likelihood of suffering

4HEALTH INFORMATION TECHNOLOGY
from fall related injuries. Following their recruitment, they will be made to wear waist belts
that will contain in-built accelerometers, which in turn will be connected to android mobile
phones. Prior to incorporation of the accelerometers in the belts, help will be taken from IT
experts, with the aim of developing computer algorithms that will help in the acquisition of
proper signals of the accelerometers (Habib et al., 2014). Under circumstances when the
patients show movement that might lead to a sudden descent to the floor such as, backward,
forward, lateral right, lateral left, gait deviation, sudden getting up from a supine position or
picking up objects from the floor, changes will be observed in the signal of the accelerometer
(Liu et al., 2014). While the threshold values will be set at levels observed during conduction
of everyday activities, the impact of fall would bring about a sharp increase in the signals to
maximum values.
Detection of signals beyond the threshold limit would immediately send an automatic
notification and alert to the mobile phones of healthcare personnel located within 150m of the
location of the patients. The signals would also be audible to attract attention of other
healthcare staff located nearby. This would allow the staff to immediately rush to the patient
and prevent their sudden and unexpected fall. However, one major limitation of using this
approach can be accredited to the fact that under circumstances when the battery of the
accelerometer does not work, there might be a delay or failure to send alert notification to the
concerned healthcare personnel, thus averting the prevention and management of falls with
the use of healthcare technology.
Conclusion- Fall detection has been identified as an important challenge that creates
an impact on the patients, as well as their carers. Falls also act as a major contributor to the
decline in functional activity of the patients, and their subsequent loss of independence.
Owing to the fact that falls among hospitalised patients, increases their healthcare costs and
the length of hospitalisation, improvements in detection of falls would decrease the aid

5HEALTH INFORMATION TECHNOLOGY
response time. Wearable accelerometers can therefore serve as an effective fall prevention
strategy.

6HEALTH INFORMATION TECHNOLOGY
References
Centers for Disease Control and Prevention. (2017). Important Facts about Falls. Retrieved
from https://www.cdc.gov/homeandrecreationalsafety/falls/adultfalls.html
Danielsen, A., Olofsen, H., & Bremdal, B. A. (2016). Increasing fall risk awareness using
wearables: a fall risk awareness protocol. Journal of biomedical informatics, 63, 184-
194.
Gao, Y., Li, H., & Luo, Y. (2015). An empirical study of wearable technology acceptance in
healthcare. Industrial Management & Data Systems, 115(9), 1704-1723.
Habib, M., Mohktar, M., Kamaruzzaman, S., Lim, K., Pin, T., & Ibrahim, F. (2014).
Smartphone-based solutions for fall detection and prevention: challenges and open
issues. Sensors, 14(4), 7181-7208.
Khangura, S., Polisena, J., Clifford, T. J., Farrah, K., & Kamel, C. (2014). Rapid review: an
emerging approach to evidence synthesis in health technology
assessment. International journal of technology assessment in health care, 30(1), 20-
27.
Koshmak, G., Loutfi, A., & Linden, M. (2016). Challenges and issues in multisensor fusion
approach for fall detection. Journal of Sensors, 2016.
Lehoux, P. (2014). The problem of health technology. Routledge.
Liu, Y., Redmond, S. J., Shany, T., Woolgar, J., Narayanan, M. R., Lord, S. R., & Lovell, N.
H. (2014, August). Validation of an accelerometer-based fall prediction model.
In 2014 36th Annual International Conference of the IEEE Engineering in Medicine
and Biology Society (pp. 4531-4534). IEEE.

7HEALTH INFORMATION TECHNOLOGY
Mohler, M. J., Wendel, C. S., Taylor-Piliae, R. E., Toosizadeh, N., & Najafi, B. (2016).
Motor performance and physical activity as predictors of prospective falls in
community-dwelling older adults by frailty level: application of wearable
technology. Gerontology, 62(6), 654-664.
Patel, M. S., Asch, D. A., & Volpp, K. G. (2015). Wearable devices as facilitators, not
drivers, of health behavior change. Jama, 313(5), 459-460.
Qiu, H., Rehman, R. Z. U., Yu, X., & Xiong, S. (2018). Application of Wearable Inertial
Sensors and A New Test Battery for Distinguishing Retrospective Fallers from Non-
fallers among Community-dwelling Older People. Scientific reports, 8(1), 16349.
Singh, I., Okeke, J., & Edwards, C. (2015). Outcome of in-patient falls in hospitals with
100% single rooms and multi-bedded wards. Age and ageing, 44(6), 1032-1035.
Staggs, V. S., Mion, L. C., & Shorr, R. I. (2014). Assisted and unassisted falls: different
events, different outcomes, different implications for quality of hospital care. The
Joint Commission Journal on Quality and Patient Safety, 40(8), 358-364.
Weil, T. P. (2015). Patient falls in hospitals: An increasing problem. Geriatric
Nursing, 36(5), 342-347.
Yang, K., Ahn, C. R., Vuran, M. C., & Aria, S. S. (2016). Semi-supervised near-miss fall
detection for ironworkers with a wearable inertial measurement unit. Automation in
Construction, 68, 194-202.
Zheng, Y. L., Ding, X. R., Poon, C. C. Y., Lo, B. P. L., Zhang, H., Zhou, X. L., ... & Zhang,
Y. T. (2014). Unobtrusive sensing and wearable devices for health informatics. IEEE
Transactions on Biomedical Engineering, 61(5), 1538-1554.