Evaluation and Integration of an Automatic Fall Prediction System (Florida)

Project Final Report (PDF, 311.1 KB) Disclaimer

Project Details - Ended

Project Categories

Summary:

Falls among the elderly are a significant cause of morbidity, mortality, and increased end-of-life health care costs. Most falls are related to predispositions to unsteadiness, impaired gait, muscle weakness, impaired cognitive and sensory functioning, and prior fall history. In addition, antipsychotic and antidepressant drugs contribute to fall risk by affecting cognitive and perceptual motor processes. Studies examining fall-risk factors cite the following as the most common: unsteady gait, need for extensive assistance in activities of daily living (ADL), and wandering, all of which relate to patterns in movement. An increase in the variability in stride-to-stride velocity has also been identified as an important risk factor for subsequent falls. Thus, changes in the quality and quantity of movement are prominent features associated with changes in health, medication regimens, cognitive impairment, and other predisposing factors involved in fall risk. 

This project sought to confirm the hypothesis that variability in voluntary movement paths of assisted living facility (ALF) residents would be greater in patients who fell the week preceding their fall as compared to residents who did not fall. To evaluate this hypothesis, a prospective observational study using telesurveillance technology was employed. The research determined if a measure of movement variability called Fractal D path tortuosity (Fractal D) would increase fall predictability beyond estimates provided by a fall.  

The main objectives of this project were to:

  • Evaluate the relationship between conventional fall-risk assessment measures using performance on standardized gait and balance (SGB) tests and Fractal D movement tortuosity measures. 
  • Evaluate tortuosity changes preceding a fall. 
  • Gather requirements for a software module to perform online fall-risk assessment in community-based settings. 

Over a period of a year, the movements of 53 elderly residents in two ALFs were monitored and their falls were recorded. Baseline SGB assessments were completed during this time. The velocity, distance and duration, and changes in direction during the individual's daytime movements in common areas of congregate living settings were tracked. Mean Fractal D during the week preceding a fall in 23 individuals who subsequently fell was statistically significantly higher than for 30 individuals who did not fall. Analysis showed that only Fractal D and a history of one or more previous falls were significant fall predictors. 

The project team determined that the relationship between SGB and subsequent falls is weak, although there is a relationship between some SGB measures and Fractal D. The team was able to demonstrate that an automatic dynamic quantitative assessment of the variability of everyday movements is an independent predictor of fall risk which, when combined with other known risk factors for falls, can significantly improve the accuracy of fall prediction than can other risk factors alone. This work led to the creation of a patented system of hardware and customized software that provides a reliable and automatic assessment of Fractal D and can be used in ALFs and nursing homes.

Evaluation and Integration of an Automatic Fall Prediction System - 2012

Summary Highlights

  • Principal Investigator: 
  • Funding Mechanism: 
    PAR: HS08-269: Exploratory and Developmental Grant to Improve Health Care Quality Through Health Information Technology (IT) (R21)
  • Grant Number: 
    R21 HS 018205
  • Project Period: 
    December 2009 – September 2012
  • AHRQ Funding Amount: 
    $299,452
  • PDF Version: 
    (PDF, 214.57 KB)

Summary: Falls among the elderly are a significant cause of morbidity, mortality, and increased end-of-life health care costs. Reducing the occurrence of falls can greatly improve patients’ quality of life. This study developed and evaluated a method to track variability in everyday movements as an additional means to predict risk of falls for elderly residents in assisted living facilities (ALF). It aimed to demonstrate that increased movement variability is a stronger predictor of fall risk than two other well-known risk factors—history of falls and use of prescribed psychoactive medications—and that collectively, prediction of fall risk is significantly improved. Dr. Kearns and his research team anticipated that the new method will be a useful tool for relating changes in fall risk to alterations in health and medications. The tool has been patented and commercial venture initiated to distribute the technology internationally.

This project recruited 53 volunteer residents of two ALF facilities. Baseline standardized gait and balance (SGB) assessments were completed. The velocity, distance, duration, and changes in direction during the volunteers’ daytime movements in common areas of congregate living settings were tracked over 12 months by a movement tracking system (MTS) via ultra-wideband active tag radio frequency identification devices. Prospective and retrospective fall histories were evaluated to determine the relationship of SGB and a measure of movement variability called Fractal D path tortuosity (Fractal D), derived from MTS data using software created for this project. Fractal D is a measure of deviation from a straight line of travel.

During the study, a complete evaluation of participant medications was conducted, with particular emphasis on identifying and recording the number of psychoactive and non-psychoactive medications that each participant was prescribed. Each participant’s activities of daily living (ADL) status was measured at time of enrollment and 12-month retrospective fall incident data was collected. Information about the causes of falls was obtained from ALF staff using a standardized fall-incident assessment that was also used to collect the 12-month prospective fall data. Medications, ADLs, residents’ history of falls, and Fractal D were entered as predictors in a multinomial logistic regression analysis, with falls as the outcome measure. The study team hypothesized that SGB would vary significantly with the MTS Fractal D measures, allowing Fractal D to be used as a proxy for SGB assessments while yielding improved fall prediction.

Specific Aims:

  • Evaluate the relationship between conventional fall-risk assessment measures using performance on SGB tests and Fractal D movement tortuosity measures obtained through the MTS. (Achieved)
  • Evaluate tortuosity changes preceding a fall. (Achieved)
  • Gather requirements for a software module to perform online fall-risk assessment in communitybased settings. (Achieved)

2012 Activities: The research team developed and published a manuscript in September in the Journal of the American Medical Directors Association, titled “Path tortuosity in everyday ambulation of elderly persons’ increases predictability of fall risk beyond that provided by fall history, medication use, and standardized gait and balance assessments.” This paper represents the first in a series of monographs being prepared by the team comparing Fractal D with known predictors of falling in older persons, such as having had a fall in the previous year, presence of psychoactive medications, and SGB assessments.

The first-phase medication analysis to evaluate the impact of psychoactive medications on fall risk in the subjects was completed. A manuscript describing the results of this analysis, in combination with the SGB analysis and the Fractal D tracking data, was developed and submitted to a peer-reviewed journal. Work proceeded on secondary analyses of this data. A 1-year no-cost extension was used to collect and analyze additional data. As last reported in the AHRQ Research Reporting System, project progress was on track and budget spending was on target. The project ended in September 2012.

A patent that resulted from the work was awarded and the technology has been licensed to a company. The team will market the product pending release of the research papers. Dr. Kearns was appointed to the implementation team for the Veterans Affairs (VA) Department Real-Time Location System Project, the intent of which is to place tracking technology in more than 150 VA-operated hospitals. He will also provide consultation concerning the development of a data repository that will be established to make these data available to researchers nationwide. Finally, the research team continues its work with the VA Smart Home Project to reduce the risk of falls among veterans receiving inpatient treatment for traumatic brain injury.

Impact and Findings: The major finding was that Fractal D is an independent predictor of future falls. Fractal D in combination with a history of one or more falls in the prior year is a strong fall predictor. The addition of a continuous dynamic assessment of changes in everyday movement patterns obtained automatically and unobtrusively up to the time of a fall significantly improves fall-risk estimation accuracy beyond that provided by other known predictors. In congregate living settings such as nursing homes and ALFs, the costs of the location-aware technology are kept relatively low by economies of scale since the infrastructure need not be pervasive, individual tag costs are low, and more than 100 residents can be monitored and assessed simultaneously.

While there was a significant difference in Fractal D for those who fell versus those who did not, the results did not indicate when group differences emerged. Auxiliary analyses indicated that those who fell did not differ significantly from those who did not at the time of the first week of the study, but were significantly different at the time of the fall. This change was not readily predictable from trends in the data nor was it linked to the duration until the fall. For those who fell, the correlation between Fractal D in the 7 days immediately preceding the index event with Fractal D in the week prior was 0.97, but was only 0.67 with participants’ measures during the first week of the study. The results are consistent with the hypothesis that Fractal D delivered by the online monitoring system is more predictive of falls in the near future than in the more distant past.

Target Population: Elderly*

Strategic Goal: Develop and disseminate health IT evidence and evidence-based tools to improve health care decisionmaking through the use of integrated data and knowledge management.

Business Goal: Knowledge Creation

* This target population is one of AHRQ’s priority populations.

Evaluation and Integration of an Automatic Fall Prediction System - 2011

Summary Highlights

  • Principal Investigator: 
  • Funding Mechanism: 
    PAR: HS08-269: Exploratory and Developmental Grant to Improve Health Care Quality Through Health Information Technology (R21)
  • Grant Number: 
    R21 HS 018205
  • Project Period: 
    December 2009 - September 2012
  • AHRQ Funding Amount: 
    $299,452
  • PDF Version: 
    (PDF, 206.96 KB)

Summary: Falls among the elderly are a significant cause of morbidity, mortality, and increased end-oflife health care costs. Reducing the occurrence of falls can greatly improve patients' quality of life. This study is developing and evaluating a method to track variability in everyday movements as an additional means to predict risk of falls for elderly residents in assisted living facilities (ALF). It aims to demonstrate that increased movement variability is a stronger predictor of fall risk than two other well-known risk factors - history of falls and use of prescribed psychoactive medications - and that collectively, prediction of fall risk is significantly improved. Dr. Kearns and his research team anticipate that the new method will be a useful tool for relating changes in fall risk to alterations in health and medications. The tool has been patented and commercial venture initiated to distribute the technology internationally.

This project recruited 53 volunteer residents from two ALF facilities. Baseline standardized gait and balance (SGB) assessments were completed. The velocity, distance and duration, and changes in direction during movements of the volunteers' daytime movements in common areas of congregate living settings were tracked over 12 months by a movement tracking system (MTS) via ultra-wideband active tag radio frequency identification devices. Prospective and retrospective fall histories were evaluated to determine the relationship of SGB and a measure of movement variability called Fractal D path tortuosity (Fractal D) derived from MTS data using software created for this project. Fractal D is a measure of deviation from a straight line of travel.

During the study, a complete evaluation of participant medications was conducted, with particular emphasis on identifying and recording the number of psychoactive and non-psychoactive medications that each participant was prescribed. Each participant's activities of daily living (ADL) status was measured at the time of enrollment, along with 12-month retrospective fall incident data. Information about the causes of falls was obtained from ALF staff using a standardized fall incident assessment also used to collect the 12-month prospective fall data. Medications, ADLs, and residents' history of falls and Fractal D were entered as predictors in a multinomial logistic regression analysis, with falls as the outcome measure. The study team hypothesized that SGB would vary significantly with the MTS Fractal D measures, allowing Fractal D to be used as a proxy for SGB assessments while yielding improved fall prediction.

Specific Aims:

  • Evaluate the relationship between conventional fall-risk assessment measures using performance on SGB tests and Fractal D movement tortuosity measures obtained through the MTS. (Achieved)
  • Evaluate tortuosity changes preceding a fall. (Achieved)
  • Gather requirements for a software module to perform online fall-risk assessment in community-based settings. (Achieved)

2011 Activities: All medication data and fall history information for the baseline period and the monitoring interval was entered into the project database. Additionally, the research team continued medication coding and analysis. An abstract describing the results of the multinomial logistic regressions comparing traditional fall risk factors (prior fall and presence of psychoactive medications), against MTS Fractal D measures was submitted for presentation at the International Society for Gerontechnology's 2012 annual meeting to be held in Boston, November 14-18.

Results from the 53 subjects indicate that Fractal D is linked to future fall activity in ALF residents and that its contribution is quantifiable. Analyses of SGB measures and future fall risk showed that stride time coefficient of variation (COV) was a significant predictor of future falls for 35 of 53 subjects who could generate data. Fractal D was correlated with number of steps and time required to complete the 180 Degree Turn Test and negatively correlated with the number of degrees rotated and sway area. Fractal D correlated positively with the time required to complete the Get up and Go Test and positively with Walking Test Dual Task stride-to-stride velocity COV.

As last self-reported in the AHRQ Research Reporting System, project progress and activities are on track and the project budget spending is on target.

Preliminary Impact and Findings: The logistic regression analysis performed on the 53 subjects revealed that the odds of falling increased by 4.06 times for every 0.1 increment in Fractal D levels the week before the event, and increased 3.45 times if a fall had occurred in the year prior to the study. The number of psychoactive medications approached but did not reach significance as a contributor to falls; neither was the mean path length a significant predictor of future falls, although there was a strong trend for longer paths and an absence of psychoactive medications to be associated with reduced fall risk. The concordance rate for the overall model was 82 percent.

SGB measures were available for too few subjects, (37 of 53) to conduct a multinomial logistic regression including the other measures listed above, largely due to the frailty of the subjects; many simply could not perform the stride test or other tests. Stride time COV was compared with the 7-day Fractal D mean, presence of more than one psychoactive medication, and the mean distance traveled in the 7 days before the event as predictors in a multinomial logistic regression. The results of the logistic regression on the reduced set of 34 subjects demonstrated that the COV was the best predictor of future falls. Fall probability increased 1.48 times for every .01 increase in the COV. No other variable was significantly related to fall risk, although Fractal D approached and may have reached statistical significance had more subjects been able to perform the stride time test. The concordance for the final model with 34 subjects was 87 percent. The logistic regression analysis was repeated on the same subjects dropping COV, and Fractal D was found to be the only significant predictor. A 0.1 increase in Fractal D was associated with a 4.17 times increase in fall likelihood. Neither the presence of more than one psychiatric medication nor the mean travel distance in the 7 days before the event was a significant predictor; the concordance rate for the model was 75.8 percent.

The study results indicate that a telesurveillance technology capable of extracting spatial variability information from free-moving elderly in assisted living facilities can provide useful information predictive of future falls in individuals who may be too frail to engage in standardized gait and balance testing.

Target Population: Elderly*

Strategic Goal: Develop and disseminate health IT evidence and evidence-based tools to improve health care decisionmaking through the use of integrated data and knowledge management.

Business Goal: Knowledge Creation

* This target population is one of AHRQ's priority populations.

Evaluation and Integration of an Automatic Fall Prediction System - 2010

Summary Highlights

  • Principal Investigator: 
  • Funding Mechanism: 
    PAR: HS08-269: Exploratory and Developmental Grant to Improve Health Care Quality Through Health Information Technology (R21)
  • Grant Number: 
    R21 HS 018205
  • Project Period: 
    December 2009 – November 2011
  • AHRQ Funding Amount: 
    $299,452
  • PDF Version: 
    (PDF, 362.86 KB)


Target Population: Elderly*

Summary: Falls among the elderly are a significant cause of morbidity, mortality, and increased end-of-life health care costs. Reducing the occurrence of falls can greatly improve patients’ quality of life. This study seeks to develop a means to relate health and medication changes to falls and to provide measures to predict the risk of falls for elderly residents in assisted living facilities (ALF).

This project recruited 50 volunteer residents from two ALF facilities. Baseline standardized gait and balance (SGB) assessments were completed. The velocity, direction, and duration of the volunteer’s daytime movements in common areas of congregate living settings will be tracked for 12 months by a movement tracking system (MTS) via radio frequency identification devices. Prospective and retrospective fall histories will be evaluated to determine the relationship of SGB and a measure of movement variability called “tortuosity,” (Fractal D) derived from MTS data.

During the study interval, a complete evaluation of participant medications will be conducted, with particular emphasis on identifying and recording the number of psychoactive and non-psychoactive medications that each participant is prescribed. Each participant’s activities of daily living (ADL) status will be measured at the time of enrollment, along with 12-month retrospective data from fall incident records. To the extent possible, information about the causes of falls will be obtained from ALF nursing staff using a fall assessment scale developed at the James A. Haley Veterans Administration Veteran’s Integrated Service Network (VISN8) Patient Safety Center of Inquiry. This instrument will also be used to collect the 12-month prospective fall data. Medications, ADLs, and residents’ history of falls will be treated as covariates in the regression analysis predicting fractal dimension and prospective falls.

The study team hypothesizes that SGB varies significantly with MTS tortuosity measures, allowing tortuosity to be used as a proxy for SGB assessments while yielding improved fall predictions.

Specific Aims:
  • Evaluate the relationship between conventional fall-risk assessment measures using performance on SGB tests and Fractal D movement tortuosity measures obtained through the MTS. (Ongoing)
  • Evaluate tortuosity changes preceding a fall. (Ongoing)
  • Gather requirements for a software module to perform online fall-risk assessment in community-based settings. (Ongoing)

2010 Activities: Recruitment materials were finalized and the equipment located in the two ALF research sites was upgraded to the latest standards of software and firmware to enhance reliability of the results. Subject identification and recruitment was started at both research sites. The team completed recruitment activities and the planned recruitment target of subjects was met.

As of September, all enrolled subjects provided both standardized gait and balance assessments and had generated Mini Mental State Examinations (MMSE) scores. The data from the gait and balance assessments is being prepared for formal analysis by project staff. Preliminary analyses were carried out on the gait and balance measures collected at each assisted living facility.

Fractal D data was collected on 60 subjects. The first set of subjects will complete 12 months of monitoring in February 2011. The team anticipates completing data collection in June 2011 with the targeted 50 subjects.

Grantee's Most Recent Self-Reported Quarterly Status (as of December 2010): Significant progress has been made and the project is ahead of schedule. Budget spending is roughly on target. Future tasks will focus on data collection and analysis.

Preliminary Impact and Findings: The mean age of the participants was 73.5 years (SD=12.2). The youngest was 37, the oldest 94. The youngest participant was almost 20 years younger than the next youngest participant. Partly because of the young age of the 37-year-old participant and partly because of the requirement that participants be able to undergo the SGB, the average age for this subset of participants was below the average for previously-published data for these two facilities. The average MMSE score was 18.8 (SD=6.95), on a 0 to 30 scale for which ‘0’ is the lowest. The range and average MMSE scores were similar to previously reported results for participants in these ALFs.

Twenty (57.2 percent) participants ambulate independently. Of those who use assistive devices, one (2.9 percent) uses a cane, 12 (34.3 percent) use rolling walkers, and three (8.6 percent) use wheelchairs. The relatively even split between the 57 percent fully-ambulatory participants and those using mobility aids will be an important basis for classifying participants in future analyses when evaluating the SGB data. The 35 participants collectively generated more than 11 million positional data points. The number of paths ranged widely, from 48 to 4,987, yielding a total of 46,139 Fractal D scores. The Pearson product moment correlation between Fractal D and total MMSE was -0.46, n=35, p=0.006.

In the present analysis, the negative correlations between the two subscales and Fractal D were the same value -0.442, n=35, p

Strategic Goal: Develop and disseminate health IT evidence and evidence-based tools to improve health care decisionmaking through the use of integrated data and knowledge management.

Business Goal: Knowledge Creation

*AHRQ Priority Population.

Evaluation and Integration of an Automatic Fall Prediction System - Final Report

Citation:
Kearns W. Evaluation and Integration of an Automatic Fall Prediction System - Final Report. (Prepared by the University of South Florida under Grant No. R21 HS018205). Rockville, MD: Agency for Healthcare Research and Quality, 2012. (PDF, 311.1 KB)

The findings and conclusions in this document are those of the author(s), who are responsible for its content, and do not necessarily represent the views of AHRQ. No statement in this report should be construed as an official position of AHRQ or of the U.S. Department of Health and Human Services.
Principal Investigator: 
Document Type: 
Population: 
This project does not have any related resource.
This project does not have any related survey.
This project does not have any related project spotlight.
This project does not have any related survey.
This project does not have any related story.
This project does not have any related emerging lesson.