Development and validation of a robotic multifactorial fall-risk predictive model: A one-year prospective study in community-dwelling older adults

A systematic review of fall prediction models for community-dwelling older adults: comparison between models based on research cohorts and models based on routinely collected data

BACKGROUND

Prediction models can identify fall-prone individuals. Prediction models can be based on either data from research cohorts (cohort-based) or routinely collected data (RCD-based). We review and compare cohort-based and RCD-based studies describing the development and/or validation of fall prediction models for community-dwelling older adults.

METHODS

Medline and Embase were searched via Ovid until January 2023. We included studies describing the development or validation of multivariable prediction models of falls in older adults (60+). Both risk of bias and reporting quality were assessed using the PROBAST and TRIPOD, respectively.

RESULTS

We included and reviewed 28 relevant studies, describing 30 prediction models (23 cohort-based and 7 RCD-based), and external validation of two existing models (one cohort-based and one RCD-based). The median sample sizes for cohort-based and RCD-based studies were 1365 [interquartile range (IQR) 426-2766] versus 90 441 (IQR 56 442-128 157), and the ranges of fall rates were 5.4% to 60.4% versus 1.6% to 13.1%, respectively. Discrimination performance was comparable between cohort-based and RCD-based models, with the respective area under the receiver operating characteristic curves ranging from 0.65 to 0.88 versus 0.71 to 0.81. The median number of predictors in cohort-based final models was 6 (IQR 5-11); for RCD-based models, it was 16 (IQR 11-26). All but one cohort-based model had high bias risks, primarily due to deficiencies in statistical analysis and outcome determination.

CONCLUSIONS

Cohort-based models to predict falls in older adults in the community are plentiful. RCD-based models are yet in their infancy but provide comparable predictive performance with no additional data collection efforts. Future studies should focus on methodological and reporting quality.

Testing Dynamic Balance in People with Multiple Sclerosis: A Correlational Study between Standard Posturography and Robotic-Assistive Device

BACKGROUND

Robotic devices are known to provide pivotal parameters to assess motor functions in Multiple Sclerosis (MS) as dynamic balance. However, there is still a lack of validation studies comparing innovative technologies with standard solutions. Thus, this study's aim was to compare the postural assessment of fifty people with MS (PwMS) during dynamic tasks performed with the gold standard EquiTest® and the robotic platform hunova®, using Center of Pressure (COP)-related parameters and global balance indexes.

METHODS

Pearson's ρ correlations were run for each COP-related measure and the global balance index was computed from EquiTest® and hunova® in both open (EO) and closed-eyes (EC) conditions.

RESULTS

Considering COP-related parameters, all correlations were significant in both EO (0.337 ≤ ρ ≤ 0.653) and EC (0.344 ≤ ρ ≤ 0.668). Furthermore, Pearson's analysis of global balance indexes revealed relatively strong for visual and vestibular, and strong for somatosensory system associations (ρ = 0.573; ρ = 0.494; ρ = 0.710, respectively).

CONCLUSIONS

Findings confirm the use of hunova® as a valid device for dynamic balance assessment in MS, suggesting that such a robotic platform could allow for a more sensitive assessment of balance over time, and thus a better evaluation of the effectiveness of personalized treatment, thereby improving evidence-based clinical practice.

The PRO-HOME Project. A multicomponent intervention for the protected discharge from the hospital of multimorbid and polytreated older individuals by using innovative technologies: A pilot study

BACKGROUD

Discharge planning from the hospital of frail older patients is an important step to avoid inappropriate long-stay hospitalizations and to prevent the risks related to the prolonged hospitalization. In this frame, we developed an experimental trial-'PRO-HOME', a multicomponent programme of interventions for multimorbid and polytreated hospitalized older patients.

AIM

The main aim of the study was to develop a protected discharge facility using a mini apartment equipped with advanced architectural and technological components to reduce the length of hospital stay of older participants (aged 65+ years old) admitted to the hospital for an acute event, deemed stable and dischargeable.

MATERIALS AND METHODS

This is a pilot randomized controlled study, comparing 30 hospitalized participants included in a multidimensional, transitional care programme based on information and communication technologies to 30 patients in standard usual care until hospital discharge.

RESULTS

We presented the study design of the PRO-HOME programme, including architectural and technological components, the enrolment procedures, the components of the intervention that is physical activity, cognitive training and life-style education and the evaluation method of the intervention based on the Comprehensive Geriatric Assessment to explore the changes in the individual domains that are target of the multicomponent intervention.

CONCLUSIONS

The final results will suggest whether the PRO-HOME programme represents a useful and feasible intervention to reduce the length of hospital stay of multimorbid and polytreated hospitalized older patients and improve their physical and cognitive performances and overall quality of life.

PATIENT OR PUBLIC CONTRIBUTION

Due to the characteristics of the population of interest of the PRO-HOME study, we involved in the study design and programme of the activities the participants enrolled in a previous smart home-based project named MoDiPro carried-out during a 3-year period. The elderly participants from the local population involved were asked, by means of focus groups, for feedback on their experience in MoDiPro, and their suggestions were integrated into the design phase of the current PRO-HOME project. The focus groups included open group interviews with a qualitative collection of the patients' feedback so that the participants could interact with each other.

Cardiovascular disease and the risk of incident falls and mortality among adults aged ≥ 65 years presenting to the emergency department: a cohort study from national registry data in Denmark

BACKGROUND

Falls cause 58% of injury-related Emergency Department (ED) attendances. Previous research has highlighted the potential role of cardiovascular risk factors for falls. This study investigated the impact of cardiovascular disease (CVD) risk on three-year incident falls, with presentation to the ED, and mortality.

METHODS

A matched cohort study design was employed using national registry data from 82,292 adults (33% male) aged ≥ 65 years living in Denmark who attended the ED in 2013. We compared age and gender matched ED attendees presenting with a fall versus another reason. The cohort was followed for three-year incident falls, with presentation to the ED, and mortality. The impact of falls-related CVDs was also examined.

RESULTS

Three-year incident falls was twofold higher among age and gender matched ED attendees aged ≥ 65 years presenting with a fall versus another reason at baseline. A presentation of falls with hip fracture had the highest percentage of incident falls in the 65-74 age group (22%) and the highest percentage mortality in all age groups (27-62%). CVD was not a significant factor in presenting with a fall at the ED, nor did it contribute significantly to the prediction of three-year incident falls. CVD was strongly associated with mortality risk among the ED fall group (RR = 1.81, 95% CI: 1.67-1.97) and showed interactions with both age and fall history.

CONCLUSION

In this large study of adults aged ≥ 65 years attending the ED utilising data from national administrative registers in Denmark, we confirm that older adults attending the ED with a fall, including those with hip fracture, were at greatest risk for future falls. While CVD did not predict incident falls, it increased the risk of mortality in the three-year follow up with advancing age. This may be informative for the provision of care pathways for older adults attending the ED due to a fall.

Classification and Definitions of Compensatory Protective Step Strategies in Older Adults: A Scoping Review

BACKGROUND

The risk for an unexpected fall can be due to increasing age, health conditions, and loss of cognitive, sensory, or musculoskeletal functions. Falls have personal and economic consequences in many countries. Different disturbances can occur during gait, such as tripping, slipping, or other unexpected circumstances that can generate a loss of balance. The strategies used to recover balance depend on many factors, but selecting a correct response strategy influences the success of balance recovery.

OBJECTIVES

(1) To collect and clarify the definitions of compensatory protective step strategies to recover balance in older adults; (2) to identify the most used methods to induce loss of balance; and (3) to identify the most used spatiotemporal variables in analyzing these actions.

METHODS

The present review has followed the PRISMA guideline extension for Scoping Review (PRISMA-ScR) and the phases proposed by Askery and O'Malley. The search was conducted in three databases: PubMed, Web of Science, and Scopus.

RESULTS

A total of 525 articles were identified, and 53 studies were included. Forty-five articles were quasi-experimental studies, six articles were randomized controlled trials, and two studies had an observational design. In total, 12 compensatory protective step strategies have been identified.

CONCLUSIONS

There are 12 compensatory protective step strategies: lowering and elevating strategy, short- and long-step strategy, backward and forward stepping for slip, single step, multiple steps, lateral sidesteps or loaded leg sidestep unloaded leg sidestep, crossover step (behind and front), and medial sidestep. To standardize the terminology applied in future studies, we recommend collecting these strategies under the term of compensatory protective step strategies. The most used methods to induce loss of balance are the tether-release, trip, waist-pull, and slip methods. The variables analyzed by articles are the number of steps, the acceleration phase and deceleration phase, COM displacement, the step initiation or step duration, stance phase time, swing phase time and double-stance duration, stride length, step length, speed step, speed gait and the type of step.

Reliability and validity of the Tinetti performance oriented mobility assessment in Chinese community-dwelling older adults

OBJECTIVE

The Tinetti Performance Oriented Mobility Assessment (POMA) has been used for assessing mobility limitations and predicting falling risk among older adults. This study aimed to evaluate the reliability and validity of the POMA in Chinese community-dwelling older adults.

METHODS

We used data from a cross-sectional study in which a sample of 627 older adults completed the POMA. Reliability was tested using internal consistencies and test-retest reliability analyses, while validity was assessed using confirmatory factor analysis and known-group approach. Floor and ceiling effects were also tested.

RESULTS

The POMA and its two subscales had good internal consistency reliability and interrater reliability. Confirmatory factor analysis indicated the POMA had a two-factor structure. The POMA and its subscales exhibited moderate-to-good discriminant validity. A high ceiling effect was detected.

CONCLUSIONS

The POMA had satisfactory reliability and validity among Chinese older adults. Nevertheless, a high ceiling effect may limit its use in community settings.

Comparative Analysis of Fall Risk Assessment Features in Community-Elderly and Stroke Survivors: Insights from Sensor-Based Data

Fall-risk assessment studies generally focus on identifying characteristics that affect postural balance in a specific group of subjects. However, falls affect a multitude of individuals. Among the groups with the most recurrent fallers are the community-dwelling elderly and stroke survivors. Thus, this study focuses on identifying a set of features that can explain fall risk for these two groups of subjects. Sixty-five community dwelling elderly (forty-nine female, sixteen male) and thirty-five stroke-survivors (twenty-two male, thirteen male) participated in our study. With the use of an inertial sensor, some features are extracted from the acceleration data of a Timed Up and Go (TUG) test performed by both groups of individuals. A short-form berg balance scale (SFBBS) score and the TUG test score were used for labeling the data. With the use of a 100-fold cross-validation approach, Relief-F and Extra Trees Classifier algorithms were used to extract sets of the top 5, 10, 15, 20, 25, and 30 features. Random Forest classifiers were trained for each set of features. The best models were selected, and the repeated features for each group of subjects were analyzed and discussed. The results show that only the stand duration was an important feature for the prediction of fall risk across all clinical tests and both groups of individuals.

Trajectory and Sway Prediction Towards Fall Prevention

Falls are the leading cause of fatal and non-fatal injuries, particularly for older persons. Imbalance can result from the body's internal causes (illness), or external causes (active or passive perturbation). Active perturbation results from applying an external force to a person, while passive perturbation results from human motion interacting with a static obstacle. This work proposes a metric that allows for the monitoring of the persons torso and its correlation to active and passive perturbations. We show that large changes in the torso sway can be strongly correlated to active perturbations. We also show that we can reasonably predict the future path and expected change in torso sway by conditioning the expected path and torso sway on the past trajectory, torso motion, and the surrounding scene. This could have direct future applications to fall prevention. Results demonstrate that the torso sway is strongly correlated with perturbations. And our model is able to make use of the visual cues presented in the panorama and condition the prediction accordingly.

Long-term trajectories of depressive symptoms and machine learning techniques for fall prediction in older adults:Evidence from the China Health and Retirement Longitudinal Study (CHARLS)

BACKGROUND

Falls are the most common adverse outcome of depression in older adults, yet a accurate risk prediction model for falls stratified by distinct long-term trajectories of depressive symptoms is still lacking.

METHODS

We collected the data of 1617 participants from the China Health and Retirement Longitudinal Study register, spanning between 2011 and 2018. The 36 input variables included in the baseline survey were regarded as candidate features. The trajectories of depressive symptoms were classified by the latent class growth model and growth mixture model. Three data balancing technologies and four machine learning algorithms were utilized to develop predictive models for fall classification of depressive prognosis.

RESULTS

Depressive symptom trajectories were divided into four categories, i.e., non-symptoms, new-onset increasing symptoms, slowly decreasing symptoms, and persistent high symptoms. The random forest-TomekLinks model achieved the best performance among the case and incident models with an AUC-ROC of 0.844 and 0.731, respectively. In the chronic model, the gradient boosting decision tree-synthetic minority oversampling technique obtained an AUC-ROC of 0.783. In the three models, the depressive symptom score was the most crucial component. The lung function was a common and significant feature in both the case and the chronic models.

CONCLUSIONS

This study suggests that the ideal model has a good chance of identifying older persons with a high risk of falling stratified by long-term trajectories of depressive symptoms. Baseline depressive symptom score, lung function, income, and injury experience are influential factors associated with falls of depression evolution.

Evaluation of a novel technology-supported fall prevention intervention - study protocol of a multi-centre randomised controlled trial in older adults at increased risk of falls

BACKGROUND

Increasing number of falls and fall-related injuries in an aging society give rise to the need for effective fall prevention and rehabilitation strategies. Besides traditional exercise approaches, new technologies show promising options for fall prevention in older adults. As a new technology-based approach, the hunova robot can support fall prevention in older adults. The objective of this study is to implement and evaluate a novel technology-supported fall prevention intervention using the hunova robot compared to an inactive control group. The presented protocol aims at introducing a two-armed, multi-centre (four sites) randomised controlled trial, evaluating the effects of this new approach on the number of falls and number of fallers as primary outcomes.

METHODS

The full clinical trial incorporates community-dwelling older adults at risk of falls with a minimum age of 65 years. Including a one-year follow-up measurement, all participants are tested four times. The training programme for the intervention group comprises 24-32 weeks in which training sessions are scheduled mostly twice a week; the first 24 training sessions use the hunova robot, these are followed by a home-based programme of 24 training sessions. Fall-related risk factors as secondary endpoints are measured using the hunova robot. For this purpose, the hunova robot measures the participants' performance in several dimensions. The test outcomes are input for the calculation of an overall score which indicates the fall risk. The hunova-based measurements are accompanied by the timed-up-and-go test as a standard test within fall prevention studies.

DISCUSSION

This study is expected to lead to new insights which may help establish a new approach to fall prevention training for older adults at risk of falls. First positive results on risk factors can be expected after the first 24 training sessions using the hunova robot. As primary outcomes, the number of falls and fallers within the study (including the one-year follow-up period) are the most relevant parameters that should be positively influenced by our new approach to fall prevention. After the study completion, approaches to examine the cost-effectiveness and develop an implementation plan are relevant aspects for further steps.

TRIAL REGISTRATION

German Clinical Trial Register (DRKS), ID: DRKS00025897. Prospectively registered 16 August 2021, https://drks.de/search/de/trial/DRKS00025897 .

Effects of blood flow restriction on spine postural control using a robotic platform: A pilot randomized cross-over study

BACKGROUND

Blood flow restriction (BFR) training improves muscle strength and functional outcomes, but the proprioceptive implications of this technique in the rehabilitation field are still unknown.

OBJECTIVE

The present study aimed at assessing the effects of BFR in terms of stabilometric and balance performance.

METHODS

In this pilot randomized cross-over study, healthy young adults were included and randomly assigned to Groups A and B. Both groups underwent a postural assessment with and without wearing a BFR device. Study participants of Group A underwent postural baseline assessment wearing BFR and then removed BFR for further evaluations, whereas subjects in Group B performed the baseline assessment without BFR and then with BFR. Stabilometric and balance performance were assessed by the robotic platform Hunova, the Balance Error Scoring System (BESS), the self-reported perceived balance (7-point Likert scale), and discomfort self-rated assessment. Moreover, the safety profile was recorded.

RESULTS

Fourteen subjects were included and randomly assigned to Group A (n: 7) and Group B (n: 7). Significant differences were shown in balance tests in static conditions performed on the Hunova robot platform in terms of average distance RMS (root-mean-square) with open eyes (OE), anteroposterior (AP) trunk oscillation range with OE, mediolateral (ML) average speed of oscillation with OE, and total excursion AP range with closed eyes (CE) (BFR: 3.44 ± 1.06; without BFR: 2.75 ± 0.72; p= 0.041). Moreover, elastic balance test showed differences in Romberg index (BFR: 0.16 ±0.16; without BFR: 0.09 ± 0.07; p= 0.047). No adverse events were reported.

CONCLUSION

Taken together, our data showed that BFR affects balance performance of healthy subjects. Further studies are needed to better characterize the possible role of BFR treatment in the context of a specific rehabilitation protocol.

Characterizing fall risk factors in Belgian older adults through machine learning: a data-driven approach

BACKGROUND

Falls are a major problem associated with ageing. Yet, fall-risk classification models identifying older adults at risk are lacking. Current screening tools show limited predictive validity to differentiate between a low- and high-risk of falling.

OBJECTIVE

This study aims at identifying risk factors associated with higher risk of falling by means of a quality-of-life questionnaire incorporating biological, behavioural, environmental and socio-economic factors. These insights can aid the development of a fall-risk classification algorithm identifying community-dwelling older adults at risk of falling.

METHODS

The questionnaire was developed by the Belgian Ageing Studies research group of the Vrije Universiteit Brussel and administered to 82,580 older adults for a detailed analysis of risk factors linked to the fall incidence data. Based on previously known risk factors, 139 questions were selected from the questionnaire to include in this study. Included questions were encoded, missing values were dropped, and multicollinearity was assessed. A random forest classifier that learns to predict falls was trained to investigate the importance of each individual feature.

RESULTS

Twenty-four questions were included in the classification-model. Based on the output of the model all factors were associated with the risk of falling of which two were biological risk factors, eight behavioural, 11 socioeconomic and three environmental risk factors. Each of these variables contributed between 4.5 and 6.5% to explaining the risk of falling.

CONCLUSION

The present study identified 24 fall risk factors using machine learning techniques to identify older adults at high risk of falling. Maintaining a mental, physical and socially active lifestyle, reducing vulnerability and feeling satisfied with the living situation contributes to reducing the risk of falling. Further research is warranted to establish an easy-to-use screening tool to be applied in daily practice.

Effects of Chinese fitness dancing on lower limb strength and fall risk in middle‐aged and older women: A cross‐sectional study

This study sought to identify the effect of Chinese fitness dancing on lower limb strength and fall risk in middle-aged and older women. The MicroFET3 portable muscle strength tester, the FreeStep test system, and tests to evaluate fall risk were used to measure the maximum muscle strength, fall risk index, and static balance ability of extensor muscle groups in the lower limbs. Compared with the irregular exercise group, the maximum muscle strength of extensor muscle groups in the lower limb, five sit-to-stand test timings, fall risk index, static balance ability, and lower limb flexibility did not improve significantly in the 1-year regular exercise group (p > 0.01). However, these indicators were significantly improved in the 10-year regular exercise group compared with the 1-year regular exercise group (p < 0.01). Long-term regular participation in Chinese fitness dancing significantly increased muscle strength in the lower limbs and effectively lowered the fall risk index in middle-aged and older women. Thus, long-term regular participation in Chinese fitness dancing can be used as a preventive measure to increase muscle strength in the lower limbs and reduce the risk of falls in middle-aged and older women.

Robots in Healthcare: a Scoping Review

Purpose of Review

Robots are increasingly being adopted in healthcare to carry out various tasks that enhance patient care. This scoping review aims to establish the types of robots being used in healthcare and identify where they are deployed.

Recent Findings

Technological advancements have enabled robots to conduct increasingly varied and complex roles in healthcare. For instance, precision tasks such as improving dexterity following stroke or assisting with percutaneous coronary intervention.

Summary

This review found that robots have played 10 main roles across a variety of clinical environments. The two predominant roles were surgical and rehabilitation and mobility. Although robots were mainly studied in the surgical theatre and rehabilitation unit, other settings ranged from the hospital ward to inpatient pharmacy. Healthcare needs are constantly evolving, as demonstrated by COVID-19, and robots may assist in adapting to these changes. The future will involve increased telepresence and infrastructure systems will have to improve to allow for this.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43154-022-00095-4.

Dynamic performance-exposure algorithm for falling risk assessment and prevention of falls in community-dwelling older adults

This study aimed to design a dynamic performance-exposure algorithm for falling risk assessment and prevention of falls in community-dwelling older adults. It involved a cross-sectional and follow-up survey assessing retrospective and prospective falls and respective performance-related, exposure and performance-exposure risk factors. In total, 500 Portuguese community-dwelling adults participated. Data modelling showed significant (p<0.05) relationships between the above risk factors and selected nine key ordered outcomes explaining falls to include in the algorithm: previous falls; health conditions; balance; lower strength; perceiving action boundaries; fat mass; environmental hazards; rest periods; and physical activity. Respective high-, moderate- and low-risk cutoffs were established. The results demonstrated a dynamic relationship between older adults' performance capacity and the exposure to fall opportunity, counterbalanced by the action boundary perception, supporting the build algorithm's conceptual framework. Fall prevention measures should consider the factors contributing most to the individual risk of falling and their distance from low-risk safe values.

The Use of Static Posturography Cut-Off Scores to Identify the Risk of Falling in Older Adults

BACKGROUND

Falling is the most common accident that occurs in daily living and the second leading cause of unintentional injury death worldwide. The complexity of the risk factors associated with falling makes older people at risk of falling difficult to identify. The aim of the study was to identify the cut-off scores of standing posturography measures that can be used to predict the risk of falling in older adults.

METHODS

This observational study involved 267 elderly people aged 65 to 85 years (73.99 SD 7.51) living in south-eastern Poland. The subjects were divided into two groups: a group with a high risk of falling and a group with a low risk of falling, based on their timed up-and-go test. Postural stability was assessed during eyes-open and eyes-closed trials using the two-plate stability platform CQ Stab 2P.

RESULTS

The best accuracy, sensitivity, and specificity were observed for the sway path, anterior-posterior sway path, and medial-lateral sway path with open and closed eyes. The clinical cut-off score to predict the risk of falling was 350.63 for the sway path with open eyes, 272.64 for the anterior-posterior sway path, and 159.63 for the medial-lateral sway path. The clinical cut-off score for sway path with closed eyes was 436.11.

CONCLUSIONS

Static posturography screenings in clinical practice may also be useful for detecting typical balance changes in older adults.

Intelligent Fall-Risk Assessment Based on Gait Stability and Symmetry Among Older Adults Using Tri-Axial Accelerometry

This study aimed to use the k-nearest neighbor (kNN) algorithm, which combines gait stability and symmetry derived from a normalized cross-correlation (NCC) analysis of acceleration signals from the bilateral ankles of older adults, to assess fall risk. Fifteen non-fallers and 12 recurrent fallers without clinically significant musculoskeletal and neurological diseases participated in the study. Sex, body mass index, previous falls, and the results of the 10 m walking test (10 MWT) were recorded. The acceleration of the five gait cycles from the midsection of each 10 MWT was used to calculate the unilateral NCC coefficients for gait stability and bilateral NCC coefficients for gait symmetry, and then kNN was applied for classifying non-fallers and recurrent fallers. The duration of the 10 MWT was longer among recurrent fallers than it was among non-fallers (p &lt; 0.05). Since the gait signals were acquired from tri-axial accelerometry, the kNN F1 scores with the x-axis components were 92% for non-fallers and 89% for recurrent fallers, and the root sum of squares (RSS) of the signals was 95% for non-fallers and 94% for recurrent fallers. The kNN classification on gait stability and symmetry revealed good accuracy in terms of distinguishing non-fallers and recurrent fallers. Specifically, it was concluded that the RSS-based NCC coefficients can serve as effective gait features to assess the risk of falls.

Effectiveness of Platform-Based Robot-Assisted Rehabilitation for Musculoskeletal or Neurologic Injuries: A Systematic Review

During the last ten years the use of robotic-assisted rehabilitation has increased significantly. Compared with traditional care, robotic rehabilitation has several potential advantages. Platform-based robotic rehabilitation can help patients recover from musculoskeletal and neurological conditions. Evidence on how platform-based robotic technologies can positively impact on disability recovery is still lacking, and it is unclear which intervention is most effective in individual cases. This systematic review aims to evaluate the effectiveness of platform-based robotic rehabilitation for individuals with musculoskeletal or neurological injuries. Thirty-eight studies met the inclusion criteria and evaluated the efficacy of platform-based rehabilitation robots. Our findings showed that rehabilitation with platform-based robots produced some encouraging results. Among the platform-based robots studied, the VR-based Rutgers Ankle and the Hunova were found to be the most effective robots for the rehabilitation of patients with neurological conditions (stroke, spinal cord injury, Parkinson's disease) and various musculoskeletal ankle injuries. Our results were drawn mainly from studies with low-level evidence, and we think that our conclusions should be taken with caution to some extent and that further studies are needed to better evaluate the effectiveness of platform-based robotic rehabilitation devices.

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature

BACKGROUND

The term "data science" encompasses several methods, many of which are considered cutting edge and are being used to influence care processes across the world. Nursing is an applied science and a key discipline in health care systems in both clinical and administrative areas, making the profession increasingly influenced by the latest advances in data science. The greater informatics community should be aware of current trends regarding the intersection of nursing and data science, as developments in nursing practice have cross-professional implications.

OBJECTIVES

This study aimed to summarize the latest (calendar year 2020) research and applications of nursing-relevant patient outcomes and clinical processes in the data science literature.

METHODS

We conducted a rapid review of the literature to identify relevant research published during the year 2020. We explored the following 16 topics: (1) artificial intelligence/machine learning credibility and acceptance, (2) burnout, (3) complex care (outpatient), (4) emergency department visits, (5) falls, (6) health care-acquired infections, (7) health care utilization and costs, (8) hospitalization, (9) in-hospital mortality, (10) length of stay, (11) pain, (12) patient safety, (13) pressure injuries, (14) readmissions, (15) staffing, and (16) unit culture.

RESULTS

Of 16,589 articles, 244 were included in the review. All topics were represented by literature published in 2020, ranging from 1 article to 59 articles. Numerous contemporary data science methods were represented in the literature including the use of machine learning, neural networks, and natural language processing.

CONCLUSION

This review provides an overview of the data science trends that were relevant to nursing practice in 2020. Examinations of such literature are important to monitor the status of data science's influence in nursing practice.

Perspective: Balance Assessments in Progressive Supranuclear Palsy: Lessons Learned

Many studies have examined aspects of balance in progressive supranuclear palsy (PSP), but guidance on the feasibility of standardized objective balance assessments and balance scales in PSP is lacking. Balance tests commonly used in Parkinson's disease often cannot be easily administered or translated to PSP. Here we briefly review methodology in prior studies of balance in PSP; then we focus on feasibility by presenting our experience with objective balance assessment in PSP-Richardson syndrome and PSP-parkinsonism during a crossover rTMS intervention trial. We highlight lessons learned, safety considerations, and future approaches for objective balance assessment in PSP.

Objective evaluation of the risk of falls in individuals with traumatic brain injury: feasibility and preliminary validation. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:4658-4661. [PMID: 34892252 DOI: 10.1109/embc46164.2021.9630020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Falls are a significant health concern for individuals with traumatic brain injury (TBI). For developing effective preemptive strategies to reduce falls, it is essential to get an accurate and objective assessment of fall-risk. The current investigation evaluates the feasibility of a robotic, posturography-based fall-risk assessment to objectively quantify the risk of falls in individuals with TBI. Five individuals with chronic TBI (age: 56.2 ± 4.7 years, time since injury: 13.09±11.95 years) performed the fall-risk assessment on hunova- a commercial robotic platform for assessing and training balance. The unique assessment considers multifaceted fall-driving components, including static and dynamic balance, sit-to-stand, limits of stability, responses to perturbations, gait speed, and history of previous falls and provides a composite score for risk of falls, called silver index (SI), a number between 0 (no risk) and 100 (high risk) based on a machine learning-based predictive model. The SI score for individuals with TBI was 66±32.1 (min: 32, max: 100) - categorized as medium-to-high risk of falls. The construct validity of SI outcome was performed by evaluating its relationship with clinical outcomes of functional balance and mobility (Berg Balance Scale (BBS), Timed-Up and Go (TUG), and gait speed) as well as posturography outcomes (Center of Pressure (CoP) area and velocity). The bivariate Pearson correlation coefficient, although not statistically significant, suggested the presence of linear relationships (0.52 > r > 0.84) between SI and functional and posturography outcomes, supporting the construct validity of SI. A large sample is needed to further prove the validity of the SI outcome before it is used for meaningful interpretations of the risk of falls in individuals with TBI.Clinical Relevance- Clinical assessments of risk of falls are traditionally based on questionnaires that may lack objectivity, consistency, and accuracy. The current work tests the feasibility of using a robotic platform-based assessment to objectively quantify the risk of falls in individuals with TBI.

The Added Value of Combined Timed Up and Go Test, Walking Speed, and Grip Strength on Predicting Recurrent Falls in Chinese Community-dwelling Elderly

Purpose

To determine whether combined performance-based models could exert better predictive values toward discriminating community-dwelling elderly with high risk of any-falls or recurrent-falls.

Participants and Methods

This prospective cohort study included a total of 875 elderly participants (mean age: 67.10±5.94 years) with 513 females and 362 males, recruited from Hangu suburb area of Tianjin, China. All participants completed comprehensive assessments.

Methods

We documented information about sociodemographic information, behavioral characteristics and medical conditions. Three functional tests—timed up and go test (TUGT), walking speed (WS), and grip strength (GS) were used to create combined models. New onsets of any-falls and recurrent-falls were ascertained at one-year follow-up appointment.

Results

In total 200 individuals experienced falls over a one-year period, in which 66 individuals belonged to the recurrent-falls group (33%). According to the receiver operating characteristic curve (ROC), the cutoff points of TUGT, WS, and GS toward recurrent-falls were 10.31 s, 0.9467 m/s and 0.3742 kg/kg respectively. We evaluated good performance as “+” while poor performance as “–”. After multivariate adjustment, we found “TUGT >10.31 s” showed a strong correlation with both any-falls (adjusted odds ratio (OR)=2.025; 95% confidence interval (CI)=1.425–2.877) and recurrent-falls (adjusted OR=2.150; 95%CI=1.169–3.954). Among combined functional models, “TUGT >10.31 s, GS <0.3742 kg/kg, WS >0.9467 m/s” showed strongest correlation with both any-falls (adjusted OR=5.499; 95%CI=2.982–10.140) and recurrent-falls (adjusted OR=8.260; 95%CI=3.880–17.585). And this combined functional model significantly increased discriminating abilities on screening recurrent-fallers than a single test (C-statistics=0.815, 95%CI=0.782–0.884, P<0.001), while not better than a single test in predicting any-fallers (P=0.083).

Conclusion

Elderly people with poor TUGT performance, weaker GS but quicker WS need to be given high priority toward fall prevention strategies for higher risks and frequencies. Meanwhile, the combined “TUGT–, GS–, WS+” model presents increased discriminating ability and could be used as a conventional tool to discriminate recurrent-fallers in clinical practice.

Balance and visual reliance in post-COVID syndrome patients assessed with a robotic system: a multi-sensory integration deficit

The symptoms of SARS-CoV-2 infection are not limited to the acute phase, with vertigo, peripheral neuropathies, headache, fatigue, memory loss, and depression being the most common post-acute clinical manifestations. Such post-COVID syndrome is a new clinically relevant challenge for diagnosis and therapy. Our goal was to quantify deficit in balance and proprioception related to post-COVID syndrome and, in this sense, we prospectively analyzed data of 66 post-COVID-19 outpatients (mean age 47.3 ± 11.1 years, 50 females, 25 hospitalized), evaluated using the robotic device hunova. The dynamic balance was assessed with open (OE) and closed eyes (CE) and three indexes, proportional to subject instability, were measured: the sway path and two oscillation ranges. Hospitalized group showed the worst performance with respect to non-hospitalized patients and normality range in both visual conditions for the sway path and the oscillation ranges, with the worst performance being with CE. When compared to normality ranges, post-COVID patients were significantly more distant from normality in the OE condition compared to the CE condition. These results suggest that independently from the severity of the disease experienced, post-COVID syndrome makes the elastic balance test performances more distant from the normality when the subject integrates vision, somatosensory information, and vestibular information. In the absence of visual feedback, patients seem to implement compensatory strategies, presumably seeking more significant feedback from the lower limbs, which improve their performance. These data suggest a new mechanism of the post-COVID syndrome that deserves further investigation for its potential impact on activities of daily living.

Comparing Machine Learning Methods to Improve Fall Risk Detection in Elderly with Osteoporosis from Balance Data

Falls are a multifactorial cause of injuries for older people. Subjects with osteoporosis are particularly vulnerable to falls. We study the performance of different computational methods to identify people with osteoporosis who experience a fall by analysing balance parameters. Balance parameters, from eyes open and closed posturographic studies, and prospective registration of falls were obtained from a sample of 126 community-dwelling older women with osteoporosis (age 74.3 ± 6.3) using World Health Organization Questionnaire for the study of falls during a follow-up of 2.5 years. We analyzed model performance to determine falls of every developed model and to validate the relevance of the selected parameter sets. The principal findings of this research were (1) models built using oversampling methods with either IBk (KNN) or Random Forest classifier can be considered good options for a predictive clinical test and (2) feature selection for minority class (FSMC) method selected previously unnoticed balance parameters, which implies that intelligent computing methods can extract useful information with attributes which otherwise are disregarded by experts. Finally, the results obtained suggest that Random Forest classifier using the oversampling method to balance the data independent of the set of variables used got the best overall performance in measures of sensitivity (>0.71), specificity (>0.18), positive predictive value (PPV >0.74), and negative predictive value (NPV >0.66) independent of the set of variables used. Although the IBk classifier was built with oversampling data considering information from both eyes opened and closed, using all variables got the best performance (sensitivity >0.81, specificity >0.19, PPV = 0.97, and NPV = 0.66).

Random Forest for Automatic Feature Importance Estimation and Selection for Explainable Postural Stability of a Multi-Factor Clinical Test

Falling is a common incident that affects the health of elder adults worldwide. Postural instability is one of the major contributors to this problem. In this study, we propose a supplementary method for measuring postural stability that reduces doctor intervention. We used simple clinical tests, including the timed-up and go test (TUG), short form berg balance scale (SFBBS), and short portable mental status questionnaire (SPMSQ) to measure different factors related to postural stability that have been found to increase the risk of falling. We attached an inertial sensor to the lower back of a group of elderly subjects while they performed the TUG test, providing us with a tri-axial acceleration signal, which we used to extract a set of features, including multi-scale entropy (MSE), permutation entropy (PE), and statistical features. Using the score for each clinical test, we classified our participants into fallers or non-fallers in order to (1) compare the features calculated from the inertial sensor data, and (2) compare the screening capabilities of the multifactor clinical test against each individual test. We use random forest to select features and classify subjects across all scenarios. The results show that the combination of MSE and statistic features overall provide the best classification results. Meanwhile, PE is not an important feature in any scenario in our study. In addition, a t-test shows that the multifactor test of TUG and BBS is a better classifier of subjects in this study.