Cost-Effectiveness and Value of Information Analysis of an Ambient Intelligent Geriatric Management (AmbIGeM) System Compared to Usual Care to Prevent Falls in Older People in Hospitals.

BACKGROUND: The Ambient Intelligent Geriatric Management (AmbIGeM) system combines wearable sensors with artificial intelligence to trigger alerts to hospital staff before a fall. A clinical trial found no effect across a heterogenous population, but reported a reduction in the injurious falls rate in a post hoc analysis of patients on Geriatric Evaluation Management Unit (GEMU) wards. Cost-effectiveness and Value of Information (VoI) analyses of the AmbIGeM system in GEMU wards was undertaken. METHODS: An Australian health-care system perspective and 5-year time horizon were used for the cost-effectiveness analysis. Implementation costs, inpatient costs and falls data were collected. Injurious falls were defined as causing bruising, laceration, fracture, loss of consciousness, or if the patient reported persistent pain. To compare costs and outcomes, generalised linear regression models were used to adjust for baseline differences between the intervention and usual care groups. Bootstrapping was used to represent uncertainty. For the VoI analysis, 10,000 different sample sizes with randomly sampled values ranging from 1 to 50,000 were tested to estimate the optimal sample size of a new trial that maximised the Expected Net Benefits of Sampling. RESULTS: An adjusted 0.036 fewer injurious falls (adjusted rate ratio of 0.56) and AUD$4554 lower costs were seen in the intervention group. However, uncertainty that the intervention is cost effective for the prevention of an injurious fall was present at all monetary values of this effectiveness outcome. A new trial with a sample of 4376 patients was estimated to maximise the Expected Net Benefit of Sampling, generating a net benefit of AUD$186,632 at a benefit-to-cost ratio of 1.1. CONCLUSIONS: The benefits to cost ratio suggests that a new trial of the AmbIGeM system in GEMU wards may not be high-value compared to other potential trials, and that the system should be implemented. However, a broader analysis of options for preventing falls in GEMU is required to fully inform decision making. TRIAL REGISTRATION: Australian and New Zealand Clinical Trial Registry (ACTRN 12617000981325).

Patient Acceptability of a Novel Technological Solution (Ambient Intelligent Geriatric Management System) to Prevent Falls in Geriatric and General Medicine Wards: A Mixed-Methods Study.

INTRODUCTION: As effective interventions to prevent inpatient falls are lacking, a novel technological intervention was trialed. The Ambient Intelligent Geriatric Management (AmbIGeM) system used wearable sensors that detected and alerted staff of patient movements requiring supervision. While the system did not reduce falls rate, it is important to evaluate the acceptability, usability, and safety of the AmbIGeM system, from the perspectives of patients and informal carers. METHODS: We conducted a mixed-methods study using semistructured interviews, a pre-survey and post-survey. The AmbIGeM clinical trial was conducted in two geriatric evaluation and management units and a general medical ward, in two Australian hospitals, and a subset of participants were recruited. Within 3 days of being admitted to the study wards and enrolling in the trial, 31 participants completed the pre-survey. Prior to discharge (post-intervention), 30 participants completed the post-survey and 27 participants were interviewed. Interview data were thematically analyzed and survey data were descriptively analyzed. RESULTS: Survey and interview participants had an average age of 83 (SD 9) years, 65% were female, and 41% were admitted with a fall. Participants considered the AmbIGeM system a good idea. Most but not all thought the singlet and sensor component as acceptable and comfortable, with no privacy concerns. Participants felt reassured with extra monitoring, although sometimes misunderstood the purpose of AmbIGeM as detecting patient falls. Participants' acceptability was strongly positive, with median 8+ (0-10 scale) on pre- and post-surveys. DISCUSSION/CONCLUSION: Patients' acceptability is important to optimize outcomes. Overall older patients considered the AmbIGeM system as acceptable, usable, and improving safety. The findings will be important to guide refinement of this and other similar technology developments.

Effectiveness of the Wearable Sensor-based Ambient Intelligent Geriatric Management (AmbIGeM) System in Preventing Falls in Older People in Hospitals.

BACKGROUND: The Ambient Intelligent Geriatric Management (AmbIGeM) system augments best practice and involves a novel wearable sensor (accelerometer and gyroscope) worn by patients where the data captured by the sensor are interpreted by algorithms to trigger alerts on clinician handheld mobile devices when risk movements are detected. METHODS: A 3-cluster stepped-wedge pragmatic trial investigating the effect on the primary outcome of falls rate and secondary outcome of injurious fall and proportion of fallers. Three wards across 2 states were included. Patients aged ≥65 years were eligible. Patients requiring palliative care were excluded. The trial was registered with the Australia and New Zealand Clinical Trials registry, number 12617000981325. RESULTS: A total of 4924 older patients were admitted to the study wards with 1076 excluded and 3240 (1995 control, 1245 intervention) enrolled. The median proportion of study duration with valid readings per patient was 49% ((interquartile range [IQR] 25%-67%)). There was no significant difference between intervention and control relating to the falls rate (adjusted rate ratio = 1.41, 95% confidence interval [0.85, 2.34]; p = .192), proportion of fallers (odds ratio = 1.54, 95% confidence interval [0.91, 2.61]; p = .105), and injurious falls rate (adjusted rate ratio = 0.90, 95% confidence interval [0.38, 2.14]; p = .807). In a post hoc analysis, falls and injurious falls rate were reduced in the Geriatric Evaluation and Management Unit wards when the intervention period was compared to the control period. CONCLUSIONS: The AmbIGeM system did not reduce the rate of falls, rate of injurious falls, or proportion of fallers. There remains a case for further exploration and refinement of this technology given the post hoc analysis findings with the Geriatric Evaluation and Management Unit wards. Clinical Trials Registration Number: 12617000981325.

A Multidisciplinary Exploratory Approach for Investigating the Experience of Older Adults Attending Hospital Services.

BACKGROUND: The public areas of the hospital built environment have hardly been investigated for their age-friendliness. OBJECTIVE: This exploratory, multidisciplinary pilot study investigates the relationship between the physical environment and design of hospital spaces and older people's outpatient experience. METHODS: Sixteen participants were recruited from a geriatric Outpatient Clinic at a metropolitan public hospital in Australia. Participants were engaged in a concurrent mixed-method approach, comprising a comprehensive geriatric survey, walking observation, semi-structured interview and an independent architectural audit. RESULTS: Several elements arising from the hospital environment were identified as facilitators and barriers for its utilization and intrinsically related to participants' physical capacity. DISCUSSION: Age-friendly hospital design needs to consider strategies to remove barriers for older adults of different capacities, thus promoting healthy aging.

Effectiveness of an Ambient Intelligent Geriatric Management system (AmbIGeM) to prevent falls in older people in hospitals: protocol for the AmbIGeM stepped wedge pragmatic trial.

BACKGROUND: Although current best practice recommendations contribute to falls prevention in hospital, falls and injury rates remain high. There is a need to explore new interventions to reduce falls rates, especially in geriatric and general medical wards where older patients and those with cognitive impairment are managed. DESIGN AND METHODS: A three-cluster stepped wedge pragmatic trial, with an embedded qualitative process, of the Ambient Intelligent Geriatric Management (AmbIGeM) system (wearable sensor device to alert staff of patients undertaking at-risk activities), for preventing falls in older patients compared with standard care. The trial will occur on three acute/subacute wards in two hospitals in Adelaide and Perth, Australia. PARTICIPANTS: Patients aged >65 years admitted to study wards. A waiver (Perth) and opt-out of consent (Adelaide) was obtained for this study. Patients requiring palliative care will be excluded. OUTCOMES: The primary outcome is falls rate; secondary outcome measures are: (1) proportion of participants falling; (2) rate of injurious inpatient falls/1000 participant bed-days; (3) acceptability and safety of the interventions from patients and clinical staff perspectives; and (4) hospital costs, mortality and use of residential care to 3 months postdischarge. DISCUSSION: This study investigates a novel technological approach to preventing falls in hospitalised older people. We hypothesise that the AmbIGeM intervention will reduce falls and injury rates, with an economic benefit attributable to the intervention. If successful, the AmbIGeM system will be a useful addition to falls prevention in hospital wards with high proportions of older people and people with cognitive impairment. : Trial registration NUMBER: Australian and New Zealand Clinical Trial Registry: ACTRN 12617000981325; Pre-results.

An Adaptive Markov Random Field for Structured Compressive Sensing.

Exploiting intrinsic structures in sparse signals underpins the recent progress in compressive sensing (CS). The key for exploiting such structures is to achieve two desirable properties: generality (i.e., the ability to fit a wide range of signals with diverse structures) and adaptability (i.e., being adaptive to a specific signal). Most existing approaches, however, often only achieve one of these two properties. In this study, we propose a novel adaptive Markov random field sparsity prior for CS, which not only is able to capture a broad range of sparsity structures, but also can adapt to each sparse signal through refining the parameters of the sparsity prior with respect to the compressed measurements. To maximize the adaptability, we also propose a new sparse signal estimation where the sparse signals, support, noise and signal parameter estimation are unified into a variational optimization problem, which can be effectively solved with an alternative minimization scheme. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed method in recovery accuracy, noise tolerance, and runtime.

Evaluation and refinement of a handheld health information technology tool to support the timely update of bedside visual cues to prevent falls in hospitals.

AIM: To evaluate clinicians' perspectives, before and after clinical implementation (i.e. trial) of a handheld health information technology (HIT) tool, incorporating an iPad device and automatically generated visual cues for bedside display, for falls risk assessment and prevention in hospital. METHODS: This pilot study utilized mixed-methods research with focus group discussions and Likert-scale surveys to elicit clinicians' attitudes. The study was conducted across three phases within two medical wards of the Queen Elizabeth Hospital. Phase 1 (pretrial) involved focus group discussion (five staff) and surveys (48 staff) to elicit preliminary perspectives on tool use, benefits and barriers to use and recommendations for improvement. Phase 2 (tool trial) involved HIT tool implementation on two hospital wards over consecutive 12-week periods. Phase 3 (post-trial) involved focus group discussion (five staff) and surveys (29 staff) following tool implementation, with similar themes as in Phase 1. Qualitative data were evaluated using content analysis, and quantitative data using descriptive statistics and logistic regression analysis, with subgroup analyses on user status (P ≤ 0.05). RESULTS: Four findings emerged on clinicians' experience, positive perceptions, negative perceptions and recommendations for improvement of the tool. Pretrial, clinicians were familiar with using visual cues in hospital falls prevention. They identified potential benefits of the HIT tool in obtaining timely, useful falls risk assessment to improve patient care. During the trial, the wards differed in methods of tool implementation, resulting in lower uptake by clinicians on the subacute ward. Post-trial, clinicians remained supportive for incorporating the tool into clinical practice; however, there were issues with usability and lack of time for tool use. Staff who had not used the tool had less appreciation for it improving their understanding of patients' falls risk factors (odds ratio 0.12), or effectively preventing hospital falls (odds ratio 0.12). Clinicians' recommendations resulted in subsequent technological refinement of the tool, and provision of an additional iPad device for more efficient use. CONCLUSION: This study adds to the limited pool of knowledge about clinicians' attitudes toward health technology use in falls avoidance. Clinicians were willing to use the HIT tool, and their concerns about its usability were addressed in ongoing tool improvement. Including end-users in the development and refinement processes, as well as having high staff uptake of new technologies, is important in improving their acceptance and usage, and in maximizing beneficial feedback to further inform tool development.

Use and clinical efficacy of standard and health information technology fall risk assessment tools.

OBJECTIVE: To evaluate the health information technology (HIT) compared to Fall Risk for Older Persons (FROP) tool in fall risk screening. METHODS: A HIT tool trial was conducted on the geriatric evaluation and management (GEM, n = 111) and acute medical units (AMU, n = 424). RESULTS: Health information technology and FROP scores were higher on GEM versus AMU, with no differences between people who fell and people who did not fall. Both score completion rates were similar, and their values correlated marginally (Spearman's correlation coefficient 0.33, P < 0.01). HIT and FROP scores demonstrated similar sensitivity (80 vs 82%) and specificity (32 vs 36%) for detecting hospital falls. Hospital fall rates trended towards reduction on AMU (4.20 vs 6.96, P = 0.15) and increase on GEM (10.98 vs 6.52, P = 0.54) with HIT tool implementation. CONCLUSIONS: Health information technology tool acceptability and scoring were comparable to FROP screening, with mixed effects on fall rate with HIT tool implementation. Clinician partnership remains key to effective tool development.

A battery-less and wireless wearable sensor system for identifying bed and chair exits in a pilot trial in hospitalized older people.

Falls in hospitals are common, therefore strategies to minimize the impact of these events in older patients and needs to be examined. In this pilot study, we investigate a movement monitoring sensor system for identifying bed and chair exits using a wireless wearable sensor worn by hospitalized older patients. We developed a movement monitoring sensor system that recognizes bed and chair exits. The system consists of a machine learning based activity classifier and a bed and chair exit recognition process based on an activity score function. Twenty-six patients, aged 71 to 93 years old, hospitalized in the Geriatric Evaluation and Management Unit participated in the supervised trials. They wore over their attire a battery-less, lightweight and wireless sensor and performed scripted activities such as getting off the bed and chair. We investigated the system performance in recognizing bed and chair exits in hospital rooms where RFID antennas and readers were in place. The system's acceptability was measured using two surveys with 0-10 likert scales. The first survey measured the change in user perception of the system before and after a trial; the second survey, conducted only at the end of each trial, measured user acceptance of the system based on a multifactor sensor acceptance model. The performance of the system indicated an overall recall of 81.4%, precision of 66.8% and F-score of 72.4% for joint bed and chair exit recognition. Patients demonstrated improved perception of the system after use with overall score change from 7.8 to 9.0 and high acceptance of the system with score ≥ 6.7 for all acceptance factors. The present pilot study suggests the use of wireless wearable sensors is feasible for detecting bed and chair exits in a hospital environment.

Modelling Predictors of Molecular Response to Frontline Imatinib for Patients with Chronic Myeloid Leukaemia.

BACKGROUND: Treatment of patients with chronic myeloid leukaemia (CML) has become increasingly difficult in recent years due to the variety of treatment options available and challenge deciding on the most appropriate treatment strategy for an individual patient. To facilitate the treatment strategy decision, disease assessment should involve molecular response to initial treatment for an individual patient. Patients predicted not to achieve major molecular response (MMR) at 24 months to frontline imatinib may be better treated with alternative frontline therapies, such as nilotinib or dasatinib. The aims of this study were to i) understand the clinical prediction 'rules' for predicting MMR at 24 months for CML patients treated with imatinib using clinical, molecular, and cell count observations (predictive factors collected at diagnosis and categorised based on available knowledge) and ii) develop a predictive model for CML treatment management. This predictive model was developed, based on CML patients undergoing imatinib therapy enrolled in the TIDEL II clinical trial with an experimentally identified achieving MMR group and non-achieving MMR group, by addressing the challenge as a machine learning problem. The recommended model was validated externally using an independent data set from King Faisal Specialist Hospital and Research Centre, Saudi Arabia. PRINCIPLE FINDINGS: The common prognostic scores yielded similar sensitivity performance in testing and validation datasets and are therefore good predictors of the positive group. The G-mean and F-score values in our models outperformed the common prognostic scores in testing and validation datasets and are therefore good predictors for both the positive and negative groups. Furthermore, a high PPV above 65% indicated that our models are appropriate for making decisions at diagnosis and pre-therapy. Study limitations include that prior knowledge may change based on varying expert opinions; hence, representing the category boundaries of each predictive factor could dramatically change performance of the models.

Sequence Learning with Passive RFID Sensors for Real-Time Bed-Egress Recognition in Older People.

Getting out of bed and ambulating without supervision is identified as one of the major causes of patient falls in hospitals and nursing homes. Therefore, increased supervision is proposed as a key strategy toward falls prevention. An emerging generation of batteryless, lightweight, and wearable sensors are creating new possibilities for ambulatory monitoring, where the unobtrusive nature of such sensors makes them particularly adapted for monitoring older people. In this study, we investigate the use of a batteryless radio-frequency identification (RFID) tag response to analyze bed-egress movements. We propose a bed-egress movement detection framework that includes a novel sequence learning classifier with a set of features derived from bed-egress motion analysis. We analyzed data from 14 healthy older people (66-86 years old) who wore a wearable embodiment of a batteryless accelerometer integrated RFID sensor platform loosely attached over their clothes at sternum level, and undertook a series of activities including bed-egress in two clinical room settings. The promising results indicate the efficacy of our batteryless bed-egress monitoring framework.

Effectiveness of a Batteryless and Wireless Wearable Sensor System for Identifying Bed and Chair Exits in Healthy Older People.

Aging populations are increasing worldwide and strategies to minimize the impact of falls on older people need to be examined. Falls in hospitals are common and current hospital technological implementations use localized sensors on beds and chairs to alert caregivers of unsupervised patient ambulations; however, such systems have high false alarm rates. We investigate the recognition of bed and chair exits in real-time using a wireless wearable sensor worn by healthy older volunteers. Fourteen healthy older participants joined in supervised trials. They wore a batteryless, lightweight and wireless sensor over their attire and performed a set of broadly scripted activities. We developed a movement monitoring approach for the recognition of bed and chair exits based on a machine learning activity predictor. We investigated the effectiveness of our approach in generating bed and chair exit alerts in two possible clinical deployments (Room 1 and Room 2). The system obtained recall results above 93% (Room 2) and 94% (Room 1) for bed and chair exits, respectively. Precision was >78% and 67%, respectively, while F-score was >84% and 77% for bed and chair exits, respectively. This system has potential for real-time monitoring but further research in the final target population of older people is necessary.

Memristive crypto primitive for building highly secure physical unclonable functions.

Physical unclonable functions (PUFs) exploit the intrinsic complexity and irreproducibility of physical systems to generate secret information. The advantage is that PUFs have the potential to provide fundamentally higher security than traditional cryptographic methods by preventing the cloning of devices and the extraction of secret keys. Most PUF designs focus on exploiting process variations in Complementary Metal Oxide Semiconductor (CMOS) technology. In recent years, progress in nanoelectronic devices such as memristors has demonstrated the prevalence of process variations in scaling electronics down to the nano region. In this paper, we exploit the extremely large information density available in nanocrossbar architectures and the significant resistance variations of memristors to develop an on-chip memristive device based strong PUF (mrSPUF). Our novel architecture demonstrates desirable characteristics of PUFs, including uniqueness, reliability, and large number of challenge-response pairs (CRPs) and desirable characteristics of strong PUFs. More significantly, in contrast to most existing PUFs, our PUF can act as a reconfigurable PUF (rPUF) without additional hardware and is of benefit to applications needing revocation or update of secure key information.

Framework for preventing falls in acute hospitals using passive sensor enabled radio frequency identification technology.

We describe a distributed architecture for a real-time falls prevention framework capable of providing a technological intervention to mitigate the risk of falls in acute hospitals through the development of an AmbIGeM (Ambient Intelligence Geritatric Management system). Our approach is based on using a battery free, wearable sensor enabled Radio Frequency Identification device. Unsupervised classification of high risk falls activities are used to facilitate an immediate response from caregivers by alerting them of the high risk activity, the particular patient, and their location. Early identification of high risk falls activities through a longitudinal and unsupervised setting in real-time allows the preventative intervention to be administered in a timely manner. Furthermore, real-time detection allows emergency protocols to be deployed immediately in the event of a fall. Finally, incidents of high risk activities are automatically documented to allow clinicians to customize and optimize the delivery of care to suit the needs of patients identified as being at most risk.

Towards falls prevention: a wearable wireless and battery-less sensing and automatic identification tag for real time monitoring of human movements.

Falls related injuries among elderly patients in hospitals or residents in residential care facilities is a significant problem that causes emotional and physical trauma to those involved while presenting a rising healthcare expense in countries such as Australia where the population is ageing. Novel approaches using low cost and privacy preserving sensor enabled Radio Frequency Identification (RFID) technology may have the potential to provide a low cost and effective technological intervention to prevent falls in hospitals. We outline the details of a wearable sensor enabled RFID tag that is battery free, low cost, lightweight, maintenance free and can be worn continuously for automatic and unsupervised remote monitoring of activities of frail patients at acute hospitals or residents in residential care. The technological developments outlined in the paper forms part of an overall technological intervention developed to reduce falls at acute hospitals or in residential care facilities. This paper outlines the details of the technology, underlying algorithms and the results (where an accuracy of 94-100% was achieved) of a successful pilot trial.