Prediction of activity type in preschool children using machine learning techniques

Objectives Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Design Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Methods Eleven children aged 3–6 years (mean age = 4.8 ± 0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Results Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Conclusions Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

Repeatability of static load bearing exercises during rehabilitation of individuals with transfemoral amputation fitted with osseointegrated implant

Bone-anchored prostheses, relying on implants to attach the prosthesis directly to the residual skeleton, are the ultimate resort for patients with transfemoral amputations (TFA) experiencing severe socket discomfort. The first patient receiving a bone-anchored prosthesis underwent the surgery in 1990 in the Sahlgrenska University Hospital (Sweden). To date, there are two commercially available implants: OPRA (Integrum, Sweden) and ILP (Orthodynamics, Germany). The key to success to this technique is a firm bone-implant bonding, depending on increasing mechanical stress applied daily during load bearing exercises (LBE). The loading data could be analysed through different biomechanical variables. The intra-tester reliability of these exercises will be presented here. Moreover the effect of increase of loading, axes of application of the load and body weight as well as the difference between force and moment variables will be discussed.

Demographics and discharge outcomes of dysvascular and non-vascular lower limb amputees at a subacute rehabilitation unit: A 7-year series

Objective To examine personal and social demographics, and rehabilitation discharge outcomes of dysvascular and non-vascular lower limb amputees. Methods In total, 425 lower limb amputation inpatient rehabilitation admissions (335 individuals) from 2005 to 2011 were examined. Admission and discharge descriptive statistics (frequency, percentages) were calculated and compared by aetiology. Results Participants were male (74%), aged 65 years (s.d. 14), born in Australia (72%), had predominantly dysvascular aetiology (80%) and a median length of stay 48 days (interquartile range (IQR): 25–76). Following amputation, 56% received prostheses for mobility, 21% (n = 89) changed residence and 28% (n = 116) required community services. Dysvascular amputees were older (mean 67 years, s.d. 12 vs 54 years, s.d. 16; P < 0.001) and recorded lower functional independence measure – motor scores at admission (z = 3.61, P < 0.001) and discharge (z = 4.52, P < 0.001). More nonvascular amputees worked before amputation (43% vs 11%; P < 0.001), were prescribed a prosthesis by discharge (73% vs 52%; P < 0.001) and had a shorter length of stay (7 days, 95% confidence interval: –3 to 17), although this was not statistically significant. Conclusions Differences exist in social and demographic outcomes between dysvascular and non-vascular lower limb amputees.

Functional adaptation and rehabilitation following total knee replacement

This research project evaluated the biomechanical and functional outcomes of patients following total knee replacement measured at 6 and 12 months following surgery. Using more objective measures, patients were examined to determine changes in biomechanical and neuromuscular function during performance of activities of daily living such as walking, stair climbing and turning. Adaptations in joint positioning and performance were identified and progressive improvements were made in some areas of locomotor function. The findings of the study provided important objective information to contribute to the design and evaluation of prostheses, new surgical and rehabilitation procedures and improved recovery of patients.

Developing and evaluating interventions that are applicable and relevant to inpatients and those who care for them; a multiphase, pragmatic action research approach

Background Randomised controlled trials may be of limited use to evaluate the multidisciplinary and multimodal interventions required to effectively treat complex patients in routine clinical practice; pragmatic action research approaches may provide a suitable alternative. Methods A multiphase, pragmatic, action research based approach was developed to identify and overcome barriers to nutritional care in patients admitted to a metropolitan hospital hip-fracture unit. Results Four sequential action research cycles built upon baseline data including 614 acute hip-fracture inpatients and 30 purposefully sampled clinicians. Reports from Phase I identified barriers to nutrition screening and assessment. Phase II reported post-fracture protein-energy intakes and intake barriers. Phase III built on earlier results; an explanatory mixed-methods study expanded and explored additional barriers and facilitators to nutritional care. Subsequent changes to routine clinical practice were developed and implemented by the treating team between Phase III and IV. These were implemented as a new multidisciplinary, multimodal nutritional model of care. A quasi-experimental controlled, ‘before-and-after’ study was then used to compare the new model of care with an individualised nutritional care model. Engagement of the multidisciplinary team in a multiphase, pragmatic action research intervention doubled energy and protein intakes, tripled return home discharge rates, and effected a 75% reduction in nutritional deterioration during admission in a reflective cohort of hip-fracture inpatients. Conclusions This approach allowed research to be conducted as part of routine clinical practice, captured a more representative patient cohort than previously reported studies, and facilitated exploration of barriers and engagement of the multidisciplinary healthcare workers to identify and implement practical solutions. This study demonstrates substantially different findings to those previously reported, and is the first to demonstrate that multidisciplinary, multimodal nutrition care reduces intake barriers, delivers a higher proportional increase in protein and energy intake compared with baseline than other published intervention studies, and improves patient outcomes when compared with individualised nutrition care. The findings are considered highly relevant to clinical practice and have high translation validity. The authors strongly encourage the development of similar study designs to investigate complex health problems in elderly, multi-morbid patient populations as a way to evaluate and change clinical practice.

Cost effectiveness of osseointegration

Individuals with limb amputation fitted with conventional socket-suspended prostheses often experience socket-related discomfort leading to a significant decrease in quality of life. Bone-anchored prostheses are increasingly acknowledged as viable alternative method of attachment of artificial limb. In this case, the prosthesis is attached directly to the residual skeleton through a percutaneous fixation. To date, a few osseointegration fixations are commercially available. Several devices are at different stages of development particularly in Europe and the US. [1-15] Clearly, surgical procedures are currently blooming worldwide. Indeed, Australia and Queensland, in particular, have one of the fastest growing populations. Previous studies involving either screw-type implants or press-fit fixations for bone-anchorage have focused on biomechanics aspects as well as the clinical benefits and safety of the procedure. [16-25] In principle, bone-anchored prostheses should eliminate lifetime expenses associated with sockets and, consequently, potentially alleviate the financial burden of amputation for governmental organizations. Sadly, publications focusing on cost-effectiveness are sparse. In fact, only one study published by Haggstrom et al (2012), reported that “despite significantly fewer visits for prosthetic service the annual mean costs for osseointegrated prostheses were comparable with socket-suspended prostheses”.[26] Consequently, governmental organizations such as Queensland Artificial Limb Services (QALS) are facing a number of challenges while adjusting financial assistance schemes that should be fair and equitable to their clients fitted with bone-anchored prostheses. Clearly, more scientific evidence extracted from governmental databases is needed to further consolidate the analyses of financial burden associated with both methods of attachment (i.e., conventional sockets prostheses, bone-anchored prostheses). The purposes of the presentation will be: 1. To outline methodological avenues to assess the cost-effectiveness of bone-anchored prostheses compared to conventional sockets prostheses, 2. To highlight the potential obstacles and limitations in cost-effectiveness analyses of bone-anchored prostheses, 3. To present preliminary results of a cost-comparison analysis focusing on the comparison of the costs expressed in dollars over QALS funding cycles for both methods of attachment.

Osseointegration internationally: Australia is playing a key role?

Individuals with limb amputation fitted with conventional socket-suspended prostheses often experience socket-related discomfort leading to a significant decrease in quality of life. Bone-anchored prostheses are increasingly acknowledged as viable alternative method of attachment of artificial limb. In this case, the prosthesis is attached directly to the residual skeleton through a percutaneous fixation. To date, a few osseointegration fixations are commercially available. Several devices are at different stages of development particularly in Europe and the US.[1-15] Clearly, surgical procedures are currently blooming worldwide. Indeed, Australia and Queensland in particular have one of the fastest growing populations. Previous studies involving either screw-type implants or press-fit fixations for bone-anchorage have focused on fragmented biomechanics aspects as well as the clinical benefits and safety of the procedure. [16-25] However, very few publications have synthetized this information and provided an overview of the current developments in bone-anchored prostheses worldwide, let alone in Australia. The purposes of the presentation will be: 1. To provide an overview of the state-of-art developments in bone-anchored prostheses with as strong emphasis on the design of fixations, treatment, benefits, risks as well as future opportunities and challenges, 2. To present the current international developments of procedures for bone-anchored prostheses in terms of numbers of centers, number of cases and typical case-mix, 3. To highlight the current role Australia is playing as a leader worldwide in terms of growing population, broadest range of case-mix, choices of fixations, development of reimbursement schemes, unique clinical outcome registry for evidence-based practice, cutting-edge research, consumer demand and general public interest.

Evaluation framework to assess benefits and harms of bone-anchored prosthesis

Bone-anchored prostheses are increasingly acknowledged as viable alternative method of attachment of artificial limb compared to socket-suspended prostheses. To date, a few osseointegration fixations are commercially available. Several devices are at different stages of development particularly in Europe and the US. Clearly, the current momentum experienced worldwide is creating a need for a standardized evaluation framework to assess the benefits and safety of each procedure.

Osseointegrated prosthetic limb for amputees: Over hundred cases

The Osseointegrated Prosthetic Limb (OPL) was introduced in 2011. Prior to its advent all prostheses consisted of stump and socket mechanisms which did not changed dramatically since Ambroise Pare lower limb prosthesis in 1525. These socket prostheses failed to address a few major requirements of normal gait. Our hypothesis was that using an Osseointegrated Prosthetic limb will result in superior function of daily activities, without compromising patients’ safety.The aims of this paper are (A) to describe the surgical procedure of the OPL; and (B) to present data on potential risks and benefits with assessment of clinical and functional outcomes at follow up

Osseointegrated prosthetic limb for amputees: Single stage surgery

The Osseointegrated Prosthetic Limb (OPL) was introduced in 2011. The socket prostheses failed to address a few major requirements of normal gait. Our hypothesis was that using an Osseointegrated Prosthetic limb will result in superior function of daily activities, without compromising patients’ safety. Traditionally this surgery was done as a two-stage procedure. The aims of this study were (A)to describe the single - surgical procedure of the OPL; and (B)To present data on potential risks and benefits with sssessment of clinical and functional outcomes at follow up.

Osseointegration for limb loss: Can Australia play a key role?

Individuals with limb amputation fitted with conventional socket-suspended prostheses often experience socket related discomfort leading to a significant decrease in quality of life. Most of these concerns can be overcome by surgical techniques enabling bone-anchored prostheses. In this case, the prosthesis is attached directly to the residual skeleton through a percutaneous implant. The aim of this study is to present the current advances in these surgical techniques worldwide with a strong focus on the developments in Australia and Queensland.

Description of body posture during Static load bearing exercises for individuals with transfemoral amputation fitted with bone-anchored prosthesis

The rehabilitation programs of bone-anchorage prostheses relying either on the OPRA (Integrum, Sweden) or the ILP (Orthodynamics, Germany) fixation involve some forms of static load bearing exercises (LBE). So far, most of biomechanical studies of these static LBEs focused on the direct measurements of the actual forces and moments applied on the OPRA fixation of individuals with transfemoral amputation (TFA). To date, the proof-of-concept of an apparatus to conduct these kinetic measurements has been presented, along with some preliminary data. The understanding of the kinetic data is essential to improve rehabilitation programs as well as the design of upcoming loading frames. However, kinetic information alone is difficult to interpret without concomitant kinematic data. The purpose of this preliminary study was to introduce a qualitative analysis describing the different body postures during LBE for a group of TFAs.

Static load bearing exercises during rehabilitation of individuals with transfemoral amputation fitted with osseointegrated implant: Kinetic analysis

The desire to solve problems caused by socket prostheses in transfemoral amputees and the acquired success of osseointegration in the dental application has led to the introduction of osseointegration in the orthopedic surgery. Since its first introduction in 1990 in Gothenburg Sweden the osseointegrated (OI) orthopedic fixation has proven several benefits[1]. The surgery consists of two surgical procedures followed by a lengthy rehabilitation program. The rehabilitation program after an OI implant includes a specific training period with a short training prosthesis. Since mechanical loading is considered to be one of the key factors that influence bone mass and the osseointegration of bone-anchored implants, the rehabilitation program will also need to include some form of load bearing exercises (LBE). To date there are two frequently used commercially available human implants. We can find proof in the literature that load bearing exercises are performed by patients with both types of OI implants. We refer to two articles, a first one written by Dr. Aschoff and all and published in 2010 in the Journal of Bone and Joint Surgery.[2] The second one presented by Hagberg et al in 2009 gives a very thorough description of the rehabilitation program of TFA fitted with an OPRA implant. The progression of the load however is determined individually according to the residual skeleton’s quality, pain level and body weight of the participant.[1] Patients are using a classical bathroom weighing scale to control the load on the implant during the course of their rehabilitation. The bathroom scale is an affordable and easy-to-use device but it has some important shortcomings. The scale provides instantaneous feedback to the patient only on the magnitude of the vertical component of the applied force. The forces and moments applied along and around the three axes of the implant are unknown. Although there are different ways to assess the load on the implant for instance through inverse dynamics in a motion analysis laboratory [3-6] this assessment is challenging. A recent proof- of-concept study by Frossard et al (2009) showed that the shortcomings of the weighing scale can be overcome by a portable kinetic system based on a commercial transducer[7].

Load applied on a bone-anchored transfemoral prosthesis: characterisation of a prosthesis : a pilot study

The objectives of this study were (A) to record the inner prosthesis loading during activities of daily living (ADL), (B) to present a set of variables comparing loading data, and (C) to provide an example of characterisation of two prostheses. The load was measured at 200 Hz using a multi-axial transducer mounted between the residuum and the knee of an individual with unilateral transfemoral amputation fitted with a bone-anchored prosthesis. The load was measured while using two different prostheses including a mechanically (PRO1) and a microprocessor controlled (PRO2) knee during six ADL. The characterisation of prosthesis was achieved using a set of variables split into four categories, including temporal characteristics, maximum loading, loading slopes and impulse. Approximately 360 gait cycles were analysed for each prosthesis. PRO1 showed a cadence improved by 19% and 7%, a maximum force on the long axis reduced by 11% and 19%, as well as an impulse reduced by 32% and 15% during descent of incline and stairs compared to PRO2, respectively. This work confirmed that the proposed apparatus and characterisation can reveal how changes of prosthetic components are translated into inner loading.

Bone-anchored prosthesis: Evidence that “gains” overcome the “pain”

Most of socket related discomforts leading to a significant decrease in quality of life of individuals with limb amputation can be overcome by surgical techniques enabling bone-anchored prostheses. To date, the OPRA two-stage procedure (i.e., S1, S2) is the most acknowledged treatment. However, surgical implantations of osseointegrated fixations are developing at an unprecedented pace worldwide.[1-18] Clearly, this option is becoming accessible to a wide range of individuals with limb amputations. The team led by Dr Rickard Branemark has published a number of landmark articles each focusing on a particular aspect (e.g., health related quality of life, functional outcomes, bone remodelling, infection rate). [1-3, 19-32] However, evidences presented in this prospective study are remarkable. Functional outcome, health-related quality of life and complications were considered concurrently for a large population (i.e., 51 participants) over an extended period of time (i.e., up to year follow up). Therefore, the “gain” and “pain” of the whole procedure were truly contrasted for the first time. The results confirmed that OPRA surgical and rehabilitation procedures improved significantly prosthetic use, mobility, global situation and fewer problems. Furthermore, the authors reported 47 episodes of infections for 63% (32) participants between post-op S1 and two years follow up. A total of 87% (41) were superficial infections recorded for 28 participants between post-op S2 and two years follow up, while 13% (6) were deep infections occurring for 4 participants during post-op S1 and S2. As expected, post-op S2 phase was the most prone to both infections. More importantly, the vast majority of infections were effectively treated with oral antibiotics. Clearly, this study provided definitive evidence that the benefits of OPRA fixation overcome complications. This article is also establishing reporting standards and benchmark data for future studies focusing on bone-anchored prostheses.