138 research outputs found
Supplemental material for Efficacy of mobile application interventions for the treatment of post-traumatic stress disorder: A systematic review
No full textSupplemental Material for Efficacy of mobile application interventions for the treatment of post-traumatic stress disorder: A systematic review by Alice Wickersham, Petros Minas Petrides, Victoria Williamson and Daniel Leightley: the STRONG STAR Consortium in Digital Health</p
AI for defence: readiness, resilience and mental health
No full textArtificial Intelligence (AI) is a cross-cutting technology that is making a major impact on behavioural analysis in both the defence and mental health domains. Employing AI well could boost readiness and resilience of military personnel. This article explores how AI is being used today in research and practice for Mental Health in the Defence domain. We identify key challenges that exist and signpost the important trends and directions of travel that could build bridges between these domains for the ultimate benefit of both
Navigating the software development landscape: Introducing the term Research Viable Product (RVP)
No full textIn the field of research software engineering, common terms such as minimum viable product (MVP), minimum marketable product (MMP), proof of concept (PoC), and prototype are used but often fail to adequately describe software designed specifically for research contexts. These terms do not capture the essential aspects of software that must adhere to rigorous testing protocols, uphold data integrity, and comply with research ethics. This position statement introduces the term Research Viable Product (RVP) to more accurately define software products developed for research purposes. An RVP is characterised by its readiness for research application, designed to test hypotheses, collect data, and evaluate efficacy while maintaining stringent data governance and security standards. Unlike MVPs, which focus on minimal features for early market feedback, RVPs prioritize core elements vital for research integrity. This distinction is crucial because it addresses the unique challenges of developing software within a research setting, focusing on the need for a shift in software development approaches to better meet the demands of research integrity and participant involvement. This paper advocates for the adoption of the RVP terminology to enhance the clarity and relevance in the development and evaluation of research-focused software
3D human action recognition and motion analysis using selective representations
No full textWith the advent of marker-based motion capture, attempts have been made to recognise
and quantify attributes of “type”, “content” and “behaviour” from the motion data.
Current work exists to obtain quick and easy identification of human motion for use in
multiple settings, such as healthcare and gaming by using activity monitors, wearable
technology and low-cost accelerometers. Yet, analysing human motion and generating
representative features to enable recognition and analysis in an efficient and comprehensive
manner has proved elusive thus far. This thesis proposes practical solutions that
are based on insights from clinicians, and learning attributes from motion capture data
itself. This culminates in an application framework that learns the type, content and
behaviour of human motion for recognition, quantitative clinical analysis and outcome
measures.
While marker-based motion capture has many uses, it also has major limitations that
are explored in this thesis, not least in terms of hardware costs and practical utilisation.
These drawbacks have led to the creation of depth sensors capable of providing robust,
accurate and low-cost solution to detecting and tracking anatomical landmarks on the
human body, without physical markers. This advancement has led researchers to develop
low-cost solutions to important healthcare tasks, such as human motion analysis as a
clinical aid in prevention care. In this thesis a variety of obstacles in handling markerless
motion capture are identified and overcome by employing parameterisation of Axis-
Angles, applying Euler Angles transformations to Exponential Maps, and appropriate
distance measures between postures.
While developing an efficient, usable and deployable application framework for clinicians,
this thesis introduces techniques to recognise, analyse and quantify human motion in the
context of identifying age-related change and mobility. The central theme of this thesis
is the creation of discriminative representations of the human body using novel encoding
and extraction approaches usable for both marker-based and marker-less motion capture
data. The encoding of the human pose is modelled based on the spatial-temporal
characteristics to generate a compact, efficient parameterisation. This combination allows
for the detection of multiple known and unknown motions in real-time. However,
in the context of benchmarking a major drawback exists, the lack of a clinically valid
and relevant dataset to enable benchmarking. Without a dataset of this type, it is difficult
to validated algorithms aimed at healthcare application. To this end, this thesis
introduces a dataset that will enable the computer science community to benchmark
healthcare-related algorithms
Digital Analysis of Sit-to-Stand in Masters Athletes, Healthy Old People, and Young Adults Using a Depth Sensor
No full textThe aim of this study was to compare the performance between young adults (n = 15), healthy old people (n = 10), and masters athletes (n = 15) using a depth sensor and automated digital assessment framework. Participants were asked to complete a clinically validated assessment of the sit-to-stand technique (five repetitions), which was recorded using a depth sensor. A feature encoding and evaluation framework to assess balance, core, and limb performance using time- and speed-related measurements was applied to markerless motion capture data. The associations between the measurements and participant groups were examined and used to evaluate the assessment framework suitability. The proposed framework could identify phases of sit-to-stand, stability, transition style, and performance between participant groups with a high degree of accuracy. In summary, we found that a depth sensor coupled with the proposed framework could identify performance subtleties between groups
Understanding NHS hospital admissions in England, Scotland and Wales: data linkage to the King’s College Military Cohort Study
No full textABSTRACT
Objective
Secondary health systems in the United Kingdom (UK) are unique for recording Outpatient, Inpatient and Accident & Emergency (A&E) visits in the form of electronic health (eHealth) records. Linking regional healthcare datasets is a problematic, further challenging when linking externally, such as to the King’s College Military Cohort Study (KCMCS). We introduce our methodology used for eRecord linkage.
Approach
eHealth records from England, Scotland and Wales offer a variety of parameters such as admission/discharge date, diagnosis, treatment/procedure undertaken and the cost of treatment. To acquire eHealth records, unique patient identifiers: NHS number, forename, surname, sex and date of birth extracted from KCMCS were provided to each region. The KCMCS contains self-reported questionnaire results for 9,990 serving/ex-serving military personal, 8,602 participants consented to linkage. eHealth records prepared for linkage in two stages. First, admission and discharge date were checked to ensure a valid date. Second, episodes were checked for consistency, ensuring that no records for individual participants were duplicated. Data available varied based on the region, this disparity between regions can result in data type variation. Hence, linkage was performed on mutual variables to ensure a uniform admission history. Creation of the linked dataset was as follows. First, records and episodes relating to an individual were brought together, to create a personal admission history. Secondly, personal admission history were linked to the KCMCS.
Results
Linking to regional health datasets is not without its challenges. England, Scotland and Wales obtain, store and process eHealth records using different methodologies. A total of 6,336 (76.66%) participants were matched by regional health providers, with a total of 61,558 eHealth records. A total of 187 eHealth records were identified and discounted from linkage due to failure to meet criteria listed above. Verifying diagnoses completeness, Inpatient admissions were consistently code, with full completeness. Conversely, Outpatient admissions were poorly coded with 98% lacking any type of diagnosis. In addition, A&E records were sparsely coded; we identified four different regional and local coding systems to identify reason for admission. The eHealth records show promise for identifying health traits of the military. However, further work is required to identify synergy and overcome regional variations.
Conclusion
Linkage techniques provide new opportunities for exploring the health of serving and veteran population. However, quality of identifier and linkage error are still of major concern. Further, record completeness, diagnoses accuracy and data cleaning impact the data quality
Developing a Tool for Identifying Clinical Risk From Free-Text Clinical Records:Natural Language Processing Study
No full textBackground:Electronic patient records are a valuable yet underused data source; they have been explored in research using natural language processing, but not yet within a third-sector organization.Objective:This study aimed to apply natural language processing to develop a risk identification tool capable of discerning high and low suicide risk among veterans, using electronic patient records from a United Kingdom–based veteran mental health charity.Methods:A total of 20,342 notes were extracted for this purpose. To develop the risk tool, 70% of the records formed the training dataset, while the remaining 30% were allocated for testing and evaluation. The classification framework was devised and trained to categorize risk as a binary outcome: 1 indicating high risk and 0 indicating low risk.Results:The efficacy of each classifier model was assessed by comparing its results with those from clinical risk assessments. A logistic regression classifier was found to perform best and was used to develop the final model. This comparison allowed for the calculation of the positive predictive value (mean 0.74, SD 0.059; 95% CI 0.70-0.77), negative predictive value (mean 0.73, SD 0.024; 95% CI 0.72-0.75), sensitivity (mean 0.75, SD 0.017; 95% CI 0.74-0.76), F1-score (mean 0.74, SD 0.033; 95% CI 0.72-0.76), and accuracy, which was measured using the Youden index (mean 0.73, SD 0.035; 95% CI 0.71-0.76).Conclusions:The risk identification tool successfully determined the correct risk category of veterans from a large sample of clinical notes. Future studies should investigate whether this tool can detect more nuanced differences in risk and be generalizable across data sources
Automated Analysis and Quantification of Human Mobility using a Depth Sensor
No full textAnalysis and quantification of human motion to support clinicians in the decision-making process is the desired outcome for many clinical-based approaches. However, generating statistical models that are free from human interpretation and yet representative is a difficult task. In this work, we propose a framework that automatically recognises and evaluates human mobility impairments using the Microsoft Kinect One depth sensor. The framework is composed of two parts. Firstly, it recognises motions, such as sit-to-stand or walking 4 metres, using abstract feature representation techniques and machine learning. Secondly, evaluation of the motion sequence in the temporal domain by comparing the test participant with a statistical mobility model, generated from tracking movements of healthy people. To complement the framework, we propose an automatic method to enable a fairer, unbiased approach to label motion capture data. Finally, we demonstrate the ability of the framework to recognise and provide clinically relevant feedback to highlight mobility concerns, hence providing a route towards stratified rehabilitation pathways and clinician led interventions
Identifying probable post-traumatic stress disorder: applying supervised machine learning to data from a UK military cohort
No full textBackground: Early identification of probable post-traumatic stress disorder (PTSD) can lead to early intervention and treatment. Aims: This study aimed to evaluate supervised machine learning (ML) classifiers for the identification of probable PTSD in those who are serving, or have recently served in the United Kingdom (UK) Armed Forces. Methods: Supervised ML classification techniques were applied to a military cohort of 13,690 serving and ex-serving UK Armed Forces personnel to identify probable PTSD based on self-reported service exposures and a range of validated self-report measures. Data were collected between 2004 and 2009. Results: The predictive performance of supervised ML classifiers to detect cases of probable PTSD were encouraging when compared to a validated measure, demonstrating a capability of supervised ML to detect the cases of probable PTSD. It was possible to identify which variables contributed to the performance, including alcohol misuse, gender and deployment status. A satisfactory sensitivity was obtained across a range of supervised ML classifiers, but sensitivity was low, indicating a potential for false negative diagnoses. Conclusions: Detection of probable PTSD based on self-reported measurement data is feasible, may greatly reduce the burden on public health and improve operational efficiencies by enabling early intervention, before manifestation of symptoms
- …
