Explore the vast range of titles available.

The Leap Motion controller (LMC) offers a low-cost means of markerless hand tracking, however, its utility is limited by a small field of view and reliance on appropriate sensor positioning. A recent update from Leap Motion has enabled the use of a multiple LMC device on a single computer, allowing the tracking of hands from multiple orientations, potentially overcoming the aforementioned limitations. This study describes a method of implementing a multi-LMC setup and evaluates its effect on the validity and reliability of the derived kinematics. This study implemented a Kabsch algorithm and Kalman filter to re-orientate and fuse the trajectories captured by three LMC at different orientations. Reliability was assessed by comparing between-day differences in maximum joint angles (ΔMJA) and a calculated coefficient of multiple correlations (CMC). Validity was assessed by comparing the LMC to the gold standard, a Vicon markered motion capture (MMC) system, and calculating the ΔMJA and applying the linear fit method. The proposed method was evaluated by comparing the reliability and validity of the single-LMC setups to the multi-LMC setup. A multi-LMC setup proved successful in improving the reliability and validity of kinematic data, most notably where reliability and validity were poor and variation was high between the single-LMC setups. Findings suggest that through implementing the proposed method, limitations associated with single-LMC setups, notably its reliance on optimal sensor positioning, can be overcome.

Chronic exertional compartment syndrome (CECS) is a condition occurring most frequently in the lower limbs and often requires corrective surgery to alleviate symptoms. Amongst military personnel, the success rates of this surgery can be as low as 20%, presenting a challenge in determining whether surgery is worthwhile. In this study, the data of 132 fasciotomies for CECS was analysed and using combinatorial feature selection methods, coupled with input from clinicians, identified a set of key clinical features contributing to the occupational outcomes of surgery. Features were utilised to develop a machine learning model for predicting return-to-work outcomes 12-months post-surgery. An AUC of 0.85 ± 0.08 was achieved using a linear-SVM, trained using 6 features (height, mean arterial pressure, pre-surgical score on the exercise-induced leg pain questionnaire, time from initial presentation to surgery, and whether a patient had received a prior surgery for CECS). To facilitate trust and transparency, interrogation strategies were used to identify reasons why certain patients were misclassified, using instance hardness measures. Model interrogation revealed that patient difficulty was associated with an overlap in the clinical characteristics of surgical outcomes, which was best handled by XGBoost and SVM-based models. The methodology was compiled into a machine learning framework, termed AITIA, which can be applied to other clinical problems. AITIA extends the typical machine learning pipeline, integrating the proposed interrogation strategy, allowing to user to reason and decide whether to trust the developed model based on the sensibility of its decision-making.

Primary therapy for high-risk bladder cancer (BCa) is repeated instillations of the tuberculosis vaccine Bacillus Calmette-Guerin (BCG). Although BCG reduces the risk of recurrence by more than half, the mechanisms underlying its immune-activating effects remain unknown. Our objective was to investigate how the immune response differs between BCG responders and non-responders and to compare systemic and local immune responses. We performed single-cell RNA sequencing (scRNA-seq) of isolated immune cells adjacent to high-risk bladders in BCG responders and non-responders before and after BCG. We also compared concurrent scRNA-seq profiles of circulating immune cell populations with those of bladder immune cells. We identify an increase in Th17-like Th1 cells in BCG responders, characterized by greater expression of pro-inflammatory cytokines. Alternatively, non-responders show increased CD8+ T-cell exhaustion and T regulatory cells. We identify that the primary mechanism driving divergent T-cell activity is altered polarization and immunosuppressive signaling with myeloid cells. Using a machine-learning-based approach, we identify that Th17-like Th1 cytokines, such as IL-17, IL-21, and IL-26, are predictive of response, which is subsequently validated in a separate BCG-treated BCa cohort. Together, these findings suggest that dynamic regulation of myeloid-T cell interactions can be critical for outcomes of BCG treated bladder cancer.

Background The digitisation of healthcare records has generated vast amounts of unstructured data, presenting opportunities for improvements in disease diagnosis when clinical coding falls short, such as in the recording of patient symptoms. This study presents an approach using natural language processing to extract clinical concepts from free-text which are used to automatically form diagnostic criteria for lung cancer from unstructured secondary-care data. Methods Patients aged 40 and above who underwent a chest x-ray (CXR) between 2016 and 2022 were included. ICD-10 and unstructured data were pulled from their electronic health records (EHRs) over the preceding 12 months to the CXR. The unstructured data were processed using named entity recognition to extract symptoms, which were mapped to SNOMED-CT codes. Subsumption of features up the SNOMED-CT hierarchy was used to mitigate against sparse features and a frequency-based criteria, combined with univariate logarithmic probabilities, was applied to select candidate features to take forward to the model development phase. A genetic algorithm was employed to identify the most discriminating features to form the diagnostic criteria. Results 75002 patients were included, with 1012 lung cancer diagnoses made within 12 months of the CXR. The best-performing model achieved an AUROC of 0.72. Results showed that an existing ‘disorder of the lung’, such as pneumonia, and a ‘cough’ increased the probability of a lung cancer diagnosis. ‘Anomalies of great vessel’, ‘disorder of the retroperitoneal compartment’ and ‘context-dependent findings’, such as pain, statistically reduced the risk of lung cancer, making other diagnoses more likely. The performance of the developed model was compared to the existing cancer risk scores, demonstrating superior performance. Conclusions The proposed methods demonstrated success in leveraging unstructured secondary-care data to derive diagnostic criteria for lung cancer, outperforming existing risk tools. These advancements show potential for enhancing patient care and results. However, it is essential to tackle specific limitations by integrating primary care data to ensure a more thorough and unbiased development of diagnostic criteria. Moreover, the study highlights the importance of contextualising SNOMED-CT concepts into meaningful terminology that resonates with clinicians, facilitating a clearer and more tangible understanding of the criteria applied.

Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making allowing users to know when to ignore the model’s recommendations. However, existing approaches for quantifying decision-making uncertainty are not model-agnostic, or they rely on complex mathematical derivations that are not easily understood by laypersons or end-users, making them less useful for explaining the model’s decision-making process. This work proposes a set of class-independent meta-heuristics that can characterise the complexity of an instance in terms of factors that are mutually relevant to both human and ML decision-making. The measures are integrated into a meta-learning framework that estimates the risk of misclassification. The proposed framework outperformed predicted probabilities and entropy-based methods of identifying instances at risk of being misclassified. Furthermore, the proposed approach resulted in uncertainty estimates that proves more independent of model accuracy and calibration than existing approaches. The proposed measures and framework demonstrate promise for improving model development for more complex instances and provides a new means of model abstention and explanation.

Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making allowing users to know when to ignore the model’s recommendations. However, existing approaches for quantifying decision-making uncertainty are not model-agnostic, or they rely on complex mathematical derivations that are not easily understood by laypersons or end-users, making them less useful for explaining the model’s decision-making process. This work proposes a set of class-independent meta-heuristics that can characterise the complexity of an instance in terms of factors that are mutually relevant to both human and ML decision-making. The measures are integrated into a meta-learning framework that estimates the risk of misclassification. The proposed framework outperformed predicted probabilities and entropy-based methods of identifying instances at risk of being misclassified. Furthermore, the proposed approach resulted in uncertainty estimates that proves more independent of model accuracy and calibration than existing approaches. The proposed measures and framework demonstrate promise for improving model development for more complex instances and provides a new means of model abstention and explanation.

Background The COVID-19 pandemic has led to significant morbidity and mortality, with the former impacting and limiting individuals requiring high physical fitness, including sportspeople and emergency services. Methods Observational cohort study of 4 groups: hospitalised, community illness with on-going symptoms (community-symptomatic), community illness now recovered (community-recovered) and comparison. A total of 113 participants (aged 39 ± 9, 86% male) were recruited: hospitalised ( n  = 35), community-symptomatic ( n  = 34), community-recovered ( n  = 18) and comparison ( n  = 26), approximately five months following acute illness. Participant outcome measures included cardiopulmonary imaging, submaximal and maximal exercise testing, pulmonary function, cognitive assessment, blood tests and questionnaires on mental health and function. Results Hospitalised and community-symptomatic groups were older (43 ± 9 and 37 ± 10, P  = 0.003), with a higher body mass index (31 ± 4 and 29 ± 4, P  < 0.001), and had worse mental health (anxiety, depression and post-traumatic stress), fatigue and quality of life scores. Hospitalised and community-symptomatic participants performed less well on sub-maximal and maximal exercise testing. Hospitalised individuals had impaired ventilatory efficiency (higher VE/V̇CO 2 slope, 29.6 ± 5.1, P  < 0.001), achieved less work at anaerobic threshold (70 ± 15, P  < 0.001) and peak (231 ± 35, P  < 0.001), and had a reduced forced vital capacity (4.7 ± 0.9, P  = 0.004). Clinically significant abnormal cardiopulmonary imaging findings were present in 6% of hospitalised participants. Community-recovered individuals had no significant differences in outcomes to the comparison group. Conclusion Symptomatically recovered individuals who suffered mild-moderate acute COVID-19 do not differ from an age-, sex- and job-role-matched comparison population five months post-illness. Individuals who were hospitalised or continue to suffer symptoms may require a specific comprehensive assessment prior to return to full physical activity.

Factors driving freshwater salinization syndrome (FSS) influence the severity of impacts and chances for recovery. We hypothesize that spread of FSS across ecosystems is a function of interactions among five state factors: human activities, geology, flowpaths, climate, and time. (1) Human activities drive pulsed or chronic inputs of salt ions and mobilization of chemical contaminants. (2) Geology drives rates of erosion, weathering, ion exchange, and acidification‐alkalinization. (3) Flowpaths drive salinization and contaminant mobilization along hydrologic cycles. (4) Climate drives rising water temperatures, salt stress, and evaporative concentration of ions and saltwater intrusion. (5) Time influences consequences, thresholds, and potentials for ecosystem recovery. We hypothesize that state factors advance FSS in distinct stages, which eventually contribute to failures in systems‐level functions (supporting drinking water, crops, biodiversity, infrastructure, etc.). We present future research directions for protecting freshwaters at risk based on five state factors and stages from diagnosis to prognosis to cure.

Increased expression of the cyclin‐dependent kinase inhibitor p16Ink4a (p16) is detected in neurons of human Alzheimer's disease (AD) brains and during normal aging. Importantly, selective eliminating p16‐expressing cells in AD mouse models attenuates tau pathologies and improves cognition. But whether and how p16 contributes to AD pathogenesis remains unclear. To address this question, we tested whether induction of p16 expression in neurons exacerbates AD pathologies. We created a doxycycline‐inducible system to trigger p16 up‐regulation in human‐induced pluripotent stem cells (iPSCs) and neurons differentiated from iPSCs. We demonstrated that up‐regulated p16 expression in iPSCs reduces cell proliferation, down‐regulates cell cycle genes, and up‐regulates genes involved in focal adhesion, interferon α response and PI3K‐Akt signaling. Our approach enables temporal control of p16 induction upon differentiation from iPSCs to neurons. In differentiated cortical neurons, we found that up‐regulation of p16 increases tau phosphorylation at Ser202/Thr205 and Thr231 in a cell‐autonomous manner, while amyloid beta secretion is not affected. These data suggest a critical role of p16 in regulating tau phosphorylation in neurons, and thereby contributing to pathological progression of AD. As pathological tau tangles have been shown to induce p16 expression, our studies suggest a positive feedback loop between p16 and tau to exacerbate tau pathologies. We created an inducible system to control the expression of p16, and found that tau phosphorylation was enhanced upon p16 up‐regulation in neurons differentiated from human iPSCs. As p16 expression is increased during aging, our findings suggest a possible role of age‐associated p16 up‐regulation in Alzheimer's disease. As pathological tau tangles have been shown to induce p16 expression, our studies further suggest a positive feedback loop between p16 and tau to exacerbate tau pathology.