Search

Mild Cognitive Impairment (MCI) is a condition characterized by a decline in cognitive abilities, specifically in memory, language, and attention, that is beyond what is expected due to normal aging. Detection of MCI is crucial for providing appropriate interventions and slowing down the progression of dementia. There are several automated predictive algorithms for prediction using time-to-event data, but it is not clear which is best to predict the time to conversion to MCI. There is also confusion if algorithms with fewer training weights are less accurate. We compared three algorithms, from smaller to large numbers of training weights: a statistical predictive model (Cox proportional hazards model, CoxPH), a machine learning model (Random Survival Forest, RSF), and a deep learning model (DeepSurv). To compare the algorithms under different scenarios, we created a simulated dataset based on the Alzheimer NACC dataset. We found that the CoxPH model was among the best-performing models, in all simulated scenarios. In a larger sample size (n = 6,000), the deep learning algorithm (DeepSurv) exhibited comparable accuracy (73.1%) to the CoxPH model (73%). In the past, ignoring heterogeneity in the CoxPH model led to the conclusion that deep learning methods are superior. We found that when using the CoxPH model with heterogeneity, its accuracy is comparable to that of DeepSurv and RSF. Furthermore, when unobserved heterogeneity is present, such as missing features in the training, all three models showed a similar drop in accuracy. This simulation study suggests that in some applications an algorithm with a smaller number of training weights is not disadvantaged in terms of accuracy. Since algorithms with fewer weights are inherently easier to explain, this study can help artificial intelligence research develop a principled approach to comparing statistical, machine learning, and deep learning algorithms for time-to-event predictions. [ABSTRACT FROM AUTHOR]

The most recent Ebola virus disease (EVD) outbreak in West Africa is the largest outbreak in history. As of March 27, 2016, an estimated 3,956 persons in Sierra Leone had [...]

To determine any factors that predict how an individual will adapt to post-stroke hemianopic visual field loss, with close monitoring of the adaptation process from an early stage. The Hemianopia Adaptation Study (HAST) is a prospective observational longitudinal cohort clinical study. Adult stroke survivors (n = 144) with new onset homonymous hemianopia were monitored using standardised mobility assessment course (MAC) as the primary outcome measure of adaptation. Several baseline variables were found to be good predictors of adaptation. Three variables were associated with adaptation status at 12-weeks post-stroke: inferior % visual field, % total MAC omissions, and MAC completion time (seconds). Baseline measurements of these variables can predict the adaptation at 12 weeks with moderate to high accuracy (area under ROC curve, 0.82, 95% CI 0.74–0.90). A cut-off score of ≤25% target omissions is suggested to predict which individuals are likely to adapt by 12-weeks post-stroke following gold standard care. Adaptation to hemianopia is a personal journey with several factors being important for prediction of its presence, including MAC outcomes and extent of inferior visual field loss. A clinical recommendation is made for inclusion of the MAC as part of a functional assessment for hemianopia. The mobility assessment course (MAC) should be considered as an assessment of mobility/scanning in the rehabilitation of patients with homonymous hemianopia. A cut-off score of ≤25% omissions on MAC could be employed to determine those likely to adapt to hemianopia long-term. Targeted support and therapy for patients with significant visual loss in the inferior visual field area should be considered. [ABSTRACT FROM AUTHOR]

Aims: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and a key risk factor for ischaemic stroke. Following AF detection, treatment with oral anticoagulation can significantly lower mortality and morbidity rates associated with this risk. The availability of several hand-held devices which can detect AF may enable trained health professionals to adopt AF screening approaches which do not interfere with people's daily routines. This study aims to investigate the effectiveness of a hand-held device (the MyDiagnostick single-lead Electrocardiogram (ECG) sensor) in screening for AF when embedded into the handles of supermarket trolleys. Methods: A mixed methods two-phase approach will be taken. The quantitative first phase will involve the recruitment of 2000 participants from a convenience sample at four large supermarkets with pharmacies. Prospective participants will be asked to conduct their shopping using a trolley embedded with a MyDiagnostick sensor. If the device identifies a participant with AF, the in-store pharmacist will be dispatched to take a manual pulse measurement and a static control sensor reading and offer a cardiologist consultation referral. When the sensor does not detect AF, a researcher will confirm the reading with a manual pulse measurement. ECGs will be compiled, and the sensitivity, specificity and positive and negative predictive values will be determined. A qualitative second phase will consist of semi-structured interviews carried out with those pharmacists and store managers in-store during the running of the trial period. These will explore the perceptions of staff regarding the merits of embedding sensors in the handles of supermarket trolleys to detect AF. Conclusion: This feasibility study will inform a larger future definitive trial. [ABSTRACT FROM AUTHOR]

Background: In cerebral malaria, the retina can be used to understand disease pathogenesis. The mechanisms linking sequestration, brain swelling, and death remain poorly understood. We hypothesized that retinal vascular leakage would be associated with brain swelling.Methods: We used retinal angiography to study blood-retinal barrier integrity. We analyzed retinal leakage, histopathology, brain magnatic resonance imaging (MRI), and associations with death and neurological disability in prospective cohorts of Malawian children with cerebral malaria.Results: Three types of retinal leakage were seen: large focal leak (LFL), punctate leak (PL), and vessel leak. The LFL and PL were associated with death (odds ratio [OR] = 13.20, 95% confidence interval [CI] = 5.21-33.78 and OR = 8.58, 95% CI = 2.56-29.08, respectively) and brain swelling (P < .05). Vessel leak and macular nonperfusion were associated with neurological disability (OR = 3.71, 95% CI = 1.26-11.02 and OR = 9.06, 95% CI = 1.79-45.90). Large focal leak was observed as an evolving retinal hemorrhage. A core of fibrinogen and monocytes was found in 39 (93%) white-centered hemorrhages.Conclusions: Blood-retina barrier breakdown occurs in 3 patterns in cerebral malaria. Associations between LFL, brain swelling, and death suggest that the rapid accumulation of cerebral hemorrhages, with accompanying fluid egress, may cause fatal brain swelling. Vessel leak, from barrier dysfunction, and nonperfusion were not associated with severe brain swelling but with neurological deficits, suggesting hypoxic injury in survivors. [ABSTRACT FROM AUTHOR]

Background: Renal ischemia reperfusion injury (R‐IRI) can cause acute kidney injury (AKI) and chronic kidney disease (CKD), resulting in significant morbidity and mortality. To understand the underlying mechanisms, reproducible small‐animal models of AKI and CKD are needed. We describe how innovative technologies for measuring kidney function noninvasively in small rodents allow successful refinement of the R‐IRI models, and offer the unique opportunity to monitor longitudinally in individual animals the transition from AKI to CKD. Methods: Male BALB/c mice underwent bilateral renal pedicle clamping (AKI) or unilateral renal pedicle clamping with delayed contralateral nephrectomy (CKD) under isoflurane anesthetic. Transdermal GFR monitoring and multispectral optoacoustic tomography (MSOT) in combination with statistical analysis were used to identify and standardize variables within these models. Results: Pre‐clamping anesthetic time was one of the most important predictors of AKI severity after R‐IRI. Standardizing pre‐clamping time resulted in a more predictably severe AKI model. In the CKD model, MSOT demonstrated initial improvement in renal function, followed by significant progressive reduction in function between weeks 2 and 4. Performing contralateral nephrectomy on day 14 enabled the development of CKD with minimal mortality. Conclusions: Noninvasive monitoring of global and individual renal function after R‐IRI is feasible and reproducible. These techniques can facilitate refinement of kidney injury models and enable the degree of injury seen in preclinical models to be translated to those seen in the clinical setting. Thus, future therapies can be tested in a clinically relevant, noninvasive manner. [ABSTRACT FROM AUTHOR]

Current research in automated disease detection focuses on making algorithms "slimmer" reducing the need for large training datasets and accelerating recalibration for new data while achieving high accuracy. The development of slimmer models has become a hot research topic in medical imaging. In this work, we develop a two-phase model for glaucoma detection, identifying and exploiting a redundancy in fundus image data relating particularly to the geometry. We propose a novel algorithm for the cup and disc segmentation "EffUnet" with an efficient convolution block and combine this with an extended spatial generative approach for geometry modelling and classification, termed "SpaGen"We demonstrate the high accuracy achievable by EffUnet in detecting the optic disc and cup boundaries and show how our algorithm can be quickly trained with new data by recalibrating the EffUnet layer only. Our resulting glaucoma detection algorithm, "EffUnet-SpaGen", is optimized to significantly reduce the computational burden while at the same time surpassing the current state-of-art in glaucoma detection algorithms with AUROC 0.997 and 0.969 in the benchmark online datasets ORIGA and DRISHTI, respectively. Our algorithm also allows deformed areas of the optic rim to be displayed and investigated, providing explainability, which is crucial to successful adoption and implementation in clinical settings. [ABSTRACT FROM AUTHOR]

Purpose: The presence of central visual field loss does not infer the extent of peripheral visual field loss. In advanced stage glaucoma, we evaluated whether automated kinetic perimetry provided additional visual field information to that of central static perimetry. Materials and Methods: We undertook a prospective cross-sectional study of advanced-stage glaucoma defined as stages 3–4. Visual field assessment for right and left eyes was undertaken within one clinic visit using the Octopus 900 G programme and kinetic strategy. Results: We recruited 126 patients (170 eyes). Mean patient age at assessment was 55.86 years (SD 15.15). Mean kinetic reaction time was 1503.96 ms (SD 801.68). Kinetic I4e was plotted in 71% of eyes with an unadjusted area of 2513.68 degrees2 (SD 2397.91) and mean isopter radius of 23.16 degrees (SD 13.07). Kinetic I2e was plotted in 53.5% of eyes with an unadjusted area of 627.07 degrees2 (SD 1291.94) and mean isopter radius of 7.47 degrees (SD 10.59). Increased reaction time was associated with a poorer visual field (p =.001). Mean sensitivity, mean deviation and standard loss variance values on static perimetry were higher in patients who had a defined kinetic field boundary than in patients with no kinetic response to I4e stimulus (p =.0001). However, this corresponded to only small-to-medium correlation between static fields and existent kinetic fields: the presence of poor static fields did not always infer a poor kinetic visual field as poor static fields could also have good kinetic visual fields. Conclusions: Although we confirmed a lack of agreement and only a small to medium correlation between the extents of central versus peripheral visual field loss, automated kinetic perimetry did provide additional peripheral (outside the static 30-degree central field) visual field information which was clinically useful in the presence of non-informative severely defected central visual fields. [ABSTRACT FROM AUTHOR]

The utility of diffusion kurtosis imaging (DKI) for assessing intra‐tumor heterogeneity was evaluated in a rat model of glioblastoma multiforme. Longitudinal MRI including T2‐weighted and diffusion‐weighted MRI (DWI) was performed on six female Fischer rats 8, 11 and 14 days after intracranial transplantation of F98 cells. T2‐weighted images were used to measure the tumor volumes and DWI images were used to compute diffusion tensor imaging (DTI) and DWI based parametric maps including mean diffusivity (MD), mean kurtosis (MK), axial diffusivity (AD), axial kurtosis, radial diffusivity, radial kurtosis, fractional anisotropy (FA) and kurtosis fractional anisotropy (KFA). Median values from the segmented normal contralateral cortex, tumor and edema from the diffusion parameters were compared at the three imaging time points to assess any changes in tumor heterogeneity over time. ex vivo DKI was also performed in a representative sample and compared with histology. Significant differences were observed between normal cortex, tumor and edema in both the DTI and DKI parameters. Notably, at the earliest time point MK and KFA were significantly different between normal cortex and tumor in comparison with MD or FA. Although a decreasing trend in MD, AD and FA values of the tumor were observed as the tumor grew, no significant changes in any of the DTI or DKI parameters were observed longitudinally. While DKI was equally sensitive to DTI in differentiating tumor from edema and normal brain, it was unable to detect longitudinal increases in intra‐tumoral heterogeneity in the F98 model of glioblastoma multiforme. [ABSTRACT FROM AUTHOR]

Much recent research focuses on how to make disease detection more accurate as well as "slimmer", i.e., allowing analysis with smaller datasets. Explanatory models are a hot research topic because they explain how the data are generated. We propose a spatial explanatory modelling approach that combines Optical Coherence Tomography (OCT) retinal imaging data with clinical information. Our model consists of a spatial linear mixed effects inference framework, which innovatively models the spatial topography of key information via mixed effects and spatial error structures, thus effectively modelling the shape of the thickness map. We show that our spatial linear mixed effects (SLME) model outperforms traditional analysis-of-variance approaches in the analysis of Heidelberg OCT retinal thickness data from a prospective observational study, involving 300 participants with diabetes and 50 age-matched controls. Our SLME model has a higher power for detecting the difference between disease groups, and it shows where the shape of retinal thickness profiles differs between the eyes of participants with diabetes and the eyes of healthy controls. In simulated data, the SLME model demonstrates how incorporating spatial correlations can increase the accuracy of the statistical inferences. This model is crucial in the understanding of the progression of retinal thickness changes in diabetic maculopathy to aid clinicians for early planning of effective treatment. It can be extended to disease monitoring and prognosis in other diseases and with other imaging technologies. [ABSTRACT FROM AUTHOR]

Aims To compare the biomechanically corrected intraocular pressure (IOP) estimate (bIOP) provided by the Corvis- ST with Goldmann applanation tonometry (GAT-IOP) in patients with high-tension and normaltension primary open-angle glaucoma (POAG; HTG and NTG), ocular hypertension (OHT) and controls. Moreover, we compared dynamic corneal response parameters (DCRs) of the Corvis- ST in POAG, OHT and controls, evaluated the correlation between global visual field parameters mean deviation and pattern SD (MD and PSD) and DCRs in the POAG group. Methods 156 eyes of 156 patients were included in this prospective, single- centre, observational study, namely 41 HTG and 33 NTG, 45 OHT cases and 37 controls. Central corneal thickness (CCT), GAT-IOP and bIOP were measured, GAT-IOP was also adjusted for CCT (GATAdj). DCRs provided by Corvis- ST were evaluated, MD and PSD were recorded by 24-2 full-threshold visual field. To evaluate the difference in DCRs between OHT, HTG and NTG, a general linear model was used with sex, medications and group as fixed factors and bIOP and age as covariates. Results There was a significant difference between GAT- IOP, GATAdj and bIOP in NTG and HTG, OHT and controls. NTG corneas were significantly softer and more deformable compared with controls, OHT and HTG as demonstrated by significantly lower values of stiffness parameters A1 and highest concavity and higher values of inverse concave radius (all p<0.05). There was a significant correlation (p<0.05) between MD, PSD and many DCRs with POAG patients with softer or more compliant corneas more likely to show visual field defects. Conclusions Corneal biomechanics might be a significant confounding factor for IOP measurement that should be considered in clinical decision-making. The abnormality of corneal biomechanics in NTG and the significant correlation with visual field parameters might suggest a new risk factor for the development or progression of NTG. [ABSTRACT FROM AUTHOR]

Many moisturisers contain sun protection factors (SPF) equivalent to those found in sunscreens. However, there is a lack of research into how SPF moisturiser application compares to sunscreens in terms of coverage achieved and protection afforded. Previously we demonstrated that users incompletely covered their eyelid regions during routine sunscreen application. Here, we aimed to determine if SPF moisturiser users also displayed these tendencies. A study population of 84 participants (22 males, 62 females, age 18–57) were exposed to UV radiation and photographed using a tripod mounted UV sensitive DSLR camera on two separate visits. At visit one, images were acquired before and after applying either SPF30 sunscreen or moisturiser, then at visit two the study was repeated with the other formulation. Images were processed for facial landmark identification followed by segmentation mapping of hue saturation values to identify areas of the face that were/were not covered. Analyses revealed that application of moisturiser was significantly worse than sunscreen in terms area of the whole face missed (11.1% missed with sunscreen compared to 16.6% for SPF moisturiser p<0.001 paired t-test). This difference was primarily due to decreased coverage of the eyelid regions (14.0% missed with sunscreen, 20.9% moisturiser, p<0.001). Analysis of a post-study questionnaire revealed participants to be unaware of their incomplete coverage. Secondary analyses revealed improved coverage in males (p = 0.05), and, with moisturiser only, in participants with darker skin tones (p = 0.02). Together these data indicate that, despite potential advantages in terms of increased frequency of application of moisturiser, the areas of the face that are at higher cancer risk are likely not being protected, and that participants are unaware that they are at risk. As such, alternative sun-protection strategies should be promoted. [ABSTRACT FROM AUTHOR]