CSynth: an interactive modelling and visualization tool for 3D chromatin structure.

MOTIVATION: The 3D structure of chromatin in the nucleus is important for gene expression and regulation. Chromosome conformation capture techniques, such as Hi-C, generate large amounts of data showing interaction points on the genome but these are hard to interpret using standard tools. RESULTS: We have developed CSynth, an interactive 3D genome browser and real-time chromatin restraint-based modeller to visualize models of any chromosome conformation capture (3C) data. Unlike other modelling systems, CSynth allows dynamic interaction with the modelling parameters to allow experimentation and effects on the model. It also allows comparison of models generated from data in different tissues/cell states and the results of third-party 3D modelling outputs. In addition, we include an option to view and manipulate these complicated structures using Virtual Reality (VR) so scientists can immerse themselves in the models for further understanding. This VR component has also proven to be a valuable teaching and a public engagement tool. AVAILABILITYAND IMPLEMENTATION: CSynth is web based and available to use at csynth.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Multi-dimensional relationships among dementia, depression and prescribed drugs in England and Wales hospitals.

BACKGROUND: Dementia is a group of symptoms that largely affects older people. The majority of patients face behavioural and psychological symptoms (BPSD) during the course of their illness. Alzheimer's disease (AD) and vascular dementia (VaD) are two of the most prevalent types of dementia. Available medications provide symptomatic benefits and provide relief from BPSD and associated health issues. However, it is unclear how specific dementia, antidepressant, antipsychotic, antianxiety, and mood stabiliser drugs, used in the treatment of depression and dementia subtypes are prescribed in hospital admission, during hospital stay, and at the time of discharge. To address this, we apply multi-dimensional data analytical approaches to understand drug prescribing practices within hospitals in England and Wales. METHODS: We made use of the UK National Audit of Dementia (NAD) dataset and pre-processed the dataset. We evaluated the pairwise Pearson correlation of the dataset and selected key data features which are highly correlated with dementia subtypes. After that, we selected drug prescribing behaviours (e.g. specific medications at the time of admission, during the hospital stay, and upon discharge), drugs and disorders. Then to shed light on the relations across multiple features or dimensions, we carried out multiple regression analyses, considering the number of dementia, antidepressant, antipsychotic, antianxiety, mood stabiliser, and antiepileptic/anticonvulsant drug prescriptions as dependent variables, and the prescription of other drugs, number of patients with dementia subtypes (AD/VaD), and depression as independent variables. RESULTS: In terms of antidepressant drugs prescribed in hospital admission, during stay and discharge, the number of sertraline and venlafaxine prescriptions were associated with the number of VaD patients whilst the number of mirtazapine prescriptions was associated with frontotemporal dementia patients. During admission, the number of lamotrigine prescriptions was associated with frontotemporal dementia patients, and with the number of valproate and dosulepin prescriptions. During discharge, the number of mirtazapine prescriptions was associated with the number of donepezil prescriptions in conjunction with frontotemporal dementia patients. Finally, the number of prescriptions of donepezil/memantine at admission, during hospital stay and at discharge exhibited positive association with AD patients. CONCLUSION: Our analyses reveal a complex, multifaceted set of interactions among prescribed drug types, dementia subtypes, and depression.

Pharmacological treatment of hypertension in people without prior cerebrovascular disease for the prevention of cognitive impairment and dementia.

BACKGROUND: This is an update of a Cochrane Review first published in 2006 (McGuinness 2006), and previously updated in 2009 (McGuinness 2009). Hypertension is a risk factor for dementia. Observational studies suggest antihypertensive treatment is associated with lower incidences of cognitive impairment and dementia. There is already clear evidence to support the treatment of hypertension after stroke. OBJECTIVES: To assess whether pharmacological treatment of hypertension can prevent cognitive impairment or dementia in people who have no history of cerebrovascular disease. SEARCH METHODS: We searched the Specialised Register of the Cochrane Dementia and Cognitive Improvement Group, CENTRAL, MEDLINE, Embase, three other databases, as well as many trials registries and grey literature sources, most recently on 7 July 2020. SELECTION CRITERIA: We included randomised controlled trials (RCTs) in which pharmacological interventions to treat hypertension were given for at least 12 months. We excluded trials of pharmacological interventions to lower blood pressure in non-hypertensive participants. We also excluded trials conducted solely in people with stroke. DATA COLLECTION AND ANALYSIS: Two authors independently assessed trial quality and extracted data. We contacted study authors for additional information. We collected information regarding incidence of dementia, cognitive decline, change in blood pressure, adverse effects and quality of life. We assessed the certainty of evidence using GRADE. MAIN RESULTS: We included 12 studies, totaling 30,412 participants, in this review. Eight studies compared active treatment with placebo. Of the four non-placebo-controlled studies, two compared intensive versus standard blood pressure reduction. The two final included studies compared different classes of antihypertensive drug. Study durations varied from one to five years. The combined result of four placebo-controlled trials that reported incident dementia indicated no evidence of a difference in the risk of dementia between the antihypertensive treatment group and the placebo group (236/7767 versus 259/7660, odds ratio (OR) 0.89, 95% confidence interval (CI) 0.72 to 1.09; very low certainty evidence, downgraded due to study limitations and indirectness). The combined results from five placebo-controlled trials that reported change in Mini-Mental State Examination (MMSE) may indicate a modest benefit from antihypertensive treatment (mean difference (MD) 0.20, 95% CI 0.10 to 0.29; very low certainty evidence, downgraded due to study limitations, indirectness and imprecision). The certainty of evidence for both cognitive outcomes was downgraded on the basis of study limitations and indirectness. Study durations were too short, overall, to expect a significant difference in dementia rates between groups. Dementia and cognitive decline were secondary outcomes for most studies. Additional sources of bias include: the use of antihypertensive medication by the placebo group in the placebo-controlled trials; failure to reach recruitment targets; and early termination of studies on safety grounds. Meta-analysis of the placebo-controlled trials reporting results found a mean change in systolic blood pressure of -9.25 mmHg (95% CI -9.73, -8.78) between treatment (n = 8973) and placebo (n = 8820) groups, and a mean change in diastolic blood pressure of -2.47 mmHg (95% CI -2.70, -2.24) between treatment (n = 7700) and placebo (n = 7509) groups (both low certainty evidence downgraded on the basis of study limitations and inconsistency). Three trials - SHEP 1991, LOMIR MCT IL 1996 and MRC 1996 - reported more withdrawals due to adverse events in active treatment groups than placebo groups. Participants on active treatment in Syst Eur 1998 were less likely to discontinue treatment due to side effects, and participants on active treatment in HYVET 2008 reported fewer 'serious adverse events' than in the placebo group. There was no evidence of a difference in withdrawals rates between groups in SCOPE 2003, and results were unclear for Perez Stable 2000 and Zhang 2018. Heterogeneity precluded meta-analysis. Five of the placebo-controlled trials provided quality of life (QOL) data. Heterogeneity again precluded meta-analysis. SHEP 1991, Syst Eur 1998 and HYVET 2008 reported no evidence of a difference in QOL measures between active treatment and placebo groups over time. The SCOPE 2003 sub-study (Degl'Innocenti 2004) showed a smaller drop in QOL measures in the active treatment compared to the placebo group. LOMIR MCT IL 1996 reported an improvement in a QOL measure at twelve months in one active treatment group and deterioration in another. AUTHORS' CONCLUSIONS: High certainty randomised controlled trial evidence regarding the effect of hypertension treatment on dementia and cognitive decline does not yet exist. The studies included in this review provide low certainty evidence (downgraded primarily due to study limitations and indirectness) that pharmacological treatment of hypertension, in people without prior cerebrovascular disease, leads to less cognitive decline compared to controls. This difference is below the level considered clinically significant. The studies included in this review also provide very low certainty evidence that pharmacological treatment of hypertension, in people without prior cerebrovascular disease, prevents dementia.

Service evaluation comparing Acute Care at Home for older people service and conventional service within an acute hospital care of elderly ward.

AIMS AND OBJECTIVES: This study evaluated the impact of a consultant-led Acute Care at Home service in comparison with conventional hospital admission to a care of elderly ward. BACKGROUND: Globally, there has been an increased demand for healthcare services caused by population growth and a rise in chronic conditions and an ageing population. Acute Care at Home services offer acute, hospital-level care in a person's own home. Five services have been commissioned across Northern Ireland since 2014 with limited research investigating their feasibility and effectiveness. DESIGN: Quantitative design, using service evaluation methodology. METHODS: A 1-year retrospective chart review was undertaken exploring admission demographics and post-discharge clinical outcomes of patients admitted to a Northern Ireland, Care of the Elderly ward (n = 191) and a consultant-led Acute Care at Home Service (n = 314) between April 2018-March 2019. Data were analysed using descriptive and inferential data analysis methods including frequencies, independent t tests and chi-square analysis. Outcome measurements included length of stay, 30-day, 3- and 6-month readmission and mortality rates, functional ability and residence on discharge. STROBE checklist was used in reporting this study. RESULTS: Acute Care at Home services are associated with higher readmission and mortality rates at 30 days, 3 and 6 months. Fewer patients die while under Acute Care at Home care. Patients admitted to the Acute Care at Home services experience a reduced length of stay and decreased escalation in domiciliary care packages and are less likely to require subacute rehabilitation on discharge. There is no difference in gender, age and early warnings score between the two cohorts. CONCLUSION: The Acute Care at Home service is a viable alternative to hospital for older patients. It prevents functional decline and the need for domiciliary care or nursing home placement. It is likely that the Acute Care at Home service has higher mortality and readmissions rates due to treating a higher proportion of dependent, frail older adults. RELEVANCE TO CLINICAL PRACTICE: Acute Care at Home services continue to evolve worldwide. This service evaluation has confirmed that Acute Care at Home services are safe and cost-effective alternatives to traditional older people hospital services. Such services offer patient choice, reduce length of stay and costs and prevent functional decline of older adults. This study accentuates the need to expand Acute Care at Home provision and capacity throughout Northern Ireland.

Shaping a data-driven era in dementia care pathway through computational neurology approaches.

BACKGROUND: Dementia is caused by a variety of neurodegenerative diseases and is associated with a decline in memory and other cognitive abilities, while inflicting an enormous socioeconomic burden. The complexity of dementia and its associated comorbidities presents immense challenges for dementia research and care, particularly in clinical decision-making. MAIN BODY: Despite the lack of disease-modifying therapies, there is an increasing and urgent need to make timely and accurate clinical decisions in dementia diagnosis and prognosis to allow appropriate care and treatment. However, the dementia care pathway is currently suboptimal. We propose that through computational approaches, understanding of dementia aetiology could be improved, and dementia assessments could be more standardised, objective and efficient. In particular, we suggest that these will involve appropriate data infrastructure, the use of data-driven computational neurology approaches and the development of practical clinical decision support systems. We also discuss the technical, structural, economic, political and policy-making challenges that accompany such implementations. CONCLUSION: The data-driven era for dementia research has arrived with the potential to transform the healthcare system, creating a more efficient, transparent and personalised service for dementia.

A practical computerized decision support system for predicting the severity of Alzheimer's disease of an individual.

Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression, and k-Nearest Neighbor for regression and Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbor for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predictive performance of models incorporating CFA was shown to consistently have higher accuracy than those based solely on biomarker modalities. We found that KRR and SVM were the best performing regression and classification methods respectively. The optimal SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the best performance of the KRR model was reported with combined CFA and MRI neuroimaging data, i.e., R 2 = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power of CFA and their widespread use in clinical practice, we then designed a data-driven and self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating the severity of AD of an individual on a continuous spectrum. The system implemented an automated computational approach for data pre-processing, modelling, and validation and used exclusively the scores of selected cognitive measures as data entries. Taken together, we have developed an objective and practical CDSS to aid AD diagnosis.

The evaluation of a healthcare passport to improve quality of care and communication for people living with dementia (EQuIP): a protocol paper for a qualitative, longitudinal study.

BACKGROUND: There is an urgent need for the development of simple communication tools that convey the strengths, assets, and healthcare needs of people living with dementia. A Healthcare Passport may improve communication with range of health and social support services, enhancing quality and continuity of care, and to permit a consideration of the challenges and how these might be managed effectively and compassionately. This study aims to evaluate the acceptability and use of this type of intervention for people living with dementia and their carers. METHODS/DESIGN: This is a qualitative longitudinal study informed by a critical realist review. The participants will be individuals identified as having mild-moderate dementia and informal carers. The in-depth interviews will occur at three points over the course of 18 months as they use the passport. This will be supplemented by analysis of the content of the passports and information from health and social care providers on the daily practicalities of using the passport in a range of healthcare settings. DISCUSSION: By using a critical realist review and a qualitative, longitudinal approach, the study allows for the assessment of a complex intervention in a manner which goes beyond evaluating the basic efficacy of the passport, but looking more deeply at how it worked, for whom, and in what context. It has the potential to develop new data on how interventions improve communication across a range of service providers, while encouraging health and social care professionals to respect and encourage the development of self-management and retention of personhood throughout the progression of life-limiting illnesses.

First on-sky SCAO validation of full LQG control with vibration mitigation on the CANARY pathfinder.

Adaptive optics provides real time correction of wavefront disturbances on ground based telescopes. Optimizing control and performance is a key issue for ever more demanding instruments on ever larger telescopes affected not only by atmospheric turbulence, but also by vibrations, windshake and tracking errors. Linear Quadratic Gaussian control achieves optimal correction when provided with a temporal model of the disturbance. We present in this paper the first on-sky results of a Kalman filter based LQG control with vibration mitigation on the CANARY instrument at the Nasmyth platform of the 4.2-m William Herschel Telescope. The results demonstrate a clear improvement of performance for full LQG compared with standard integrator control, and assess the additional improvement brought by vibration filtering with a tip-tilt model identified from on-sky data, thus validating the strategy retained on the instrument SPHERE at the VLT.

Impact of Different Diagnostic Measures on Drug Class Association with Dementia Progression Risk: A Longitudinal Prospective Cohort Study.

Background: The Clinical Dementia Rating Scale Sum of Boxes (CDRSOB) score is known to be highly indicative of cognitive-functional status and is regularly employed for clinical and research purposes. Objective: Our aim is to determine whether CDRSOB is consistent with clinical diagnosis in evaluating drug class associations with risk of progression to mild cognitive impairment (MCI) and dementia. Methods: We employed weighted Cox regression analysis on longitudinal NACC data, to identify drug classes associated with disease progression risk, using clinical diagnosis and CDRSOB as the outcome. Results: Aspirin (antiplatelet/NSAID), angiotensin II inhibitors (antihypertensive), and Parkinson's disease medications were significantly associated with reduced risk of progression to MCI/dementia and Alzheimer's disease medications were associated with increased MCI-to-Dementia progression risk with both clinical diagnosis and CDRSOB as the outcome. However, certain drug classes/subcategories, like anxiolytics, antiadrenergics, calcium (Ca2+) channel blockers, and diuretics (antihypertensives) were associated with reduced risk of disease progression, and SSRIs (antidepressant) were associated with increased progression risk only with CDRSOB. Additionally, metformin (antidiabetic medication) was associated with reduced MCI-to-Dementia progression risk only with clinical diagnosis as the outcome. Conclusions: Although the magnitude and direction of the effect were primarily similar for both diagnostic outcomes, we demonstrate that choice of diagnostic measure can influence the significance of risk/protection attributed to drug classes and consequently the conclusion of findings. A consensus must be reached within the research community with respect to the most accurate diagnostic outcome to identify risk and improve reproducibility.

Survival in dementia and predictors of mortality: a review.

OBJECTIVE: Dementia is an important cause of mortality and, with the ageing population and increasing prevalence of dementia, reliable data on prognosis and survival will be of interest to patients and caregivers as well as providers and commissioners of health and social care. A review of the literature was undertaken to determine the rates of survival in dementia and Alzheimer's disease (AD) and to identify factors that are or are not predictive of mortality in dementia and AD. METHODS: Relevant articles on mortality in dementia were identified following a search of several electronic databases from 1990 to September 2012. Inclusion criteria were reports on prospective community or clinic based cohorts published in English since 1990, to reflect more recent recognition of possible predictors. RESULTS: Median survival time from age of onset of dementia ranges from 3.3 to 11.7 years, with most studies in the 7 to 10-year period. Median survival time from age of disease diagnosis ranges from 3.2 to 6.6 years for dementia or AD cohorts as a whole. Age was consistently reported as a predictor of mortality, with male gender a less consistent predictor. Increased disease severity and functional impairment were often associated with mortality. CONCLUSIONS: Substantial heterogeneity in the design of included studies limits the ability to prognosticate for individual patients. However, it is clear that dementia and AD are associated with significant mortality. Reasons for the increased mortality are not established.

The development of effective biomarkers for Alzheimer's disease: a review.

OBJECTIVE: There is a widely recognised need to develop effective Alzheimer's disease (AD) biomarkers to aid the development of disease-modifying treatments, to facilitate early diagnosis and to improve clinical care. This overview aims to summarise the utility of key neuroimaging and cerebrospinal fluid (CSF) biomarkers for AD, before focusing on the latest efforts to identify informative blood biomarkers. DESIGN: A literature search was performed using PubMed up to September 2011 for reviews and primary research studies of neuroimaging (magnetic resonance imaging, magnetic resonance spectroscopy, positron emission tomography and amyloid imaging), CSF and blood-based (plasma, serum and platelet) biomarkers in AD and mild cognitive impairment. Citations within individual articles were examined to identify additional studies relevant to this review. RESULTS: Evidence of AD biomarker potential was available for imaging techniques reflecting amyloid burden and neurodegeneration. Several CSF measures are promising, including 42 amino acid ß-amyloid peptide (Aß42 ); total tau (T-tau) protein, reflecting axonal damage; and phosphorylated tau (P-tau), reflecting neurofibrillary tangle pathology. Studies of plasma Aß have produced inferior diagnostic discrimination. Alternative plasma and platelet measures are described, which represent potential avenues for future research. CONCLUSIONS: Several imaging and CSF markers demonstrate utility in predicting AD progression and determining aetiology. These require standardisation before forming core elements of diagnostic criteria. The enormous potential available for identifying a minimally-invasive, easily-accessible blood measure as an effective AD biomarker currently remains unfulfilled.

The role of cognitive biases and personality variables in subclinical delusional ideation.

INTRODUCTION: A number of cognitive biases, most notably a data gathering bias characterised by "jumping to conclusions" (JTC), and the "bias against disconfirmatory evidence" (BADE), have been shown to be associated with delusions and subclinical delusional ideation. Certain personality variables, particularly "openness to experience", are thought to be associated with schizotypy. METHODS: Using structural equation modelling, we examined the association between two higher order subfactors ("aspects") of "openness to experience" (labelled "openness" and "intellect"), these cognitive biases, and their relationship to subclinical delusional ideation in 121 healthy, nonpsychiatric controls. RESULTS: Our results suggest that cognitive biases (specifically the data gathering bias and BADE) and the "openness" aspect are independently associated with subclinical delusional ideation, and the data gathering bias is weakly associated with "positive schizotypy". "Intellect" is negatively associated with delusional ideation and might play a potential protective role. CONCLUSIONS: Cognitive biases and personality are likely to be independent risk factors for the development of delusions.

Encouraging lifestyle behaviour change in mild cognitive impairment patients: development of appropriate educational material.

OBJECTIVES: A healthy lifestyle may help maintain cognitive function and reduce the risk of developing dementia. This study employed a focus group approach in order to gain insight into opinions of mild cognitive impairment (MCI) patients, caregivers (CG) and health professionals (HP) regarding lifestyle and its relationship with cognition. The qualitative data were used to design, develop and pilot test educational material (EM) to help encourage lifestyle behaviour change. METHOD: Data gathering phase: structured interviews were conducted with HP (n = 10), and focus groups with MCI patients (n = 24) and CG (n = 12). EM was developed and pilot tested with a new group of MCI patients (n = 21) and CG (n = 6). RESULTS: HP alluded to the lack of clinical trial evidence for a lifestyle and MCI risk link. Although they felt that lifestyle modifications should be recommended to MCI patients, they appeared hesitant in communicating this information and discussions were often patient-driven. MCI patients lacked awareness of the lifestyle cognition link. Participants preferred EM to be concise, eye-catching and in written format, with personal delivery of information favoured. Most pilot testers approved of the EM but were heterogeneous in terms of lifestyle, willingness to change and support needed to change. CONCLUSION: MCI patients need to be made more aware of the importance of lifestyle for cognition. EM such as those developed here, which are specifically tailored for this population would be valuable for HP who, currently, appear reticent in initiating lifestyle-related discussions. Following further evaluation, the EM could be used in health promotion activities targeting MCI patients.

Comparison of TLD calibration methods for 192Ir dosimetry.

For the purpose of dose measurement using a high-dose rate (192)Ir source, four methods of thermoluminescent dosimeter (TLD) calibration were investigated. Three of the four calibration methods used the (192)Ir source. Dwell times were calculated to deliver 1 Gy to the TLDs irradiated either in air or water. Dwell time calculations were confirmed by direct measurement using an ionization chamber. The fourth method of calibration used 6 MV photons from a medical linear accelerator, and an energy correction factor was applied to account for the difference in sensitivity of the TLDs in (192)Ir and 6 MV. The results of the four TLD calibration methods are presented in terms of the results of a brachytherapy audit where seven Australian centers irradiated three sets of TLDs in a water phantom. The results were in agreement within estimated uncertainties when the TLDs were calibrated with the (192)Ir source. Calibrating TLDs in a phantom similar to that used for the audit proved to be the most practical method and provided the greatest confidence in measured dose. When calibrated using 6 MV photons, the TLD results were consistently higher than the (192)Ir-calibrated TLDs, suggesting this method does not fully correct for the response of the TLDs when irradiated in the audit phantom.

Cognitive factors associated with subclinical delusional ideation in the general population.

Cognitive biases have been found to be associated with delusions in schizophrenia and schizotypy. In the current study, we examined the relationship between subclinical delusional ideation, measured using the Peters Delusions Inventory, and cognitive biases including the bias against disconfirmatory evidence (BADE), 'jumping to conclusions', and need for closure, evaluated using the computerized BADE program, in a sample of 117 healthy, non-psychiatric controls. Our results suggest that subclinical delusional ideation is associated with BADE, greater need for closure, a 'jumping to conclusions' response style, and a tendency to rate absurd and unlikely interpretations of an event as more plausible, which might be indicative of insufficient evidence integration or 'liberal acceptance'. These cognitive biases, which occur in a much milder fashion than seen in typical deluded patient samples, may nonetheless additively play a role in the development of delusional ideation, and suggest common pathways seen in healthy and psychiatric samples.

The impact of hearing impairment and hearing aid use on progression to mild cognitive impairment in cognitively healthy adults: An observational cohort study.

INTRODUCTION: We assessed the association of self-reported hearing impairment and hearing aid use with cognitive decline and progression to mild cognitive impairment (MCI). METHODS: We used a large referral-based cohort of 4358 participants obtained from the National Alzheimer's Coordinating Center. The standard covariate-adjusted Cox proportional hazards model, the marginal structural Cox model with inverse probability weighting, standardized Kaplan-Meier curves, and linear mixed-effects models were applied to test the hypotheses. RESULTS: Hearing impairment was associated with increased risk of MCI (standardized hazard ratio [HR] 2.58, 95% confidence interval [CI: 1.73 to 3.84], P = .004) and an accelerated rate of cognitive decline (P < .001). Hearing aid users were less likely to develop MCI than hearing-impaired individuals who did not use a hearing aid (HR 0.47, 95% CI [0.29 to 0.74], P = .001). No difference in risk of MCI was observed between individuals with normal hearing and hearing-impaired adults using hearing aids (HR 0.86, 95% CI [0.56 to 1.34], P = .51). DISCUSSION: Use of hearing aids may help mitigate cognitive decline associated with hearing loss.

Alzheimer's Disease Assessments Optimized for Diagnostic Accuracy and Administration Time.

OBJECTIVE: Despite the potential of machine learning techniques to improve dementia diagnostic processes, research outcomes are often not readily translated to or adopted in clinical practice. Importantly, the time taken to administer diagnostic assessment has yet to be taken into account in feature-selection based optimisation for dementia diagnosis. We address these issues by considering the impact of assessment time as a practical constraint for feature selection of cognitive and functional assessments in Alzheimer's disease diagnosis. METHODS: We use three different feature selection algorithms to select informative subsets of dementia assessment items from a large open-source dementia dataset. We use cost-sensitive feature selection to optimise our feature selection results for assessment time as well as diagnostic accuracy. To encourage clinical adoption and further evaluation of our proposed accuracy-vs-cost optimisation algorithms, we also implement a sandbox-like toolbox with graphical user interface to evaluate user-chosen subsets of assessment items. RESULTS: We find that there are subsets of accuracy-cost optimised assessment items that can perform better in terms of diagnostic accuracy and/or total assessment time than most other standard assessments. DISCUSSION: Overall, our analysis and accompanying sandbox tool can facilitate clinical users and other stakeholders to apply their own domain knowledge to analyse and decide which dementia diagnostic assessment items are useful, and aid the redesigning of dementia diagnostic assessments. Clinical Impact (Clinical Research): By optimising diagnostic accuracy and assessment time, we redesign predictive and efficient dementia diagnostic assessments and develop a sandbox interface to facilitate evaluation and testing by clinicians and non-specialists.

Practical Strategies for Extreme Missing Data Imputation in Dementia Diagnosis.

Accurate computational models for clinical decision support systems require clean and reliable data but, in clinical practice, data are often incomplete. Hence, missing data could arise not only from training datasets but also test datasets which could consist of a single undiagnosed case, an individual. This work addresses the problem of extreme missingness in both training and test data by evaluating multiple imputation and classification workflows based on both diagnostic classification accuracy and computational cost. Extreme missingness is defined as having ∼50% of the total data missing in more than half the data features. In particular, we focus on dementia diagnosis due to long time delays, high variability, high attrition rates and lack of practical data imputation strategies in its diagnostic pathway. We identified and replicated the extreme missingness structure of data from a real-world memory clinic on a larger open dataset, with the original complete data acting as ground truth. Overall, we found that computational cost, but not accuracy, varies widely for various imputation and classification approaches. Particularly, we found that iterative imputation on the training dataset combined with a reduced-feature classification model provides the best approach, in terms of speed and accuracy. Taken together, this work has elucidated important factors to be considered when developing a predictive model for a dementia diagnostic support system.

Multiple Cost Optimisation for Alzheimer's Disease Diagnosis.

Current machine learning techniques for dementia diagnosis often do not take into account real-world practical constraints, which may include, for example, the cost of diagnostic assessment time and financial budgets. In this work, we built on previous cost-sensitive feature selection approaches by generalising to multiple cost types, while taking into consideration that stakeholders attempting to optimise the dementia care pathway might face multiple non-fungible budget constraints. Our new optimisation algorithm involved the searching of cost-weighting hyperparameters while constrained by total budgets. We then provided a proof of concept using both assessment time cost and financial budget cost. We showed that budget constraints could control the feature selection process in an intuitive and practical manner, while adjusting the hyperparameter increased the range of solutions selected by feature selection. We further showed that our budget-constrained cost optimisation framework could be implemented in a user-friendly graphical user interface sandbox tool to encourage non-technical users and stakeholders to adopt and to further explore and audit the model - a humans-in-the-loop approach. Overall, we suggest that setting budget constraints initially and then fine tuning the cost-weighting hyperparameters can be an effective way to perform feature selection where multiple cost constraints exist, which will in turn lead to more realistic optimising and redesigning of dementia diagnostic assessments. Clinical Relevance-By optimising diagnostic accuracy against various costs (e.g. assessment administration time and financial budget) predictive yet practical dementia diagnostic assessments can be redesigned to suit clinical use.

Lack of backscatter factor measurements in HDR applications with MOSkins.

Measurements of backscatter correction factors for intra operative (IOBT) HDR brachytherapy applicators were made using Centre for Medical Radiation Physics (CMRP), MOSFET devices. In clinical use there is an absence of backscatter material above the IOBT applicator, leading to a lower dose than predicted by conventional TG-43 dose calculations. To estimate the uncertainty in the MOSFET measurements, the dosimetric characteristics, including reproducibility, stability, linearity, and angular and energy response were measured using a HDR Ir-192 source, kilovoltage treatment unit and a high energy linac. Measurements were compared with previously published Monte Carlo data. Variability of the response of the MOSFETs due to angular variation contributed the largest uncertainty in dose measurements. Using the IOBT applicator without adequate scatter material resulted in a reduction of delivered dose of on average 10%, but was dependent on the location on the applicator and the treatment field size. Theoretical calculations based on previously published study indicated an expected reduced dose of on average 4%. MOSFET devices provide an ideal measurement tool in the presence of high dose gradients, however, the dosimetric characteristics of the detector must be accounted for when estimating the uncertainty.