Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks. Here we use image sequences of the heart, acquired using cardiac magnetic resonance imaging, to create time-resolved three-dimensional segmentations using a fully convolutional network trained on anatomical shape priors. This dense motion model formed the input to a supervised denoising autoencoder (4D survival ), which is a hybrid network consisting of an autoencoder that learns a task-specific latent code representation trained on observed outcome data, yielding a latent representation optimised for survival prediction. To handle right-censored survival outcomes, our network used a Cox partial likelihood loss function. In a study of 302 patients the predictive accuracy (quantified by Harrell’s C-index) was significantly higher (p = .0012) for our model C=0.75 (95% CI: 0.70 - 0.79) than the human benchmark of C=0.59 (95% CI: 0.53 - 0.65). This work demonstrates how a complex computer vision task using high-dimensional medical image data can efficiently predict human survival.

Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localisation tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artefacts (e.g. due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network’s ability to infer landmarks, which are then used downstream in the pipeline to initialise atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution and anatomically smooth bi-ventricular 3D models, despite the presence of artefacts in input CMR volumes.

In this work, we propose a deep learning approach for parallel magnetic resonance imaging (MRI) reconstruction, termed a variable splitting network (VS-Net), for an efficient, high-quality reconstruction of undersampled multi-coil MR data. We formulate the generalized parallel compressed sensing reconstruction as an energy minimization problem, for which a variable splitting optimization method is derived. Based on this formulation we propose a novel, end-to-end trainable deep neural network architecture by unrolling the resulting iterative process of such variable splitting scheme. VS-Net is evaluated on complex valued multicoil knee images for 4-fold and 6-fold acceleration factors. We show that VS-Net outperforms state-of-the-art deep learning reconstruction algorithms, in terms of reconstruction accuracy and perceptual quality. Our code is publicly available at https://github.com/j-duan/VS-Net.

PURPOSE Americans receive only one-half of recommended preventive services. Information technologies have been advocated to engage patients. We tested the effectiveness of an interactive preventive health record (IPHR) that links patients to their clinician's record, explains information in lay language, displays tailored recommendations and educational resources, and generates reminders. METHODSThis randomized controlled trial involved 8 primary care practices. Four thousand fi ve hundred patients were randomly selected to receive a mailed invitation to use the IPHR or usual care. Outcomes were measured using patient surveys and electronic medical record data and included IPHR use and service delivery. Comparisons were made between invited and usual-care patients and between users and nonusers among those invited to use the IPHR.RESULTS At 4 and 16 months, 229 (10.2%) and 378 (16.8%) of invited patients used the IPHR. The proportion of patients up-to-date with all services increased between baseline and 16 months by 3.8% among intervention patients (from 11.4% to 15.2%, P <.001) and by 1.5% among control patients (from 11.1% to 12.6%, P = .07), a difference of 2.3% (P = .05). Greater increases were observed among patients who used the IPHR. At 16 months, 25.1% of users were up-todate with all services, double the rate among nonusers. At 4 months, delivery of colorectal, breast, and cervical cancer screening increased by 19%, 15%, and 13%, respectively, among users.CONCLUSIONS Information systems that feature patient-centered functionality, such as the IPHR, have potential to increase preventive service delivery. Engaging more patients to use systems could have important public health benefi ts. Ann Fam Med 2012;10:312-319. doi:10.1370/afm.1383. INTRODUCTIONA mericans receive only one-half of recommended preventive services.1 Among the various causes is poor access to reliable information. Patients need evidence-based information about what is recommended-tailored to their individual risk factors (eg, age, sex, co mbordities, prior testing, family history, health behaviors)-and presented in an understandable format.2 They need reminders when services are due, guidance to deal with inconsistent recommendations, and access to decision aids for choices that require shared decision making. [3][4][5] To act on their choices, patients need written plans and logistical details. 6,7 Clinicians often lack time and resources to provide this information. 8 One proposed solution is to harness the power of information technology, especially personal health records. For the purposes of this article, personal health records are broadly defi ned as health information systems used by patients, whereas electronic health records (EHRs) are systems primarily used by clinicians. 313 INT ER AC T IVE PR E V ENT IV E HE A LT H R ECOR Dgive patients direct access to the EHR of their clinician, 9,10 which is empowering, speeds access to results, and enables patients to discover inaccuracies in their medical record. The next gene...

PURPOSE Health care leaders encourage clinicians to offer portals that enable patients to access personal health records, but implementation has been a challenge. Although large integrated health systems have promoted use through costly advertising campaigns, other implementation methods are needed for small to medium-sized practices where most patients receive their care. METHODSWe conducted a mixed methods assessment of a proactive implementation strategy for a patient portal (an interactive preventive health record [IPHR]) offered by 8 primary care practices. The practices implemented a series of learning collaboratives with practice champions and redesigned workflow to integrate portal use into care. Practice implementation strategies, portal use, and factors influencing use were assessed prospectively.RESULTS A proactive and customized implementation strategy designed by practices resulted in 25.6% of patients using the IPHR, with the rate increasing 1.0% per month over 31 months. Fully 23.5% of IPHR users signed up within 1 day of their office visit. Older patients and patients with comorbidities were more likely to use the IPHR, but blacks and Hispanics were less likely. Older age diminished as a factor after adjusting for comorbidities. Implementation by practice varied considerably (from 22.1% to 27.9%, P <.001) based on clinician characteristics and workflow innovations adopted by practices to enhance uptake.CONCLUSIONS By directly engaging patients to use a portal and supporting practices to integrate use into care, primary care practices can match or potentially surpass the usage rates achieved by large health systems. 2014;12:418-426. doi: 10.1370/afm.1691. Ann Fam Med INTRODUCTIONE lectronic personal health records hold great promise for improving health. High-quality personal health records can facilitate connectivity between patients and clinicians, allow patients to view their medical record, support online clinical and administrative transactions, deliver essential resources to promote informed decision making, and more actively engage patients in care. 1 In the United States, regulations developed by the Office of the National Coordinator and the Centers for Medicare and Medicaid Services to strengthen the functionality of electronic health record systems (meaningful use regulations) encourage practices to engage patients in care through information technology, such as personal health records. 2,3Although patients appear interested, 4,5 practices cannot meet this need without infrastructure, workflow, and cultural changes. Most published experiences with engaging patients online have occurred in integrated health systems that have resources and business models to support adoption, implementation, and maintenance of the personal health record. [6][7][8][9] For example, between 2002 and 2009, Kaiser Permanente and Group Health Cooperative of Puget Sound made major investments to promote online services, resulting in uptake by 27% and 58% of patients, respectively, over 6 to 9 years. 419...

Distributed Lag Models (DLMs) are used in environmental health studies to analyze the time-delayed effect of an exposure on an outcome of interest. Given the increasing need for analytical tools for evaluation of the effects of exposure to multi-pollutant mixtures, this study attempts to extend the classical DLM framework to accommodate and evaluate multiple longitudinally observed exposures. We introduce 2 techniques for quantifying the time-varying mixture effect of multiple exposures on an outcome of interest. Lagged WQS, the first technique, is based on Weighted Quantile Sum (WQS) regression, a penalized regression method that estimates mixture effects using a weighted index. We also introduce Tree-based DLMs, a nonparametric alternative for assessment of lagged mixture effects. This technique is based on the Random Forest (RF) algorithm, a nonparametric, tree-based estimation technique that has shown excellent performance in a wide variety of domains. In a simulation study, we tested the feasibility of these techniques and evaluated their performance in comparison to standard methodology. Both methods exhibited relatively robust performance, accurately capturing pre-defined non-linear functional relationships in different simulation settings. Further, we applied these techniques to data on perinatal exposure to environmental metal toxicants, with the goal of evaluating the effects of exposure on neurodevelopment. Our methods identified critical neurodevelopmental windows showing significant sensitivity to metal mixtures.

ObjectiveTo develop a simple systemic lupus erythematosus (SLE) severity index that requires knowledge of only American College of Rheumatology (ACR) criteria and subcriteria.MethodsThis study used demographic, mortality and medical records data of 1915 patients with lupus from the Lupus Family Registry and Repository. The data were randomly split (2:1 ratio) into independent training and validation sets. A logistic regression with ridge penalty was used to model the probability of being prescribed major immunosuppressive drugs—a surrogate indicator of lupus severity. ACR criteria and subcriteria were used as predictor variables in this model, and the resulting regression coefficient estimates obtained from the training data were used as item weightings to construct the severity index.ResultsThe resulting index was tested on the independent validation dataset and was found to have high predictive accuracy for immunosuppressive use and early mortality. The index was also found to be strongly correlated with a previously existing severity score for lupus. In addition, demographic factors known to influence lupus severity (eg, age of onset, gender and ethnicity) all showed robust associations with our severity index that were consistent with observed clinical trends.ConclusionsThis new index can be easily computed using ACR criteria, which may be among the most readily available data elements from patient medical records. This tool may be useful in lupus research, especially large dataset analyses to stratify patients by disease severity, an important prognostic indicator in SLE.

ObjectiveDeficiencies and excess of essential elements and toxic metals are implicated in amyotrophic lateral sclerosis (ALS), but the age when metal dysregulation appears remains unknown. This study aims to determine whether metal uptake is dysregulated during childhood in individuals eventually diagnosed with ALS.MethodsLaser ablation‐inductively coupled plasma‐mass spectrometry was used to obtain time series data of metal uptake using biomarkers in teeth from autopsies or dental extractions of ALS (n = 36) and control (n = 31) participants. Covariate data included sex, smoking, occupational exposures, and ALS family history. Case–control differences were identified in temporal profiles of metal uptake for individual metals using distributed lag models. Weighted quantile sum (WQS) regression was used for metals mixture analyses. Similar analyses were performed on an ALS mouse model to further verify the relevance of dysregulation of metals in ALS.ResultsMetal levels were higher in cases than in controls: 1.49 times for chromium (1.11–1.82; at 15 years), 1.82 times for manganese (1.34–2.46; at birth), 1.65 times for nickel (1.22–2.01; at 8 years), 2.46 times for tin (1.65–3.30; at 2 years), and 2.46 times for zinc (1.49–3.67; at 6 years). Co‐exposure to 11 elements indicated that childhood metal dysregulation was associated with ALS. The mixture contribution of metals to disease outcome was likewise apparent in tooth biomarkers of an ALS mouse model, and differences in metal distribution were evident in ALS mouse brains compared to brains from littermate controls.InterpretationOverall, our study reveals direct evidence that altered metal uptake during specific early life time windows is associated with adult‐onset ALS.