There is a great opportunity to use high-quality patient journals and health registers to develop machine learning-based Clinical Decision Support Systems (CDSS). To implement a CDSS tool in a clinical workflow, there is a need to integrate, validate and test this tool on the Electronic Health Record (EHR) systems used to store and manage patient data. However, it is often not possible to get the necessary access to an EHR system due to legal compliance. We propose an architecture for generating and using synthetic EHR data for CDSS tool development. The architecture is implemented in a system called SyntHIR. The SyntHIR system uses the Fast Healthcare Interoperability Resources (FHIR) standards for data interoperability, the Gretel framework for generating synthetic data, the Microsoft Azure FHIR server as the FHIR-based EHR system and SMART on FHIR framework for tool transportability. We demonstrate the usefulness of SyntHIR by developing a machine learning-based CDSS tool using data from the Norwegian Patient Register (NPR) and Norwegian Patient Prescriptions (NorPD). We demonstrate the development of the tool on the SyntHIR system and then lift it to the Open DIPS environment. In conclusion, SyntHIR provides a generic architecture for CDSS tool development using synthetic FHIR data and a testing environment before implementing it in a clinical setting. However, there is scope for improvement in terms of the quality of the synthetic data generated. The code is open source and available at //github.com/potter-coder89/SyntHIR.git.
相關內容
Contemporary practices such as InnerSource and DevOps promote software reuse. This study investigates the implications of using contemporary practices on software reuse. In particular, we investigate the costs, benefits, challenges, and potential improvements in contemporary reuse at Ericsson. We performed the study in two phases: a) the initial data collection based on a combination of data collection methods (e.g., interviews, discussions, company portals), and b) a follow-up group discussion after a year to understand the status of the challenges and improvements identified in the first phase. Our results indicate that developing reusable assets resulted in upfront costs, such as additional effort in ensuring compliance. Furthermore, development with reuse also resulted in additional effort, for example, in integrating and understanding reusable assets. Ericsson perceived the additional effort as an investment resulting in long-term benefits such as improved quality, productivity, customer experience, and way of working. Ericsson's main challenge was increased pressure on the producers of reusable assets, which was mitigated by scaling the InnerSource adoption. InnerSource success is evident from the increase in the contributions to reusable assets. In addition, Ericsson implemented measures such as automating the compliance check, which enhanced the maturity of reusable assets and resulted in increased reuse.
While significant advancements in artificial intelligence (AI) have catalyzed progress across various domains, its full potential in understanding visual perception remains underexplored. We propose an artificial neural network dubbed VISION, an acronym for "Visual Interface System for Imaging Output of Neural activity," to mimic the human brain and show how it can foster neuroscientific inquiries. Using visual and contextual inputs, this multimodal model predicts the brain's functional magnetic resonance imaging (fMRI) scan response to natural images. VISION successfully predicts human hemodynamic responses as fMRI voxel values to visual inputs with an accuracy exceeding state-of-the-art performance by 45%. We further probe the trained networks to reveal representational biases in different visual areas, generate experimentally testable hypotheses, and formulate an interpretable metric to associate these hypotheses with cortical functions. With both a model and evaluation metric, the cost and time burdens associated with designing and implementing functional analysis on the visual cortex could be reduced. Our work suggests that the evolution of computational models may shed light on our fundamental understanding of the visual cortex and provide a viable approach toward reliable brain-machine interfaces.
Deep neural networks have reached human-level performance on many computer vision tasks. However, the objectives used to train these networks enforce only that similar images are embedded at similar locations in the representation space, and do not directly constrain the global structure of the resulting space. Here, we explore the impact of supervising this global structure by linearly aligning it with human similarity judgments. We find that a naive approach leads to large changes in local representational structure that harm downstream performance. Thus, we propose a novel method that aligns the global structure of representations while preserving their local structure. This global-local transform considerably improves accuracy across a variety of few-shot learning and anomaly detection tasks. Our results indicate that human visual representations are globally organized in a way that facilitates learning from few examples, and incorporating this global structure into neural network representations improves performance on downstream tasks.
The need for skilled medical support is growing in the era of digital healthcare. This research presents an innovative strategy, utilising the RuBERT model, for categorising user inquiries in the field of medical consultation with a focus on expert specialisation. By harnessing the capabilities of transformers, we fine-tuned the pre-trained RuBERT model on a varied dataset, which facilitates precise correspondence between queries and particular medical specialisms. Using a comprehensive dataset, we have demonstrated our approach's superior performance with an F1-score of over 92%, calculated through both cross-validation and the traditional split of test and train datasets. Our approach has shown excellent generalisation across medical domains such as cardiology, neurology and dermatology. This methodology provides practical benefits by directing users to appropriate specialists for prompt and targeted medical advice. It also enhances healthcare system efficiency, reduces practitioner burden, and improves patient care quality. In summary, our suggested strategy facilitates the attainment of specific medical knowledge, offering prompt and precise advice within the digital healthcare field.
An accurate estimation of the state of health (SOH) of batteries is critical to ensuring the safe and reliable operation of electric vehicles (EVs). Feature-based machine learning methods have exhibited enormous potential for rapidly and precisely monitoring battery health status. However, simultaneously using various health indicators (HIs) may weaken estimation performance due to feature redundancy. Furthermore, ignoring real-world driving behaviors can lead to inaccurate estimation results as some features are rarely accessible in practical scenarios. To address these issues, we proposed a feature-based machine learning pipeline for reliable battery health monitoring, enabled by evaluating the acquisition probability of features under real-world driving conditions. We first summarized and analyzed various individual HIs with mechanism-related interpretations, which provide insightful guidance on how these features relate to battery degradation modes. Moreover, all features were carefully evaluated and screened based on estimation accuracy and correlation analysis on three public battery degradation datasets. Finally, the scenario-based feature fusion and acquisition probability-based practicality evaluation method construct a useful tool for feature extraction with consideration of driving behaviors. This work highlights the importance of balancing the performance and practicality of HIs during the development of feature-based battery health monitoring algorithms.
Cancer is a significant health issue globally and it is well known that cancer risk varies geographically. However in many countries there are no small area-level data on cancer risk factors with high resolution and complete reach, which hinders the development of targeted prevention strategies. Using Australia as a case study, the 2017-2018 National Health Survey was used to generate prevalence estimates for 2221 small areas across Australia for eight cancer risk factor measures covering smoking, alcohol, physical activity, diet and weight. Utilising a recently developed Bayesian two-stage small area estimation methodology, the model incorporated survey-only covariates, spatial smoothing and hierarchical modelling techniques, along with a vast array of small area-level auxiliary data, including census, remoteness, and socioeconomic data. The models borrowed strength from previously published cancer risk estimates provided by the Social Health Atlases of Australia. Estimates were internally and externally validated. We illustrated that in 2017-18 health behaviours across Australia exhibited more spatial disparities than previously realised by improving the reach and resolution of formerly published cancer risk factors. The derived estimates reveal higher prevalence of unhealthy behaviours in more remote areas, and areas of lower socioeconomic status; a trend that aligns well with previous work. Our study addresses the gaps in small area level cancer risk factor estimates in Australia. The new estimates provide improved spatial resolution and reach and will enable more targeted cancer prevention strategies at the small area level, supporting policy makers, researchers, and the general public in understanding the spatial distribution of cancer risk factors in Australia. To help disseminate the results of this work, they will be made available in the Australian Cancer Atlas 2.0.
National surveys of the healthcare system in the United States were conducted to characterize the structure of healthcare system and investigate the impact of evidence-based innovations in healthcare systems on healthcare services. Administrative data is additionally available to researchers raising the question of whether inferences about healthcare organizations based on the survey data can be enhanced by incorporating information from auxiliary data. Administrative data can provide information for dealing with under-coverage-bias and non-response in surveys and for capturing more sub-populations. In this study, we focus on the use of administrative claims data to improve estimates about means of survey items for the finite population. Auxiliary information from the claims data is incorporated using multiple imputation to impute values of non-responding or non-surveyed organizations. We derive multiple versions of imputation strategy, and the logical development of methodology is compared to two incumbent approaches: a na\"ive analysis that ignores the sampling probabilities and a traditional survey analysis weighting by the inverses of the sampling probabilities. , and illustrate the methods using data from The National Survey of Healthcare Organizations and Systems and The Centers for Medicare & Medicaid Services Medicare claims data to make inferences about relationships of characteristics of healthcare organizations and healthcare services they provide.
As an alternative to using administrative areas for the evaluation of small-area health inequalities, Sauzet et al suggested to take an ego-centred approach and model the spatial correlation structure of health outcomes at individual level. Existing tools for the analysis of spatial data in R may appear too complex to non-specialists which may limit the use of the approach. We present the R package EgoCor which offers a user-friendly interface displaying in one function a range of graphics and tables of parameters to facilitate the decision making about which exponential parameters fit best either raw data or residuals. This function is based on the functions of the R package gstat. Moreover, we implemented a function providing the measure of uncertainty proposed by Dyck and Sauzet. With the R package EgoCor the modelling of spatial correlation structure of health outcomes with a measure of uncertainty is made available to non specialists.
Saliency maps have become one of the most widely used interpretability techniques for convolutional neural networks (CNN) due to their simplicity and the quality of the insights they provide. However, there are still some doubts about whether these insights are a trustworthy representation of what CNNs use to come up with their predictions. This paper explores how rescuing the sign of the gradients from the saliency map can lead to a deeper understanding of multi-class classification problems. Using both pretrained and trained from scratch CNNs we unveil that considering the sign and the effect not only of the correct class, but also the influence of the other classes, allows to better identify the pixels of the image that the network is really focusing on. Furthermore, how occluding or altering those pixels is expected to affect the outcome also becomes clearer.
A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to pre-train a neural network with unlabeled data, followed by fine-tuning for a downstream task with limited annotations. Contrastive learning, a particular variant of SSL, is a powerful technique for learning image-level representations. In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues. Specifically, we propose (1) novel contrasting strategies that leverage structural similarity across volumetric medical images (domain-specific cue) and (2) a local version of the contrastive loss to learn distinctive representations of local regions that are useful for per-pixel segmentation (problem-specific cue). We carry out an extensive evaluation on three Magnetic Resonance Imaging (MRI) datasets. In the limited annotation setting, the proposed method yields substantial improvements compared to other self-supervision and semi-supervised learning techniques. When combined with a simple data augmentation technique, the proposed method reaches within 8% of benchmark performance using only two labeled MRI volumes for training, corresponding to only 4% (for ACDC) of the training data used to train the benchmark.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191