Implementation of a Spaced Learning Program for Educating CRNAs on a Scalpel-Bougie Cricothyrotomy Procedure for Emergency Front of Neck Access

Certified registered nurse anesthetists (CRNAs) who are responsible for airway management, may lack adequate continuing education for emergency front of neck access (EFONA), an advanced skill necessary in situations when a patient cannot be intubated and cannot be oxygenated (CICO). The purpose of this study was to improve CRNA knowledge and confidence when performing a scalpel-bougie cricothyrotomy for EFONA in a CICO event through the implementation of a spaced learning intervention. Thirteen CRNAs at a 160-bed community hospital participated in a 3-week educational intervention. Week 1: online preintervention survey followed by an educational video. Week 2: video review and skills component practiced on a cricothyrotomy trainer. Week 3: skills component practiced on a cricothyrotomy trainer followed by postintervention survey. This was a single-arm study and Wilcoxon sign ranked tests and a paired t-test were utilized to monitor for change in CRNA knowledge, confidence, and skill in performing EFONA. Implementation of a 3-week spaced learning program for educating CRNAs to perform a scalpel-bougie cricothyrotomy significantly increased CRNA knowledge, confidence, and skill when performing EFONA. Utilizing a spaced learning program may therefore improve provider skills, resulting in optimized patient care during a CICO event, leading to improved patient safety and outcomes.

A multi-center distributed learning approach for Parkinson's disease classification using the traveling model paradigm

Distributed learning is a promising alternative to central learning for machine learning (ML) model training, overcoming data-sharing problems in healthcare. Previous studies exploring federated learning (FL) or the traveling model (TM) setup for medical image-based disease classification often relied on large databases with a limited number of centers or simulated artificial centers, raising doubts about real-world applicability. This study develops and evaluates a convolution neural network (CNN) for Parkinson's disease classification using data acquired by 83 diverse real centers around the world, mostly contributing small training samples. Our approach specifically makes use of the TM setup, which has proven effective in scenarios with limited data availability but has never been used for image-based disease classification. Our findings reveal that TM is effective for training CNN models, even in complex real-world scenarios with variable data distributions. After sufficient training cycles, the TM-trained CNN matches or slightly surpasses the performance of the centrally trained counterpart (AUROC of 83% vs. 80%). Our study highlights, for the first time, the effectiveness of TM in 3D medical image classification, especially in scenarios with limited training samples and heterogeneous distributed data. These insights are relevant for situations where ML models are supposed to be trained using data from small or remote medical centers, and rare diseases with sparse cases. The simplicity of this approach enables a broad application to many deep learning tasks, enhancing its clinical utility across various contexts and medical facilities.

Federated and distributed learning applications for electronic health records and structured medical data: a scoping review

OBJECTIVES

Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations, and discusses potential innovations.

MATERIALS AND METHODS

We searched 5 databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from 3 primary perspectives, including data quality, modeling strategies, and FL frameworks.

RESULTS

Out of the 1193 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis.

CONCLUSIONS

The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

CEDAR: communication efficient distributed analysis for regressions

Electronic health records (EHRs) offer great promises for advancing precision medicine and, at the same time, present significant analytical challenges. Particularly, it is often the case that patient-level data in EHRs cannot be shared across institutions (data sources) due to government regulations and/or institutional policies. As a result, there are growing interests about distributed learning over multiple EHRs databases without sharing patient-level data. To tackle such challenges, we propose a novel communication efficient method that aggregates the optimal estimates of external sites, by turning the problem into a missing data problem. In addition, we propose incorporating posterior samples of remote sites, which can provide partial information on the missing quantities and improve efficiency of parameter estimates while having the differential privacy property and thus reducing the risk of information leaking. The proposed approach, without sharing the raw patient level data, allows for proper statistical inference. We provide theoretical investigation for the asymptotic properties of the proposed method for statistical inference as well as differential privacy, and evaluate its performance in simulations and real data analyses in comparison with several recently developed methods.

Mobility-Aware Federated Learning Considering Multiple Networks

Federated learning (FL) is a distributed training method for machine learning models (ML) that maintain data ownership on users. However, this distributed training approach can lead to variations in efficiency due to user behaviors or characteristics. For instance, mobility can hinder training by causing a client dropout when a device loses connection with other devices on the network. To address this issue, we propose a FL coordination algorithm, MoFeL, to ensure efficient training even in scenarios with mobility. Furthermore, MoFeL evaluates multiple networks with different central servers. To evaluate its effectiveness, we conducted simulation experiments using an image classification application that utilizes machine models trained by a convolutional neural network. The simulation results demonstrate that MoFeL outperforms traditional training coordination algorithms in FL, with 156.5% more training cycles, in scenarios with high mobility compared to an algorithm that does not consider mobility aspects.

Comparing Decentralized Learning Methods for Health Data Models to Nondecentralized Alternatives: Protocol for a Systematic Review

BACKGROUND

Considering the soaring health-related costs directed toward a growing, aging, and comorbid population, the health sector needs effective data-driven interventions while managing rising care costs. While health interventions using data mining have become more robust and adopted, they often demand high-quality big data. However, growing privacy concerns have hindered large-scale data sharing. In parallel, recently introduced legal instruments require complex implementations, especially when it comes to biomedical data. New privacy-preserving technologies, such as decentralized learning, make it possible to create health models without mobilizing data sets by using distributed computation principles. Several multinational partnerships, including a recent agreement between the United States and the European Union, are adopting these techniques for next-generation data science. While these approaches are promising, there is no clear and robust evidence synthesis of health care applications.

OBJECTIVE

The main aim is to compare the performance among health data models (eg, automated diagnosis and mortality prediction) developed using decentralized learning approaches (eg, federated and blockchain) to those using centralized or local methods. Secondary aims are comparing the privacy compromise and resource use among model architectures.

METHODS

We will conduct a systematic review using the first-ever registered research protocol for this topic following a robust search methodology, including several biomedical and computational databases. This work will compare health data models differing in development architecture, grouping them according to their clinical applications. For reporting purposes, a PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 flow diagram will be presented. CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies)-based forms will be used for data extraction and to assess the risk of bias, alongside PROBAST (Prediction Model Risk of Bias Assessment Tool). All effect measures in the original studies will be reported.

RESULTS

The queries and data extractions are expected to start on February 28, 2023, and end by July 31, 2023. The research protocol was registered with PROSPERO, under the number 393126, on February 3, 2023. With this protocol, we detail how we will conduct the systematic review. With that study, we aim to summarize the progress and findings from state-of-the-art decentralized learning models in health care in comparison to their local and centralized counterparts. Results are expected to clarify the consensuses and heterogeneities reported and help guide the research and development of new robust and sustainable applications to address the health data privacy problem, with applicability in real-world settings.

CONCLUSIONS

We expect to clearly present the status quo of these privacy-preserving technologies in health care. With this robust synthesis of the currently available scientific evidence, the review will inform health technology assessment and evidence-based decisions, from health professionals, data scientists, and policy makers alike. Importantly, it should also guide the development and application of new tools in service of patients' privacy and future research.

TRIAL REGISTRATION

PROSPERO 393126; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=393126.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/45823.

In-Network Learning: Distributed Training and Inference in Networks

In this paper, we study distributed inference and learning over networks which can be modeled by a directed graph. A subset of the nodes observes different features, which are all relevant/required for the inference task that needs to be performed at some distant end (fusion) node. We develop a learning algorithm and an architecture that can combine the information from the observed distributed features, using the processing units available across the networks. In particular, we employ information-theoretic tools to analyze how inference propagates and fuses across a network. Based on the insights gained from this analysis, we derive a loss function that effectively balances the model's performance with the amount of information transmitted across the network. We study the design criterion of our proposed architecture and its bandwidth requirements. Furthermore, we discuss implementation aspects using neural networks in typical wireless radio access and provide experiments that illustrate benefits over state-of-the-art techniques.

Straggler- and Adversary-Tolerant Secure Distributed Matrix Multiplication Using Polynomial Codes

Large matrix multiplications commonly take place in large-scale machine-learning applications. Often, the sheer size of these matrices prevent carrying out the multiplication at a single server. Therefore, these operations are typically offloaded to a distributed computing platform with a master server and a large amount of workers in the cloud, operating in parallel. For such distributed platforms, it has been recently shown that coding over the input data matrices can reduce the computational delay by introducing a tolerance against straggling workers, i.e., workers for which execution time significantly lags with respect to the average. In addition to exact recovery, we impose a security constraint on both matrices to be multiplied. Specifically, we assume that workers can collude and eavesdrop on the content of these matrices. For this problem, we introduce a new class of polynomial codes with fewer non-zero coefficients than the degree +1. We provide closed-form expressions for the recovery threshold and show that our construction improves the recovery threshold of existing schemes in the literature, in particular for larger matrix dimensions and a moderate to large number of colluding workers. In the absence of any security constraints, we show that our construction is optimal in terms of recovery threshold.

An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction

OBJECTIVE

Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.

MATERIALS AND METHODS

2025 T1-weighted magnetic resonance imaging scans were used to investigate the effect of sample sizes on FL and TM for brain age prediction. We evaluated models across 18 scenarios varying the number of samples per site (1, 2, 5, 10, and 20) and the number of training rounds (20, 40, and 200).

RESULTS

Our results demonstrate that the TM outperforms FL, for every sample size examined. In the extreme case when each site provided only one sample, FL achieved a mean absolute error (MAE) of 18.9 ± 0.13 years, while the TM achieved a MAE of 6.21 ± 0.50 years, comparable to central learning (MAE = 5.99 years).

DISCUSSION

Although FL is more commonly used, our study demonstrates that TM is the best implementation for small sample sizes.

CONCLUSION

The TM offers new opportunities to apply machine learning models in rare diseases and pediatric research but also allows even small hospitals to contribute small datasets.

Levels of Autonomous Radiology

Radiology, being one of the younger disciplines of medicine with a history of just over a century, has witnessed tremendous technological advancements and has revolutionized the way we practice medicine today. In the last few decades, medical imaging modalities have generated seismic amounts of medical data. The development and adoption of artificial intelligence applications using this data will lead to the next phase of evolution in radiology. It will include automating laborious manual tasks such as annotations, report generation, etc, along with the initial radiological assessment of patients and imaging features to aid radiologists in their diagnostic and treatment planning workflow. We propose a level-wise classification for the progression of automation in radiology, explaining artificial intelligence assistance at each level with the corresponding challenges and solutions. We hope that such discussions can help us address challenges in a structured way and take the necessary steps to ensure the smooth adoption of new technologies in radiology.

Effective Model Update for Adaptive Classification of Text Streams in a Distributed Learning Environment

In this study, we propose dynamic model update methods for the adaptive classification model of text streams in a distributed learning environment. In particular, we present two model update strategies: (1) the entire model update and (2) the partial model update. The former aims to maximize the model accuracy by periodically rebuilding the model based on the accumulated datasets including recent datasets. Its learning time incrementally increases as the datasets increase, but we alleviate the learning overhead by the distributed learning of the model. The latter fine-tunes the model only with a limited number of recent datasets, noting that the data streams are dependent on a recent event. Therefore, it accelerates the learning speed while maintaining a certain level of accuracy. To verify the proposed update strategies, we extensively apply them to not only fully trainable language models based on CNN, RNN, and Bi-LSTM, but also a pre-trained embedding model based on BERT. Through extensive experiments using two real tweet streaming datasets, we show that the entire model update improves the classification accuracy of the pre-trained offline model; the partial model update also improves it, which shows comparable accuracy with the entire model update, while significantly increasing the learning speed. We also validate the scalability of the proposed distributed learning architecture by showing that the model learning and inference time decrease as the number of worker nodes increases.

The Future of Causal Inference

The past several decades have seen exponential growth in causal inference approaches and their applications. In this commentary, we provide our top-10 list of emerging and exciting areas of research in causal inference. These include methods for high-dimensional data and precision medicine, causal machine learning, causal discovery, and others. These methods are not meant to be an exhaustive list; instead, we hope that this list will serve as a springboard for stimulating the development of new research.

Blockchain Empowered Federated Learning Ecosystem for Securing Consumer IoT Features Analysis

Resource constraint Consumer Internet of Things (CIoT) is controlled through gateway devices (e.g., smartphones, computers, etc.) that are connected to Mobile Edge Computing (MEC) servers or cloud regulated by a third party. Recently Machine Learning (ML) has been widely used in automation, consumer behavior analysis, device quality upgradation, etc. Typical ML predicts by analyzing customers' raw data in a centralized system which raises the security and privacy issues such as data leakage, privacy violation, single point of failure, etc. To overcome the problems, Federated Learning (FL) developed an initial solution to ensure services without sharing personal data. In FL, a centralized aggregator collaborates and makes an average for a global model used for the next round of training. However, the centralized aggregator raised the same issues, such as a single point of control leaking the updated model and interrupting the entire process. Additionally, research claims data can be retrieved from model parameters. Beyond that, since the Gateway (GW) device has full access to the raw data, it can also threaten the entire ecosystem. This research contributes a blockchain-controlled, edge intelligence federated learning framework for a distributed learning platform for CIoT. The federated learning platform allows collaborative learning with users' shared data, and the blockchain network replaces the centralized aggregator and ensures secure participation of gateway devices in the ecosystem. Furthermore, blockchain is trustless, immutable, and anonymous, encouraging CIoT end users to participate. We evaluated the framework and federated learning outcomes using the well-known Stanford Cars dataset. Experimental results prove the effectiveness of the proposed framework.

Infrastructure platform for privacy-preserving distributed machine learning development of computer-assisted theragnostics in cancer

INTRODUCTION

Emerging evidence suggests that data-driven support tools have found their way into clinical decision-making in a number of areas, including cancer care. Improving them and widening their scope of availability in various differing clinical scenarios, including for prognostic models derived from retrospective data, requires co-ordinated data sharing between clinical centres, secondary analyses of large multi-institutional clinical trial data, or distributed (federated) learning infrastructures. A systematic approach to utilizing routinely collected data across cancer care clinics remains a significant challenge due to privacy, administrative and political barriers.

METHODS

An information technology infrastructure and web service software was developed and implemented which uses machine learning to construct clinical decision support systems in a privacy-preserving manner across datasets geographically distributed in different hospitals. The infrastructure was deployed in a network of Australian hospitals. A harmonized, international ontology-linked, set of lung cancer databases were built with the routine clinical and imaging data at each centre. The infrastructure was demonstrated with the development of logistic regression models to predict major cardiovascular events following radiation therapy.

RESULTS

The infrastructure implemented forms the basis of the Australian computer-assisted theragnostics (AusCAT) network for radiation oncology data extraction, reporting and distributed learning. Four radiation oncology departments (across seven hospitals) in New South Wales (NSW) participated in this demonstration study. Infrastructure was deployed at each centre and used to develop a model predicting for cardiovascular admission within a year of receiving curative radiotherapy for non-small cell lung cancer. A total of 10417 lung cancer patients were identified with 802 being eligible for the model. Twenty features were chosen for analysis from the clinical record and linked registries. After selection, 8 features were included and a logistic regression model achieved an area under the receiver operating characteristic (AUROC) curve of 0.70 and C-index of 0.65 on out-of-sample data.

CONCLUSION

The infrastructure developed was demonstrated to be usable in practice between clinical centres to harmonize routinely collected oncology data and develop models with federated learning. It provides a promising approach to enable further research studies in radiation oncology using real world clinical data.

Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction

Background: Machine learning models have been developed for numerous medical prognostic purposes. These models are commonly developed using data from single centers or regional registries. Including data from multiple centers improves robustness and accuracy of prognostic models. However, data sharing between multiple centers is complex, mainly because of regulations and patient privacy issues. Objective: We aim to overcome data sharing impediments by using distributed ML and local learning followed by model integration. We applied these techniques to develop 1-year TAVI mortality estimation models with data from two centers without sharing any data. Methods: A distributed ML technique and local learning followed by model integration was used to develop models to predict 1-year mortality after TAVI. We included two populations with 1,160 (Center A) and 631 (Center B) patients. Five traditional ML algorithms were implemented. The results were compared to models created individually on each center. Results: The combined learning techniques outperformed the mono-center models. For center A, the combined local XGBoost achieved an AUC of 0.67 (compared to a mono-center AUC of 0.65) and, for center B, a distributed neural network achieved an AUC of 0.68 (compared to a mono-center AUC of 0.64). Conclusion: This study shows that distributed ML and combined local models techniques, can overcome data sharing limitations and result in more accurate models for TAVI mortality estimation. We have shown improved prognostic accuracy for both centers and can also be used as an alternative to overcome the problem of limited amounts of data when creating prognostic models.

Synergy Between Point-of-Care Testing and Laboratory Consolidations

Central or area laboratories will offer an improved number of diagnostic testing services, where drivers for change will involve chronic disease clinical care for an increasingly older population, new emerging diagnostic technologies and personalized medicine. Higher automation quality and ever more diagnostic field integration will lead to higher productivity by means of an improved throughput. At the same time Point of Care Testing (POCT) site of patient care allows for timely medical assessment, which can lead to improved patient outcomes, more effectiveness and patient satisfaction. POCT test introduction in clinical practice should be assessed by an outcome-based policy to avoid adverse events, failure to diagnose providing appropriate timed treatment. The use of POCT devices does not only require technological considerations for the production and management of acceptable tests possibly managed by central laboratory, but also implicates a shift in diagnostic practice across all health organizations. The interaction between laboratory professionals and clinicians will be enriched with new methods of evaluation of patient needs in the internet of things and mobile Health worlds, where boundaries between POCT and central laboratory or hospital and primary healthcare will no longer exist and where all data can be shared and disseminated among stakeholders in the healthcare system.

Delay-Tolerant Distributed Inference in Tracking Networks

This paper discusses asynchronous distributed inference in object tracking. Unlike many studies, which assume that the delay in communication between partial estimators and the central station is negligible, our study focuses on the problem of asynchronous distributed inference in the presence of delays. We introduce an efficient data fusion method for combining the distributed estimates, where delay in communications is not negligible. To overcome the delay, predictions are made for the state of the system based on the most current available information from partial estimators. Simulation results show the efficacy of the methods proposed.

Implementation of the Australian Computer-Assisted Theragnostics (AusCAT) network for radiation oncology data extraction, reporting and distributed learning

INTRODUCTION

There is significant potential to analyse and model routinely collected data for radiotherapy patients to provide evidence to support clinical decisions, particularly where clinical trials evidence is limited or non-existent. However, in practice there are administrative, ethical, technical, logistical and legislative barriers to having coordinated data analysis platforms across radiation oncology centres.

METHODS

A distributed learning network of computer systems is presented, with software tools to extract and report on oncology data and to enable statistical model development. A distributed or federated learning approach keeps data in the local centre, but models are developed from the entire cohort.

RESULTS

The feasibility of this approach is demonstrated across six Australian oncology centres, using routinely collected lung cancer data from oncology information systems. The infrastructure was used to validate and develop machine learning for model-based clinical decision support and for one centre to assess patient eligibility criteria for two major lung cancer radiotherapy clinical trials (RTOG-9410, RTOG-0617). External validation of a 2-year overall survival model for non-small cell lung cancer (NSCLC) gave an AUC of 0.65 and C-index of 0.62 across the network. For one centre, 65% of Stage III NSCLC patients did not meet eligibility criteria for either of the two practice-changing clinical trials, and these patients had poorer survival than eligible patients (10.6 m vs. 15.8 m, P = 0.024).

CONCLUSION

Population-based studies on routine data are possible using a distributed learning approach. This has the potential for decision support models for patients for whom supporting clinical trial evidence is not applicable.

A Multi-Core Controller for an Embedded AI System Supporting Parallel Recognition

Recent advances in artificial intelligence (AI) technology encourage the adoption of AI systems for various applications. In most deployments, AI-based computing systems adopt the architecture in which the central server processes most of the data. This characteristic makes the system use a high amount of network bandwidth and can cause security issues. In order to overcome these issues, a new AI model called federated learning was presented. Federated learning adopts an architecture in which the clients take care of data training and transmit only the trained result to the central server. As the data training from the client abstracts and reduces the original data, the system operates with reduced network resources and reinforced data security. A system with federated learning supports a variety of client systems. To build an AI system with resource-limited client systems, composing the client system with multiple embedded AI processors is valid. For realizing the system with this architecture, introducing a controller to arbitrate and utilize the AI processors becomes a stringent requirement. In this paper, we propose an embedded AI system for federated learning that can be composed flexibly with the AI core depending on the application. In order to realize the proposed system, we designed a controller for multiple AI cores and implemented it on a field-programmable gate array (FPGA). The operation of the designed controller was verified through image and speech applications, and the performance was verified through a simulator.

Open-Source Federated Learning Frameworks for IoT: A Comparative Review and Analysis

The rapid development of Internet of Things (IoT) systems has led to the problem of managing and analyzing the large volumes of data that they generate. Traditional approaches that involve collection of data from IoT devices into one centralized repository for further analysis are not always applicable due to the large amount of collected data, the use of communication channels with limited bandwidth, security and privacy requirements, etc. Federated learning (FL) is an emerging approach that allows one to analyze data directly on data sources and to federate the results of each analysis to yield a result as traditional centralized data processing. FL is being actively developed, and currently, there are several open-source frameworks that implement it. This article presents a comparative review and analysis of the existing open-source FL frameworks, including their applicability in IoT systems. The authors evaluated the following features of the frameworks: ease of use and deployment, development, analysis capabilities, accuracy, and performance. Three different data sets were used in the experiments-two signal data sets of different volumes and one image data set. To model low-power IoT devices, computing nodes with small resources were defined in the testbed. The research results revealed FL frameworks that could be applied in the IoT systems now, but with certain restrictions on their use.

Accounting for data variability in multi-institutional distributed deep learning for medical imaging

OBJECTIVES

Sharing patient data across institutions to train generalizable deep learning models is challenging due to regulatory and technical hurdles. Distributed learning, where model weights are shared instead of patient data, presents an attractive alternative. Cyclical weight transfer (CWT) has recently been demonstrated as an effective distributed learning method for medical imaging with homogeneous data across institutions. In this study, we optimize CWT to overcome performance losses from variability in training sample sizes and label distributions across institutions.

MATERIALS AND METHODS

Optimizations included proportional local training iterations, cyclical learning rate, locally weighted minibatch sampling, and cyclically weighted loss. We evaluated our optimizations on simulated distributed diabetic retinopathy detection and chest radiograph classification.

RESULTS

Proportional local training iteration mitigated performance losses from sample size variability, achieving 98.6% of the accuracy attained by centrally hosting in the diabetic retinopathy dataset split with highest sample size variance across institutions. Locally weighted minibatch sampling and cyclically weighted loss both mitigated performance losses from label distribution variability, achieving 98.6% and 99.1%, respectively, of the accuracy attained by centrally hosting in the diabetic retinopathy dataset split with highest label distribution variability across institutions.

DISCUSSION

Our optimizations to CWT improve its capability of handling data variability across institutions. Compared to CWT without optimizations, CWT with optimizations achieved performance significantly closer to performance from centrally hosting.

CONCLUSION

Our work is the first to identify and address challenges of sample size and label distribution variability in simulated distributed deep learning for medical imaging. Future work is needed to address other sources of real-world data variability.

The Algorithms of Distributed Learning and Distributed Estimation about Intelligent Wireless Sensor Network

The intelligent wireless sensor network is a distributed network system with high “network awareness”. Each intelligent node (agent) is connected by the topology within the neighborhood which not only can perceive the surrounding environment, but can adjusts its own behavior according to its local perception information to constructs a distributed learning algorithms. Therefore, three basic intelligent network topologies of centralized, non-cooperative, and cooperative are intensively investigated in this paper. The main contributions of the paper include two aspects. First, based on algebraic graph, three basic theoretical frameworks for distributed learning and distributed parameter estimation of cooperative strategy are surveyed: increment strategy, consensus strategy, and diffusion strategy. Second, based on classical adaptive learning algorithm and online updating law, the implementation process of distributed estimation algorithm and the latest research progress of above three distributed strategies are investigated.

Role of the hippocampus in the spacing effect during memory retrieval

It is well known that distributed learning (DL) leads to improved memory performance compared with massed learning (ML) (i.e., spacing effect). However, the extent to which the hippocampus is involved in the spacing effect at shorter and longer retention intervals remains unclear. To address this issue, two groups of participants were asked to encode face-scene pairs at 20-min, 1-day, and 1-month intervals before they were scanned using fMRI during an associative recognition task. The pairs were repeated six times in either a massed (i.e., six times in 1 day) or a distributed (i.e., six times over 3 days, twice per day) manner. The results showed that compared with that in the ML group, the activation of the left hippocampus was stronger in the DL group when the participants retrieved old pairs correctly and rejected new pairs correctly at different retention intervals. In addition, the posterior hippocampus was more strongly activated when the new associations were rejected correctly after DL than ML, especially at the 1-month interval. Hence, our results provide evidence that the hippocampus is involved in better memory performance after DL compared to ML at both shorter and longer retention intervals.

External Validation of Radiation-Induced Dyspnea Models on Esophageal Cancer Radiotherapy Patients

Purpose: Radiation-induced lung disease (RILD), defined as dyspnea in this study, is a risk for patients receiving high-dose thoracic irradiation. This study is a TRIPOD (Transparent Reporting of A Multivariable Prediction Model for Individual Prognosis or Diagnosis) Type 4 validation of previously-published dyspnea models via secondary analysis of esophageal cancer SCOPE1 trial data. We quantify the predictive performance of these two models for predicting the maximal dyspnea grade ≥ 2 within 6 months after the end of high-dose chemo-radiotherapy for primary esophageal cancer.

Materials and methods: We tested the performance of two previously published dyspnea risk models using baseline, treatment and follow-up data on 258 esophageal cancer patients in the UK enrolled into the SCOPE1 multi-center trial. The tested models were developed from lung cancer patients treated at MAASTRO Clinic (The Netherlands) from the period 2002 to 2011. The adverse event of interest was dyspnea ≥ Grade 2 (CTCAE v3) within 6 months after the end of radiotherapy. As some variables were missing randomly and cannot be imputed, 212 patients in the SCOPE1 were used for validation of model 1 and 255 patients were used for validation of model 2. The model parameter Forced Expiratory Volume in 1 s (FEV₁), as a predictor to both validated models, was imputed using the WHO performance status. External validation was performed using an automated, decentralized approach, without exchange of individual patient data.

Results: Out of 258 patients with esophageal cancer in SCOPE1 trial data, 38 patients (14.7%) developed radiation-induced dyspnea (≥ Grade 2) within 6 months after chemo-radiotherapy. The discrimination performance of the models in esophageal cancer patients treated with high-dose external beam radiotherapy was moderate, area under curve (AUC) of 0.68 (95% CI 0.55–0.76) and 0.70 (95% CI 0.58–0.77), respectively. The curves and AUCs derived by distributed learning were identical to the results from validation on a local host.

Conclusion: We have externally validated previously published dyspnea models using an esophageal cancer dataset. FEV₁ that is not routinely measured for esophageal cancer was imputed using WHO performance status. Prediction performance was not statistically different from previous training and validation sets. Risk estimates were dominated by WHO score in Model 1 and baseline dyspnea in Model 2. The distributed learning approach gave the same answer as local processing, and could be performed without accessing a validation site's individual patients-level data.

Using technology to increase student (and faculty satisfaction with) engagement in medical education

Faculty dissatisfaction with diminishing levels of student engagement in lifestyle medicine sessions prompted this exploratory project that compared differences in students' substantive engagement in medical preclinical and clinical level lifestyle medicine sessions. The preclinical and clinical level sessions had the same learning objectives and learning tasks, properly aligned with that level of student learning, but were offered in different learning formats, either traditional classroom approaches or technology-enhanced approaches. At the preclinical level, we transferred a nonmandatory, face-to-face session to a nonmandatory, fully online session. At the clinical level, we introduced two novel technology tools. We utilized Zoom technologies, which afforded students the ability to access the session from anywhere, and employed Hickey's use of "promoting" student submissions as one method for increasing student-student interaction during the synchronous session. We used indicators of behavioral engagement of Henrie et al. (Henrie CR, Halverson LR, Graham CR. Comput Educ 90: 36-53, 2015) as the framework for determining applicable engagement behaviors, including attendance, assignment completion, interactions (responding/feedback/endorsements), and the quality of (and faculty satisfaction with) the face-to-face and/or online interactions. We expected to observe higher levels of engagement behaviors in the technology-enhanced approach and found that to be the case at both the preclinical and clinical levels, in both mandatory/nonmandatory and synchronous/asynchronous formats. However, it was the increase in both the level and substance of the students' interactions in the technology-enhanced sessions that provided surprising results. A review of the sessions with enhanced engagement highlight the role of student autonomy, a construct with strongly established associations to student motivation and engagement.

Distributed Learning Fractal Algorithm for Optimizing a Centralized Control Topology of Wireless Sensor Network Based on the Hilbert Curve L-System

Wireless sensor networks (WSNs) consist of a large number of small devices or nodes, called micro controller units (MCUs) and located in homes and/or offices, to be operated through the internet from anywhere, making these devices smarter and more efficient. Quality of service routing is one of the critical challenges in WSNs, especially in surveillance systems. To improve the efficiency of the network, in this article we proposes a distributed learning fractal algorithm (DFLA) to design the control topology of a wireless sensor network (WSN), whose nodes are the MCUs distributed in a physical space and which are connected to share parameters of the sensors such as concentrations of C O 2 , humidity, temperature within the space or adjustment of the intensity of light inside and outside the home or office. For this, we start defining the production rules of the L-systems to generate the Hilbert fractal, since these rules facilitate the generation of this fractal, which is a fill-space curve. Then, we model the optimization of a centralized control topology of WSNs and proposed a DFLA to find the best two nodes where a device can find the highly reliable link between these nodes. Thus, we propose a software defined network (SDN) with strong mobility since it can be reconfigured depending on the amount of nodes, also we employ a target coverage because distributed learning fractal algorithm (DLFA) only consider reliable links among devices. Finally, through laboratory tests and computer simulations, we demonstrate the effectiveness of our approach by means of a fractal routing in WSNs, by using a large amount of WSNs devices (from 16 to 64 sensors) for real time monitoring of different parameters, in order to make efficient WSNs and its application in a forthcoming Smart City.

Distributed Learning in the Classroom: Effects of Rereading Schedules Depend on Time of Test

Research with adults in laboratory settings has shown that distributed rereading is a beneficial learning strategy but its effects depend on time of test. When learning outcomes are measured immediately after rereading, distributed rereading yields no benefits or even detrimental effects on learning, but the beneficial effects emerge two days later. In a preregistered experiment, the effects of distributed rereading were investigated in a classroom setting with school students. Seventh-graders (N = 191) reread a text either immediately or after 1 week. Learning outcomes were measured after 4 min or 1 week. Participants in the distributed rereading condition reread the text more slowly, predicted their learning success to be lower, and reported a lower on-task focus. At the shorter retention interval, massed rereading outperformed distributed rereading in terms of learning outcomes. Contrary to students in the massed condition, students in the distributed condition showed no forgetting from the short to the long retention interval. As a result, they performed equally well as the students in the massed condition at the longer retention interval. Our results indicate that distributed rereading makes learning more demanding and difficult and leads to higher effort during rereading. Its effects on learning depend on time of test, but no beneficial effects were found, not even at the delayed test.

Providing Health Sciences Services in a Joint-Use Distributed Learning Library System: An Organizational Case Study

The purpose of this organizational case study is to describe the complexities librarians face when serving a multi-campus institution that supports both a joint-use library and expanding health sciences academic partnerships. In a system without a centralized health science library administration, liaison librarians are identifying dispersed programs and user groups and collaborating to define their unique service and outreach needs within a larger land-grant university. Using a team-based approach, health sciences librarians are communicating to integrate research and teaching support, systems differences across dispersed campuses, and future needs of a new community-based medical program.

DISCRN: A Distributed Storytelling Framework for Intelligence Analysis

Storytelling connects entities (people, organizations) using their observed relationships to establish meaningful storylines. This can be extended to spatiotemporal storytelling that incorporates locations, time, and graph computations to enhance coherence and meaning. But when performed sequentially these computations become a bottleneck because the massive number of entities make space and time complexity untenable. This article presents DISCRN, or distributed spatiotemporal ConceptSearch-based storytelling, a distributed framework for performing spatiotemporal storytelling. The framework extracts entities from microblogs and event data, and links these entities using a novel ConceptSearch to derive storylines in a distributed fashion utilizing key-value pair paradigm. Performing these operations at scale allows deeper and broader analysis of storylines. The novel parallelization techniques speed up the generation and filtering of storylines on massive datasets. Experiments with microblog posts such as Twitter data and Global Database of Events, Language, and Tone events show the efficiency of the techniques in DISCRN.

Distributed retrieval practice promotes superior recall of anatomy information

Effortful retrieval produces greater long-term recall of information when compared to studying (i.e., reading), as do learning sessions that are distributed (i.e., spaced apart) when compared to those that are massed together. Although the retrieval and distributed practice effects are well-established in the cognitive science literature, no studies have examined their additive effect with regard to learning anatomy information. The aim of this study was to determine how the benefits of retrieval practice vary with massed versus distributed learning. Participants used the following strategies to learn sets of skeletal muscle anatomy: (1) studying on three different days over a seven day period (SSSS_7,2,0 ), (2) studying and retrieving on three different days over a seven day period (SRSR_7,2,0 ), (3) studying on two different days over a two day period (SSSSSS_2,0 ), (4) studying and retrieving on two separate days over a two day period (SRSRSR_2,0 ), and (5) studying and retrieving on one day (SRx6₀ ). All strategies consisted of 12 learning phases and lasted exactly 24 minutes. Muscle information retention was assessed via free recall and using repeated measures ANOVAs. A week after learning, the recall scores were 24.72 ± 3.12, 33.88 ± 3.48, 15.51 ± 2.48, 20.72 ± 2.94, and 12.86 ± 2.05 for the SSSS_7,2,0 , SRSR_7,2,0 , SSSSSS_2,0 , STSTST_2,0 , and SRx6₀ strategies, respectively. In conclusion, the distributed strategies produced significantly better recall than the massed strategies, the retrieval-based strategies produced significantly better recall than the studying strategies, and the combination of distributed and retrieval practice generated the greatest recall of anatomy information. Anat Sci Educ 10: 339-347. © 2016 American Association of Anatomists.

A Distributed Learning Method for ℓ 1 -Regularized Kernel Machine over Wireless Sensor Networks

In wireless sensor networks, centralized learning methods have very high communication costs and energy consumption. These are caused by the need to transmit scattered training examples from various sensor nodes to the central fusion center where a classifier or a regression machine is trained. To reduce the communication cost, a distributed learning method for a kernel machine that incorporates ℓ1 norm regularization (ℓ1-regularized) is investigated, and a novel distributed learning algorithm for the ℓ1-regularized kernel minimum mean squared error (KMSE) machine is proposed. The proposed algorithm relies on in-network processing and a collaboration that transmits the sparse model only between single-hop neighboring nodes. This paper evaluates the proposed algorithm with respect to the prediction accuracy, the sparse rate of model, the communication cost and the number of iterations on synthetic and real datasets. The simulation results show that the proposed algorithm can obtain approximately the same prediction accuracy as that obtained by the batch learning method. Moreover, it is significantly superior in terms of the sparse rate of model and communication cost, and it can converge with fewer iterations. Finally, an experiment conducted on a wireless sensor network (WSN) test platform further shows the advantages of the proposed algorithm with respect to communication cost.

At the same time or apart in time? The role of presentation timing and retrieval dynamics in generalization

Several bodies of research have found different results with regard to presentation timing, categorization, and generalization. Both presenting instances at the same time (simultaneous) and presenting instances apart in time (spacing) have been shown to facilitate generalization. In this study, we resolved these results by examining simultaneous, massed, and spaced presentations in 2-year-old children's (N = 144) immediate and long-term performance on a novel noun generalization task. Results revealed that, when tested immediately, children in the simultaneous condition outperformed children in all other conditions. However, when tested after 15 min, children in the spaced condition outperformed children in all other conditions. Results are discussed in terms of how retrieval dynamics during learning affect abstraction, retention, and generalization across time.