Pilot deployment of a cloud-based universal medical image repository in a large public health system: A protocol study.
Ontology highlight
ABSTRACT:
SUBMITTER: Pacheco VMG
PROVIDER: S-EPMC11361589 | biostudies-literature | 2024
REPOSITORIES: biostudies-literature
Publications
Pilot deployment of a cloud-based universal medical image repository in a large public health system: A protocol study.
Pacheco Viviane Margarida Gomes VMG Paiva Joselisa Peres Queiroz JPQ Furriel Brunna Carolinne Rocha Silva BCRS Santos Paulo Victor PV Ferreira Junior José Raniery JR Reis Marcio Rodrigues Cunha MRC Tornieri Daniel D Ribeiro Guilherme Alberto Sousa GAS Silva Luan Oliveira LO Nogueira Solange Amorim SA Loureiro Rafael Maffei RM Calixto Wesley Pacheco WP
PloS one 20240829 8
This paper outlines the protocol for the deployment of a cloud-based universal medical image repository system. The proposal aims not only at the deployment but also at the automatic expansion of the platform, incorporating Artificial Intelligence (AI) for the analysis of medical image examinations. The methodology encompasses efficient data management through a universal database, along with the deployment of various AI models designed to assist in diagnostic decision-making. By presenting this ...[more]
Similar Datasets
Project description:Cloud computing has pioneered the emerging world by manifesting itself as a service through internet and facilitates third party infrastructure and applications. While customers have no visibility on how their data is stored on service provider's premises, it offers greater benefits in lowering infrastructure costs and delivering more flexibility and simplicity in managing private data. The opportunity to use cloud services on pay-per-use basis provides comfort for private data owners in managing costs and data. With the pervasive usage of internet, the focus has now shifted towards effective data utilization on the cloud without compromising security concerns. In the pursuit of increasing data utilization on public cloud storage, the key is to make effective data access through several fuzzy searching techniques. In this paper, we have discussed the existing fuzzy searching techniques and focused on reducing the searching time on the cloud storage server for effective data utilization. Our proposed Asymmetric Classifier Multikeyword Fuzzy Search method provides classifier search server that creates universal keyword classifier for the multiple keyword request which greatly reduces the searching time by learning the search path pattern for all the keywords in the fuzzy keyword set. The objective of using BTree fuzzy searchable index is to resolve typos and representation inconsistencies and also to facilitate effective data utilization.
| S-EPMC4562092 | biostudies-other
Project description:BackgroundDeep neural networks (DNNs) are widely investigated in medical image classification to achieve automated support for clinical diagnosis. It is necessary to evaluate the robustness of medical DNN tasks against adversarial attacks, as high-stake decision-making will be made based on the diagnosis. Several previous studies have considered simple adversarial attacks. However, the vulnerability of DNNs to more realistic and higher risk attacks, such as universal adversarial perturbation (UAP), which is a single perturbation that can induce DNN failure in most classification tasks has not been evaluated yet.MethodsWe focus on three representative DNN-based medical image classification tasks (i.e., skin cancer, referable diabetic retinopathy, and pneumonia classifications) and investigate their vulnerability to the seven model architectures of UAPs.ResultsWe demonstrate that DNNs are vulnerable to both nontargeted UAPs, which cause a task failure resulting in an input being assigned an incorrect class, and to targeted UAPs, which cause the DNN to classify an input into a specific class. The almost imperceptible UAPs achieved > 80% success rates for nontargeted and targeted attacks. The vulnerability to UAPs depended very little on the model architecture. Moreover, we discovered that adversarial retraining, which is known to be an effective method for adversarial defenses, increased DNNs' robustness against UAPs in only very few cases.ConclusionUnlike previous assumptions, the results indicate that DNN-based clinical diagnosis is easier to deceive because of adversarial attacks. Adversaries can cause failed diagnoses at lower costs (e.g., without consideration of data distribution); moreover, they can affect the diagnosis. The effects of adversarial defenses may not be limited. Our findings emphasize that more careful consideration is required in developing DNNs for medical imaging and their practical applications.
| S-EPMC7792111 | biostudies-literature
Project description:IntroductionThe epidemic of opioid use disorder and opioid overdose carries extensive morbidity and mortality and necessitates a multi-pronged, community-level response. Bystander administration of the opioid overdose antidote naloxone is effective, but it is not universally available and requires consistent effort on the part of citizens to proactively carry naloxone. An alternate approach would be to position naloxone kits where they are most needed in a community, in a manner analogous to automated external defibrillators. We hypothesized that opioid overdoses would show geospatial clustering within a community, leading to potential target sites for such publicly deployed naloxone (PDN).MethodsWe performed a retrospective chart review of 700 emergency medical service (EMS) runs that involved opioid overdose or naloxone administration in Cambridge, Massachusetts, between October 16, 2016 and May 10, 2017. We used geospatial analysis to examine for clustering in general, and to identify specific clusters amenable to PDN sites.ResultsOpioid-related emergency medical services (EMS) runs in Cambridge, Massachusetts (MA), exhibit significant geospatial clustering, and we identified three clusters of opioid-related EMS runs in Cambridge, MA, with distinct characteristics. Models of PDN sites at these clusters show that approximately 40% of all opioid-related EMS runs in Cambridge, MA, would be accessible within 200 meters of PDN sites placed at cluster centroids.ConclusionIdentifying clusters of opioid-related EMS runs within a community may help to improve community coverage of naloxone, and strongly suggests that PDN could be a useful adjunct to bystander-administered naloxone in stemming the tide of opioid-related death.
| S-EPMC6040905 | biostudies-literature
Project description:ObjectivesArtificial intelligence (AI) holds great promise for transforming the healthcare industry. However, despite its potential, AI is yet to see widespread deployment in clinical settings in significant part due to the lack of publicly available clinical data and the lack of transparency in the published AI algorithms. There are few clinical data repositories publicly accessible to researchers to train and test AI algorithms, and even fewer that contain specialized data from the perioperative setting. To address this gap, we present and release the Medical Informatics Operating Room Vitals and Events Repository (MOVER).Materials and methodsThis first release of MOVER includes adult patients who underwent surgery at the University of California, Irvine Medical Center from 2015 to 2022. Data for patients who underwent surgery were captured from 2 different sources: High-fidelity physiological waveforms from all of the operating rooms were captured in real time and matched with electronic medical record data.ResultsMOVER includes data from 58 799 unique patients and 83 468 surgeries. MOVER is available for download at https://doi.org/10.24432/C5VS5G, it can be downloaded by anyone who signs a data usage agreement (DUA), to restrict traffic to legitimate researchers.DiscussionTo the best of our knowledge MOVER is the only freely available public data repository that contains electronic health record and high-fidelity physiological waveforms data for patients undergoing surgery.ConclusionMOVER is freely available to all researchers who sign a DUA, and we hope that it will accelerate the integration of AI into healthcare settings, ultimately leading to improved patient outcomes.
| S-EPMC10582520 | biostudies-literature
Project description:BackgroundCloud computing is a unique paradigm that is aggregating resources available from cloud service providers for use by customers on demand and pay per use basis. There is a Cloud federation that integrates the four primary Cloud models and the Cloud aggregator that integrates multiple computing services. A systematic mapping study provides an overview of work done in a particular field of interest and identifies gaps for further research.ObjectivesThe objective of this paper was to conduct a study of deployment and designs models for Cloud using a systematic mapping process. The methodology involves examining core aspect of the field of study using the research, contribution and topic facets.ResultsThe results obtained indicated that there were more publications on solution proposals, which constituted 41.98% of papers relating to design and deployment models on the Cloud. Out of this, 5.34% was on security, 1.5% on privacy, 6.11% on configuration, 7.63% on implementation, 11.45% on service deployment, and 9.92% of the solution proposal was on design. The results obtained will be useful for further studies by the academia and industry in this broad topic that was examined.
| S-EPMC6642572 | biostudies-literature
Project description:The spot instance model is a virtual machine pricing scheme in which some resources of cloud providers are offered to the highest bidder. This leads to the formation of a spot price, whose fluctuations can determine customers to be overbid by other users and lose the virtual machine they rented. In this paper we propose OptiSpot, a heuristic to automate application deployment decisions on cloud providers that offer the spot pricing model. In particular, with our approach it is possible to determine: (i) which and how many resources to rent in order to run a cloud application, (ii) how to map the application components to the rented resources, and (iii) what spot price bids to use to minimize the total cost while maintaining an acceptable level of performance. To drive the decision making, our algorithm combines a multi-class queueing network model of the application with a Markov model that describes the stochastic evolution of the spot price and its influence on virtual machine reliability. We show, using a model developed for a real enterprise application and historical traces of the Amazon EC2 spot instance prices, that our heuristic finds low cost solutions that indeed guarantee the required levels of performance. The performance of our heuristic method is compared to that of nonlinear programming and shown to markedly accelerate the finding of low-cost optimal solutions.
| S-EPMC6959408 | biostudies-literature
Project description:To bring the quantum computing capacities to the personal edge devices, the optimum approach is to have simple non-error-corrected personal devices that offload the computational tasks to scalable quantum computers via edge servers with cryogenic components and fault-tolerant schemes. Hence the network elements deploy different encoding protocols. This article proposes quantum terminals that are compatible with different encoding protocols; paving the way for realizing mobile edge-quantum computing. By accommodating the atomic lattice processor inside a cavity, the entangling mechanism is provided by the Rydberg cavity-QED technology. The auxiliary atom, responsible for photon emission, senses the logical qubit state via the long-range Rydberg interaction. In other words, the state of logical qubit determines the interaction-induced level-shift at the central atom and hence derives the system over distinguished eigenstates, featuring photon emission at the early or late times controlled by quantum interference. Applying an entanglement-swapping gate on two emitted photons would make the far-separated logical qubits entangled regardless of their encoding protocols. The proposed scheme provides a universal photonic interface for clustering the processors and connecting them with the quantum memories and quantum cloud compatible with different encoding formats.
| S-EPMC11224409 | biostudies-literature
Project description:BackgroundSkin cancer diagnostics is challenging, and mastery requires extended periods of dedicated practice.ObjectiveThe aim of the study was to determine if self-paced pattern recognition training in skin cancer diagnostics with clinical and dermoscopic images of skin lesions using a large-scale interactive image repository (LIIR) with patient cases improves primary care physicians' (PCPs') diagnostic skills and confidence.MethodsA total of 115 PCPs were randomized (allocation ratio 3:1) to receive or not receive self-paced pattern recognition training in skin cancer diagnostics using an LIIR with patient cases through a quiz-based smartphone app during an 8-day period. The participants' ability to diagnose skin cancer was evaluated using a 12-item multiple-choice questionnaire prior to and 8 days after the educational intervention period. Their thoughts on the use of dermoscopy were assessed using a study-specific questionnaire. A learning curve was calculated through the analysis of data from the mobile app.ResultsOn average, participants in the intervention group spent 2 hours 26 minutes quizzing digital patient cases and 41 minutes reading the educational material. They had an average preintervention multiple choice questionnaire score of 52.0% of correct answers, which increased to 66.4% on the postintervention test; a statistically significant improvement of 14.3 percentage points (P<.001; 95% CI 9.8-18.9) with intention-to-treat analysis. Analysis of participants who received the intervention as per protocol (500 patient cases in 8 days) showed an average increase of 16.7 percentage points (P<.001; 95% CI 11.3-22.0) from 53.9% to 70.5%. Their overall ability to correctly recognize malignant lesions in the LIIR patient cases improved over the intervention period by 6.6 percentage points from 67.1% (95% CI 65.2-69.3) to 73.7% (95% CI 72.5-75.0) and their ability to set the correct diagnosis improved by 10.5 percentage points from 42.5% (95% CI 40.2%-44.8%) to 53.0% (95% CI 51.3-54.9). The diagnostic confidence of participants in the intervention group increased on a scale from 1 to 4 by 32.9% from 1.6 to 2.1 (P<.001). Participants in the control group did not increase their postintervention score or their diagnostic confidence during the same period.ConclusionsSelf-paced pattern recognition training in skin cancer diagnostics through the use of a digital LIIR with patient cases delivered by a quiz-based mobile app improves the diagnostic accuracy of PCPs.Trial registrationClinicalTrials.gov NCT05661370; https://classic.clinicaltrials.gov/ct2/show/NCT05661370.
| S-EPMC10448292 | biostudies-literature
Project description:BACKGROUND:Long-term management of Parkinson's disease does not reach its full potential because we lack knowledge about individual variations in clinical presentation and disease progression. Continuous and longitudinal assessments in real-life (ie, within the patients' own home environment) might fill this knowledge gap. OBJECTIVE:The primary aim of the Parkinson@Home study is to evaluate the feasibility and compliance of using multiple wearable sensors to collect clinically relevant data. Our second aim is to address the usability of these data for answering clinical research questions. Finally, we aim to build a database for future validation of novel algorithms applied to sensor-derived data from Parkinson's patients during daily functioning. METHODS:The Parkinson@Home study is a two-phase observational study involving 1000 Parkinson's patients and 250 physiotherapists. Disease status is assessed using a short version of the Parkinson's Progression Markers Initiative protocol, performed by certified physiotherapists. Additionally, participants will wear a set of sensors (smartwatch, smartphone, and fall detector), and use these together with a customized smartphone app (Fox Insight), 24/7 for 3 months. The sensors embedded within the smartwatch and fall detector may be used to estimate physical activity, tremor, sleep quality, and falls. Medication intake and fall incidents will be measured via patients' self-reports in the smartphone app. Phase one will address the feasibility of the study protocol. In phase two, mathematicians will distill relevant summary statistics from the raw sensor signals, which will be compared against the clinical outcomes. RESULTS:Recruitment of 300 participants for phase one was concluded in March, 2016, and the follow-up period will end in June, 2016. Phase two will include the remaining participants, and will commence in September, 2016. CONCLUSIONS:The Parkinson@Home study is expected to generate new insights into the feasibility of integrating self-collected information from wearable sensors into both daily routines and clinical practices for Parkinson's patients. This study represents an important step towards building a reliable system that translates and integrates real-life information into clinical decisions, with the long-term aim of delivering personalized disease management support. CLINICALTRIAL:ClinicalTrials.gov NCT02474329; https://clinicaltrials.gov/ct2/show/NCT02474329 (Archived at http://www.webcitation.org/6joEc5P1v).
| S-EPMC5018102 | biostudies-literature
Project description:IntroductionExposure to poor environmental conditions has been associated with deterioration of physical and mental health, and with reduction of cognitive performance. Environmental conditions may also influence cognitive development of children, but epidemiological evidence is scant. In developed countries, children spend 930 hours per year in a classroom, second only to time spent in their bedroom. Using continuous sensing technology, we investigate the relationship between indoor environmental quality (IEQ) and cognitive performance of school-aged children. The proposed study will result in a better understanding of the effects of environmental characteristics on cognitive performance, thereby paving the way for experimental studies.Methods and analysisA study protocol is presented to reliably measure IEQ in schools. We will monitor the IEQ of 280 classrooms for 5 years, covering approximately 10 000 children. Each classroom in the sample is permanently equipped with a sensor measuring air quality (carbon dioxide and coarse particles), temperature, relative humidity, light intensity and noise levels, all at 1 min intervals. The location of sensing equipment within and across rooms has been validated by a pilot study. Academic performance of school-aged children is measured through standardised cognitive tests. In addition, a series of health indicators is collected (eg, school absence and demand for healthcare), together with an extensive set of sociodemographic characteristics (eg, parental income, education, occupational status).Ethics and disseminationMedical Ethical Approval for the current study was waived by the Medical Ethical Committee azM/UM (METC 2018-0681). In addition, data on student performance and health stems from an already existing data infrastructure that are granted with ethical approval by the Ethical Review Committee Inner City faculties (ERCIC_092_12_07_2018). Health data are obtained from the 'The Healthy Primary School of the Future' (HPSF) project. Medical Ethical Approval for HPSF was waived by the Medical Ethical Committee of Zuyderland, Heerlen (METC 14 N-142). The HPSF study protocol was registered in the database ClinicalTrials.gov on 14-06-2016 with reference number NCT02800616, this study is currently in the Results stage. Data collection from Gemeentelijke Gezondheidsdienst Zuid-Limburg (GGD-ZL) is executed by researchers of HPSF, this procedure has been fully approved by the Medical Ethical Committee of Zuyderland. The questionnaires on level of comfort will be filled in anonymously by students and teachers. The study will follow the EU General Data Protection Regulation (EU GDPR) and Dutch data protection law to ensure protection of personal data, as well as maintain proper data management and anonymisation.The protocol discussed in this paper includes significant efforts focused on integrating results and making them available to both the scientific community and the wider public, including policy makers. The results will lead to multiple scientific articles that will be disseminated through peer-reviewed international journals, as well as through conference presentations. In addition, we will exploit ongoing collaboration with project stakeholders and project partners to disseminate information to the target audience. For example, the results will be presented to school boards in the Netherlands, through engagement with the Coalition for Green Schools, as well as to school boards in USA, through engagement with the Center for Green Schools.Trial registration numberNCT02800616; Results.
| S-EPMC7076238 | biostudies-literature