scholarly journals PreSS/MD: Predictor of Skin Sensitization Caused by Chemicals Leaching from Medical Devices

2022 ◽  
Author(s):  
Joyce Borba ◽  
Vinicius Alves ◽  
Rodolpho Braga ◽  
Daniel Korn ◽  
Nicole Kleinstreuer ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Devices ◽  
Model Development ◽  
Safety Evaluation ◽  
Toxicity Testing ◽  
Toxicity Assessment ◽  
Machine Learning Algorithms ◽  
International Standards ◽  
Skin Sensitization ◽  
Qsar Models

Abstract Safety evaluation for medical devices includes the toxicity assessment of chemicals used in device manufacturing, cleansing and/or sterilization that may leach into a patient. According to international standards on biocompatibility assessments (ISO 10993), chemicals that could be released from medical devices should be evaluated for their potential to induce skin sensitization/allergenicity, and one of the commonly used approaches is the guinea pig maximization test (GPMT). However, there is growing trend in regulatory science to move away from costly animal assays to employing New Approach Methodologies including computational methods. Herein, we developed a new computational tool for rapid and accurate prediction of the GPMT outcome that we named PreSS/MD (Predictor of Skin Sensitization for Medical Devices). To enable model development, we (i) collected, curated, and integrated the largest publicly available dataset for GPMT; (ii) succeeded in developing externally predictive (balanced accuracy of 70-74% as evaluated by both 5-fold external cross-validation and testing of novel compounds) Quantitative Structure-Activity Relationships (QSAR) models for GPMT using machine learning algorithms, including Deep Learning; and (iii) developed a publicly accessible web portal integrating PreSS/MD models that enables the prediction of GPMT outcomes for any molecules using. We expect that PreSS/MD will be used by both researchers and regulatory agencies to support safety assessment for medical devices and help replace, reduce or refine the use of animals in toxicity testing. PreSS/MD is freely available at https://pressmd.mml.unc.edu/. Keywords: sensitization, GPMT, QSAR, deep learning,

Use of QSAR Modeling to Predict the Carcinogenicity of Color Additives

2013 ◽  
Author(s):  
Ronald Brown ◽  
Shannon White ◽  
Jennifer Goode ◽  
Prachi Pradeep ◽  
Stephen Merrill
Keyword(s):  
Medical Devices ◽  
Safety Evaluation ◽  
Toxicity Testing ◽  
Quantitative Structure Activity Relationship ◽  
Draft Guidance ◽  
Qsar Modeling ◽  
Wide Range ◽  
Qsar Models ◽  
Us Fda ◽  
Radiological Health

Patients may be exposed to potentially carcinogenic color additives released from polymers used to manufacture medical devices; therefore, the need exists to adequately assess the safety of these compounds. The US FDA Center for Devices and Radiological Health (CDRH) recently issued draft guidance that, when final, will include FDA’s recommendations for the safety evaluation of color additives and other potentially toxic chemical entities that may be released from device materials. Specifically, the draft guidance outlines an approach that calls for evaluating the potential for the color additive to be released from the device in concert with available toxicity information about the additive to determine what types of toxicity information, if any, are necessary. However, when toxicity data are not available from the literature for the compounds of interest, a scientific rationale can sometimes be provided for omission of these tests. Although the FDA has issued draft guidance on this topic, the Agency continues to explore alternative approaches to understand when additional toxicity testing is needed to assure the safety of medical devices that contain color additives. An emerging approach that may be useful for determining the need for further testing of compounds released from device materials is Quantitative Structure Activity Relationship (QSAR) modeling. In this paper, we have shown how three publically available QSAR models (OpenTox/Lazar, Toxtree, and the OECD Toolbox) are able to successfully predict the carcinogenic potential of a set of color additives with a wide range of structures. As a result, this computational modeling approach may serve as a useful tool for determining the need to conduct carcinogenicity testing of color additives intended for use in medical devices.

Safety Evaluation of Medical Devices: US Food and Drug Administration and International Standards Organization Guidelines

1999 ◽  
Vol 18 (4) ◽  
pp. 275-283 ◽  
Author(s):  
Sharon J. Northup
Keyword(s):  
Medical Devices ◽  
Degradation Products ◽  
Blood Compatibility ◽  
Developmental Toxicity ◽  
Safety Evaluation ◽  
Chemical Characterization ◽  
Biological Evaluation ◽  
International Standards ◽  
Screening Tests ◽  
Mechanisms Of Toxicity

During the last 20 years, safety evaluation of medical devices has evolved from screening assays to the “pharmaceutical model” of preclinical testing. Biocompatibility testing guidelines for medical devices are published in the International Organization for Standardization (ISO) document 10993–1: Biological evaluation of medical devices—Part 1: Evaluation and testing. These guidelines are recognized by most national regulatory bodies and supplement, but do not supersede, the guidelines published by the individual nations or the testing requirements for a specific medical device. The ISO 10993 series includes screening tests for nonspecific mechanisms of toxicity (cytotoxicity, acute systemic toxicity, subchronic toxicity, local toxicity, and chronic toxicity) and specific mechanisms (blood compatibility, genotoxicity, carcinogenicity, pyrogenicity, and reproductive and developmental toxicity). Other ISO 10993 standards cover chemical characterization of materials, degradation products, toxicokinetics, sample preparation, permissible limits of sterilization and process residues, and clinical studies. This review examines the scope of these standards and identifies exceptions between these guidelines and selected national and vertical standards for medical devices.

A Survey of Network Embedding for Drug Analysis and Prediction

2020 ◽  
Vol 21 ◽  
Author(s):  
Zhixian Liu ◽  
Qingfeng Chen ◽  
Wei Lan ◽  
Jiahai Liang ◽  
Yiping Pheobe Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Protein Function ◽  
Dimensional Space ◽  
Auxiliary Information ◽  
Matrix Decomposition ◽  
Drug Analysis ◽  
Machine Learning Algorithms ◽  
Superior Performance ◽  
Network Embedding ◽  
Similarity Estimation

: Traditional network-based computational methods have shown good results in drug analysis and prediction. However, these methods are time consuming and lack universality, and it is difficult to exploit the auxiliary information of nodes and edges. Network embedding provides a promising way for alleviating the above problems by transforming network into a low-dimensional space while preserving network structure and auxiliary information. This thus facilitates the application of machine learning algorithms for subsequent processing. Network embedding has been introduced into drug analysis and prediction in the last few years, and has shown superior performance over traditional methods. However, there is no systematic review of this issue. This article offers a comprehensive survey of the primary network embedding methods and their applications in drug analysis and prediction. The network embedding technologies applied in homogeneous network and heterogeneous network are investigated and compared, including matrix decomposition, random walk, and deep learning. Especially, the Graph neural network (GNN) methods in deep learning are highlighted. Further, the applications of network embedding in drug similarity estimation, drug-target interaction prediction, adverse drug reactions prediction, protein function and therapeutic peptides prediction are discussed. Several future potential research directions are also discussed.

Acute and Sub-acute Oral Toxicity Assessment of a Standardized Polyherbal Preparation POL-6 in Rats

2019 ◽  
Vol 9 (3) ◽  
pp. 207-216
Author(s):  
Lalit Sharma ◽  
Aditi Sharma ◽  
Girdhari L. Gupta ◽  
Gopal Singh Bisht
Keyword(s):  
Histopathological Examination ◽  
Safety Evaluation ◽  
Centella Asiatica ◽  
Toxicity Assessment ◽  
Ocimum Sanctum ◽  
Oral Toxicity ◽  
Significant Treatment ◽  
Body Weights ◽  
Total Body ◽  
Hematobiochemical Parameters

Background: A standardized polyherbal preparation (POL-6) containing six plant extracts Hypericum perforatum, Bacopa monnieri, Centella asiatica, Withania somnifera, Ocimum sanctum and Camellia sinesis have good antioxidant, anti-inflammatory, and immunomodulatory activities. The present study was carried out to evaluate the safety profile of POL-6 through acute and subacute oral toxicity models in Wistar rats. Methods: In acute safety evaluation, a single dose of 2000mg/kg of POL-6 was given orally to five rats and was observed for 14 days. In subacute safety evaluation POL-6 at the doses of 250, 500 and 1000 mg/kg was given orally to the rats once a day for 28 days. The animals were observed for the signs of toxicity and mortality during the study period. Results: In acute toxicity evaluation, POL-6 treatment did not show any toxic signs and mortality in animals during the observation period. In subacute toxicity studies, no changes were seen in any of the dose levels of POL-6 treatment during the total body weights, organ weights and hematobiochemical parameters examination of the rats. No lesions were seen during the gross/histopathological examination. Conclusion: The study revealed that administration of POL-6 for 28 days showed no significant treatment generated toxic effects in the animals, hence it can be considered as non-toxic if it is ingested in a time not greater than a month.

scholarly journals Semantic segmentation of PolSAR image data using advanced deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rajat Garg ◽  
Anil Kumar ◽  
Nikunj Bansal ◽  
Manish Prateek ◽  
Shashi Kumar
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Urban Area ◽  
Urban Areas ◽  
Learning Algorithms ◽  
Semantic Segmentation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Deep Learning Model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

scholarly journals New Results on Radioactive Mixture Identification and Relative Count Contribution Estimation

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4155
Author(s):  
Bulent Ayhan ◽  
Chiman Kwan
Keyword(s):  
Deep Learning ◽  
Noise Source ◽  
Simulated Data ◽  
Nuclear Material ◽  
Machine Learning Algorithms ◽  
Detector Response ◽  
Nuclear Materials ◽  
Ratio Estimation ◽  
Analysis Software ◽  
Detector Distance

Detecting nuclear materials in mixtures is challenging due to low concentration, environmental factors, sensor noise, source-detector distance variations, and others. This paper presents new results on nuclear material identification and relative count contribution (also known as mixing ratio) estimation for mixtures of materials in which there are multiple isotopes present. Conventional and deep-learning-based machine learning algorithms were compared. Realistic simulated data using Gamma Detector Response and Analysis Software (GADRAS) were used in our comparative studies. It was observed that a deep learning approach is highly promising.

scholarly journals A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xiaoguo Zhang ◽  
Dawei Wang ◽  
Jiang Shao ◽  
Song Tian ◽  
Weixiong Tan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ct Images ◽  
Community Acquired Pneumonia ◽  
Machine Learning Algorithms ◽  
Multi Layer Perceptron ◽  
Selection Methods ◽  
Medical Centers ◽  
Global Pandemic ◽  
Diagnostic Time ◽  
Logistic Regression Classifier

AbstractSince its first outbreak, Coronavirus Disease 2019 (COVID-19) has been rapidly spreading worldwide and caused a global pandemic. Rapid and early detection is essential to contain COVID-19. Here, we first developed a deep learning (DL) integrated radiomics model for end-to-end identification of COVID-19 using CT scans and then validated its clinical feasibility. We retrospectively collected CT images of 386 patients (129 with COVID-19 and 257 with other community-acquired pneumonia) from three medical centers to train and externally validate the developed models. A pre-trained DL algorithm was utilized to automatically segment infected lesions (ROIs) on CT images which were used for feature extraction. Five feature selection methods and four machine learning algorithms were utilized to develop radiomics models. Trained with features selected by L1 regularized logistic regression, classifier multi-layer perceptron (MLP) demonstrated the optimal performance with AUC of 0.922 (95% CI 0.856–0.988) and 0.959 (95% CI 0.910–1.000), the same sensitivity of 0.879, and specificity of 0.900 and 0.887 on internal and external testing datasets, which was equivalent to the senior radiologist in a reader study. Additionally, diagnostic time of DL-MLP was more efficient than radiologists (38 s vs 5.15 min). With an adequate performance for identifying COVID-19, DL-MLP may help in screening of suspected cases.

scholarly journals Quantum algorithm for quicker clinical prognostic analysis: an application and experimental study using CT scan images of COVID-19 patients

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Kinshuk Sengupta ◽  
Praveen Ranjan Srivastava
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Image Classification ◽  
Machine Learning Algorithms ◽  
Classification Task ◽  
Clinical Image ◽  
Prototype Model ◽  
Learning Models ◽  
Accuracy Measure ◽  
Quantum Machine Learning

Abstract Background In medical diagnosis and clinical practice, diagnosing a disease early is crucial for accurate treatment, lessening the stress on the healthcare system. In medical imaging research, image processing techniques tend to be vital in analyzing and resolving diseases with a high degree of accuracy. This paper establishes a new image classification and segmentation method through simulation techniques, conducted over images of COVID-19 patients in India, introducing the use of Quantum Machine Learning (QML) in medical practice. Methods This study establishes a prototype model for classifying COVID-19, comparing it with non-COVID pneumonia signals in Computed tomography (CT) images. The simulation work evaluates the usage of quantum machine learning algorithms, while assessing the efficacy for deep learning models for image classification problems, and thereby establishes performance quality that is required for improved prediction rate when dealing with complex clinical image data exhibiting high biases. Results The study considers a novel algorithmic implementation leveraging quantum neural network (QNN). The proposed model outperformed the conventional deep learning models for specific classification task. The performance was evident because of the efficiency of quantum simulation and faster convergence property solving for an optimization problem for network training particularly for large-scale biased image classification task. The model run-time observed on quantum optimized hardware was 52 min, while on K80 GPU hardware it was 1 h 30 min for similar sample size. The simulation shows that QNN outperforms DNN, CNN, 2D CNN by more than 2.92% in gain in accuracy measure with an average recall of around 97.7%. Conclusion The results suggest that quantum neural networks outperform in COVID-19 traits’ classification task, comparing to deep learning w.r.t model efficacy and training time. However, a further study needs to be conducted to evaluate implementation scenarios by integrating the model within medical devices.

Sign in / Sign up

Export Citation Format

Share Document