Trends in Development of Novel Machine Learning Methods for the Identification of Gliomas in Datasets That Include Non-Glioma Images: A Systematic Review

PurposeMachine learning has been applied to the diagnostic imaging of gliomas to augment classification, prognostication, segmentation, and treatment planning. A systematic literature review was performed to identify how machine learning has been applied to identify gliomas in datasets which include non-glioma images thereby simulating normal clinical practice.Materials and MethodsFour databases were searched by a medical librarian and confirmed by a second librarian for all articles published prior to February 1, 2021: Ovid Embase, Ovid MEDLINE, Cochrane trials (CENTRAL), and Web of Science-Core Collection. The search strategy included both keywords and controlled vocabulary combining the terms for: artificial intelligence, machine learning, deep learning, radiomics, magnetic resonance imaging, glioma, as well as related terms. The review was conducted in stepwise fashion with abstract screening, full text screening, and data extraction. Quality of reporting was assessed using TRIPOD criteria.ResultsA total of 11,727 candidate articles were identified, of which 12 articles were included in the final analysis. Studies investigated the differentiation of normal from abnormal images in datasets which include gliomas (7 articles) and the differentiation of glioma images from non-glioma or normal images (5 articles). Single institution datasets were most common (5 articles) followed by BRATS (3 articles). The median sample size was 280 patients. Algorithm testing strategies consisted of five-fold cross validation (5 articles), and the use of exclusive sets of images within the same dataset for training and for testing (7 articles). Neural networks were the most common type of algorithm (10 articles). The accuracy of algorithms ranged from 0.75 to 1.00 (median 0.96, 10 articles). Quality of reporting assessment utilizing TRIPOD criteria yielded a mean individual TRIPOD ratio of 0.50 (standard deviation 0.14, range 0.37 to 0.85).ConclusionSystematic review investigating the identification of gliomas in datasets which include non-glioma images demonstrated multiple limitations hindering the application of these algorithms to clinical practice. These included limited datasets, a lack of generalizable algorithm training and testing strategies, and poor quality of reporting. The development of more robust and heterogeneous datasets is needed for algorithm development. Future studies would benefit from using external datasets for algorithm testing as well as placing increased attention on quality of reporting standards.Systematic Review Registrationwww.crd.york.ac.uk/prospero/display_record.php?ID=CRD42020209938, International Prospective Register of Systematic Reviews (PROSPERO 2020 CRD42020209938).

The Effects of Bariatric Surgery and Gastrectomy on the Absorption of Drugs, Vitamins, and Mineral Elements

Bariatric surgery, which is an effective treatment for obesity, and gastrectomy, which is the primary treatment method for gastric cancer, alter the anatomy and physiology of the digestive system. Weight loss and changes in the gastrointestinal tract may affect the pharmacokinetic parameters of oral medications. Both bariatric and cancer patients use drugs chronically or temporarily. It is important to know how surgery affects their pharmacokinetics to ensure an effective and safe therapy. The Cochrane, PubMed, and Scopus databases were searched independently by two authors. The search strategy included controlled vocabulary and keywords. Studies show that bariatric surgery and gastrectomy most often reduce the time to maximum plasma concentration (tmax) and decrease the maximum plasma concentration (Cmax) in comparison with the values of these parameters measured in healthy volunteers. Vitamin and mineral deficiencies are also observed. The effect depends on the type of surgery and the properties of the drug. It is recommended to use the drugs that have been tested on these groups of patients as it is possible to monitor them.

National Data Sharing Policy in the Era of Open Science: A Systematic Literature Review

Research data sharing activities provide many benefits to the research ecosystem. However, in the Indonesian context, there is a lack of policy in regulating research data sharing mechanisms which makes researchers reluctant to undertake the practice of data sharing. Research funders and research institutions play a critical role in developing data-sharing policies. Research related to the policy of research data sharing is important in order to design policies to encourage the practice of research data sharing. A systematic literature review was conducted to see how data-sharing policies were formulated and implemented in various research institutions. The data were taken from Scopus and Dimension indexers using controlled vocabulary. The roles of research institutions and funders as well as policy instruments were analyzed to see patterns that occur between the parties. We examine 23 articles containing data sharing policies. it was found that the funders have the greatest role in determining the design of the data sharing policy. Funders view that research data is an asset in research funded by public funding so that the benefits must be returned to the community. Research institutes play a role as a provider of research infrastructure that contributes to data creation. Meanwhile, researchers as research actors need to provide input in developing data sharing mechanisms and regulating data sensitivity aspects and legal aspects in research data sharing.

Populating NCBI template for submissions using BioNumerics v7.6 v2

PURPOSE: to define the standard operating procedure for collecting isolate metadata using BioNumerics for submission of food/environmental isolates to NCBI. SCOPE: to provide a standardized procedure to collect isolate metadata using BioNumerics for submission of food/environmental isolates to NCBI. RESPONSIBILITIES- SOP Responsible Officials: Ruth Timme, Maria Balkey The GenomeTrakr Network Management will be responsible to monitor GenomeTrakr submissions processed through Bionumerics and ensure that all GT labs are familiar with the mandatory metadata fields required for submission of GenomeTrakr sequencing records to NCBI. V3: Dropdown menus from controlled vocabulary added to the ncbi_update submission sheet

Compassion fatigue in pediatric hematology, oncology, and bone marrow transplant healthcare providers: An integrative review

Objective Compassion fatigue (CF), which includes burnout and secondary traumatic stress, is highly prevalent among healthcare providers (HCPs). Ultimately, if left untreated, CF is often associated with absenteeism, decreased work performance, poor job satisfaction, and providers leaving their positions. To identify risk factors for developing CF and interventions to combat it in pediatric hematology, oncology, and bone marrow transplant (PHOB) HCPs. Methods An integrative review was conducted. Controlled vocabulary relevant to neoplasms, CF, pediatrics, and HCPs was used to search PubMed, Cumulative Index to Nursing and Allied Health Literature (CINAHL), PsycINFO, and Web of Science MEDLINE. Inclusion criteria were the following: English language and PHOB population. Exclusion criteria were the following: did not address question, wrong study population, mixed study population where PHOB HCPs were only part of the population, articles about moral distress as this is a similar but not the same topic as CF, conference abstracts, and book chapters. Results A total of 16 articles were reviewed: 3 qualitative, 6 quantitative, 3 mixed methods, and 4 non research. Three themes were explored: (1) high-risk populations for developing CF, (2) sources of stress in PHOB HCPs, and (3) workplace interventions to decrease CF. Significance of results PHOB HCPs are at high risk of developing CF due to high morbidity and mortality in their patient population. Various interventions, including the use of a clinical support nurse, debriefing, support groups, respite rooms, and retreats, have varying degrees of efficacy to decrease CF in this population.

Categorizing sequences of concern by function to better assess mechanisms of microbial pathogenesis

To identify sequences with a role in microbial pathogenesis, we assessed the adequacy of their annotation by existing controlled vocabularies and sequence databases. Our goal was to regularize descriptions of microbial pathogenesis for improved integration with bioinformatic applications. Here we review the challenges of annotating sequences for pathogenic activity. We relate the categorization of more than 2750 sequences of pathogenic microbes through a controlled vocabulary called Functions of Sequences of Concern (FunSoCs). These allow for an ease of description by both humans and machines. We provide a subset of 220 fully annotated sequences in the supplementary material as examples. The use of this compact (∼30 terms) controlled vocabulary has potential benefits for research in microbial genomics, public health, biosecurity, biosurveillance, and the characterization of new and emerging pathogens.

An FSKX compliant source attribution model for salmonellosis and a look at its major hidden pitfalls

To reduce the burden of human society that is caused by zoonotic diseases, it is important to attribute sources to human illnesses. One powerful approach in supporting any intervention decision is mathematical modelling. This paper presents a source attribution model which considers five sources (broilers, laying hens, pigs, turkeys) for salmonellosis and uses two datasets from Germany collected over two time periods; one from 2004 to 2007 and one from 2010 to 2011. The model uses a Bayesian modelling approach derived from the so-called Hald model and is based on microbial subtyping. In this case, Salmonella isolates from humans and animals were subtyped with respect to serovar and phage type. Based on that typing, the model estimates how many human salmonellosis cases can be attributed to each of the considered sources. A reference description of the model is available under DOI: 10.1111/zph.12645. Here, we present this model as a ready-to-use resource in the Food Safety Knowledge Exchange (FSKX) format. This open information exchange format allows to re-use, modify, and further develop the model and uses model metadata and controlled vocabulary to harmonise the annotation. In addition to the model, we discuss some technical pitfalls that might occur when running this Bayesian model based on Markov chain Monte Carlo calculations. As source attribution of zoonotic disease is one useful tool for the One Health approach, our work facilitates the exchange, adjustment, and re-usage of this source attribution model by the international and multi-sectoral community.

NIMG-35. MACHINE LEARNING GLIOMA GRADE PREDICTION LITERATURE: A TRIPOD ANALYSIS OF REPORTING QUALITY

PURPOSE Reporting guidelines are crucial in model development studies to ensure the quality, transparency and objectivity of reporting. While machine learning (ML) models have proven themselves effective in predicting glioma grade, their potential use can only be determined if they are clearly and comprehensively reported. Reporting quality has not yet been evaluated for ML glioma grade prediction studies, to our knowledge. We measured published literature against the TRIPOD Statement, a checklist of items considered essential for the reporting of diagnostic studies. MATERIALS AND METHODS A literature review, in agreement with PRISMA, was conducted by a university librarian in October 2020 and verified by a second librarian in February 2021 using four databases: Cochrane trials (CENTRAL), Ovid Embase, Ovid MEDLINE, and Web of Science core-collection. Keywords and controlled vocabulary included artificial intelligence, machine learning, deep learning, radiomics, magnetic resonance imaging, glioma, and glioblastoma. Publications were screened in Covidence and scored against the 27 items in the TRIPOD Statement that were relevant and applicable. RESULTS The search identified 11,727 candidate articles with 1,135 articles undergoing full text review. 86 articles met the criteria for our study. The mean adherence rate to TRIPOD was 44.4% (range: 22.2% - 66.7%), with poor reporting adherence in categories including abstract (0%), model performance (0%), title (1.2%), justification of sample size (2.3%), full model specification (2.3%), participant demographics and missing data (7%). Studies had high reporting adherence in categories including results interpretation (100%), background (98.8%), study design/source of data (96.5%), and objectives (95.3%). CONCLUSION Existing publications on the use of ML in glioma grade prediction have a low overall quality of reporting. Improvements can be made in the reporting of titles and abstracts, justification of sample size, and model specification and performance.

NIMG-38. MEASURING ADHERENCE TO TRIPOD OF ARTIFICIAL INTELLIGENCE PAPERS IN THE GLIOMA SEGMENTATION

PURPOSE Generalizability, reproducibility and objectivity are critical elements that need to be considered when translating machine learning models into clinical practice. While a large body of literature has been published on machine learning methods for segmentation of brain tumors, a systematic evaluation of paper quality and reproducibility has not been done. We investigated the use of “Transparent Reporting of studies on prediction models for Individual Prognosis Or Diagnosis” (TRIPOD) items, among papers published in this relatively new and growing field. METHODS According to PRISMA a literature review was performed on four databases, Ovid Embase, Ovid MEDLINE, Cochrane trials (CENTRAL) and Web of science core-collection first in October 2020 and a second time in February 2021. Keywords and controlled vocabulary included artificial intelligence, machine learning, deep learning, radiomics, magnetic resonance imaging, glioma, and glioblastoma. The publications were assessed in order to the TRIPOD items. RESULTS 37 publications from our database search were screened in TRIPOD and yielded an average score of 12.08 with the maximum score being 16 and the minimum score 7. The best scoring item was interpretation (item 19) where all papers scored a point. The lowest scoring items were the title, the abstract, risk groups and the model performance (items number 1, 2, 11 and 16), where no paper scored a point. Less than 1% of the papers discussed the problem of missing data (item 9) and the funding of research (item 22). CONCLUSION TRIPOD analysis showed that a majority of the papers do not score high on critical elements that allow reproducibility, translation, and objectivity of research. An average score of 12.08 (40%) indicates that the publications usually achieve a relatively low score. The categories that were consistently poorly described include the ML network description, measuring model performance, title details and inclusion of information into the abstract.

NIMG-23. MACHINE LEARNING METHODS IN GLIOMA GRADE PREDICTION: A SYSTEMATIC REVIEW

PURPOSE Machine learning (ML) technologies have demonstrated highly accurate prediction of glioma grade, though it is unclear which methods and algorithms are superior. We have conducted a systematic review of the literature in order to identify the ML applications most promising for future research and clinical implementation. MATERIALS AND METHODS A literature review, in agreement with PRISMA, was conducted by a university librarian in October 2020 and verified by a second librarian in February 2021 using four databases: Cochrane trials (CENTRAL), Ovid Embase, Ovid MEDLINE, and Web of Science core-collection. Keywords and controlled vocabulary included artificial intelligence, machine learning, deep learning, radiomics, magnetic resonance imaging, glioma, and glioblastoma. Screening of publications was done in Covidence, and TRIPOD was used for bias assessment. RESULTS The search identified 11,727 candidate articles with 1,135 articles undergoing full text review. 86 articles published since 1995 met the criteria for our study. 79% of the articles were published between 2018 and 2020. The average glioma prediction accuracy of the highest performing model in each study was 90% (range: 53% to 100%). The most common algorithm used for cML studies was Support Vector Machine (SVM) and for DL studies was Convolutional Neural Network (CNN). BRATS and TCIA datasets were used in 47% of the studies, with the average patient number of study datasets being 186 (range: 23 to 662). The average number of features used in machine learning prediction was 55 (range: 2 to 580). Classical machine learning (cML) was the primary machine learning model in 68% of studies, with deep learning (DL) used in 32%. CONCLUSIONS Using multimodal sequences in ML methods delivers significantly higher grading accuracies than single sequences. Potential areas of improvement for ML glioma grade prediction studies include increasing sample size, incorporating molecular subtypes, and validating on external datasets.