17 results
314 Large Language Model Approaches to Understand Differences Between Guidelines and Clinician Perception of Best Practices
- Part of
- Carrie E. Gold, Jorie M. Butler, Ithan D. Peltan, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 8 / Issue s1 / April 2024
- Published online by Cambridge University Press:
- 03 April 2024, pp. 96-97
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/GOALS: The Clinical Implementation stage in the translational pipeline is hampered by the tension between formal evidence and clinician perceptions. For instance, when guidelines are translated into electronic clinical decision support alerts, they are often ignored. Using advances in LLMs we present a framework to quantify these discrepancies. METHODS/STUDY POPULATION: We hypothesize that ignoring guideline-based alerts may be driven by discordances between clinical guidelines’ deterministic realities and clinician’ perception of clinical reality. Until now this has been very difficult to measure using quantitative methods. We argue that advances in Large Language Models (LLM) provide an avenue for exploring this quantitatively. Here we present the method and preliminary results comparing the responses of BioBERTT from a carefully designed set of questions when the LLM is fine-tuned using either formal guidelines or transcripts of clinicians discussing guidelines and clinical care in the parallel domain. The formal “distance” between the LLM responses is evaluated using quantitative metrics like the Hamming Distance. RESULTS/ANTICIPATED RESULTS: We present a description of the architecture used to prove or disprove our hypothesis. We will present results obtained when training the architecture with data that could be used to test the limits of our hypothesis, by fine-tuning BioBERT with diverse synthetic clinical views, either in agreement or disagreement with the formal guidelines. Results comparing sepsis guideline text with transcripts of interviews with Emergency Department clinicians discussing care practices for sepsis in the ED transcripts will also be considered. Our current emphasis is on securing a wider range of transcripts of clinicians interviewed from different clinical specialties and different clinical settings. While here we focus on clinical guidelines, the framework supports any intervention in the Clinical Implementation stage. DISCUSSION/SIGNIFICANCE: Leveraging recent advances in LLMs, we develop a framework that can quantitatively measure the differences between guidelines and clinician perception of best practices. We demonstrated the functionality of this approach using synthetic data and initiated the collection of clinician transcripts to test the framework in real clinical situations.
297 Identifying Opportunities and Challenges for Translational Informatics Approaches to Real-World Data: A Diabetes Case Study
- Part of
- Sejal Mistry, Ramkiran Gouripeddi, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 7 / Issue s1 / April 2023
- Published online by Cambridge University Press:
- 24 April 2023, p. 89
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/GOALS: Diabetes is a group of chronic metabolic diseases and significant gaps remain in our understanding of disease etiology, treatment regimens, and diabetes-related complications. The objective of study is to demonstrate how informatics techniques can leverage real-world data for diabetes research and identify barriers for implementation. METHODS/STUDY POPULATION: We evaluated informatics applications of real-world data in diabetes research conducted by the Facelli Research Group. The types of real-world data were categorized into clinical records, diabetes-related repositories, wearable sensors, and other data sources. Translational informatics applications were characterized into thematic groups of 1.) use of electronic health records, registries, and claims and other data sources to generate real-world evidence, 2.) evolution of novel methods to accelerate generation and use of real-world data, and 3.) infrastructure to support the generation and use of real-world data in translational science. A literature review is being conducted to identify additional articles meeting these themes focused on diabetes research. RESULTS/ANTICIPATED RESULTS: 6 research projects were included for analysis. The diabetes-focus spanned type 1 diabetes, type 2 diabetes, and general diabetes mellitus. Informatics methods included machine learning and data mining while real-world data sources included electronic medical records, the Environmental Determinants of Diabetes in the Young (TEDDY) study, continuous glucose monitors, and the U.S. Environmental Protection Agency (EPA) air pollution monitors. Overall, computability of real-world data, linkage of medical concepts to standardized terminologies, volume of data, and adoption of novel artificial intelligence methods were major determinants of successful implementation. Future work will systematically evaluate informatics applications of real-world data in diabetes from the academic community at large. DISCUSSION/SIGNIFICANCE: Translational informatics approaches are poised to leverage real-world data and better understand diabetes etiology, treatment regimens, and diabetes-related complications. By understanding barriers and opportunities for informatics methods, we can expedite translational applications in diabetes research.
73432 Assessment of multi-pollutant ambient air composition on type 2 diabetes mellitus using machine learning.
- Naomi Oiwa Riches, Ramkiran Gouripeddi, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 5 / Issue s1 / March 2021
- Published online by Cambridge University Press:
- 30 March 2021, p. 46
-
- Article
-
- You have access Access
- Open access
- Export citation
-
ABSTRACT IMPACT: We explored the use of machine learning to explore how multi-pollutant air quality is related to type 2 diabetes, which is more representative than the single pollutant models often employed to assess this relationship. OBJECTIVES/GOALS: Single pollutant air pollution models have correlated air pollution components with type 2 diabetes mellitus (DM). However, air pollution is a complex mixture, therefore, we explored the relationship between multi-pollutant air quality and DM incidence using machine learning. METHODS/STUDY POPULATION: Annual diabetes incidence from the CDC for each US county was downloaded for the years 2007-2016. Daily air pollution concentrations for PM2.5, PM10, CO, SO2, NO2, and O3 were downloaded from the US EPA for the years 2006-2015. K-means clustering, an unsupervised machine learning method, was employed to partition all air pollution components, for each day and county monitored, into the optimal number of clusters. Change in DM incidence was matched to air pollution clusters by county, lagged by one year. Additionally, NASA satellite-derived air pollution data will be compared to EPA data to inspect as a potential source for future clustering analysis of counties that do not have an EPA monitor. RESULTS/ANTICIPATED RESULTS: The largest increase of annual DM incidence was associated with the cluster having the highest average PM10, PM2.5, and CO, and the second greatest average NO2 concentrations. Inversely, the most significant decrease of annual DM incidence was associated with the cluster having the lowest PM10, PM2.5, and CO. While average PM10, PM2.5, SO2, NO2, and CO showed a rising tendency with elevating change of DM incidence, ozone did not show any such trend. It is anticipated that the NASA satellite-derived air pollution data will approximate the EPA air quality data and will be usable in assessing the air pollution-DM relationship for areas currently not monitored by the EPA. DISCUSSION/SIGNIFICANCE OF FINDINGS: Using an unsupervised k-means algorithm, we showed multiple ambient air components were related to increased incidence of T2DM even when average concentrations were below the National Ambient Air Quality Standards. This work could help guide policy making regarding air quality standards in the future.
27337 Characterizing Temporal Patterns in Glucose Dysregulation Following SARS-CoV-2 Infection
- Sejal Mistry, Ramkiran Gouripeddi, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 5 / Issue s1 / March 2021
- Published online by Cambridge University Press:
- 30 March 2021, p. 46
-
- Article
-
- You have access Access
- Open access
- Export citation
-
ABSTRACT IMPACT: Understanding the longitudinal glucose changes following SARS-CoV-2 infection can inform point-of-care guidelines and elucidate the viral hypothesis of diabetes mellitus pathogenesis. OBJECTIVES/GOALS: Hyperglycemia has emerged as an important manifestation of SARS-CoV-2 infection in both diabetic and non-diabetic patients. Whether clinically-detectable glycemic changes persist following SARS-CoV-2 infection remain to be elucidated. This work aims to characterize temporal patterns in glucose dysregulation following SARS-CoV-2 infection. METHODS/STUDY POPULATION: Electronic health records of patients with a diagnosis of COVID-19, positive laboratory test for SARS-CoV-2, and negative history of Diabetes Mellitus prior to infection were extracted from the TriNetX database. 7,502 patients with at least one blood glucose value 2 years to 2 weeks before, 2 weeks before to 2 weeks after, and 2 weeks after to 1 year after COVID-19 diagnosis were used for analysis. Temporal patterns are characterized by training state-of-the-art clustering algorithms, including fuzzy short time-series clustering, k-means for longitudinal data, and spectral clustering. Clustering performance is evaluated using internal evaluation metrics of the Silhouette coefficient, Calinski-Harabasz score, and Davies Bouldin index. RESULTS/ANTICIPATED RESULTS: Based on the success of prior clustering methods with random blood glucose measurements, we anticipate that the proposed time-series clustering algorithms will appropriately characterize temporal patterns of glycemic dysregulation. The best performing algorithm based on interval evaluation metrics will be selected for further analysis. Associations between blood glucose values and cluster membership will be evaluated using Kruskal-Wallis one-way ANOVA and effect size will be calculated using unbiased Cohen’s d. Clinical phenotypes for each cluster will be characterized in terms of current diagnoses, prior medication use, pertinent laboratory tests, and vital signs. DISCUSSION/SIGNIFICANCE OF FINDINGS: A clearer understanding of the longitudinal glucose changes following SARS-CoV-2 infection can elucidate clinically-detectable patterns of glycemic dysregulation, identify sub-phenotypes of patients who are more susceptive to glycemic dysregulation, and inform appropriate point-of-care guidelines.
Using supervised machine learning classifiers to estimate likelihood of participating in clinical trials of a de-identified version of ResearchMatch
- Janette Vazquez, Samir Abdelrahman, Loretta M. Byrne, Michael Russell, Paul Harris, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 5 / Issue 1 / 2021
- Published online by Cambridge University Press:
- 04 September 2020, e42
-
- Article
-
- You have access Access
- Open access
- HTML
- Export citation
-
Introduction:
Lack of participation in clinical trials (CTs) is a major barrier for the evaluation of new pharmaceuticals and devices. Here we report the results of the analysis of a dataset from ResearchMatch, an online clinical registry, using supervised machine learning approaches and a deep learning approach to discover characteristics of individuals more likely to show an interest in participating in CTs.
Methods:We trained six supervised machine learning classifiers (Logistic Regression (LR), Decision Tree (DT), Gaussian Naïve Bayes (GNB), K-Nearest Neighbor Classifier (KNC), Adaboost Classifier (ABC) and a Random Forest Classifier (RFC)), as well as a deep learning method, Convolutional Neural Network (CNN), using a dataset of 841,377 instances and 20 features, including demographic data, geographic constraints, medical conditions and ResearchMatch visit history. Our outcome variable consisted of responses showing specific participant interest when presented with specific clinical trial opportunity invitations (‘yes’ or ‘no’). Furthermore, we created four subsets from this dataset based on top self-reported medical conditions and gender, which were separately analysed.
Results:The deep learning model outperformed the machine learning classifiers, achieving an area under the curve (AUC) of 0.8105.
Conclusions:The results show sufficient evidence that there are meaningful correlations amongst predictor variables and outcome variable in the datasets analysed using the supervised machine learning classifiers. These approaches show promise in identifying individuals who may be more likely to participate when offered an opportunity for a clinical trial.
4549 Reproducible Informatics for Reproducible Translational Research
- Ram Gouripeddi, Katherine Sward, Mollie Cummins, Karen Eilbeck, Bernie LaSalle, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 4 / Issue s1 / June 2020
- Published online by Cambridge University Press:
- 29 July 2020, pp. 66-67
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/GOALS: Characterize formal informatics methods and approaches for enabling reproducible translational research. Education of reproducible methods to translational researchers and informaticians. METHODS/STUDY POPULATION: We performed a scoping review [1] of selected informatics literature (e.g. [2,3]) from PubMed and Scopus. In addition we reviewed literature and documentation of translational research informatics projects [4–21] at the University of Utah. RESULTS/ANTICIPATED RESULTS: The example informatics projects we identified in our literature covered a broad spectrum of translational research. These include research recruitment, research data requisition, study design and statistical analysis, biomedical vocabularies and metadata for data integration, data provenance and quality, and uncertainty. Elements impacting reproducibility of research include (1) Research Data: its semantics, quality, metadata and provenance; and (2) Research Processes: study conduct including activities and interventions undertaken, collections of biospecimens and data, and data integration. The informatics methods and approaches we identified as enablers of reproducibility include the use of templates, management of workflows and processes, scalable methods for managing data, metadata and semantics, appropriate software architectures and containerization, convergence methods and uncertainty quantification. In addition these methods need to be open and shareable and should be quantifiable to measure their ability to achieve reproducibility. DISCUSSION/SIGNIFICANCE OF IMPACT: The ability to collect large volumes of data collection has ballooned in nearly every area of science, while the ability to capturing research processes hasn’t kept with this pace. Potential for problematic research practices and irreproducible results are concerns.
Reproducibility is a core essentially of translational research. Translational research informatics provides methods and means for enabling reproducibility and FAIRness [22] in translational research. In addition there is a need for translational informatics itself to be reproducible to make research reproducible so that methods developed for one study or biomedical domain can be applied elsewhere. Such informatics research and development requires a mindset for meta-research [23].
The informatics methods we identified covers the spectrum of reproducibility (computational, empirical and statistical) and across different levels of reproducibility (reviewable, replicable, confirmable, auditable, and open or complete) [24–29]. While there are existing and ongoing efforts in developing informatics methods for translational research reproducibility in Utah and elsewhere, there is a need to further develop formal informatics methods and approaches: the Informatics of Research Reproducibility.
In this presentation, we summarize the studies and literature we identified and discuss our key findings and gaps in informatics methods for research reproducibility. We conclude by discussing how we are covering these topics in a translational research informatics course.
1. Pham MT, Rajić A, Greig JD, Sargeant JM, Papadopoulos A, McEwen SA. A scoping review of scoping reviews: advancing the approach and enhancing the consistency. Res Synth Methods. 2014 Dec;5(4):371–85.
2. McIntosh LD, Juehne A, Vitale CRH, Liu X, Alcoser R, Lukas JC, Evanoff B. Repeat: a framework to assess empirical reproducibility in biomedical research. BMC Med Res Methodol [Internet]. 2017 Sep 18 [cited 2018 Nov 30];17. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5604503/
3. Denaxas S, Direk K, Gonzalez-Izquierdo A, Pikoula M, Cakiroglu A, Moore J, Hemingway H, Smeeth L. Methods for enhancing the reproducibility of biomedical research findings using electronic health records. BioData Min. 2017;10:31.
4. Burnett N, Gouripeddi R, Wen J, Mo P, Madsen R, Butcher R, Sward K, Facelli JC. Harmonization of Sensor Metadata and Measurements to Support Exposomic Research. In: 2016 International Society of Exposure Science [Internet]. Research Triangle Park, NC, USA; 2017 [cited 2017 Jun 17]. Available from: http://www.intlexposurescience.org/ISES2017
5. Butcher R, Gouripeddi RK, Madsen R, Mo P, LaSalle B. CCTS Biomedical Informatics Core Research Data Service. In Salt Lake City; 2016.
6. Cummins M, Gouripeddi R, Facelli J. A low-cost, low-barrier clinical trials registry to support effective recruitment. In Salt Lake City, Utah, USA; 2016 [cited 2018 Nov 30]. Available from: //campusguides.lib.utah.edu/UtahRR16/abstracts
7. Gouripeddi R, Warner P, Madsen R, Mo P, Burnett N, Wen J, Lund A, Butcher R, Cummins MR, Facelli J, Sward K. An Infrastructure for Reproducibile Exposomic Research. In: Research Reproducibility 2016 [Internet]. Salt Lake City, Utah, USA; 2016 [cited 2018 Nov 30]. Available from: //campusguides.lib.utah.edu/UtahRR16/abstracts
8. Eilbeck K, Lewis SE, Mungall CJ, Yandell M, Stein L, Durbin R, Ashburner M. The Sequence Ontology: a tool for the unification of genome annotations. Genome Biol. 2005;6:R44.
9. Gouripeddi R, Cummins M, Madsen R, LaSalle B, Redd AM, Presson AP, Ye X, Facelli JC, Green T, Harper S. Streamlining study design and statistical analysis for quality improvement and research reproducibility. J Clin Transl Sci. 2017 Sep;1(S1):18–9.
10. Gouripeddi R, Eilbeck K, Cummins M, Sward K, LaSalle B, Peterson K, Madsen R, Warner P, Dere W, Facelli JC. A Conceptual Architecture for Reproducible On-demand Data Integration for Complex Diseases. In: Research Reproducibility 2016 (UtahRR16) [Internet]. Salt Lake City, Utah, USA; 2016 [cited 2017 Apr 25]. Available from: https://zenodo.org/record/168067
11. Gouripeddi R, Lane E, Madsen R, Butcher R, LaSalle B, Sward K, Fritz J, Facelli JC, Cummins M, Shao J, Singleton R. Towards a scalable informatics platform for enhancing accrual into clinical research studies. J Clin Transl Sci. 2017 Sep;1(S1):20–20.
12. Gouripeddi R, Deka R, Reese T, Butcher R, Martin B, Talbert J, LaSalle B, Facelli J, Brixner D. Reproducibility of Electronic Health Record Research Data Requests. In Washington, DC, USA; 2018 [cited 2018 Apr 21]. Available from: https://zenodo.org/record/1226602#.WtvvyZch270
13. Gouripeddi R, Mo P, Madsen R, Warner P, Butcher R, Wen J, Shao J, Burnett N, Rajan NS, LaSalle B, Facelli JC. A Framework for Metadata Management and Automated Discovery for Heterogeneous Data Integration. In: 2016 BD2K All Hands Meeting [Internet]. Bethesda, MD; November 29-30 [cited 2017 Apr 25]. Available from: https://zenodo.org/record/167885
14. Groat D, Gouripeddi R, Lin YK, Dere W, Murray M, Madsen R, Gestaland P, Facelli J. Identification of High-Level Formalisms that Support Translational Research Reproducibility. In: Research Reproducibility 2018 [Internet]. Salt Lake City, Utah, USA; 2018 [cited 2018 Oct 30]. Available from: //campusguides.lib.utah.edu/UtahRR18/abstracts
15. Huser V, Kahn MG, Brown JS, Gouripeddi R. Methods for examining data quality in healthcare integrated data repositories. Pac Symp Biocomput Pac Symp Biocomput. 2018;23:628–33.
16. Lund A, Gouripeddi R, Burnett N, Tran L-T, Mo P, Madsen R, Cummins M, Sward K, Facelli J. Enabling Reproducible Computational Modeling: The Utah PRISMS Ecosystem. In Salt Lake City, Utah, USA; 2018 [cited 2018 Oct 30]. Available from: //campusguides.lib.utah.edu/UtahRR18/abstracts
17. Pflieger LT, Mason CC, Facelli JC. Uncertainty quantification in breast cancer risk prediction models using self-reported family health history. J Clin Transl Sci. 2017 Feb;1(1):53–9.
18. Shao J, Gouripeddi R, Facelli J. Improving Clinical Trial Research Reproducibility using Reproducible Informatics Methods. In Salt Lake City, Utah, USA; 2018 [cited 2018 Oct 30]. Available from: //campusguides.lib.utah.edu/UtahRR18/abstracts
19. Shao J, Gouripeddi R, Facelli JC. Semantic characterization of clinical trial descriptions from ClincalTrials.gov and patient notes from MIMIC-III. J Clin Transl Sci. 2017 Sep;1(S1):12–12.
20. Tiase V, Gouripeddi R, Burnett N, Butcher R, Mo P, Cummins M, Sward K. Advancing Study Metadata Models to Support an Exposomic Informatics Infrastructure. In Ottawa, Canada; 2018 [cited 2018 Oct 30]. Available from: = http://www.eiseverywhere.com/ehome/294696/638649/?&t=8c531cecd4bb0a5efc6a0045f5bec0c3
21. Wen J, Gouripeddi R, Facelli JC. Metadata Discovery of Heterogeneous Biomedical Datasets Using Token-Based Features. In: IT Convergence and Security 2017 [Internet]. Springer, Singapore; 2017 [cited 2017 Sep 6]. p. 60–7. (Lecture Notes in Electrical Engineering). Available from: https://link.springer.com/chapter/10.1007/978-981-10-6451-7_8
22. Wilkinson MD, Dumontier M, Aalbersberg IjJ, Appleton G, Axton M, Baak A, Blomberg N, Boiten J-W, da Silva Santos LB, Bourne PE, Bouwman J, Brookes AJ, Clark T, Crosas M, Dillo I, Dumon O, Edmunds S, Evelo CT, Finkers R, Gonzalez-Beltran A, Gray AJG, Groth P, Goble C, Grethe JS, Heringa J, ’t Hoen PAC, Hooft R, Kuhn T, Kok R, Kok J, Lusher SJ, Martone ME, Mons A, Packer AL, Persson B, Rocca-Serra P, Roos M, van Schaik R, Sansone S-A, Schultes E, Sengstag T, Slater T, Strawn G, Swertz MA, Thompson M, van der Lei J, van Mulligen E, Velterop J, Waagmeester A, Wittenburg P, Wolstencroft K, Zhao J, Mons B. The FAIR Guiding Principles for scientific data management and stewardship. Sci Data. 2016 Mar 15;3:160018.
23. Ioannidis JPA. Meta-research: Why research on research matters. PLOS Biol. 2018 Mar 13;16(3):e2005468.
24. Stodden V, Borwein J, Bailey DH. Setting the default to reproducible. Comput Sci Res SIAM News. 2013;46(5):4–6.
25. Stodden V, McNutt M, Bailey DH, Deelman E, Gil Y, Hanson B, Heroux MA, Ioannidis JPA, Taufer M. Enhancing reproducibility for computational methods. Science. 2016 Dec 9;354(6317):1240–1.
26. Stodden V, McNutt M, Bailey DH, Deelman E, Gil Y, Hanson B, Heroux MA, Ioannidis JPA, Taufer M. Enhancing reproducibility for computational methods. Science. 2016 Dec 9;354(6317):1240–1.
27. Stodden V. Reproducible Research for Scientific Computing: Tools and Strategies for Changing the Culture. Comput Sci Eng. 2012 Jul 1;14(4):13–7.
28. Baker M. Muddled meanings hamper efforts to fix reproducibility crisis. Nat News Available from: http://www.nature.com/news/muddled-meanings-hamper-efforts-to-fix-reproducibility-crisis-1.20076
29. Barba LA. Terminologies for Reproducible Research. ArXiv180203311 Cs 2018 Feb 9; Available from: http://arxiv.org/abs/1802.03311
Primary care perspectives on implementation of clinical trial recruitment
- Teresa Taft, Charlene Weir, Heidi Kramer, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 4 / Issue 1 / February 2020
- Published online by Cambridge University Press:
- 26 December 2019, pp. 61-68
-
- Article
-
- You have access Access
- Open access
- HTML
- Export citation
-
Introduction:
Poor clinical trial (CT) recruitment is a significant barrier to translating basic science discoveries into medical practice. Improving support for primary care provider (PCP) referral of patients to CTs may be an important part of the solution. However, implementing CT referral support in primary care is not only technically challenging, but also presents challenges at the person and organization levels.
Methods:The objectives of this study were (1) to characterize provider and clinical supervisor attitudes and perceptions regarding CT research, recruitment, and referrals in primary care and (2) to identify perceived workflow strategies and facilitators relevant to designing a technology-supported primary care CT referral program. Focus groups were conducted with PCPs, directors, and supervisors.
Results:Analysis indicated widespread support for the intrinsic scientific value of CTs, while at the same time deep concerns regarding protecting patient well-being, perceived loss of control when patients participate in trials, concern about the impact of point-of-care referrals on clinic workflow, the need for standard processes, and the need for CT information that enables referring providers to quickly confirm that the burdens are justified by the benefits at both patient and provider levels. PCP suggestions pertinent to implementing a CT referral decision support system are reported.
Conclusion:The results from this work contribute to developing an implementation approach to support increased referral of patients to CTs.
3339 Development of a Competency-based Informatics Course for Translational Researchers
- Ram Gouripeddi, Danielle Groat, Samir E. Abdelrahman, Tom Cheatham, Mollie Cummins, Karen Eilbeck, Bernie LaSalle, Katherine Sward, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 3 / Issue s1 / March 2019
- Published online by Cambridge University Press:
- 26 March 2019, pp. 66-67
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: Translational researchers often require the use of informatics methods in their work. Lack of an understanding of key informatics principles and methods limits the abilities of translational researchers to successfully implement Findable, Accessible, Interoperable, Reusable (FAIR) principles in grant proposal submissions and performed studies. In this study we describe our work in addressing this limitation in the workforce by developing a competency-based, modular course in informatics to meet the needs of diverse translational researchers. METHODS/STUDY POPULATION: We established a Translational Research Informatics Education Collaborative (TRIEC) consisting of faculty at the University of Utah (UU) with different primary expertise in informatics methods, and working in different tiers of the translational spectrum. The TRIEC, in collaboration with the Foundation of Workforce Development of the Utah Center for Clinical and Translational Science (CCTS), gathered informatics needs of early investigators by consolidating requests for informatics services, assistance provided in grant writing, and consultations. We then reviewed existing courses and literature for informatics courses that focused on clinical and translational researchers [3–9]. Using the structure and content of the identified courses, we developed an initial draft of a syllabus for a Translational Research Informatics (TRI) course which included key informatics topics to be covered and learning activities, and iteratively refined it through discussions. The course was approved by the UU Department of Biomedical Informatics, UU Graduate School and the CCTS. RESULTS/ANTICIPATED RESULTS: The TRI course introduces informatics PhD students, clinicians, and public health practitioners who have a demonstrated interest in research, to fundamental principles and tools of informatics. At the completion of the course, students will be able to describe and identify informatics tools and methods relevant to translational research and demonstrate inter-professional collaboration in the development of a research proposal addressing a relevant translational science question that utilizes the state-of-the-art in informatics. TRI covers a diverse set of informatics content presented as modules: genomics and bioinformatics, electronic health records, exposomics, microbiomics, molecular methods, data integration and fusion, metadata management, semantics, software architectures, mobile computing, sensors, recruitment, community engagement, secure computing environments, data mining, machine learning, deep learning, artificial intelligence and data science, open source informatics tools and platforms, research reproducibility, and uncertainty quantification. The teaching methods for TRI include (1) modular didactic learning consisting of presentations and readings and face-to-face discussions of the content, (2) student presentations of informatics literature relevant to their final project, and (3) a final project consisting of the development, critique and chalk talk and formal presentations of informatics methods and/or aims of an National Institutes of Health style K or R grant proposal. For (3), the student presents their translational research proposal concept at the beginning of the course, and works with members of the TRIEC with corresponding expertise. The final course grade is a combination of the final project, paper presentations and class participation. We offered TRI to a first cohort of students in the Fall semester of 2018. DISCUSSION/SIGNIFICANCE OF IMPACT: Translational research informatics is a sub-domain of biomedical informatics that applies and develops informatics theory and methods for translational research. TRI covers a diverse set of informatics topics that are applicable across the translational spectrum. It covers both didactic material and hands-on experience in using the material in grant proposals and research studies. TRI’s course content, teaching methodology and learning activities enable students to initially learn factual informatics knowledge and skills for translational research correspond to the ‘Remember, Understand, and Apply’ levels of the Bloom’s taxonomy [10]. The final project provides opportunity for applying these informatics concepts corresponding to the ‘Analyze, Evaluate, and Create’ levels of the Bloom’s taxonomy [10]. This inter-professional, competency-based, modular course will develop an informatics-enabled workforce trained in using state-of-the-art informatics solutions, increasing the effectiveness of translational science and precision medicine, and promoting FAIR principles in research data management and processes. Future work includes opening the course to all Clinical and Translational Science Award hubs and publishing the course material as a reference book. While student evaluations for the first cohort will be available end of the semester, true evaluation of TRI will be the number of trainees taking the course and successful grant proposal submissions. References: 1. Wilkinson MD, Dumontier M, et al. The FAIR Guiding Principles for scientific data management and stewardship. Sci Data. 2016 Mar 15. 2. National Center for Advancing Translational Sciences. Translational Science Spectrum. National Center for Advancing Translational Sciences. 2015 [cited 2018 Nov 15]. Available from: https://ncats.nih.gov/translation/spectrum 3. Hu H, Mural RJ, Liebman MN. Biomedical Informatics in Translational Research. 1 edition. Boston: Artech House; 2008. 264 p. 4. Payne PRO, Embi PJ, Niland J. Foundational biomedical informatics research in the clinical and translational science era: a call to action. J Am Med Inform Assoc JAMIA. 2010;17(6):615–6. 5. Payne PRO, Embi PJ, editors. Translational Informatics: Realizing the Promise of Knowledge-Driven Healthcare. Softcover reprint of the original 1st ed. 2015 edition. Springer; 2016. 196 p. 6. Richesson R, Andrews J, editors. Clinical Research Informatics. 2nd ed. Springer International Publishing; 2019. (Health Informatics). 7. Robertson D, MD GHW, editors. Clinical and Translational Science: Principles of Human Research. 2 edition. Amsterdam: Academic Press; 2017. 808 p. 8. Shen B, Tang H, Jiang X, editors. Translational Biomedical Informatics: A Precision Medicine Perspective. Softcover reprint of the original 1st ed. 2016 edition. S.l.: Springer; 2018. 340 p. 9. Valenta AL, Meagher EA, Tachinardi U, Starren J. Core informatics competencies for clinical and translational scientists: what do our customers and collaborators need to know? J Am Med Inform Assoc. 2016 Jul 1;23(4):835–9. 10. Anderson LW, Krathwohl DR, Airasian PW, Cruikshank KA, Mayer RE, Pintrich PR, Raths J, Wittrock MC. A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives, Abridged Edition. 1 edition. New York: Pearson; 2000.
3048 Measuring the Autonomic Nervous System for Translational Research: Identification of Non-invasive Methods
- Danielle Groat, Ram Gouripeddi, Yu Keui Lin, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 3 / Issue s1 / March 2019
- Published online by Cambridge University Press:
- 26 March 2019, p. 28
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: The objective of this study is to identify and categorize non-invasive measurement methods for autonomic nervous system (ANS) symptoms that develop in hypoglycemic episodes. METHODS/STUDY POPULATION: We first reviewed literature for hypoglycemia symptomology. We then performed a selective literature review of Google Scholar, PubMed and Scopus for an ANS symptom and/or synonyms and the words ‘sensor’ or ‘detection’, e.g. ‘sweat sensor’ and ‘tremor detection’, studies utilizing non-invasive measurements in DM, and datasets of non-invasive measurements in DM. Measurement methods were then organized based on the ANS symptoms and existing metadata models for harmonizing sensors and surveys. RESULTS/ANTICIPATED RESULTS: We identified several measurement methods to for ANS symptoms during hypoglycemic events: thermometer, accelerometer, electrocardiogram (ECG), galvanic skin response (GSR), image processing, infrared imaging, thermal actuator, and ecological momentary assessment (EMA). The stage of implementation varied across the measurement methods from under development, to use in research and clinical settings, and even commercially available consumer products. Measurement methods that could be worn as wrist-band wearables or as film-based epidermal sensors would be capable of automatically gathering data with little to no effort required of the person wearing the device. Image-based methods would require the individual to actively engage in generating a photograph for analysis. In the case of EMA’s, a message containing a question is sent to the individual, often via text message, soliciting short and immediate responses. It is anticipated that one sensor alone would not be sufficient to measure ANS responses to hypoglycemia, but rather several data points would be required. For example, if the GSR was the only signal, sweat in response to vigorous exercise or a warm environment would inject noise into the signal. Including the accelerometer data would allow for the identification of body movement which would indicate exercise, while an ECG signal could confirm the exercise. DISCUSSION/SIGNIFICANCE OF IMPACT: Impaired awareness of hypoglycemia (IAH) is a complication that develops in about 30% of type 1 DM and 10% type 2 DM populations. In individuals with intact awareness of hypoglycemia, the ANS leads to symptoms which includes: shaking, trembling, anxiety, nervousness, palpitation (i.e. change in heart rate and/or function), clamminess, sweating, dry mouth, hunger, pallor (i.e. drop in blood flow and/or skin-surface temperature), and pupil dilation. IAH is defined as the onset of hypoglycemia before the appearance of autonomic warning symptoms. IAH is caused by repeated exposures to low blood glucose levels, which reduces the body’s ability to sense hypoglycemia, and therefore it is difficult for patients to recognize and self-treat. Individuals with IAH are six times more likely to experience severe hypoglycemia, an emergent condition which can lead to unconsciousness, seizure, coma, and death. Clinical investigators are developing interventions that aim to improve awareness of hypoglycemia. Surveys, observations by clinicians, and laboratory tests, often carried out in highly controlled in-patient settings, are currently used to assess the severity of IAH and the ANS’s ability to respond to hypoglycemia. In other disease states, for example heart disease and Parkinson’s disease, electrocardiograms and accelerometers have been used to assess heart function and tremor, respectively. However, there is currently a barrier to examining the efficacy of IAH interventions in real world settings as there are no established objective and non-invasive means to measure ANS symptoms due to hypoglycemia. This work encompasses the first important step necessary to direct translational researchers interested in testing the efficacy of IAH interventions and developing diagnostic tools for IAH in real-world studies outside the clinic. Next steps include evaluating these sensors and specifying EMA surveys, designing studies, and integration and assimilation of these data streams to identify true events of IAH by leveraging informatics platform such as the Utah PRISMS Informatics Ecosystem. Investigators would then be able to conduct studies that aim to develop and validate models that take sensor and EMA data as the input to detect and assess the severity of IAH.
3399 Systematically Integrating Microbiomes and Exposomes for Translational Research
- Ram Gouripeddi, Andrew Miller, Karen Eilbeck, Katherine Sward, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 3 / Issue s1 / March 2019
- Published online by Cambridge University Press:
- 26 March 2019, pp. 29-30
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: Characterize microbiome metadata describing specimens collected, genomic pipelines and microbiome results, and incorporate them into a data integration platform for enabling harmonization, integration and assimilation of microbial genomics with exposures as spatiotemporal events. METHODS/STUDY POPULATION: We followed similar methods utilized in previous efforts in charactering and developing metadata models for describing microbiome metadata. Due to the heterogeneity in microbiome and exposome data, we aligned them along a conceptual representation of different data used in translational research; microbiomes being biospecimen-derived, and exposomes being a combination of sensor measurements, surveys and computationally modelled data. We performed a review of literature describing microbiome data, metadata, and semantics [4–15], along with existing datasets [16] and developed an initial metadata model. We reviewed the model with microbiome domain experts for its accuracy and completeness, and with translational researchers for its utility in different studies, and iteratively refined it. We then incorporated the logical model into OpenFurther’s metadata repository MDR [17,18] for harmonization of different microbiome datasets, as well as integration and assimilation of microbiome-exposome events utilizing the UPIE. RESULTS/ANTICIPATED RESULTS: Our model for describing the microbiome currently includes three domains (1) the specimen collected for analysis, (2) the microbial genomics pipelines, and (3) details of the microbiome genomics. For (1), we utilized biospecimen data model that harmonizes the data structures of caTissue, OpenSpecimen and other commonly available specimen management platform. (3) includes details about the organisms, isolate, host specifics, sequencing methodology, genomic sequences and annotations, microbiome phenotype, genomic data and storage, genomic copies and associated times stamps. We then incorporated this logical model into the MDR as assets and associations that UPIE utilizes to harmonize different microbiome datasets, followed by integration and assimilation of microbiome-exposome events. Details of (2) are ongoing. DISCUSSION/SIGNIFICANCE OF IMPACT: The role of the microbiome and co-influences from environmental exposures in etio-pathology of various pulmonary conditions isn’t well understood [19–24]. This metadata model for the microbiome provides a systematic approach for integrating microbial genomics with sensor-based environmental and physiological data, and clinical data that are present in varying spatial and temporal granularities and require complex methods for integration, assimilation and analysis. Incorporation of this microbiome model will advance the performance of sensor-based exposure studies of the (UPIE) to support novel research paradigms that will improve our understanding of the role of microbiome in promoting and preventing airway inflammation by performing a range of hypothesis-driven microbiome-exposome pediatric asthma studies across the translational spectrum.
2169: Hydrogen bonding and water accessibility changes upon expansion of PolyQ tracts in ataxin-2 and ataxin-3
- Jingran Wen, Daniel Scoles, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 1 / Issue S1 / September 2017
- Published online by Cambridge University Press:
- 10 May 2018, p. 2
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: Polyglutamine (polyQ) neurodegenerative diseases, associated with the unstable expansion of polyQ tracts, are devastating diseases for which no treatments exist. Moreover, most drug discovery attempts have been hindered by the lack of understanding on the relevant pathogenic mechanisms. Here, using previously reported 3D protein predicted structures of ataxin-2 and ataxin-3, we analyze the effect of polyQ enlargement on hydrogen bonding and water accessibility patterns as a possible mechanism for pathogenesis thought enhanced protein aggregation. METHODS/STUDY POPULATION: Using the I-TASSER predicted structures of ataxin-2 and ataxin-3 with different numbers of glutamine repeats representing polyQ lengths characteristic of both normal and pathological tracts (Journal of Biomolecular Structure and Dynamics, 2016: 1–16), we identified hydrogen bonds (HBs, UCSF Chimera FindHBond module) and calculated solvent-accessible surface areas (SASA, DSSP program) for the polyQ tracts available in the 3D structures. RESULTS/ANTICIPATED RESULTS: The identified HBs were analyzed as the function of the number of glutamines in the polyQ tracts and characterized as those intra-polyQ and exter-polyQ, respectively. The SASA of the polyQ region was also studied as the function of the polyQ tract length. DISCUSSION/SIGNIFICANCE OF IMPACT: The results obtained here indicate that polyQ regions increasingly prefer self-interactions, which consistently can lead to more compact polyQ structures. The results strongly support the notion that the expansion of the polyQ region can be an intrinsic force leading to self-aggregation of polyglutamine proteins and suggest that the modulation of solvent-polyQ interactions could be a possible therapeutic strategy for polyQ diseases.
2507: Towards a scalable informatics platform for enhancing accrual into clinical research studies
- Ram Gouripeddi, Elizabeth Lane, Randy Madsen, Ryan Butcher, Bernie LaSalle, Katherine Sward, Julie Fritz, Julio C. Facelli, Mollie Cummins, Jianyin Shao, Rob Singleton
-
- Journal:
- Journal of Clinical and Translational Science / Volume 1 / Issue S1 / September 2017
- Published online by Cambridge University Press:
- 10 May 2018, p. 20
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: Issues with recruiting the targeted number of participants in a timely manner often results in underpowered studies, with more than 60% of clinical studies failing to complete or requiring extensions due to enrollment issues. The objective of this study is to develop and implement a scalable, organization wide platform to enhance accrual into clinical research studies. METHODS/STUDY POPULATION: We are developing and evaluating an informatics platform called Utah Utility for Research Recruitment (U2R2). U2R2 consists of 2 components: (i) Semantic Matcher: an automated trial criterion to patient matching component that also reports uncertainty associated with the match, and (ii) Match Delivery: mechanisms to deliver the list of matched patients for different research and clinical settings. As a first step, we limited the Semantic Matcher to utilize only structured data elements from the patient record and trial criteria. We are now including distributional semantic methods to match complete patient records and trial criteria as documents. We evaluated the first phase of U2R2 based on a randomized trial with a target enrollment of 220 participants that compares 2 treatment strategies for managing back pain (physical therapy and usual care) for individuals consulting a nonsurgical provider and symptomatic <90 days. RESULTS/ANTICIPATED RESULTS: U2R2 identified 9370 patients from the University of Utah Hospitals and Clinics as potential matches. Of these 9370, 1145 responded to the Back Pain study research team’s email or phone communications, and were further screened by phone. In total, 250 participants completed a screening visit, resulting in the current study enrollment of 130 participants. Forty-three of 1145 patients refused to participate, and 50 participants no-showed their screening visit. DISCUSSION/SIGNIFICANCE OF IMPACT: A recruitment platform can enhance potential participant identification, but requires attention to multiple issues involved with clinical research studies. Clinical eligibility criteria are usually unstructured and require human mediation and abstraction into discrete data elements for matching against patient records. In addition, key eligibility data are often embedded within text in the patient record. Distributional semantic approaches, by leveraging this content, can identify potential participants for screening with more specificity. The delivery of the list of matched patient results should consider characteristics of the research study, population, and targeted enrollment (eg, back pain being a common disorder and the possibility of the patient visiting different types of clinics), as well as organizational and socio-technical issues surrounding clinical practice and research. Embedding the delivery of match results into the clinical workflow by utilizing user-centered design approaches and involving the clinician, the clinic, and the patient in the recruitment process, could yield higher accrual indices.
2174: In silico prediction of NS1 structure and influenza A virus pathogenesis
- Joshua Klonoski, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 1 / Issue S1 / September 2017
- Published online by Cambridge University Press:
- 10 May 2018, pp. 2-3
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: This poster presents preliminary results of using in silico approaches to predict a priori, based on sequence alone, the pathogenesis of novel influenza A virus. METHODS/STUDY POPULATION: Here we analyzed the structure of the NS1 protein of 11 strains of well characterized influenza A virus with known pathogenesis, reported in the literature as LD50 values, and published sequences. We performed homology comparison of these sequences using the ExPASy SIM alignment tool for protein sequences and then predicted their 3D structures using the I-TASSER method for protein structure prediction. We retained the best 20 I-TASSER models for the NS1 sequences considered here and compared their structures with that of the X-ray crystallographic structure of the NS1 protein in the A/blue-winged teal/MN/993/1980 (H6N6). The average RMS between this experimental structure and the best 20 I-TASSER models was used as a measure of structural similarity between the 3D structures among the proteins. RESULTS/ANTICIPATED RESULTS: The sequence homology shows modest correlation between sequence and pathogenicity. Linear correlations with R values as large as 0.6 where observed for the full sequence homology and the homology of the RBD domains of the proteins. The correlations with the other protein domains were significant lower. We did not found overall correlation between the 3D structures and pathogenesis of all the variants considered here, but the initial results suggest that correlations do exists for different subgroups of viruses. In future work we will use advanced data mining methods to better understand clustering and correlation between structure and pathogenesis. DISCUSSION/SIGNIFICANCE OF IMPACT: The results presented in this poster demonstrate, as proof of concept, the use of in silico approaches to determine pathogenesis of viruses with substantial impact on human health. The ability of computationally predicting pathogenesis of rapidly mutating viruses can be an effective way to accelerate the development prevention strategies because computational methods are relatively inexpensive and much more scalable than in vivo approaches.
2166: Semantic characterization of clinical trial descriptions from ClincalTrials.gov and patient notes from MIMIC-III
- Jianyin Shao, Ram Gouripeddi, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 1 / Issue S1 / September 2017
- Published online by Cambridge University Press:
- 10 May 2018, p. 12
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: This poster presents a detailed characterization of the distribution of semantic concepts used in the text describing eligibility criteria of clinical trials reported to ClincalTrials.gov and patient notes from MIMIC-III. The final goal of this study is to find a minimal set of semantic concepts that can describe clinical trials and patients for efficient computational matching of clinical trial descriptions to potential participants at large scale. METHODS/STUDY POPULATION: We downloaded the free text describing the eligibility criteria of all clinical trials reported to ClinicalTrials.gov as of July 28, 2015, ~195,000 trials and ~2,000,000 clinical notes from MIMIC-III. Using MetaMap 2014 we extracted UMLS concepts (CUIs) from the collected text. We calculated the frequency of presence of the semantic concepts in the texts describing the clinical trials eligibility criteria and patient notes. RESULTS/ANTICIPATED RESULTS: The results show a classical power distribution, Y=210X(−2.043), R2=0.9599, for clinical trial eligibility criteria and Y=513X(−2.684), R2=0.9477 for MIMIC patient notes, where Y represents the number of documents in which a concept appears and X is the cardinal order the concept ordered from more to less frequent. From this distribution, it is possible to realize that from the over, 100,000 concepts in UMLS, there are only ~60,000 and 50,000 concepts that appear in less than 10 clinical trial eligibility descriptions and MIMIC-III patient clinical notes, respectively. This indicates that it would be possible to describe clinical trials and patient notes with a relatively small number of concepts, making the search space for matching patients to clinical trials a relatively small sub-space of the overall UMLS search space. DISCUSSION/SIGNIFICANCE OF IMPACT: Our results showing that the concepts used to describe clinical trial eligibility criteria and patient clinical notes follow a power distribution can lead to tractable computational approaches to automatically match patients to clinical trials at large scale by considerably reducing the search space. While automatic patient matching is not the panacea for improving clinical trial recruitment, better low cost computational preselection processes can allow the limited human resources assigned to patient recruitment to be redirected to the most promising targets for recruitment.
2469: Streamlining study design and statistical analysis for quality improvement and research reproducibility
- Ram Gouripeddi, Mollie Cummins, Randy Madsen, Bernie LaSalle, Andrew Middleton Redd, Angela Paige Presson, Xiangyang Ye, Julio C. Facelli, Tom Green, Steve Harper
-
- Journal:
- Journal of Clinical and Translational Science / Volume 1 / Issue S1 / September 2017
- Published online by Cambridge University Press:
- 10 May 2018, pp. 18-19
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/SPECIFIC AIMS: Key factors causing irreproducibility of research include those related to inappropriate study design methodologies and statistical analysis. In modern statistical practice irreproducibility could arise due to statistical (false discoveries, p-hacking, overuse/misuse of p-values, low power, poor experimental design) and computational (data, code and software management) issues. These require understanding the processes and workflows practiced by an organization, and the development and use of metrics to quantify reproducibility. METHODS/STUDY POPULATION: Within the Foundation of Discovery – Population Health Research, Center for Clinical and Translational Science, University of Utah, we are undertaking a project to streamline the study design and statistical analysis workflows and processes. As a first step we met with key stakeholders to understand the current practices by eliciting example statistical projects, and then developed process information models for different types of statistical needs using Lucidchart. We then reviewed these with the Foundation’s leadership and the Standards Committee to come up with ideal workflows and model, and defined key measurement points (such as those around study design, analysis plan, final report, requirements for quality checks, and double coding) for assessing reproducibility. As next steps we are using our finding to embed analytical and infrastructural approaches within the statisticians’ workflows. This will include data and code dissemination platforms such as Box, Bitbucket, and GitHub, documentation platforms such as Confluence, and workflow tracking platforms such as Jira. These tools will simplify and automate the capture of communications as a statistician work through a project. Data-intensive process will use process-workflow management platforms such as Activiti, Pegasus, and Taverna. RESULTS/ANTICIPATED RESULTS: These strategies for sharing and publishing study protocols, data, code, and results across the spectrum, active collaboration with the research team, automation of key steps, along with decision support. DISCUSSION/SIGNIFICANCE OF IMPACT: This analysis of statistical methods and process and computational methods to automate them ensure quality of statistical methods and reproducibility of research.
Uncertainty quantification in breast cancer risk prediction models using self-reported family health history
- Lance T. Pflieger, Clinton C. Mason, Julio C. Facelli
-
- Journal:
- Journal of Clinical and Translational Science / Volume 1 / Issue 1 / February 2017
- Published online by Cambridge University Press:
- 20 January 2017, pp. 53-59
-
- Article
-
- You have access Access
- Open access
- HTML
- Export citation
-
Introduction. Family health history (FHx) is an important factor in breast and ovarian cancer risk assessment. As such, multiple risk prediction models rely strongly on FHx data when identifying a patient’s risk. These models were developed using verified information and when translated into a clinical setting assume that a patient’s FHx is accurate and complete. However, FHx information collected in a typical clinical setting is known to be imprecise and it is not well understood how this uncertainty may affect predictions in clinical settings. Methods. Using Monte Carlo simulations and existing measurements of uncertainty of self-reported FHx, we show how uncertainty in FHx information can alter risk classification when used in typical clinical settings. Results. We found that various models ranged from 52% to 64% for correct tier-level classification of pedigrees under a set of contrived uncertain conditions, but that significant misclassification are not negligible. Conclusions. Our work implies that (i) uncertainty quantification needs to be considered when transferring tools from a controlled research environment to a more uncertain environment (i.e, a health clinic) and (ii) better FHx collection methods are needed to reduce uncertainty in breast cancer risk prediction in clinical settings.
Global Optimization of Atomic Cluster Structures Using Parallel Genetic Algorithms
- Ofelia Oña, Victor E. Bazterra, María C. Caputo, Marta B. Ferraro, Julio Facelli
-
- Journal:
- MRS Online Proceedings Library Archive / Volume 894 / 2005
- Published online by Cambridge University Press:
- 26 February 2011, 0894-LL08-02
- Print publication:
- 2005
-
- Article
- Export citation
-
The study of the structure and physical properties of atomic clusters is an extremely active area of research due to their importance, both in fundamental science and in applied technology. For medium size atomic clusters most of the structures reported today have been obtained by local optimizations of plausible structures using DFT (Density Functional Theory) methods and/or by global optimizations in which much more approximate methods are used to calculate the cluster’s energetics. Our previous work shows that these approaches can not be reliably used to study atomic cluster structures and that approaches based on global optimization schemes are needed. In this paper, we report the implementation and application of a parallel Genetic Algorithm (GA) to predict the structure of medium size atomic clusters.