Goal #7:  Training and career support programs for translational scientists

Applications now open for the 2024 cohort.&nbsp; Session 1: June 17, 2024 – June 22, 2024 | &nbsp;University of Michigan – Ann Arbor, MISession 2: July 28, 2024 – August 2, 2024 | &nbsp;Jackson State University &nbsp;– Jackson, MSApplication Deadline: March 14, 2024&nbsp;Program Overview The rigor of scientific research and the reproducibility of research results are essential for the validity of research findings and the trustworthiness of science. However, research rigor and reproducibility remains a significant challenge across scientific fields, especially for research with complex data types from heterogeneous sources, and long data manipulation pipelines. This is especially critical as data science and Artificial Intelligence (AI) methods emerge at lightning speed and researchers scramble to seize the opportunities that the new methods bring.&nbsp;While researchers recognize the importance of rigor and reproducibility, they often lack the resources and the technical know-how to achieve this consistently in practice. With funding from the National Institutes of Health, a multi-university team offers a nationwide program to equip faculty and technical staff in biomedical sciences with the skills needed to improve the rigor and reproducibility of their research, and help them transfer such skills to their trainees…&nbsp;Read more about the application <a href="https://midas.umich.edu/dair-3/" target="_blank" rel="noopener noreferrer">here</a>.&nbsp;<a href="https://uploads.ccos-cc.ctsa.io/Data_and_AI_Intensive_Research_with_Rigor_and_Reproducibility_2024_Flyer_a8567c01c1.pdf" target="_blank" rel="noopener noreferrer" download="download">Data and AI Intensive Research with Rigor and Reproducibility 2024 Flyer</a>

Michigan Institute for Clinical and Health Research

small_AdobeStock_318294725.jpeg

thumbnail_AdobeStock_318294725.jpeg

AdobeStock_318294725.jpeg

University of Michigan at Ann Arbor

Apply to The Data and AI Intensive Research with Rigor and Reproducibility (DAIR3) Program

- Any -

Goal #1: Advance clinical and translational science

The CCOS Communications Team interviewed researchers at the <a href="https://ccos-cc.ctsa.io/groups/program-meetings/2023/fall-meeting?view=meeting-details" target="_blank" rel="noopener noreferrer">2023 CTSA Fall Program Annual Meeting</a> poster session in November as part of a series to feature ongoing projects across the CTSA hubs. In this article, we’re featuring Dr. Adam Dziorny, NIDDK K23 Scholar in Pediatrics Critical Care and Informatics at the University of Rochester who presented his work on <a href="https://ccos-cc.ctsa.io/groups/program-meetings/2023/fall-meeting?view=poster-gallery&amp;poster=279" target="_blank" rel="noopener noreferrer">validating a machine learning model to predict acute kidney injury in children with critical illness</a>.&nbsp;&nbsp;Research Question&nbsp;Machine learning has allowed for better prediction of adverse events in children with critical illnesses, including acute kidney injury (AKI). As most machine-learning models are developed and tested using data from a single-center, there is a need for multicenter datasets because single center datasets lack generalizability. Dr. Dziorny and his team aim to use existing multicenter datasets to address this issue.&nbsp;&nbsp;&nbsp;Research Plan&nbsp;Dr. Dziorny and his team created two novel, multicenter datasets to externally validate an already existing single-center-derived AKI prediction model. The team combined data from the Virtual Pediatric Systems (VPS) and PEDSnet for one dataset and extracted data from the PICU Data Collaborative for the other. The team first identified cases that fit into their inclusion criteria and set the baseline AKI score. Features for analysis were identified and included pre-admission cardiac arrest, pH, total bilirubin, platelet count, and blood urea nitrogen. Thresholds were set based on those used in the single-center dataset.&nbsp;&nbsp;&nbsp;Dr. Dziorny and his team were successful in externally validating the existing AKI prediction model using the two derived multicenter datasets. Model discrimination was reported lower than in the original single-center model alone, which was partially attributed to differences in features within datasets.&nbsp;&nbsp;&nbsp;Next Steps&nbsp;The team concluded that external validation of a single-center derived model is possible with multicenter datasets, but attention must be paid to cohort selection, outcome definition and feature selection. Ongoing work includes re-calibration of the model, adding additional features for analysis, and generalizability testing.&nbsp;&nbsp;Reflection with the Researcher: What do you want the CTSA community to know about the work you presented?&nbsp;Dr. Dziorny wants to remind the CTSA community that “external validation is so important!” He hopes his model used for predicting acute kidney injury among critically ill children will soon be applied to additional patient settings." His work on the project continues, as the model is currently undergoing "silent validation," in which it will be implemented in real-time with electronic health records and run "in the background" to ensure validity.&nbsp;

The University of Rochester Clinical and Translational Science Award Hub

large_Adam Dziorny, MD, PhD.JPG

medium_Adam Dziorny, MD, PhD.JPG

small_Adam Dziorny, MD, PhD.JPG

thumbnail_Adam Dziorny, MD, PhD.JPG

Adam Dziorny, MD, PhD.JPG

University of Rochester Medicine

2023 CTSA Fall Program Annual Meeting Poster Spotlight: Adam Dziorny, M.D., Ph.D. 

X-logo-teal_80x66.png

ri_linkedin_fill_408497d4b5_96748f4451.png

Goal #4: Improve clinical research

A team of NIH-funded researchers led by James DuBois at Washington University in St. Louis has developed ConsentTools, a toolkit created to help clinical research professionals understand and adopt three evidence informed practices for informed consent. The toolkit can be accessed at <a href="https://consenttools.org/" target="_blank" rel="noopener noreferrer">ConsentTools.org</a>. Read below for more details about the toolkit and how it works.&nbsp;Optimizing Key InformationThe toolkit provides guidance on how to easily incorporate plain language and how to use evidence-based formatting to optimize key information.<a href="https://consenttools.org/optimizing-key-information/" target="_blank" rel="noopener noreferrer">Tools for Optimizing Key Information include</a>:<ul><li>Brief videos with examples of how to implement plain language and evidence-based formatting.</li><li>An example of key information that utilizes plain language and evidence-based formatting.</li><li>Sample language for your Institutional Review Board (IRB) application.</li></ul>&nbsp;AssessmentsMany people are at risk of impaired decision-making capacity, and researchers often overestimate how well participants understand and appreciate consent information.The toolkit provides guidance on how to administer a short validated assessment of consent understanding, including when and how to assess, and what to do with assessment results.<a href="https://consenttools.org/assessments/" target="_blank" rel="noopener noreferrer">Tools for Assessments include</a>:<ul><li>A sample validated assessment instrument, with instructions and scoring.</li><li>Brief videos demonstrating how to administer and score the assessment.</li><li>Sample language for your IRB application.</li></ul>&nbsp;Legally Authorized Representatives (LARs)The toolkit provides guidance on how to navigate this complex issue.This includes guidance on whether your participants need an LAR, and how to help participants appoint an LAR.<a href="https://consenttools.org/lars/" target="_blank" rel="noopener noreferrer">Tools for Legally Authorized Representatives include</a>:<ul><li>A tool to help educate participants and help with having the sensitive LAR discussion.</li><li>A note to file template document to document participant’s wishes.</li><li>Sample language for your IRB application.</li></ul>&nbsp;To learn how to implement these practices into electronic consent, click <a href="https://consenttools.org/econsent/" target="_blank" rel="noopener noreferrer">here</a>.CTSA members are free to use or share <a href="https://consenttools.org/" target="_blank" rel="noopener noreferrer">Consent Tools</a> materials for non-commercial purposes, with appropriate credit to ConsentTools and the <a href="https://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fbioethicsresearch.org%2F&amp;data=05%7C01%7Cpcurran%40wustl.edu%7C222613c5943244d1a49508db6dc2c1e3%7C4ccca3b571cd4e6d974b4d9beb96c6d6%7C0%7C0%7C638224455464842780%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&amp;sdata=qbNW91inr%2FtVxRE9cpRCYn%2Fm7WW6rwgIRMwcnBHsFhw%3D&amp;reserved=0" target="_blank" rel="noopener noreferrer">Bioethics Research Center</a>. Read more about <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="noopener noreferrer">Creative Commons</a> here.

Washington University in St. Louis Institute of Clinical and Translational Sciences

thumbnail_consent tools_2.png

consent tools_2.png

Washington University in St. Louis

NIH-Funded Team Creates a Clinical Research Toolkit: ConsentTools

CTSA CCOS

Home

About

CTSA Groups and Meetings

Resources

News

Help

CTSA News

Date

Share this News Post

Apply to The Data and AI Intensive Research with Rigor and Reproducibility (DAIR3) Program