Submission

This project will analyze a dataset of male firefighters with PTSD to identify risk factors and protective mechanisms associated with PTSD development and resilience. By examining demographic, psychosocial, and trauma-related factors, the study aims to inform targeted prevention and intervention strategies. Advanced statistical methods, including regression analysis and machine learning techniques, will be employed to identify key predictors of PTSD severity and resilience. The resulting predictive models will be integrated into Terasynth's PTSD exposure therapy treatment tool, ReArmor, to personalize treatment modules and intensity levels. Findings will contribute to a deeper understanding of PTSD resilience and recovery, facilitating the development of tailored support resources for firefighters at risk.

This project aims to identify risk factors and protective mechanisms associated with PTSD development and resilience in male firefighters. The primary data source for this project is a dataset of 137 male firefighters diagnosed with PTSD, available at https://dataverse.harvard.edu/file.xhtml?fileId=4382717&version=1.0. This dataset comprises 85 variables, encompassing demographic characteristics (age, education, relationship status), trauma-related factors (number, frequency, and type of events), and PTSD symptom severity measures (Intrusions, Hyperarousal, and Avoidance).

This project aligns with the GREI initiative (https://datascience.nih.gov/data-ecosystem/generalist-repository-ecosystem-initiative) by conducting a secondary analysis of existing data to address a critical health research question  and addressing post traumatic stress disorder (PTSD) in male firefighters and the predictive factors that may be associated with identifying it. The analysis will involve advanced statistical methods, including regression analysis, to identify significant predictors of PTSD severity and resilience. Additionally, machine learning techniques will be employed to develop predictive models for personalized treatment recommendations.

Project Timeline:

• Month 1-2: Data cleaning, preprocessing, exploratory data analysis, and feature engineering.
• Month 3-4: Development and validation of predictive models for PTSD severity and resilience.
• Month 5: Integration of predictive models into Terasynth & University of Central Florida's ReArmor PTSD exposure therapy software and pilot testing.
• Month 6: Manuscript preparation and dissemination of findings.

This project anticipates the following outcomes:

• Identification of key demographic, psychosocial, and trauma-related predictors of PTSD severity and resilience in male firefighters.
• Development of predictive models capable of accurately classifying firefighters at high risk for PTSD.
• Generation of data-driven recommendations for targeted prevention and intervention strategies.

These findings will be shared through multiple channels:

• Peer-reviewed publications: A manuscript will be prepared detailing the methodology, results, and implications of the study for submission to a relevant scientific journal.
• Conference presentations: The project and its findings will be presented at relevant scientific and professional conferences.
• Terasynth's website and blog: A summary of the project, its findings, and implications will be made accessible to the public through Terasynth's website and blog.

To ensure the project adheres to FAIR principles:

• Findable: The dataset used, along with the code and metadata, will be made available through a persistent identifier (DOI) assigned upon manuscript publication.
• Accessible: The data and code will be accessible through a public repository (e.g., GitHub, Dataverse) with clear usage licenses.
• Interoperable: The data and code will be provided in standard formats (e.g., CSV, R Markdown) to ensure compatibility and reuse across different platforms.
• Reusable: The data and code will be accompanied by comprehensive documentation and metadata, facilitating reuse and future research.

The project will also address relevant CARE principles by:

• Ensuring the data is used in a way that respects the autonomy and privacy of the individuals involved.
• Acknowledging the contributions of the data providers and the community.
• Promoting the responsible use of the data and findings for the benefit of the community.

To ensure replicability and reproducibility:

• The code used for data analysis and model development will be made available along with the dataset.
• The analysis will be conducted using reproducible workflows (e.g., R Markdown) that document each step of the process.
• The methodology will be described in detail in the manuscript, allowing other researchers to replicate the analysis and validate the findings.

This project is expected to make significant contributions to the field of PTSD research and intervention, particularly within the context of male firefighters. The identification of specific risk factors and protective mechanisms will advance our understanding of the complex interplay of factors contributing to PTSD development and resilience in this high-risk population. This knowledge will be crucial for informing the development of targeted prevention programs and support resources tailored to the unique needs of male firefighters. The insights gained will directly inform the enhancement of Terasynth's ReArmor PTSD exposure therapy software, with the goal of improving its efficacy and personalization capabilities. By integrating predictive models into ReArmor, we aim to further extend the impact of this research in the realm of virtual reality exposure therapy.

The project's potential impact on diagnosis, treatment, and prevention is substantial. The development of predictive models for PTSD risk will enable early identification of firefighters at high risk, facilitating timely intervention and support. The integration of these models into Terasynth & University of Central Florida's ReArmor tool will personalize treatment plans, potentially leading to improved treatment outcomes and reduced PTSD burden. Furthermore, the project's findings will inform the development of targeted prevention strategies, including trauma-informed care practices within fire departments, to promote mental health awareness and support.

Terasynth's team comprises experts in AI/ML, data science, and partnerships that allow for collaboration with clinical psychologists, strategically assembled to leverage the strengths of each member. The team's collaborative approach emphasizes open communication, shared decision-making, and iterative feedback to foster innovation and ensure project success. Our expertise in statistical analysis includes proficiency in regression modeling, machine learning techniques, and data visualization, essential for identifying key predictors and developing robust predictive models for PTSD risk and resilience.

Several key considerations will contribute to the success of this project:

• Terasynth's expertise in AI/ML and PTSD exposure therapy software: This ensures the effective analysis of the dataset and integration of findings into ReArmor.
• The team's collaborative approach: This fosters efficient problem-solving and knowledge sharing.
• Adherence to FAIR and CARE principles: This promotes data transparency, reproducibility, and ethical data handling.
• The project's alignment with the GREI initiative: This emphasizes the importance of secondary data analysis in addressing critical health research questions.
• The potential for significant impact on PTSD diagnosis, treatment, and prevention: This highlights the project's relevance for impact and potential to improve the well-being of male firefighters.