biotrace2csv: Data Extraction Tool for BioTrace+ PDF Data Reports
biotrace2csv is a free, open-source command-line tool that automates the extraction of heart rate variability and physiological data from BioTrace+ PDF reports into CSV format, achieving 100% accuracy with manual extraction while reducing processing time by approximately 50-fold.
Original paper licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
In the quiet corners of sports science and psychology, researchers often look for clues about how the human body handles stress and focus. One way they do this is by listening to the subtle rhythms of the heart. While a heartbeat might seem like a simple, steady drum, the time between each beat actually varies slightly, speeding up and slowing down in response to breathing, thoughts, and physical effort. Scientists call this variation heart rate variability, and it serves as a window into the body's automatic nervous system. To study this, researchers use specialized equipment to record these tiny fluctuations during activities like archery or meditation. The software that processes these recordings, known as BioTrace+, is excellent at creating detailed reports. However, these reports come out as printed documents rather than digital spreadsheets, forcing scientists to manually copy numbers by hand if they want to analyze them further. This tedious process is slow and prone to human error, creating a bottleneck that can stall research.
A researcher named Metehan Özsoy from Celal Bayar University recognized this problem and built a digital solution to clear the path. He created a free, open-source tool called biotrace2csv, which acts as a translator for these stubborn PDF reports. Instead of a human sitting at a computer and typing out hundreds of numbers, this software reads the document, finds the specific data points hidden among the text and graphs, and instantly converts them into a clean, organized table that any analysis program can use. The tool is designed to handle three different types of reports generated by the BioTrace+ system: those showing heart rate variability metrics, those listing physiological statistics for different body channels, and those detailing resonance frequency assessments. It can process a single file or an entire folder of mixed report types at once, automatically figuring out which kind of document it is looking at and extracting the right information without any confusion.
To prove that this automated method works as well as a human could, Özsoy tested it against the traditional way of doing things. He selected twenty reports from a study involving university students learning archery and had a human manually extract every single number from them. This manual effort took nearly twenty-four minutes to complete. When he ran the same twenty files through his new tool, the software finished the job in less than thirty seconds. The difference in speed was dramatic, with the tool working about fifty times faster than the human effort. More importantly, the numbers the software pulled out were identical to the ones the human had written down. Every single value, from the smallest heartbeat interval to the largest power measurement, matched perfectly. Even when the original reports contained strange, unreadable placeholders for missing data, the tool handled them correctly by leaving those spots blank, just as a careful human would.
The impact of this speed and accuracy became clear when the tool was applied to the full dataset of the archery study. The research involved twenty-six students who underwent a fourteen-week training program, with each student generating five separate reports. In total, there were 260 PDF files to process. If a researcher had tried to transcribe all of these by hand, it would have taken over five hours of repetitive work. With the biotrace2csv tool, the entire dataset was converted into usable data in just over six minutes. This massive reduction in time means researchers can spend their energy on understanding the science rather than on the mechanical task of data entry. By removing the possibility of human transcription errors and freeing up hours of work, the tool ensures that the data used for analysis is both consistent and reliable.
The software is written in a common programming language called Python, making it accessible to researchers on various computer systems, including Windows, Mac, and Linux. It is available for anyone to download and use, with the source code and a permanent archive of the tool hosted online for transparency. While the current version focuses strictly on extracting numerical data from these specific PDF reports, the creator has noted that future updates could add features like pulling out session names and dates or filtering out specific types of data. For now, however, the tool stands as a practical bridge between complex physiological reports and the clear, organized data needed to advance our understanding of how the body responds to the challenges of sport and life.
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.