In a recent article published in the journal Scientific Reports, researchers investigated the phenomenon of radiation-induced fatigue (RIF) in breast cancer patients undergoing radiotherapy (RT). This research aims to utilize objective data collected from fitness trackers to provide a more accurate and continuous monitoring of fatigue levels throughout the treatment process. By employing wearable technology, the study seeks to enhance the understanding of fatigue dynamics and improve patient management during RT.
Study: Fatigue trajectories by wearable remote monitoring of breast cancer patients during radiotherapy. Image Credit: Nan_Got/Shutterstock.com
Background
Fatigue is a common and debilitating side effect of cancer treatment, significantly impacting patients' quality of life. Radiation therapy is a standard treatment for breast cancer, but it is frequently associated with various side effects, including fatigue. RIF can manifest as a persistent sense of tiredness that does not improve with rest, affecting patients' physical and emotional well-being.
Previous studies have highlighted the need for more objective measures to assess fatigue, as numerous factors, including psychological state and personal perceptions of health can influence subjective assessments. The advent of fitness trackers presents an opportunity to gather real-time data on patients' physical activity and physiological responses, such as heart rate and step counts. This study builds on the premise that continuous monitoring can yield insights into the patterns and predictors of RIF, ultimately leading to better patient care and tailored interventions.
The Current Study
The study involved a cohort of breast cancer patients receiving RT, who were equipped with fitness trackers (Veepoo H03 smart watch) to monitor their daily activities, including step counts (STP) and heart rate (HR). The patients were divided into two groups based on their RT fractionation schedules: moderately hypofractionated and conventional.
Data collection occurred over the course of 3 to 5 weeks, with patients instructed to wear the trackers continuously. The study employed a web application to facilitate data aggregation and analysis, ensuring that medical staff had access to the information throughout the treatment period.
To assess RIF, the researchers utilized the Common Terminology Criteria for Adverse Events (CTCAE) version 5.0, categorizing fatigue into grades based on severity. The data collected from the fitness trackers were processed to identify repeated activity windows (RAWs), which allowed for a detailed analysis of patients' activity patterns. Machine learning techniques, particularly the Bagged Trees model, were employed to analyze the high-dimensional data, aiming to correlate the objective measures of activity with the subjective reports of fatigue.
Results and Discussion
The findings revealed that nearly half of the participants experienced RIF during their treatment. The analysis of the fitness tracker data indicated significant variations in patients' activity levels, with notable differences in step counts and heart rates correlating with reported fatigue levels.
The Bagged Trees model demonstrated a high predictive accuracy for identifying RIF, achieving a training area under the curve (AUC) of 89% and a test AUC of 86%. This suggests that the objective data collected from fitness trackers can effectively characterize fatigue trajectories in patients undergoing RT.
The study also highlighted the importance of understanding individual activity patterns. The researchers found that the timing of activity windows and the variability in heart rates provided valuable insights into patients' daily habits and fatigue levels. This intra-patient analysis allowed for a more nuanced understanding of how fatigue manifests over time, emphasizing the need for personalized approaches to managing RIF.
However, the study faced several limitations. The short battery life of the fitness trackers hindered continuous data collection, as patients were required to replace their devices every few days. Additionally, the limited memory capacity of the trackers meant that data from previous days could be lost, particularly if patients did not return to the RT department promptly. These technical challenges highlight the need for improved wearable technology to enhance data collection efficiency.
Conclusion
In conclusion, this study demonstrates the potential of fitness trackers to provide objective insights into radiation-induced fatigue among breast cancer patients undergoing radiotherapy. By leveraging wearable technology, the researchers were able to capture real-time data on patients' activity levels and physiological responses, revealing significant correlations with reported fatigue.
The findings advocate for the broader implementation of remote monitoring in oncology, as it offers a promising avenue for enhancing patient care and tailoring interventions to individual needs. Future research should focus on addressing the technical limitations encountered in this study and expanding the sample size to validate the findings further. Overall, the integration of objective monitoring into cancer care represents a significant step toward improving the quality of life for patients facing the challenges of treatment-related fatigue.
Journal Reference
Barillaro A., Feoli C. et al. (2024). Fatigue trajectories by wearable remote monitoring of breast cancer patients during radiotherapy. Scientific Reports 14, 27276. DOI: 10.1038/s41598-024-78805-5, https://www.nature.com/articles/s41598-024-78805-5