⚡ Quick Summary
This study introduces the PANSAM-14, a shortened version of the Positive And Negative Sleep Appraisal Measure, developed using machine learning techniques, specifically eXtreme Gradient Boosting (XGBoost). The new tool demonstrates high predictive accuracy for assessing individuals’ dysfunctional beliefs about sleep, with an impressive R² score of 0.93.
🔍 Key Details
- 📊 Dataset: 1,000 participants from South Korea
- 🧩 Features used: PANSAM scores across four subscales
- ⚙️ Technology: eXtreme Gradient Boosting (XGBoost) and SymScore
- 🏆 Performance: R² scores of 0.94, 0.92, 0.94, and 0.94 for subscales
🔑 Key Takeaways
- 📊 PANSAM-14 is a streamlined tool for assessing sleep appraisal.
- 💡 Machine learning was effectively utilized to refine the original PANSAM.
- 👩🔬 Data was collected through an online survey from 1,000 participants.
- 🏆 High accuracy achieved with R² scores around 0.93 for total score predictions.
- 🤖 SymScore provided a practical and interpretable scoring system.
- 🌍 Study conducted in South Korea, highlighting regional insights into sleep appraisal.
- 🆔 Clinical relevance: Useful for clinicians assessing dysfunctional sleep beliefs.
📚 Background
Sleep is a critical component of overall health, yet many individuals harbor dysfunctional beliefs about sleep that can exacerbate sleep-related issues. The original Positive And Negative Sleep Appraisal Measure (PANSAM) was designed to evaluate these beliefs across multiple dimensions. However, its length and complexity posed challenges for practical application in clinical settings. This study aimed to address these challenges by developing a more concise and effective tool.
🗒️ Study
Conducted in South Korea, the study involved an online survey of 1,000 participants to gather data on their PANSAM scores across four subscales. Researchers employed eXtreme Gradient Boosting (XGBoost) to identify the most representative items from each subscale, ensuring that the new measure would maintain predictive accuracy while being more user-friendly.
📈 Results
The development of the PANSAM-14 resulted in the selection of 14 key items that demonstrated high predictive accuracy for the total subscale scores, with R² values of 0.94 across the board. The SymScore-based scoring system provided a comparable performance to the XGBoost model, achieving an overall R² of 0.93, thus confirming its reliability and validity.
🌍 Impact and Implications
The introduction of the PANSAM-14 has significant implications for both clinical practice and research. By offering a reliable and valid tool for assessing dysfunctional beliefs about sleep, clinicians can better understand and address sleep-related issues in their patients. This advancement not only streamlines the assessment process but also enhances the potential for targeted interventions, ultimately improving patient outcomes in sleep health.
🔮 Conclusion
The study highlights the transformative potential of machine learning in developing psychological assessment tools. The PANSAM-14 stands as a testament to how technology can refine traditional measures, making them more accessible and effective. As we continue to explore the intersection of technology and health, further research in this area is encouraged to enhance our understanding of sleep and its impact on overall well-being.
💬 Your comments
What are your thoughts on the development of the PANSAM-14? How do you think machine learning can further improve psychological assessments? Let’s engage in a discussion! 💬 Share your insights in the comments below or connect with us on social media:
Machine learning approached a 14-item shortened version of the Positive And Negative Sleep Appraisal Measure (PANSAM-14).
Abstract
BACKGROUND: This study aimed to develop a shortened version of the Positive And Negative Sleep Appraisal Measure (PANSAM) that accurately predicts the total score across its four subscales using a machine learning-based approach to streamline the subscales of PANSAM using eXtreme Gradient Boosting (XGBoost).
METHODS: We collected data from 1,000 participants in South Korea through an online survey, measuring the PANSAM scores for each subscale. To identify the most representative items within each subscale, we used eXtreme Gradient Boosting (XGBoost), which can assess the predictive strength of each item based on the R² score. Additionally, we assigned optimal weights using the Symbolic Regression-Based Clinical Score Generator (SymScore) to ensure a refined and interpretable scoring system.
RESULTS: We developed the SymScore-based PANSAM-14, selecting 14 representative items across the four subscales: Subscale 1 (Items 12, 15, 16, and 24), Subscale 2 (Items 10, 18, and 21), Subscale 3 (Items 3, 11, and 19), and Subscale 4 (Items 1, 13, 25, and 29). These selected items demonstrated high accuracy in predicting subscale scores (R² = 0.94, 0.92, 0.94, and 0.94). We then developed a simple and interpretable scoring table using SymScore, achieving performance in predicting the total score comparable to the XGBoost-based version (R² = 0.93, 0.93, 0.94, and 0.95) while offering a practical and interpretable alternative.
CONCLUSION: The SymScore-based PANSAM-14 exhibits high predictive accuracy for the total subscale scores. It can be used as a useful, reliable, and valid tool for assessing individuals’ dysfunctional beliefs about sleep.
Author: [‘Lim M’, ‘Kim S’, ‘Jeon S’, ‘Jeong EM’, ‘Kim J’, ‘Chung S’]
Journal: Sleep Breath
Citation: Lim M, et al. Machine learning approached a 14-item shortened version of the Positive And Negative Sleep Appraisal Measure (PANSAM-14). Machine learning approached a 14-item shortened version of the Positive And Negative Sleep Appraisal Measure (PANSAM-14). 2026; 30:(unknown pages). doi: 10.1007/s11325-026-03629-8