Background:Machine learning(ML)methodologies offer significant flexibility and scalability,driving their adop-tion in medical research,including pain studies.However,their potential in analyzing the interplay between ...Background:Machine learning(ML)methodologies offer significant flexibility and scalability,driving their adop-tion in medical research,including pain studies.However,their potential in analyzing the interplay between pain factors and sleep remains underexplored.Objective:This study aimed to investigate the effects of pain-related factors on deep sleep duration in patients and to develop predictive models using ML techniques.Methods:Six machine learning models were employed to analyze pain-related factors affecting sleep,with the most stable and accurate model selected for further analysis.The Gradient Boosted Decision Tree(GBDT)model demonstrated superior performance,achieving an internal validation accuracy of 0.897 and an external validation accuracy of 0.885,with area under the curve(AUC)values exceeding 0.6 in both validations.Importance analysis using the GBDT model identified key factors influencing sleep duration.Results:Trauma-related pain was identified as the most significant factor affecting deep sleep duration(Impor-tance score:0.16),followed closely by the use of alternative medical therapies(Importance score:0.14).Among the 385 patients included,203 reported utilizing alternative medical therapies,such as acupuncture,moxibus-tion,and herbal remedies.Patients using these therapies experienced a reduced risk of disruptions in deep sleep duration,highlighting the potential analgesic and therapeutic effects of these interventions.Conclusion:ML models effectively identify factors influencing sleep in pain patients.Alternative therapies may mitigate deep sleep disturbances,highlighting their potential role in pain management.展开更多
Background: The balance of autonomic nervous system activity and its relationship with body composition, sleep quality, and activities of daily living among older people is still unclear. Purpose: This comparative cas...Background: The balance of autonomic nervous system activity and its relationship with body composition, sleep quality, and activities of daily living among older people is still unclear. Purpose: This comparative case study examined the characteristics of body composition, sleep quality, and autonomic nerve activity in active older adults with a younger body age-calculated from age trends in body composition and basal metabolic rate. Methods: We selected two cases with a metabolic age younger than their actual age. They had good sleep quality, no sarcopenia, strong muscle and grip strength, and balanced autonomic nervous system activity. They were compared with two other age- and gender-matched cases, who had poor sleep quality, unbalanced autonomic nervous system activity, and had a physical age closer to their actual age. Results: Older adults with more muscle mass and higher basal metabolism were younger than their actual age, had a better sleep status, and had a good balance of autonomic nervous activity during exercise stimulation. They also had lower percentages of body and visceral fat and higher percentages of body water. Conclusion: Two cases had a metabolic age younger than their actual age were found to be much younger than their actual age. However, the older adults with normal muscle mass and basal metabolic rate had poor sleep status and no sympathetic hyperactivity during exercise simulation.展开更多
基金supported by the National Natural Science Founda-tion of China(No.:82304760)Zhejiang Province Traditional Chinese Medicine Science and Technology Program Project(No.:2023ZL429)+1 种基金General scientific research projects of Zhejiang Provincial Department of Education(No.:Y202044448)Zhejiang Province College Student Sci-ence and Technology Innovation Project(No.:2017R410007).
文摘Background:Machine learning(ML)methodologies offer significant flexibility and scalability,driving their adop-tion in medical research,including pain studies.However,their potential in analyzing the interplay between pain factors and sleep remains underexplored.Objective:This study aimed to investigate the effects of pain-related factors on deep sleep duration in patients and to develop predictive models using ML techniques.Methods:Six machine learning models were employed to analyze pain-related factors affecting sleep,with the most stable and accurate model selected for further analysis.The Gradient Boosted Decision Tree(GBDT)model demonstrated superior performance,achieving an internal validation accuracy of 0.897 and an external validation accuracy of 0.885,with area under the curve(AUC)values exceeding 0.6 in both validations.Importance analysis using the GBDT model identified key factors influencing sleep duration.Results:Trauma-related pain was identified as the most significant factor affecting deep sleep duration(Impor-tance score:0.16),followed closely by the use of alternative medical therapies(Importance score:0.14).Among the 385 patients included,203 reported utilizing alternative medical therapies,such as acupuncture,moxibus-tion,and herbal remedies.Patients using these therapies experienced a reduced risk of disruptions in deep sleep duration,highlighting the potential analgesic and therapeutic effects of these interventions.Conclusion:ML models effectively identify factors influencing sleep in pain patients.Alternative therapies may mitigate deep sleep disturbances,highlighting their potential role in pain management.
文摘Background: The balance of autonomic nervous system activity and its relationship with body composition, sleep quality, and activities of daily living among older people is still unclear. Purpose: This comparative case study examined the characteristics of body composition, sleep quality, and autonomic nerve activity in active older adults with a younger body age-calculated from age trends in body composition and basal metabolic rate. Methods: We selected two cases with a metabolic age younger than their actual age. They had good sleep quality, no sarcopenia, strong muscle and grip strength, and balanced autonomic nervous system activity. They were compared with two other age- and gender-matched cases, who had poor sleep quality, unbalanced autonomic nervous system activity, and had a physical age closer to their actual age. Results: Older adults with more muscle mass and higher basal metabolism were younger than their actual age, had a better sleep status, and had a good balance of autonomic nervous activity during exercise stimulation. They also had lower percentages of body and visceral fat and higher percentages of body water. Conclusion: Two cases had a metabolic age younger than their actual age were found to be much younger than their actual age. However, the older adults with normal muscle mass and basal metabolic rate had poor sleep status and no sympathetic hyperactivity during exercise simulation.
