Statistical analysis is critical in medical research. The objective of this article is to summarize the appropriate use and reporting of commonly used statistical methods in medical research, on the basis of existing statistical guidelines and the authors’ experience in reviewing manuscripts, to provide recommendations for statistical applications and reporting.

No abstract

BackgroundAlthough associations of physical activity and smoking with mortality have been well-established, the joint impact of physical activity and smoking on premature mortality among elderly hypertensive population was still unclear. This study aimed to assess association of physical activity, smoking, and their interaction with all-cause and cardiovascular disease (CVD) mortality risk in elderly hypertensive patients.MethodsWe included 125,978 Chinese hypertensive patients aged 60–85 years [mean (SD) age, 70.5 (6.9) years] who had records in electronic health information system of Minhang District of Shanghai, China in 2007–2015. Cox regression was used to estimate individual and joint association of smoking and physical activity on all-cause and CVD mortality. Interactions were measured both additively and multiplicatively. Additive interaction was evaluated by relative excess risk due to interaction (RERI), attributable proportion due to interaction (AP) and synergy index (S).ResultsAmong 125,978 elderly hypertensive patients (median age 70.1), 28,250 deaths from all causes and 13,164 deaths from CVD were observed during the follow-up up to 11 years. There was an additive interaction between smoking and physical inactivity [RERI: all-cause 0.19 (95% CI: 0.04–0.34), CVD 0.28 (0.06–0.50); AP: all-cause 0.09 (0.02–0.16), CVD 0.14 (0.04–0.23); S: all-cause 1.21 (1.04–1.42), CVD 1.36 (1.06–1.75)], while the concurrence of both risk factors was associated with more than 2-fold risk of death [hazard ratio (HR): all-cause 2.10 (1.99–2.21), CVD 2.19 (2.02–2.38)].ConclusionOur study suggested that smoking and physical inactivity together may have amplified association on premature death compared to the sum of their individual associations, highlighting the importance of improving behavioral factors in combination and promoting a comprehensive healthy lifestyle in hypertensive elderly.

Objective: The influence of mobile phone addiction (MPA) on physical exercise in university students was explored, and peer relationships were introduced as a moderating variable. Methods: A cross-sectional study design was adopted, and an online survey questionnaire was conducted to investigate two universities in Nantong City, Jiangsu Province, and Chongzuo City, Guangxi Zhuang Autonomous Region. A total of 4959 university students completed the questionnaire. Measurement tools included the Mobile Phone Addiction Tendency Scale, the Physical Activity Rating Scale, and the Peer Rating Scale of university students. Results: University students scored 39.322 ± 15.139 for MPA and 44.022 ± 7.735 for peer relationships, with 87.8% of their physical exercise, in terms of exercise grade, being classified as medium or low intensity. The MPA of the university students was negatively correlated with peer relationships (r = −0.377, p < 0.001) and physical exercise behavior (r = −0.279, p < 0.001). The moderating effect of peer relationships on the MPA-physical exercise behavior relationship was significant (ΔR2 = 0.03, p < 0.001). Conclusions: The physical exercise of university students was at a medium or low intensity. The more serious the university students’ addiction to mobile phones was, the lower the amount of physical exercise. The physical activity of males was higher than that of females. MPA and peer relationships were the limiting factors of the physical exercise behavior of university students. Under the lower effect of peer relationship regulation, MPA had a greater negative impact on physical exercise behavior. The data from this research can provide theoretical support to improve the participation of university students in physical activities.

Background Gait disturbances may appear prior to cognitive dysfunction in the early stage of silent cerebrovascular disease (SCD). Subtle changes in gait characteristics may provide an early warning of later cognitive decline. Our team has proposed a vision-based artificial intelligent gait analyzer for the rapid detection of spatiotemporal parameters and walking pattern based on videos of the Timed Up and Go (TUG) test. The primary objective of this study is to investigate the relationship between gait features assessed by our artificial intelligent gait analyzer and cognitive function changes in patients with SCD. Methods This will be a multicenter prospective cohort study involving a total of 14 hospitals from Shanghai and Guizhou. One thousand and six hundred patients with SCD aged 60–85 years will be consecutively recruited. Eligible patients will undergo the intelligent gait assessment and neuropsychological evaluation at baseline and at 1-year follow-up. The intelligent gait analyzer will divide participant into normal gait group and abnormal gait group according to their walking performance in the TUG videos at baseline. All participants will be naturally observed during 1-year follow-up period. Primary outcome are the changes in Mini-Mental State Examination (MMSE) score. Secondary outcomes include the changes in intelligent gait spatiotemporal parameters (step length, gait speed, step frequency, step width, standing up time, and turning back time), the changes in scores on other neuropsychological tests (Montreal Cognitive Assessment, the Stroop Color Word Test, and Digit Span Test), falls events, and cerebrovascular events. We hypothesize that both groups will show a decline in MMSE score, but the decrease of MMSE score in the abnormal gait group will be more significant. Conclusion This study will be the first to explore the relationship between gait features assessed by an artificial intelligent gait analyzer and cognitive decline in patients with SCD. It will demonstrate whether subtle gait abnormalities detected by the artificial intelligent gait analyzer can act as a cognitive-related marker for patients with SCD. Trial registration This trial was registered at ClinicalTrials.gov (NCT04456348; 2 July 2020).