Explore the vast range of titles available.

Background Statistical methods that use the mid- p approach are useful tools to analyze categorical data, particularly for small and moderate sample sizes. Mid- p tests strike a balance between overly conservative exact methods and asymptotic methods that frequently violate the nominal level. Here, we examine a mid- p version of the McNemar exact conditional test for the analysis of paired binomial proportions. Methods We compare the type I error rates and power of the mid- p test with those of the asymptotic McNemar test (with and without continuity correction), the McNemar exact conditional test, and an exact unconditional test using complete enumeration. We show how the mid- p test can be calculated using eight standard software packages, including Excel. Results The mid- p test performs well compared with the asymptotic, asymptotic with continuity correction, and exact conditional tests, and almost as good as the vastly more complex exact unconditional test. Even though the mid- p test does not guarantee preservation of the significance level, it did not violate the nominal level in any of the 9595 scenarios considered in this article. It was almost as powerful as the asymptotic test. The exact conditional test and the asymptotic test with continuity correction did not perform well for any of the considered scenarios. Conclusions The easy-to-calculate mid- p test is an excellent alternative to the complex exact unconditional test. Both can be recommended for use in any situation. We also recommend the asymptotic test if small but frequent violations of the nominal level is acceptable.

Most patients with hip fractures are characterised by older age (>70 years), frailty, and functional deterioration, and their long-term outcomes are poor with increased costs. We compared the effectiveness and cost-effectiveness of giving these patients comprehensive geriatric care in a dedicated geriatric ward versus the usual orthopaedic care. We did a prospective, single-centre, randomised, parallel-group, controlled trial. Between April 18, 2008, and Dec 30, 2010, we randomly assigned home-dwelling patients with hip-fractures aged 70 years or older who were able to walk 10 m before their fracture, to either comprehensive geriatric care or orthopaedic care in the emergency department, to achieve the required sample of 400 patients. Randomisation was achieved via a web-based, computer-generated, block method with unknown block sizes. The primary outcome, analysed by intention to treat, was mobility measured with the Short Physical Performance Battery (SPPB) 4 months after surgery for the fracture. The type of treatment was not concealed from the patients or staff delivering the care, and assessors were only partly masked to the treatment during follow-up. This trial is registered with ClinicalTrials.gov, number NCT00667914. We assessed 1077 patients for eligibility, and excluded 680, mainly for not meeting the inclusion criteria such as living in a nursing home or being aged less than 70 years. Of the remaining patients, we randomly assigned 198 to comprehensive geriatric care and 199 to orthopaedic care. At 4 months, 174 patients remained in the comprehensive geriatric care group and 170 in the orthopaedic care group; the main reason for dropout was death. Mean SPPB scores at 4 months were 5·12 (SE 0·20) for comprehensive geriatric care and 4·38 (SE 0·20) for orthopaedic care (between-group difference 0·74, 95% CI 0·18–1·30, p=0·010). Immediate admission of patients aged 70 years or more with a hip fracture to comprehensive geriatric care in a dedicated ward improved mobility at 4 months, compared with the usual orthopaedic care. The results suggest that the treatment of older patients with hip fractures should be organised as orthogeriatric care. Norwegian Research Council, Central Norway Regional Health Authority, St Olav Hospital Trust and Fund for Research and Innovation, Liaison Committee between Central Norway Regional Health Authority and the Norwegian University of Science and Technology, the Department of Neuroscience at the Norwegian University of Science and Technology, Foundation for Scientific and Industrial Research at the Norwegian Institute of Technology (SINTEF), and the Municipality of Trondheim.

The relationship between two independent binomial proportions is commonly estimated and presented using the difference between proportions, the number needed to treat, the ratio of proportions or the odds ratio. Several different confidence intervals are available, but they can produce markedly different results. Some of the traditional approaches, such as the Wald interval for the difference between proportions and the Katz log interval for the ratio of proportions, do not perform well unless the sample size is large. Better intervals are available. This article describes and compares approximate and exact confidence intervals that are – with one exception – easy to calculate or available in common software packages. We illustrate the performances of the intervals and make recommendations for both small and moderate-to-large sample sizes.

It is quite common to investigate multiple hypotheses in a single study. For example, a researcher may want to investigate the effect on several outcome variables or at different time points, compare more than two groups or undertake separate analyses for subgroups. This increases the probability of type I errors. Different procedures for multiplicity adjustment are available to control the probability of type I errors. In the present article, we describe some methods for multiplicity adjustment, along with recommendations.

Background The purpose of this study was to assess trends in incidence and presentation of colorectal cancer (CRC) over a period of 37 years in a stable population in Mid-Norway. Secondarily, we wanted to predict the future burden of CRC in the same catchment area. Methods All 2268 patients diagnosed with CRC at Levanger Hospital between 1980 and 2016 were included in this study. We used Poisson regression to calculate the incidence rate ratio (IRR) and analyse factors associated with incidence. Results The incidence of CRC increased from 43/100,000 person-years during 1980–1984 to 84/100,000 person-years during 2012–2016. Unadjusted IRR increased by 1.8% per year, corresponding to an overall increase in incidence of 94.5%. Changes in population (ageing and sex distribution) contributed to 28% of this increase, whereas 72% must be attributed to primary preventable factors associated with lifestyle. Compared with the last observational period, we predict a further 40% increase by 2030, and a 70% increase by 2040. Acute colorectal obstruction was associated with tumours in the left flexure and descending colon. Spontaneous colorectal perforation was associated with tumours in the descending colon, caecum, and sigmoid colon. The incidence of obstruction remained stable, while the incidence of perforation decreased throughout the observational period. The proportion of earlier stages at diagnosis increased significantly in recent decades. Conclusion CRC incidence increased substantially from 1980 to 2016, mainly due to primary preventable factors. The incidence will continue to increase during the next two decades, mainly due to further ageing of the population.

Background Adolescence is a critical period with elevated vulnerability to suicidality. Despite the importance of protective factors in reducing suicidal ideation (SI) and suicide attempts (SA), research in this area remains limited. This study investigated the associations between protective factors in early adolescence and the subsequent outcomes of SI and SA a year later, while also examining sex differences in these associations. Methods This study utilized data from a representative sample at two timepoints, T1 ( N  = 2464, 50.8% females, mean age = 13.7, SD = 0.6) in 1998 and T2 ( N  = 2432, 50.4% females, mean age = 14.9, SD = 0.6) one year later, collected as part of the longitudinal Youth and Mental Health Study (YAMHS) in Norway. Individual, social and environmental protective factors were identified based on prior research and theoretical frameworks. We used linear (or ordinal logistic) regression analyses with SI (or SA) as dependent variable, and one protective factor, sex and their interaction as covariates. Results Positive self-perceptions (T1) were significantly associated with reduced SI and SA one year later (T2) for both sexes. Specifically, self-worth was more strongly associated with reduced SI in females ( B = -0.16, 95% CI: -0.20 to -0.12, p  <.001) than males ( B = -0.08, 95% CI: -0.12 to -0.04, p  <.001). The interaction between sex and social competence influenced the likelihood of SA, with males (OR = 0.24, 95% CI: 0.13 to 0.42, p  <.001) showing a greater reduction than females (OR = 0.53, 95% CI: 0.35 to 0.80, p  =.009), although this association only showed a trend towards significance ( p  =.083). Higher physical activity and school connectedness/wellbeing were associated with lower SI, and school connectedness/wellbeing to lower SA, with no sex differences. No significant associations were found between task-oriented coping, attachment, family functioning or socio-economic status and SI or SA. Conclusions Fostering positive self-perception, physical activity, and school connectedness/wellbeing is important for adolescent suicide prevention, as these factors contribute to reducing suicidality. Sex differences were observed in the associations between self-worth and SI, as well as social competence and SA. Future research should explore additional protective factors across sex and gender groups.

Time-restricted eating (TRE) and high-intensity interval training (HIIT) improve cardiometabolic health in individuals with overweight/obesity, with high adherence rates in supervised settings. Long-term maintenance of TRE and HIIT in real-world settings is unknown. In our previous TREHIIT trial, 131 women (body mass index (BMI) ≥ 27 kg/m 2 ) were randomized to 7 weeks of TRE (eating window 10-h/day), HIIT (3 sessions/week), a combination (TREHIIT), or no intervention (CON). We investigated self-reported continuation of TRE and/or HIIT after 2 years. Fifty-nine participants (39.0 years (standard deviation (SD) 6.1), BMI 30.7 kg/m 2 (SD 4.2)) attended the follow-up. Of those who completed the 7-week TRE or HIIT intervention, 46% maintained TRE and 45% continued HIIT for 2 years. There were no statistically significant (at p  < .01) between-group differences in cardiometabolic outcomes, but non-significant lower body mass in HIIT (-4.2 kg, 95% confidence interval (CI), -7.7 to -0.7, p  = .019) and visceral fat in TREHIIT (-18 cm 2 , CI, -33 to -4, p  = .015) versus CON. After 2 years, HIIT and TREHIIT had ~ 4 kg lower fat mass and ~ 20 cm² lower visceral fat (both p  < .001) compared with baseline. A short-term TRE and HIIT intervention may promote long-term lifestyle changes and health benefits. Future studies should collect objective adherence data to understand long-term maintenance of TRE and HIIT.

Background Motor and cognitive impairments are frequently observed following stroke, but are often managed as distinct entities, and there is little evidence regarding how they are related. The aim of this study was to describe the prevalence of concurrent motor and cognitive impairments 3 months after stroke and to examine how motor performance was associated with memory, executive function and global cognition. Methods The Norwegian Cognitive Impairment After Stroke (Nor-COAST) study is a prospective multicentre cohort study including patients hospitalized with acute stroke between May 2015 and March 2017. The National Institutes of Health Stroke Scale (NIHSS) was used to measure stroke severity at admission. Level of disability was assessed by the Modified Rankin Scale (mRS). Motor and cognitive functions were assessed 3 months post-stroke using the Montreal Cognitive Assessment (MoCA), Trail Making Test Part B (TMT-B), 10-Word List Recall (10WLR), Short Physical Performance Battery (SPPB), dual-task cost (DTC) and grip strength (Jamar®). Cut-offs were set according to current recommendations. Associations were examined using linear regression with cognitive tests as dependent variables and motor domains as covariates, adjusted for age, sex, education and stroke severity. Results Of 567 participants included, 242 (43%) were women, mean (SD) age was 72.2 (11.7) years, 416 (75%) had an NIHSS score ≤ 4 and 475 (84%) had an mRS score of ≤2. Prevalence of concurrent motor and cognitive impairment ranged from 9.5% for DTC and 10WLR to 22.9% for grip strength and TMT-B. SPPB was associated with MoCA (regression coefficient B = 0.465, 95%CI [0.352, 0.578]), TMT-B (B = -9.494, 95%CI [− 11.726, − 7.925]) and 10WLR (B = 0.132, 95%CI [0.054, 0.211]). Grip strength was associated with MoCA (B = 0.075, 95%CI [0.039, 0.112]), TMT-B (B = -1.972, 95%CI [− 2.672, − 1.272]) and 10WLR (B = 0.041, 95%CI [0.016, 0.066]). Higher DTC was associated with more time needed to complete TMT-B (B = 0.475, 95%CI [0.075, 0.875]) but not with MoCA or 10WLR. Conclusion Three months after suffering mainly minor strokes, 30–40% of participants had motor or cognitive impairments, while 20% had concurrent impairments. Motor performance was associated with memory, executive function and global cognition. The identification of concurrent impairments could be relevant for preventing functional decline. Trial registration ClinicalTrials.gov Identifier: NCT02650531 .