Objective This paper presents an experimental design, the micro-randomized trial, developed to support optimization of just-in-time adaptive interventions (JITAIs). JITAIs are mHealth technologies that aim to deliver the right intervention components at the right times and locations to optimally support individuals’ health behaviors. Micro-randomized trials offer a way to optimize such interventions by enabling modeling of causal effects and time-varying effect moderation for individual intervention components within a JITAI. Methods The paper describes the micro-randomized trial design, enumerates research questions that this experimental design can help answer, and provides an overview of the data analyses that can be used to assess the causal effects of studied intervention components and investigate time-varying moderation of those effects. Results Micro-randomized trials enable causal modeling of proximal effects of the randomized intervention components and assessment of time-varying moderation of those effects. Conclusions Micro-randomized trials can help researchers understand whether their interventions are having intended effects, when and for whom they are effective, and what factors moderate the interventions’ effects, enabling creation of more effective JITAIs.

In mobile health interventions aimed at behavior change and maintenance, treatments are provided in real time to manage current or impending high risk situations or promote healthy behaviors in near real time. Currently there is great scientific interest in developing data analysis approaches to guide the development of mobile interventions. In particular data from mobile health studies might be used to examine effect moderators—individual characteristics, time-varying context or past treatment response that moderate the effect of current treatment on a subsequent response. This paper introduces a formal definition for moderated effects in terms of potential outcomes, a definition that is particularly suited to mobile interventions, where treatment occasions are numerous, individuals are not always available for treatment, and potential moderators might be influenced by past treatment. Methods for estimating moderated effects are developed and compared. The proposed approach is illustrated using BASICS-Mobile, a smartphone-based intervention designed to curb heavy drinking and smoking among college students.

Prolonged mechanical ventilation after cardiac surgery can be accurately predicted by readily available pre- and intraoperative information.

BACKGROUND: Cross-sectional studies in ulcerative colitis (UC) have shown at best a moderate association between histologic and clinical measures of disease activity, but few longitudinal studies have evaluated this relationship. As endoscopy and histology are both independent predictors of clinical outcomes in UC, there remains a need to assess these measures in parallel to demonstrate clinical benefit. HICKORY (NCT02100696) is an ongoing Phase 3 study evaluating etrolizumab in anti-tumor necrosis factor (aTNF)–experienced patients with moderate-to-severe UC. The correlation between histologic changes and established disease activity measures at end of induction (week 14) was assessed using data from the open-label induction (OLI) cohort of HICKORY. METHODS: Study analysis is based on data from patients in the OLI cohort who received ≥1 dose of etrolizumab 105 mg subcutaneously every 4 weeks during the 14-week induction phase. Baseline and week 14 biopsies were scored by 1 of 4 central readers using the Nancy histologic index (NHI) and the Robarts histopathology index (RHI) in patients who had active baseline histology (NHI >1 and RHI >3) and complete scoring at week 14 (n = 97). Binary week 14 histologic outcomes were characterized by presence or absence of neutrophils (NHI ≤1 or RHI ≤3 and Geboes subgrades 2B.0/3.0). Mayo Clinic score (MCS) endoscopic subscore (ES) was used to assess endoscopy. Pairwise associations were quantified by Spearman correlation (ρ; for correlation between change from baseline scores) and Cohen kappa coefficients (κ; for agreement among week 14 outcomes). ΔNHI and ΔRHI were compared to determine presence of a minimum clinically important difference (MCID) in MCS (∆MCS ≥3 from baseline). RESULTS: At week 14, 22% (21/97), 23% (22/97), and 8% (8/97) of patients achieved resolution of neutrophilic inflammation based on either NHI or RHI/Geboes, endoscopic improvement (ES ≤ 1), and endoscopic remission (ES = 0), respectively. Among patients with endoscopic improvement and endoscopic remission, neutrophilic resolution was achieved in 55% (12/22) and 75% (6/8) of patients, respectively. ΔNHI and ΔRHI were highly correlated (ρ = 0.91). There was weak to no association between ΔNHI/ΔRHI/ΔES and Δfecal calprotectin (ρ = –0.02 to 0.38), ΔC-reactive protein (ρ = 0.03 to 0.07), Δalbumin (ρ = –0.19 to –0.10), Δhemoglobin (ρ = –0.22 to –0.19), and Δsegmented neutrophils in the blood (ρ = –0.06 to 0.01). Weak correlations were observed between ΔNHI/ΔRHI and ΔES (ρ = 0.26–0.27), Δrectal bleeding (ρ = 0.24–0.28), and Δstool frequency (ρ = 0.40–0.42). Correlations between NHI, RHI/Geboes, and ES with symptomatic outcomes were weak (κ = 0.28–0.45). Difference in the mean grouped by achievement of ΔMCS ≥3 suggests MCIDs in ΔNHI and ΔRHI of 1.2 and 8.6, respectively. CONCLUSION(S): The analysis showed weak to moderate agreement between changes in histologic scores and changes in endoscopic scores, and weak to no agreement between changes in histologic scores and changes in laboratory results at week 14. There was a weak correlation between histologic scores and symptoms at the end of induction. MCID results suggest that both the NHI and RHI appear to effectively evaluate neutrophilic resolution, making the changes in score more clinically interpretable.

Cancer clinical trials are routinely designed to assess the effect of treatment on disease progression and death, often in terms of a composite endpoint called progression‐free survival. When progression status is known only at periodic assessment times, the progression time is interval censored, and complications arise in the analysis of progression‐free survival. Despite the advances in methods for dealing with interval‐censored data, naive methods such as right‐endpoint imputation are widely adopted in this setting. We examine the asymptotic and empirical properties of estimators of the marginal progression‐free survival functions and associated treatment effects under this scheme. Specifically, we explore the determinants of the asymptotic bias and point out that there is typically a loss in power of tests for treatment effects. Copyright © 2015 John Wiley & Sons, Ltd.