Randomized trials typically estimate average relative treatment effects, but decisions on the benefit of a treatment are possibly better informed by more individualized predictions of the absolute treatment effect. In case of a binary outcome, these predictions of absolute individualized treatment effect require knowledge of the individual's risk without treatment and incorporation of a possibly differential treatment effect (ie, varying with patient characteristics). In this article, we lay out the causal structure of individualized treatment effect in terms of potential outcomes and describe the required assumptions that underlie a causal interpretation of its prediction. Subsequently, we describe regression models and model estimation techniques that can be used to move from average to more individualized treatment effect predictions. We focus mainly on logistic regression‐based methods that are both well‐known and naturally provide the required probabilistic estimates. We incorporate key components from both causal inference and prediction research to arrive at individualized treatment effect predictions. While the separate components are well known, their successful amalgamation is very much an ongoing field of research. We cut the problem down to its essentials in the setting of a randomized trial, discuss the importance of a clear definition of the estimand of interest, provide insight into the required assumptions, and give guidance with respect to modeling and estimation options. Simulated data illustrate the potential of different modeling options across scenarios that vary both average treatment effect and treatment effect heterogeneity. Two applied examples illustrate individualized treatment effect prediction in randomized trial data.

Individual participant data meta-analysis (IPD-MA) is considered the gold standard for investigating subgroup effects. Frequently used regression-based approaches to detect subgroups in IPD-MA are: meta-regression, per-subgroup meta-analysis (PS-MA), meta-analysis of interaction terms (MA-IT), naive one-stage IPD-MA (ignoring potential study-level confounding), and centred one-stage IPD-MA (accounting for potential study-level confounding). Clear guidance on the analyses is lacking and clinical researchers may use approaches with suboptimal efficiency to investigate subgroup effects in an IPD setting. Therefore, our aim is to overview and compare the aforementioned methods, and provide recommendations over which should be preferred. We conducted a simulation study where we generated IPD of randomised trials and varied the magnitude of subgroup effect (0, 25, 50% relative reduction), between-study treatment effect heterogeneity (none, medium, large), ecological bias (none, quantitative, qualitative), sample size (50,100,200), and number of trials (5,10) for binary, continuous and time-to-event outcomes. For each scenario, we assessed the power, false positive rate (FPR) and bias of aforementioned five approaches. Naive and centred IPD-MA yielded the highest power, whilst preserving acceptable FPR around the nominal 5% in all scenarios. Centred IPD-MA showed slightly less biased estimates than naïve IPD-MA. Similar results were obtained for MA-IT, except when analysing binary outcomes (where it yielded less power and FPR < 5%). PS-MA showed similar power as MA-IT in non-heterogeneous scenarios, but power collapsed as heterogeneity increased, and decreased even more in the presence of ecological bias. PS-MA suffered from too high FPRs in non-heterogeneous settings and showed biased estimates in all scenarios. Meta-regression showed poor power (< 20%) in all scenarios and completely biased results in settings with qualitative ecological bias. Our results indicate that subgroup detection in IPD-MA requires careful modelling. Naive and centred IPD-MA performed equally well, but due to less bias of the estimates in the presence of ecological bias, we recommend the latter.

Background Modelling non-linear associations between an outcome and continuous patient characteristics, whilst investigating heterogeneous treatment effects, is one of the opportunities offered by individual participant data meta-analysis (IPD-MA). Splines offer great flexibility, but guidance is lacking. Objective To introduce modelling of nonlinear associations using restricted cubic splines (RCS), natural B-splines, P-splines, and smoothing splines in IPD-MA to estimate absolute treatment effects. Methods We describe the pooling of spline-based models using pointwise and multivariate meta-analysis (two-stage methods) and one-stage generalised additive mixed effects models (GAMMs). We illustrate their performance on three IPD-MA scenarios of five studies each: one where only the associations differ across studies, one where only the ranges of the effect modifier differ and one where both differ. We also evaluated the approaches in an empirical example, modelling the risk of fever and/or ear pain in children with acute otitis media conditional on age. Results In the first scenario, all pooling methods showed similar results. In the second and third scenario, pointwise meta-analysis was flexible but showed non-smooth results and wide confidence intervals; multivariate meta-analysis failed to converge with RCS, but was efficient with natural B-splines. GAMMs produced smooth pooled regression curves in all settings. In the empirical example, results were similar to the second and third scenario, except for multivariate meta-analysis with RCS, which now converged. Conclusion We provide guidance on the use of splines in IPD-MA, to capture heterogeneous treatment effects in presence of non-linear associations, thereby facilitating estimation of absolute treatment effects to enhance personalized healthcare.

Background: It is debated whether primary tumor laterality (PTL) is prognostic in all patients with colorectal liver metastases (CRLM) or only those with KRAS wild-type or KRAS-mutated tumors; Methods: We systematically reviewed PubMed for studies reporting on resected CRLM originating from left-sided (LS) versus right-sided (RS) colon cancer stratified by KRAS status. Individual participant data (IPD) were used if available. Given that there are two definitions of PTL, we performed two meta-analyses for KRAS-mutated and two for wild-type patients. To assess if an interaction underlies the possible difference between the effects of PTL in KRAS-mutated vs. wild-type CRLM, we similarly performed two meta-analyses of interaction terms; Results: The meta-analyses included eight studies and 7475 patients. PTL had a prognostic association with OS in patients with wild-type tumors (HR for LS: 0.71 [0.60–0.84]), but not in those with KRAS-mutated tumors (HR: 0.99 [0.82–1.19]). This difference stemmed from a truly variable effect of PTL for each KRAS status (mutated vs. wild-type) as the meta-analysis of interaction terms showed a significant interaction between them (HR:1.38 [1.24–1.53]). Similar results were obtained when the second definition of PTL (LS to not include the rectum) was used; Conclusions: KRAS status modifies the association of tumor site with survival. Right-sided tumors are associated with worse OS only in patients with wild-type CRLM.

There is little known about the dynamics within responses to Borrelia spp. upon repeated exposure to tick bites and the development of serological markers over time. Most studies have investigated antibody development in risk populations over a short period of time. Therefore, we aimed to study the dynamics of anti-Borrelia antibodies in forestry service workers over 8 years in association with tick bite exposure. Methods: Blood samples from 106 forestry service workers originally included in the 200 Functional Genomics Project (Radboudumc, Nijmegen, the Netherlands) were followed for 8 years and tested annually for anti-Borrelia antibodies (ELISA and Western blot). IgG seroconversion was related to the number of tick bites in the previous year, which was obtained through annual questionnaires. The hazard ratio for Borrelia IgG seroconversion was calculated using Cox regression survival analysis and a logistic regression model, both adjusting for age, gender and smoking. Results: Borrelia IgG seropositivity in the study population did not vary significantly between years and the average prevalence was 13.4%. Of the 27 subjects that underwent seroconversion during the study period, 22 reconverted from positive to negative. Eleven subjects seroconverted a second time. The total seroconversion rate per year (negative to positive) was 4.5%. Active smoking was associated with IgG seroconversion in the >5 tick bites group (p < 0.05). According to the two models used, the risks of IgG seroconversion in the >5 tick bites group were HR = 2.93 (p = 0.10) and OR = 3.36 (p < 0.0005). Conclusions: Borrelia IgG seroconversion in forestry service workers was significantly related to increasing tick bite exposure in a survival and logistic regression model adjusting for age, gender and smoking.