Modeling Risk Factors for Intraindividual Variability: A Mixed-Effects Beta-Binomial Model Applied to Cognitive Function in Older People in the English Longitudinal Study of Ageing.

Cognitive functioning in older age profoundly impacts quality of life and health. While most research on cognition in older age has focused on mean levels, intraindividual variability (IIV) around this may have risk factors and outcomes independent of the mean value. Investigating risk factors associated with IIV has typically involved deriving a summary statistic for each person from residual error around a fitted mean. However, this ignores uncertainty in the estimates, prohibits exploring associations with time-varying factors, and is biased by floor/ceiling effects. To address this, we propose a mixed-effects location scale beta-binomial model for estimating average probability and IIV in a word recall test in the English Longitudinal Study of Ageing. After adjusting for mean performance, an analysis of 9,873 individuals across 7 (mean = 3.4) waves (2002-2015) found IIV to be greater at older ages, with lower education, in females, with more difficulties in activities of daily living, in later birth cohorts, and when interviewers recorded issues potentially affecting test performance. Our study introduces a novel method for identifying groups with greater IIV in bounded discrete outcomes. Our findings have implications for daily functioning and care, and further work is needed to identify the impact for future health outcomes.

Risk Factors Associated with PTLD Related Mortality in Adult Multivisceral Transplant Recipients - A Single Centre Cohort Study.

Background: PTLD is a heterogeneous group of lymphoproliferative diseases which can add significant mortality following multivisceral transplantation (MVTx). Our study aimed to identify potential risk factors of mortality in adult MVTx recipients who developed PTLD. Methods: All adult recipients of intestinal-containing grafts transplanted in our institution between 2013 and 2022, and who developed PTLD, were included in the study. Results: PTLD-associated mortality was 28.6% (6/21). Increased relative risk of mortality was associated with Stage 3 ECOG performance score (p=0.005; HR 34.77; 95%CI 2.94-410.91), if the recipients had a splenectomy (p=0.036; HR 14.36; 95%CI 1.19-172.89), or required retransplantation (p=0.039; HR 11.23; 95% CI 1.13-112.12). There was a significant trend for increased risk of PTLD mortality with higher peak EBV load (p=0.008), longer time from MVTx to PTLD diagnosis (p=0.008), and higher donor age (p 0.001). Peak LDH before treatment commencement was significantly higher in the mortality group vs the survival group (520.3 +- 422.8 IU/L vs 321.8 +- 154.4 IU/L; HR 1.00, 95%CI 1.00 to 1.01, p=0.019). Peak viral load prior to treatment initiation (Cycle Threshold (CT) cutoff = 32) correlated with the relative risk of death in MVTx patients who developed PTLD [29.4 (3.5) CTs in survivors compared to 23.0 (4.0) CTs in the mortality group]. Conclusions: This is the first study to identify risk factors for PTLD-associated mortality in an adult MVTx recipient cohort. Validation in larger multicentre studies and subsequent risk stratification according to these risk factors may contribute to better survival in this group of patients.

Sociodemographic characteristics and longitudinal progression of multimorbidity: A multistate modelling analysis of a large primary care records dataset in England.

BACKGROUND: Multimorbidity, characterised by the coexistence of multiple chronic conditions in an individual, is a rising public health concern. While much of the existing research has focused on cross-sectional patterns of multimorbidity, there remains a need to better understand the longitudinal accumulation of diseases. This includes examining the associations between important sociodemographic characteristics and the rate of progression of chronic conditions. METHODS AND FINDINGS: We utilised electronic primary care records from 13.48 million participants in England, drawn from the Clinical Practice Research Datalink (CPRD Aurum), spanning from 2005 to 2020 with a median follow-up of 4.71 years (IQR: 1.78, 11.28). The study focused on 5 important chronic conditions: cardiovascular disease (CVD), type 2 diabetes (T2D), chronic kidney disease (CKD), heart failure (HF), and mental health (MH) conditions. Key sociodemographic characteristics considered include ethnicity, social and material deprivation, gender, and age. We employed a flexible spline-based parametric multistate model to investigate the associations between these sociodemographic characteristics and the rate of different disease transitions throughout multimorbidity development. Our findings reveal distinct association patterns across different disease transition types. Deprivation, gender, and age generally demonstrated stronger associations with disease diagnosis compared to ethnic group differences. Notably, the impact of these factors tended to attenuate with an increase in the number of preexisting conditions, especially for deprivation, gender, and age. For example, the hazard ratio (HR) (95% CI; p-value) for the association of deprivation with T2D diagnosis (comparing the most deprived quintile to the least deprived) is 1.76 ([1.74, 1.78]; p < 0.001) for those with no preexisting conditions and decreases to 0.95 ([0.75, 1.21]; p = 0.69) with 4 preexisting conditions. Furthermore, the impact of deprivation, gender, and age was typically more pronounced when transitioning from an MH condition. For instance, the HR (95% CI; p-value) for the association of deprivation with T2D diagnosis when transitioning from MH is 2.03 ([1.95, 2.12], p < 0.001), compared to transitions from CVD 1.50 ([1.43, 1.58], p < 0.001), CKD 1.37 ([1.30, 1.44], p < 0.001), and HF 1.55 ([1.34, 1.79], p < 0.001). A primary limitation of our study is that potential diagnostic inaccuracies in primary care records, such as underdiagnosis, overdiagnosis, or ascertainment bias of chronic conditions, could influence our results. CONCLUSIONS: Our results indicate that early phases of multimorbidity development could warrant increased attention. The potential importance of earlier detection and intervention of chronic conditions is underscored, particularly for MH conditions and higher-risk populations. These insights may have important implications for the management of multimorbidity.

Sample size estimation using a latent variable model for mixed outcome co-primary, multiple primary and composite endpoints.

Mixed outcome endpoints that combine multiple continuous and discrete components are often employed as primary outcome measures in clinical trials. These may be in the form of co-primary endpoints, which conclude effectiveness overall if an effect occurs in all of the components, or multiple primary endpoints, which require an effect in at least one of the components. Alternatively, they may be combined to form composite endpoints, which reduce the outcomes to a one-dimensional endpoint. There are many advantages to joint modeling the individual outcomes, however in order to do this in practice we require techniques for sample size estimation. In this article we show how the latent variable model can be used to estimate the joint endpoints and propose hypotheses, power calculations and sample size estimation methods for each. We illustrate the techniques using a numerical example based on a four-dimensional endpoint and find that the sample size required for the co-primary endpoint is larger than that required for the individual endpoint with the smallest effect size. Conversely, the sample size required in the multiple primary case is similar to that needed for the outcome with the largest effect size. We show that the empirical power is achieved for each endpoint and that the FWER can be sufficiently controlled using a Bonferroni correction if the correlations between endpoints are less than 0.5. Otherwise, less conservative adjustments may be needed. We further illustrate empirically the efficiency gains that may be achieved in the composite endpoint setting.

Explaining the Sex Effect on Survival in Cystic Fibrosis: a Joint Modeling Study of UK Registry Data.

BACKGROUND: Male sex is associated with better lung function and survival in people with cystic fibrosis but it is unclear whether the survival benefit is solely due to the sex-effect on lung function. METHODS: This study analyzes data between 1996 and 2015 from the longitudinal registry study of the UK Cystic Fibrosis Registry. We jointly analyze repeated measurements and time-to-event outcomes to assess how much of the sex effect on lung function also explains survival. These novel methods allow examination of association between percent of forced expiratory volume in 1 second (%FEV1) and covariates such as sex and genotype, and survival, in the same modeling framework. We estimate the probability of surviving one more year with a probit model. RESULTS: The dataset includes 81,129 lung function measurements of %FEV1 on 9,741 patients seen between 1996 and 2015 and captures 1,543 deaths. Males compared with females experienced a more gradual decline in %FEV1 (difference 0.11 per year 95% confidence interval [CI] = 0.08, 0.14). After adjusting for confounders, both overall level of %FEV1 and %FEV1 rate of change are associated with the concurrent hazard for death. There was evidence of a male survival advantage (probit coefficient 0.15; 95% CI = 0.10, 0.19) which changed little after adjustment for %FEV1 using conventional approaches but was attenuated by 37% on adjustment for %FEV1 level and slope in the joint model (0.09; 95% CI = 0.06, 0.12). CONCLUSIONS: We estimate that about 37% of the association of sex on survival in cystic fibrosis is mediated through lung function.

Greater variability in lipid measurements associated with cardiovascular disease and mortality: A 10-year diabetes cohort study.

AIM: To examine the associations between variability in lipids and the risk of cardiovascular disease (CVD) and mortality in patients with type 2 diabetes based on low-density lipoprotein-cholesterol (LDL-C), the total cholesterol (TC) to high-density lipoprotein-cholesterol (HDL-C) ratio and triglycerides (TG). MATERIALS AND METHODS: A retrospective cohort study included 125 047 primary care patients with type 2 diabetes aged 45-84 years without CVD during 2008-2012. The variability of LDL-C, TC to HDL-C and TG was determined using the standard deviation of variables in a mixed effects model to minimize regression dilution bias. The associations between variability in lipids and CVD and mortality risk were assessed by Cox regression. Subgroup analyses based on patients' baseline characteristics were also conducted. RESULTS: A total of 19 913 CVD events and 15 329 mortalities were recorded after a median follow-up period of 77.5 months (0.8 million person-years), suggesting a positive linear relationship between variability in lipids and the risk of CVD and mortality. Each unit increase in the variability of LDL-C (mmol/L), the TC to HDL-C ratio and TG (mmol/L) was associated with a 27% (HR: 1.27 [95% CI: 1.20-1.34]), 31% (HR:1.31 [95% CI: 1.25-1.38]) and 9% (HR: 1.09 [95% CI: 1.04-1.15]) increase in the risk of composite endpoint of CVD and mortality, respectively. Age-specific effects were also found when comparing LDL-C variability, with patients aged 45-54 years (HR: 1.70 [95% CI: 1.42-2.02]) exhibiting a 53% increased risk for the composite endpoints than those aged 75-84 years (HR: 1.11 [95% CI: 1.01-1.23]). Similar age effects were observed for both the TC to HDL-C ratio and TG variability. Significant associations remained consistent among most of the subgroups. CONCLUSIONS: Variability in respective lipids are significant factors in predicting CVD and mortality in primary care patients with type 2 diabetes, with the strongest effects related to LDL-C and the TC to HDL-C ratio and most significant in the younger age group of patients aged 45-54 years. Further study is warranted to confirm these findings.

Factors predicting poor glycemic control in the first two years of childhood onset type 1 diabetes in a cohort from East London, UK: Analyses using mixed effects fractional polynomial models.

BACKGROUND/OBJECTIVE: Poor early glycemic control in childhood onset type 1 diabetes (T1D) is associated with future risk of acute and chronic complications. Our aim was to identify the predictors of higher glycated hemoglobin (HbA1c) within 24 months of T1D diagnosis in children and adolescents. METHODS: Mixed effects models with fractional polynomials were used to analyze longitudinal data of patients <19 years of age, followed from T1D diagnosis for up to 2 years, at three diabetes clinics in East London, United Kingdom. RESULTS: A total of 2209 HbA1c observations were available for 356 patients (52.5% female; 64.4% non-white), followed from within 3 months of diagnosis during years 2005 to 2015, with a mean ± SD of 6.2 ± 2.5 HbA1c observations/participant. The mean age and HbA1c at diagnosis were 8.9 ± 4.3 years and 10.7% ±4.3% (or expressed as mmol/mol HbA1c mean ± SD 92.9 ± 23.10 mmol/mol) respectively. Over the 2 years following T1D diagnosis, HbA1c levels were mostly above the National Institute for Health, Care and Excellence (NICE), UK recommendations of 7.5% (<58 mmol/mol). Significant (P < .05) predictors of poorer glycemic control were: Age at diagnosis (12-18 years), higher HbA1c at baseline (>9.5%, ie, >80 mmol/mol), clinic site, non-white ethnicity, and period (pre-year 2011) of diagnosis. Additionally in univariable analyses, frequency of clinic visits, HbA1c at diagnosis, and type of insulin treatment regimen showed association with poor glycemic control (P < .05). CONCLUSIONS: Major risk factors of poorer glycemic control during 3-24 months following childhood onset T1D are: diagnosis prior to 2011, higher HbA1c levels at baseline, age at diagnosis, non-white ethnicity, and clinic site.

Mixed-effects models for health care longitudinal data with an informative visiting process: A Monte Carlo simulation study.

Electronic health records are being increasingly used in medical research to answer more relevant and detailed clinical questions; however, they pose new and significant methodological challenges. For instance, observation times are likely correlated with the underlying disease severity: Patients with worse conditions utilise health care more and may have worse biomarker values recorded. Traditional methods for analysing longitudinal data assume independence between observation times and disease severity; yet, with health care data, such assumptions unlikely hold. Through Monte Carlo simulation, we compare different analytical approaches proposed to account for an informative visiting process to assess whether they lead to unbiased results. Furthermore, we formalise a joint model for the observation process and the longitudinal outcome within an extended joint modelling framework. We illustrate our results using data from a pragmatic trial on enhanced care for individuals with chronic kidney disease, and we introduce user-friendly software that can be used to fit the joint model for the observation process and a longitudinal outcome.

Dynamic Prediction of Survival in Cystic Fibrosis: A Landmarking Analysis Using UK Patient Registry Data.

BACKGROUND: Cystic fibrosis (CF) is an inherited, chronic, progressive condition affecting around 10,000 individuals in the United Kingdom and over 70,000 worldwide. Survival in CF has improved considerably over recent decades, and it is important to provide up-to-date information on patient prognosis. METHODS: The UK Cystic Fibrosis Registry is a secure centralized database, which collects annual data on almost all CF patients in the United Kingdom. Data from 43,592 annual records from 2005 to 2015 on 6181 individuals were used to develop a dynamic survival prediction model that provides personalized estimates of survival probabilities given a patient's current health status using 16 predictors. We developed the model using the landmarking approach, giving predicted survival curves up to 10 years from 18 to 50 years of age. We compared several models using cross-validation. RESULTS: The final model has good discrimination (C-indexes: 0.873, 0.843, and 0.804 for 2-, 5-, and 10-year survival prediction) and low prediction error (Brier scores: 0.036, 0.076, and 0.133). It identifies individuals at low and high risk of short- and long-term mortality based on their current status. For patients 20 years of age during 2013-2015, for example, over 80% had a greater than 95% probability of 2-year survival and 40% were predicted to survive 10 years or more. CONCLUSIONS: Dynamic personalized prediction models can guide treatment decisions and provide personalized information for patients. Our application illustrates the utility of the landmarking approach for making the best use of longitudinal and survival data and shows how models can be defined and compared in terms of predictive performance.

A sensitivity analysis approach for informative dropout using shared parameter models.

Shared parameter models (SPMs) are a useful approach to addressing bias from informative dropout in longitudinal studies. In SPMs it is typically assumed that the longitudinal outcome process and the dropout time are independent, given random effects and observed covariates. However, this conditional independence assumption is unverifiable. Currently, sensitivity analysis strategies for this unverifiable assumption of SPMs are underdeveloped. In principle, parameters that can and cannot be identified by the observed data should be clearly separated in sensitivity analyses, and sensitivity parameters should not influence the model fit to the observed data. For SPMs this is difficult because it is not clear how to separate the observed data likelihood from the distribution of the missing data given the observed data (i.e., 'extrapolation distribution'). In this article, we propose a new approach for transparent sensitivity analyses for informative dropout that separates the observed data likelihood and the extrapolation distribution, using a typical SPM as a working model for the complete data generating mechanism. For this model, the default extrapolation distribution is a skew-normal distribution (i.e., it is available in a closed form). We propose anchoring the sensitivity analysis on the default extrapolation distribution under the specified SPM and calibrate the sensitivity parameters using the observed data for subjects who drop out. The proposed approach is used to address informative dropout in the HIV Epidemiology Research Study.

Estimating the association between blood pressure variability and cardiovascular disease: An application using the ARIC Study.

The association between visit-to-visit systolic blood pressure variability and cardiovascular events has recently received a lot of attention in the cardiovascular literature. But, blood pressure variability is usually estimated on a person-by-person basis and is therefore subject to considerable measurement error. We demonstrate that hazard ratios estimated using this approach are subject to bias due to regression dilution, and we propose alternative methods to reduce this bias: a two-stage method and a joint model. For the two-stage method, in stage one, repeated measurements are modelled using a mixed effects model with a random component on the residual standard deviation (SD). The mixed effects model is used to estimate the blood pressure SD for each individual, which, in stage two, is used as a covariate in a time-to-event model. For the joint model, the mixed effects submodel and time-to-event submodel are fitted simultaneously using shared random effects. We illustrate the methods using data from the Atherosclerosis Risk in Communities study.

Effect of early glycemic control on HbA1c tracking and development of vascular complications after 5 years of childhood onset type 1 diabetes: Systematic review and meta-analysis.

OBJECTIVE: A systematic review and meta-analysis was conducted to investigate if glycemic control measured by glycated hemoglobin (HbA1c) levels near diagnosis are predictive of future glycemic outcomes and vascular complications in childhood onset type 1 diabetes (T1D). METHODS: Evidence was gathered using electronic databases (MEDLINE, EMBASE, Web of Science, CINAHL, Scopus, and Cochrane Library up to February 2017) and snowballing techniques. Studies investigating the association between the exposure "early glycemic control" and main outcome: "tracking of early control" and secondary outcome: risk of future complications; in children and young people aged 0 to 19 years at baseline; were systematically double-reviewed, quality assessed, and outcome data extracted for synthesis and meta-analysis. FINDINGS: Five studies (N = 4227 participants) were eligible. HbA1c levels were sub-optimal throughout the study period but tended to stabilize in a "track" by 6 months after T1D diagnosis. The group with low HbA1c <53 mmol/mol (<7%) at baseline had lower long-term HbA1c levels than the higher HbA1c group. The estimated standardized mean difference between the sub groups showed a reduction of HbA1c levels on average by 1.6% (range -0.95% to -2.28%) from baseline. Only one study investigated the association between early glycemic control and development of vascular complications in childhood onset T1D. INTERPRETATIONS: Glycemic control after the first few months of childhood onset T1D, remains stable but sub-optimal for a decade. The low and high HbA1c levels at baseline seem to "track" in their respective tracks during the 10-year follow-up, however, the initial difference between groups narrows over time. PROSPERO: CRD42015024546 http://www.crd.york.ac.uk/PROSPERO/display_record.asp?ID=CRD42015024546.

The use of repeated blood pressure measures for cardiovascular risk prediction: a comparison of statistical models in the ARIC study.

Many prediction models have been developed for the risk assessment and the prevention of cardiovascular disease in primary care. Recent efforts have focused on improving the accuracy of these prediction models by adding novel biomarkers to a common set of baseline risk predictors. Few have considered incorporating repeated measures of the common risk predictors. Through application to the Atherosclerosis Risk in Communities study and simulations, we compare models that use simple summary measures of the repeat information on systolic blood pressure, such as (i) baseline only; (ii) last observation carried forward; and (iii) cumulative mean, against more complex methods that model the repeat information using (iv) ordinary regression calibration; (v) risk-set regression calibration; and (vi) joint longitudinal and survival models. In comparison with the baseline-only model, we observed modest improvements in discrimination and calibration using the cumulative mean of systolic blood pressure, but little further improvement from any of the complex methods. © 2016 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

Extending DerSimonian and Laird's methodology to perform network meta-analyses with random inconsistency effects.

Network meta-analysis is becoming more popular as a way to compare multiple treatments simultaneously. Here, we develop a new estimation method for fitting models for network meta-analysis with random inconsistency effects. This method is an extension of the procedure originally proposed by DerSimonian and Laird. Our methodology allows for inconsistency within the network. The proposed procedure is semi-parametric, non-iterative, fast and highly accessible to applied researchers. The methodology is found to perform satisfactorily in a simulation study provided that the sample size is large enough and the extent of the inconsistency is not very severe. We apply our approach to two real examples.

A design-by-treatment interaction model for network meta-analysis with random inconsistency effects.

Network meta-analysis is becoming more popular as a way to analyse multiple treatments simultaneously and, in the right circumstances, rank treatments. A difficulty in practice is the possibility of 'inconsistency' or 'incoherence', where direct evidence and indirect evidence are not in agreement. Here, we develop a random-effects implementation of the recently proposed design-by-treatment interaction model, using these random effects to model inconsistency and estimate the parameters of primary interest. Our proposal is a generalisation of the model proposed by Lumley and allows trials with three or more arms to be included in the analysis. Our methods also facilitate the ranking of treatments under inconsistency. We derive R and I(2) statistics to quantify the impact of the between-study heterogeneity and the inconsistency. We apply our model to two examples.

Demographic factors associated with within-individual variability of lung function for adults with cystic fibrosis: A UK registry study.

BACKGROUND: Lung function is a key outcome used in the evaluation of disease progression in cystic fibrosis. The variability of individual lung function measurements over time (within-individual variability) has been shown to predict subsequent lung function changes. Nevertheless, the association between within-individual lung function variability and demographic and genetic covariates has not been quantified. METHODS: We performed a longitudinal analysis of data from a cohort of 7099 adults with cystic fibrosis (between 18 and 49 years old) from the UK cystic fibrosis registry, containing annual review data between 1996 and 2020. A mixed-effects location-scale model is used to quantify mean FEV1 (forced expiratory volume in 1 s) trajectories and FEV1 within-individual variability as a function of sex, age at annual review, diagnosis after first year of life, homozygous F508 genotype and birth cohort. RESULTS: Mean FEV1 decreased with age and lung function variability showed a near-quadratic trend by age. Males showed higher FEV1 mean and variability than females across the whole age range. Earlier diagnosis and homozygous F508 genotype were also associated with higher FEV1 mean and variability. Individuals who died during follow-up showed on average higher lung function variability than those who survived. CONCLUSIONS: Key variables known to be linked with mean lung function in cystic fibrosis are also associated with an individual's lung function variability. This work opens new avenues to understand the role played by lung function variability in disease progression and its utility in predicting key outcomes such as mortality.

Two-stage meta-analysis of survival data from individual participants using percentile ratios.

Methods for individual participant data meta-analysis of survival outcomes commonly focus on the hazard ratio as a measure of treatment effect. Recently, Siannis et al. (2010, Statistics in Medicine 29:3030-3045) proposed the use of percentile ratios as an alternative to hazard ratios. We describe a novel two-stage method for the meta-analysis of percentile ratios that avoids distributional assumptions at the study level.

A semi-competing risks model for data with interval-censoring and informative observation: an application to the MRC cognitive function and ageing study.

Semi-competing risks data occur frequently in medical research when interest is in simultaneous modelling of two or more processes, one of which may censor the others. We consider the analysis of semi-competing risks data in the presence of interval-censoring and informative loss-to-followup. The work is motivated by a data set from the MRC UK Cognitive Function and Ageing Study, which we use to model two processes, cognitive impairment and death. Analysis is carried out using a multi-state model, which is an extension of that used by Siannis et al. (Statist. Med. 2007; 26:426­442) to model semi-competing risks data with exact transition times, to data which is interval-censored. Model parameters are estimated using maximum likelihood. The role of a sensitivity parameter k, which influences the nature of informative censoring, is explored.

Employing a latent variable framework to improve efficiency in composite endpoint analysis.

Composite endpoints that combine multiple outcomes on different scales are common in clinical trials, particularly in chronic conditions. In many of these cases, patients will have to cross a predefined responder threshold in each of the outcomes to be classed as a responder overall. One instance of this occurs in systemic lupus erythematosus, where the responder endpoint combines two continuous, one ordinal and one binary measure. The overall binary responder endpoint is typically analysed using logistic regression, resulting in a substantial loss of information. We propose a latent variable model for the systemic lupus erythematosus endpoint, which assumes that the discrete outcomes are manifestations of latent continuous measures and can proceed to jointly model the components of the composite. We perform a simulation study and find that the method offers large efficiency gains over the standard analysis, the magnitude of which is highly dependent on the components driving response. Bias is introduced when joint normality assumptions are not satisfied, which we correct for using a bootstrap procedure. The method is applied to the Phase IIb MUSE trial in patients with moderate to severe systemic lupus erythematosus. We show that it estimates the treatment effect 2.5 times more precisely, offering a 60% reduction in required sample size.

Informative presence and observation in routine health data: A review of methodology for clinical risk prediction.

OBJECTIVE: Informative presence (IP) is the phenomenon whereby the presence or absence of patient data is potentially informative with respect to their health condition, with informative observation (IO) being the longitudinal equivalent. These phenomena predominantly exist within routinely collected healthcare data, in which data collection is driven by the clinical requirements of patients and clinicians. The extent to which IP and IO are considered when using such data to develop clinical prediction models (CPMs) is unknown, as is the existing methodology aiming at handling these issues. This review aims to synthesize such existing methodology, thereby helping identify an agenda for future methodological work. MATERIALS AND METHODS: A systematic literature search was conducted by 2 independent reviewers using prespecified keywords. RESULTS: Thirty-six articles were included. We categorized the methods presented within as derived predictors (including some representation of the measurement process as a predictor in the model), modeling under IP, and latent structures. Including missing indicators or summary measures as predictors is the most commonly presented approach amongst the included studies (24 of 36 articles). DISCUSSION: This is the first review to collate the literature in this area under a prediction framework. A considerable body relevant of literature exists, and we present ways in which the described methods could be developed further. Guidance is required for specifying the conditions under which each method should be used to enable applied prediction modelers to use these methods. CONCLUSIONS: A growing recognition of IP and IO exists within the literature, and methodology is increasingly becoming available to leverage these phenomena for prediction purposes. IP and IO should be approached differently in a prediction context than when the primary goal is explanation. The work included in this review has demonstrated theoretical and empirical benefits of incorporating IP and IO, and therefore we recommend that applied health researchers consider incorporating these methods in their work.