arXiv subjects

Tianxi Cai

Publications and source records attributed to Tianxi Cai.

At least 73 records · Page 4Linked to original sources

arXiv2022

Assessing the Most Vulnerable Subgroup to Type II Diabetes Associated with Statin Usage: Evidence from Electronic Health Record Data

There have been increased concerns that the use of statins, one of the most commonly prescribed drugs for treating coronary artery disease, is potentially associated with the increased risk of new-onset type II diabetes (T2D). Nevertheless, to date, there is no robust evidence supporting as to whether and what kind of populations are indeed vulnerable for developing T2D after taking statins. In this case study, leveraging the biobank and electronic health record data in the Partner Health System, we introduce a new data analysis pipeline and a novel statistical methodology that address existing limitations by (i) designing a rigorous causal framework that systematically examines the causal effects of statin usage on T2D risk in observational data, (ii) uncovering which patient subgroup is most vulnerable for developing T2D after taking statins, and (iii) assessing the replicability and statistical significance of the most vulnerable subgroup via a bootstrap calibration procedure. Our proposed approach delivers asymptotically sharp confidence intervals and debiased estimate for the treatment effect of the most vulnerable subgroup in the presence of high-dimensional covariates. With our proposed approach, we find that females with high T2D genetic risk are at the highest risk of developing T2D due to statin usage.

stat.AP↗

arXiv2022

Using a Surrogate with Heterogeneous Utility to Test for a Treatment Effect

The primary benefit of identifying a valid surrogate marker is the ability to use it in a future trial to test for a treatment effect with shorter follow-up time or less cost. However, previous work has demonstrated potential heterogeneity in the utility of a surrogate marker. When such heterogeneity exists, existing methods that use the surrogate to test for a treatment effect while ignoring this heterogeneity may lead to inaccurate conclusions about the treatment effect, particularly when the patient population in the new study has a different mix of characteristics than the study used to evaluate the utility of the surrogate marker. In this paper, we develop a novel test for a treatment effect using surrogate marker information that accounts for heterogeneity in the utility of the surrogate. We compare our testing procedure to a test that uses primary outcome information (gold standard) and a test that uses surrogate marker information, but ignores heterogeneity. We demonstrate the validity of our approach and derive the asymptotic properties of our estimator and variance estimates. Simulation studies examine the finite sample properties of our testing procedure and demonstrate when our proposed approach can outperform the testing approach that ignores heterogeneity. We illustrate our methods using data from an AIDS clinical trial to test for a treatment effect using CD4 count as a surrogate marker for RNA.

stat.ME↗

arXiv2022

Towards Optimal Use of Surrogate Markers to Improve Power

Motivated by increasing pressure for decision makers to shorten the time required to evaluate the efficacy of a treatment such that treatments deemed safe and effective can be made publicly available, there has been substantial recent interest in using an earlier or easier to measure surrogate marker, $S$, in place of the primary outcome, $Y$. To validate the utility of a surrogate marker in these settings, a commonly advocated measure is the proportion of treatment effect on the primary outcome that is explained by the treatment effect on the surrogate marker (PTE). Model based and model free estimators for PTE have also been developed. While this measure is very intuitive, it does not directly address the important questions of how $S$ can be used to make inference of the unavailable $Y$ in the next phase clinical trials. In this paper, to optimally use the information of surrogate S, we provide a framework for deriving an optimal transformation of $S$, $g_{opt}(S)$, such that the treatment effect on $g_{opt}(S)$ maximally approximates the treatment effect on $Y$ in a certain sense. Based on the optimally transformed surrogate, $g_{opt}(S)$, we propose a new measure to quantify surrogacy, the relative power (RP), and demonstrate how RP can be used to make decisions with $S$ instead of $Y$ for next phase trials. We propose nonparametric estimation procedures, derive asymptotic properties, and compare the RP measure with the PTE measure. Finite sample performance of our estimators is assessed via a simulation study. We illustrate our proposed procedures using an application to the Diabetes Prevention Program (DPP) clinical trial to evaluate the utility of hemoglobin A1c and fasting plasma glucose as surrogate markers for diabetes.

stat.ME↗

arXiv2022

Multimodal Learning on Graphs for Disease Relation Extraction

Objective: Disease knowledge graphs are a way to connect, organize, and access disparate information about diseases with numerous benefits for artificial intelligence (AI). To create knowledge graphs, it is necessary to extract knowledge from multimodal datasets in the form of relationships between disease concepts and normalize both concepts and relationship types. Methods: We introduce REMAP, a multimodal approach for disease relation extraction and classification. The REMAP machine learning approach jointly embeds a partial, incomplete knowledge graph and a medical language dataset into a compact latent vector space, followed by aligning the multimodal embeddings for optimal disease relation extraction. Results: We apply REMAP approach to a disease knowledge graph with 96,913 relations and a text dataset of 1.24 million sentences. On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10.0% (accuracy) and 17.2% (F1-score) by fusing disease knowledge graphs with text information. Further, REMAP leverages text information to recommend new relationships in the knowledge graph, outperforming graph-based methods by 8.4% (accuracy) and 10.4% (F1-score). Conclusion: REMAP is a multimodal approach for extracting and classifying disease relationships by fusing structured knowledge and text information. REMAP provides a flexible neural architecture to easily find, access, and validate AI-driven relationships between disease concepts.

cs.LG↗

arXiv2022

Augmented Transfer Regression Learning with Semi-non-parametric Nuisance Models

In contemporary statistical learning, covariate shift correction plays an important role in transfer learning when distribution of the testing data is shifted from the training data. Importance weighting, as a natural and principle strategy to adjust for covariate shift, has been commonly used in the field of transfer learning. However, this strategy is not robust to model misspecification or excessive estimation error. In this paper, we propose an augmented transfer regression learning (ATReL) approach that introduces an imputation model for the targeted response, and uses it to augment the importance weighting equation. With novel semi-non-parametric constructions and calibrated moment estimating equations for the two nuisance models, our ATReL method is less prone to (i) the curse of dimensionality compared to nonparametric approaches, and (ii) model mis-specification than parametric approaches. We show that our ATReL estimator is root-n-consistent when at least one nuisance model is correctly specified, estimation for the parametric part of the nuisance models achieves parametric rate, and the nonparametric components are rate doubly robust. Simulation studies demonstrate that our method is more robust and efficient than existing parametric and fully nonparametric (machine learning) estimators under various configurations. We also examine the utility of our method through a real example about transfer learning of phenotyping algorithm for rheumatoid arthritis across different time windows. Finally, we propose ways to enhance the intrinsic efficiency of our estimator and to incorporate modern machine learning methods with our proposed framework.

stat.ME↗

arXiv2021

Adaptive Combination of Randomized and Observational Data

Data from both a randomized trial and an observational study are sometimes simultaneously available for evaluating the effect of an intervention. The randomized data typically allows for reliable estimation of average treatment effects but may be limited in sample size and patient heterogeneity for estimating conditional average treatment effects for a broad range of patients. Estimates from the observational study can potentially compensate for these limitations, but there may be concerns about whether confounding and treatment effect heterogeneity have been adequately addressed. We propose an approach for combining conditional treatment effect estimators from each source such that it aggressively weights toward the randomized estimator when bias in the observational estimator is detected. This allows the combination to be consistent for a conditional causal effect, regardless of whether assumptions required for consistent estimation in the observational study are satisfied. When the bias is negligible, the estimators from each source are combined for optimal efficiency. We show the problem can be formulated as a penalized least squares problem and consider its asymptotic properties. Simulations demonstrate the robustness and efficiency of the method in finite samples, in scenarios with bias or no bias in the observational estimator. We illustrate the method by estimating the effects of hormone replacement therapy on the risk of developing coronary heart disease in data from the Women's Health Initiative.

stat.ME↗

arXiv2021

Efficient and Robust Semi-supervised Estimation of ATE with Partially Annotated Treatment and Response

A notable challenge of leveraging Electronic Health Records (EHR) for treatment effect assessment is the lack of precise information on important clinical variables, including the treatment received and the response. Both treatment information and response often cannot be accurately captured by readily available EHR features and require labor intensive manual chart review to precisely annotate, which limits the number of available gold standard labels on these key variables. We consider average treatment effect (ATE) estimation under such a semi-supervised setting with a large number of unlabeled samples containing both confounders and imperfect EHR features for treatment and response. We derive the efficient influence function for ATE and use it to construct a semi-supervised multiple machine learning (SMMAL) estimator. We showcase that our SMMAL estimator is semi-parametric efficient with B-spline regression under low-dimensional smooth models. We develop the adaptive sparsity/model doubly robust estimation under high-dimensional logistic propensity score and outcome regression models. Results from simulation studies support the validity of our SMMAL method and its superiority over supervised benchmarks.

stat.ME↗

arXiv2021

Semi-supervised Approach to Event Time Annotation Using Longitudinal Electronic Health Records

Large clinical datasets derived from insurance claims and electronic health record (EHR) systems are valuable sources for precision medicine research. These datasets can be used to develop models for personalized prediction of risk or treatment response. Efficiently deriving prediction models using real world data, however, faces practical and methodological challenges. Precise information on important clinical outcomes such as time to cancer progression are not readily available in these databases. The true clinical event times typically cannot be approximated well based on simple extracts of billing or procedure codes. Whereas, annotating event times manually is time and resource prohibitive. In this paper, we propose a two-step semi-supervised multi-modal automated time annotation (MATA) method leveraging multi-dimensional longitudinal EHR encounter records. In step I, we employ a functional principal component analysis approach to estimate the underlying intensity functions based on observed point processes from the unlabeled patients. In step II, we fit a penalized proportional odds model to the event time outcomes with features derived in step I in the labeled data where the non-parametric baseline function is approximated using B-splines. Under regularity conditions, the resulting estimator of the feature effect vector is shown as root-$n$ consistent. We demonstrate the superiority of our approach relative to existing approaches through simulations and a real data example on annotating lung cancer recurrence in an EHR cohort of lung cancer patients from Veteran Health Administration.

stat.ME↗

arXiv2021

Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices

Matrix completion has attracted attention in many fields, including statistics, applied mathematics, and electrical engineering. Most of the works focus on the independent sampling models under which the observed entries are sampled independently. Motivated by applications in the integration of knowledge graphs derived from multi-source biomedical data such as those from Electronic Health Records (EHR) and biomedical text, we propose the {\bf B}lock-wise {\bf O}verlapping {\bf N}oisy {\bf M}atrix {\bf I}ntegration (BONMI) to treat blockwise missingness of symmetric matrices representing relatedness between entity pairs. Our idea is to exploit the orthogonal Procrustes problem to align the eigenspace of the two sub-matrices, then complete the missing blocks by the inner product of the two low-rank components. Besides, we prove the statistical rate for the eigenspace of the underlying matrix, which is comparable to the rate under the independently missing assumption. Simulation studies show that the method performs well under a variety of configurations. In the real data analysis, the method is applied to two tasks: (i) the integrating of several point-wise mutual information matrices built by English EHR and Chinese medical text data, and (ii) the machine translation between English and Chinese medical concepts. Our method shows an advantage over existing methods.

stat.ML↗

arXiv2021

Efficient Estimation and Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling

In many contemporary applications, large amounts of unlabeled data are readily available while labeled examples are limited. There has been substantial interest in semi-supervised learning (SSL) which aims to leverage unlabeled data to improve estimation or prediction. However, current SSL literature focuses primarily on settings where labeled data is selected randomly from the population of interest. Non-random sampling, while posing additional analytical challenges, is highly applicable to many real world problems. Moreover, no SSL methods currently exist for estimating the prediction performance of a fitted model under non-random sampling. In this paper, we propose a two-step SSL procedure for evaluating a prediction rule derived from a working binary regression model based on the Brier score and overall misclassification rate under stratified sampling. In step I, we impute the missing labels via weighted regression with nonlinear basis functions to account for nonrandom sampling and to improve efficiency. In step II, we augment the initial imputations to ensure the consistency of the resulting estimators regardless of the specification of the prediction model or the imputation model. The final estimator is then obtained with the augmented imputations. We provide asymptotic theory and numerical studies illustrating that our proposals outperform their supervised counterparts in terms of efficiency gain. Our methods are motivated by electronic health records (EHR) research and validated with a real data analysis of an EHR-based study of diabetic neuropathy.

stat.ML↗

arXiv2021

Prior Adaptive Semi-supervised Learning with Application to EHR Phenotyping

Electronic Health Records (EHR) data, a rich source for biomedical research, have been successfully used to gain novel insight into a wide range of diseases. Despite its potential, EHR is currently underutilized for discovery research due to it's major limitation in the lack of precise phenotype information. To overcome such difficulties, recent efforts have been devoted to developing supervised algorithms to accurately predict phenotypes based on relatively small training datasets with gold standard labels extracted via chart review. However, supervised methods typically require a sizable training set to yield generalizable algorithms especially when the number of candidate features, $p$, is large. In this paper, we propose a semi-supervised (SS) EHR phenotyping method that borrows information from both a small labeled data where both the label $Y$ and the feature set $X$ are observed and a much larger unlabeled data with observations on $X$ only as well as a surrogate variable $S$ that is predictive of $Y$ and available for all patients, under a high dimensional setting. Under a working prior assumption that $S$ is related to $X$ only through $Y$ and allowing it to hold approximately, we propose a prior adaptive semi-supervised (PASS) estimator that adaptively incorporates the prior knowledge by shrinking the estimator towards a direction derived under the prior. We derive asymptotic theory for the proposed estimator and demonstrate its superiority over existing estimators via simulation studies. The proposed method is applied to an EHR phenotyping study of rheumatoid arthritis at Partner's Healthcare.

stat.ME↗

arXiv2021

Targeting Underrepresented Populations in Precision Medicine: A Federated Transfer Learning Approach

The limited representation of minorities and disadvantaged populations in large-scale clinical and genomics research has become a barrier to translating precision medicine research into practice. Due to heterogeneity across populations, risk prediction models are often found to be underperformed in these underrepresented populations, and therefore may further exacerbate known health disparities. In this paper, we propose a two-way data integration strategy that integrates heterogeneous data from diverse populations and from multiple healthcare institutions via a federated transfer learning approach. The proposed method can handle the challenging setting where sample sizes from different populations are highly unbalanced. With only a small number of communications across participating sites, the proposed method can achieve performance comparable to the pooled analysis where individual-level data are directly pooled together. We show that the proposed method improves the estimation and prediction accuracy in underrepresented populations, and reduces the gap of model performance across populations. Our theoretical analysis reveals how estimation accuracy is influenced by communication budgets, privacy restrictions, and heterogeneity across populations. We demonstrate the feasibility and validity of our methods through numerical experiments and a real application to a multi-center study, in which we construct polygenic risk prediction models for Type II diabetes in AA population.

stat.ML↗

arXiv2021

Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Prediction

Risk modeling with EHR data is challenging due to a lack of direct observations on the disease outcome, and the high dimensionality of the candidate predictors. In this paper, we develop a surrogate assisted semi-supervised-learning (SAS) approach to risk modeling with high dimensional predictors, leveraging a large unlabeled data on candidate predictors and surrogates of outcome, as well as a small labeled data with annotated outcomes. The SAS procedure borrows information from surrogates along with candidate predictors to impute the unobserved outcomes via a sparse working imputation model with moment conditions to achieve robustness against mis-specification in the imputation model and a one-step bias correction to enable interval estimation for the predicted risk. We demonstrate that the SAS procedure provides valid inference for the predicted risk derived from a high dimensional working model, even when the underlying risk prediction model is dense and the risk model is mis-specified. We present an extensive simulation study to demonstrate the superiority of our SSL approach compared to existing supervised methods. We apply the method to derive genetic risk prediction of type-2 diabetes mellitus using a EHR biobank cohort.

math.ST↗

arXiv2021

On the Evaluation of Surrogate Markers in Real World Data Settings

Shortcomings of randomized clinical trials are pronounced in urgent health crises, when rapid identification of effective treatments is critical. Leveraging short-term surrogates in real-world data (RWD) can guide policymakers evaluating new treatments. In this paper, we develop novel estimators for the proportion of treatment effect (PTE) on the true outcome explained by a surrogate in RWD settings. We propose inverse probability weighted and doubly robust (DR) estimators of an optimal transformation of the surrogate and PTE by semi-nonparametrically modeling the relationship between the true outcome and surrogate given baseline covariates. We show that our estimators are consistent and asymptotically normal, and the DR estimator is consistent when either the propensity score model or outcome regression model is correctly specified. We compare our proposed estimators to existing estimators and show a reduction in bias and gains in efficiency through simulations. We illustrate the utility of our method in obtaining an interpretable PTE by conducting a cross-trial comparison of two biologic therapies for ulcerative colitis.

stat.ME↗

arXiv2021

A new weighting method when not all the events are selected as cases in a nested case-control study

Nested case-control (NCC) is a sampling method widely used for developing and evaluating risk models with expensive biomarkers on large prospective cohort studies. The biomarker values are typically obtained on a sub-cohort, consisting of all the events and a subset of non-events. However, when the number of events is not small, it might not be affordable to measure the biomarkers on all of them. Due to the costs and limited availability of bio-specimens, only a subset of events is selected to the sub-cohort as cases. For these "untypical" NCC studies, we propose a new weighting method for the inverse probability weighted (IPW) estimation. We also design a perturbation method to estimate the variance of the IPW estimator with our new weights. It accounts for between-subject correlations induced by the sampling processes for both cases and controls through perturbing their sampling indicator variables, and thus, captures all the variations. Furthermore, we demonstrate, analytically and numerically, that when cases consist of only a subset of events, our new weight produces more efficient IPW estimators than the weight proposed in Samuelsen (1997) for a standard NCC design. We illustrate the estimating procedure with a study that aims to evaluate a biomarker-based risk prediction model using the Framingham cohort study.

stat.ME↗

arXiv2021

On the global identifiability of logistic regression models with misclassified outcomes

In the last decade, the secondary use of large data from health systems, such as electronic health records, has demonstrated great promise in advancing biomedical discoveries and improving clinical decision making. However, there is an increasing concern about biases in association studies caused by misclassification in the binary outcomes derived from electronic health records. We revisit the classical logistic regression model with misclassified outcomes. Despite that local identification conditions in some related settings have been previously established, the global identification of such models remains largely unknown and is an important question yet to be answered. We derive necessary and sufficient conditions for global identifiability of logistic regression models with misclassified outcomes, using a novel approach termed as the submodel analysis, and a technique adapted from the Picard-Lindelöf existence theorem in ordinary differential equations. In particular, our results are applicable to logistic models with discrete covariates, which is a common situation in biomedical studies, The conditions are easy to verify in practice. In addition to model identifiability, we propose a hypothesis testing procedure for regression coefficients in the misclassified logistic regression model when the model is not identifiable under the null.

math.ST↗

arXiv2021

Risk Prediction with Imperfect Survival Outcome Information from Electronic Health Records

Readily available proxies for time of disease onset such as time of the first diagnostic code can lead to substantial risk prediction error if performing analyses based on poor proxies. Due to the lack of detailed documentation and labor intensiveness of manual annotation, it is often only feasible to ascertain for a small subset the current status of the disease by a follow up time rather than the exact time. In this paper, we aim to develop risk prediction models for the onset time efficiently leveraging both a small number of labels on current status and a large number of unlabeled observations on imperfect proxies. Under a semiparametric transformation model for onset and a highly flexible measurement error models for proxy onset time, we propose the semisupervised risk prediction method by combining information from proxies and limited labels efficiently. From an initial estimator solely based on the labelled subset, we perform a one-step correction with the full data augmenting against a mean zero rank correlation score derived from the proxies. We establish the consistency and asymptotic normality of the proposed semi-supervised estimator and provide a resampling procedure for interval estimation. Simulation studies demonstrate that the proposed estimator performs well in finite sample. We illustrate the proposed estimator by developing a genetic risk prediction model for obesity using data from Partners Biobank Electronic Health Records (EHR).

stat.ME↗

arXiv2021

Semi-Supervised Off Policy Reinforcement Learning

Reinforcement learning (RL) has shown great success in estimating sequential treatment strategies which take into account patient heterogeneity. However, health-outcome information, which is used as the reward for reinforcement learning methods, is often not well coded but rather embedded in clinical notes. Extracting precise outcome information is a resource intensive task, so most of the available well-annotated cohorts are small. To address this issue, we propose a semi-supervised learning (SSL) approach that efficiently leverages a small sized labeled data with true outcome observed, and a large unlabeled data with outcome surrogates. In particular, we propose a semi-supervised, efficient approach to Q-learning and doubly robust off policy value estimation. Generalizing SSL to sequential treatment regimes brings interesting challenges: 1) Feature distribution for Q-learning is unknown as it includes previous outcomes. 2) The surrogate variables we leverage in the modified SSL framework are predictive of the outcome but not informative to the optimal policy or value function. We provide theoretical results for our Q-function and value function estimators to understand to what degree efficiency can be gained from SSL. Our method is at least as efficient as the supervised approach, and moreover safe as it robust to mis-specification of the imputation models.

cs.LG↗