arXiv subjects

Mohsen Sadatsafavi

Publications and source records attributed to Mohsen Sadatsafavi.

24 records · Page 2Linked to original sources

arXiv2022

Closed-Form Solution of the Unit Normal Loss Integral in Two-Dimensions

In Value of Information (VoI) analysis, the unit normal loss integral (UNLI) frequently emerges as a solution for the computation of various VoI metrics. However, one limitation of the UNLI has been that its closed-form solution is available for only one dimension, and thus can be used for comparisons involving only two strategies (where it is applied to the scalar incremental net benefit). We derived a closed-form solution for the two-dimensional UNLI, enabling closed-form VoI calculations for three strategies. We verified the accuracy of this method via simulation studies. A case study based on a three-arm clinical trial was used as an example. VoI methods based on the closed-form solutions for the UNLI can now be extended to three-decision comparisons, taking a fraction of a second to compute and not being subject to Monte Carlo error. An R implementation of this method is provided as part of the predtools package (https://github.com/resplab/predtools/).

stat.CO↗

arXiv2022

Programmable Interface for Statistical & Simulation Models (PRISM): Towards Greater Accessibility of Clinical and Healthcare Decision Models

Background: Increasingly, decision-making in healthcare relies on computer models, be it clinical prediction models at point of care or decision-analytic models at the policymaking level. Given the important role models play in both contexts, their structure and implementation be rigorously scrutinized. The ability to interrogate input/output associations without facing barriers can improve quality assurance mechanisms while satisfying privacy/confidentiality concerns and facilitating the integration of models into decision-making. This paper reports on the development of Programmable Interface for Statistical & Simulation Models (PRISM), a cloud-based platform for model accessibility. Methods: PRISM emphasizes two main principles: 1) minimal specifications on the side of model developer to make the model fit for cloud hosting, and 2) making client access completely independent of the resource requirement and software dependencies of the model. The server architecture integrates a RESTful Application Programming Interface (API) infrastructure, JSON for data transfer, a routing layer for access management, container technology for management of computer resources and package dependencies, and the capacity for synchronous or asynchronous model calls. Results: We discuss the architecture, the minimal API standards that enable a universal language for access to such models, the underlying server infrastructure, and the standards used for data transfer. An instance of PRISM is available as a service via the Peer Models Network http://peermodelsnetwork.com. Through a series of case studies, we demonstrate how interrogating models becomes possible in standardized fashion, in a way that is irrespective of the specifics of any model. Conclusions: We have developed a publicly accessible platform and minimalist standards that facilitate model accessibility for both clinical and policy models.

stat.CO↗

arXiv2021

Minding non-collapsibility of odds ratios when recalibrating risk prediction models

In clinical prediction modeling, model updating refers to the practice of modifying a prediction model before it is used in a new setting. In the context of logistic regression for a binary outcome, one of the simplest updating methods is a fixed odds-ratio transformation of predicted risks to improve calibration-in-the-large. Previous authors have proposed equations for calculating this odds-ratio based on the discrepancy between the prevalence in the original and the new population, or between the average of predicted and observed risks. We show that this method fails to consider the non-collapsibility of odds-ratio. Consequently, it under-corrects predicted risks, especially when predicted risks are more dispersed (i.e., for models with good discrimination). We suggest an approximate equation for recovering the conditional odds-ratio from the mean and variance of predicted risks. Brief simulations and a case study show that this approach reduces under-correction, sometimes substantially. R code for implementation is provided.

stat.AP↗

arXiv2021

Uncertainty and Value of Information in Risk Prediction Modeling

Background: Due to the finite size of the development sample, predicted probabilities from a risk prediction model are inevitably uncertain. We apply Value of Information methodology to evaluate the decision-theoretic implications of prediction uncertainty. Methods: Adopting a Bayesian perspective, we extend the definition of the Expected Value of Perfect Information (EVPI) from decision analysis to net benefit calculations in risk prediction. In the context of model development, EVPI is the expected gain in net benefit by using the correct predictions as opposed to predictions from a proposed model. We suggest bootstrap methods for sampling from the posterior distribution of predictions for EVPI calculation using Monte Carlo simulations. In a case study, we used subsets of data of various sizes from a clinical trial for predicting mortality after myocardial infarction to show how EVPI changes with sample size. Results: With a sample size of 1,000 and at the pre-specified threshold of 2% on predicted risks, the gain in net benefit by using the proposed and the correct models were 0.0006 and 0.0011, respectively, resulting in an EVPI of 0.0005 and a relative EVPI of 87%. EVPI was zero only at unrealistically high thresholds (>85%). As expected, EVPI declined with larger samples. We summarize an algorithm for incorporating EVPI calculations into the commonly used bootstrap method for optimism correction. Conclusion: Value of Information methods can be applied to explore decision-theoretic consequences of uncertainty in risk prediction and can complement inferential methods when developing risk prediction models. R code for implementing this method is provided.

stat.AP↗

arXiv2021

Model-based ROC (mROC) curve: examining the effect of case-mix and model calibration on the ROC plot

The performance of risk prediction models is often characterized in terms of discrimination and calibration. The Receiver Operating Characteristic (ROC) curve is widely used for evaluating model discrimination. When evaluating the performance of a risk prediction model in a new sample, the shape of the ROC curve is affected by both case-mix and the postulated model. Further, compared to discrimination, evaluating calibration has not received the same level of attention. Commonly used methods for model calibration involve subjective specification of smoothing or grouping. Leveraging the familiar ROC framework, we introduce the model-based ROC (mROC) curve to assess the calibration of a pre-specified model in a new sample. mROC curve is the ROC curve that should be observed if a pre-specified model is calibrated in the sample. We show the empirical ROC and mROC curves for a sample converge asymptotically if the model is calibrated in that sample. As a consequence, the mROC curve can be used to assess visually the effect of case-mix and model mis-calibration. Further, we propose a novel statistical test for calibration that does not require any smoothing or grouping. Simulations support the adequacy of the test. A case study puts these developments in a practical context. We conclude that mROC can easily be constructed and used to evaluate the effect of case-mix and model calibration on the ROC plot, thus adding to the utility of ROC curve analysis in the evaluation of risk prediction models. R code for the proposed methodology is provided (https://github.com/msadatsafavi/mROC/).

stat.ME↗

arXiv2019

A threshold-free summary index for quantifying the capacity of covariates to yield efficient treatment rules

The focus of this paper is on quantifying the capacity of covariates in devising efficient treatment rules when data from a randomized trial are available. Conventional one-variable-at-a-time subgroup analysis based on statistical hypothesis testing of covariate-by-treatment interaction is ill-suited for this purpose. The application of decision theory results in treatment rules that compare the expected benefit of treatment given the patient's covariates against a treatment threshold. However, determining treatment threshold is often context-specific, and any given threshold might seem arbitrary at the reporting stages of a clinical trial. We propose a threshold-free metric that quantifies the capacity of a set of covariates towards finding individuals who will benefit the most from treatment. The construct of the proposed metric is comparing the expected outcomes with and without knowledge of covariates when one of a two randomly selected patients are to be treated. We show that the resulting index can also be expressed in terms of integrated treatment benefit as a function of covariates over the entire range of treatment thresholds. We also propose a semi-parametric estimation method suitable for out-of-sample validation and adjustment for optimism. We use data from a clinical trial of preventive antibiotic therapy for reducing exacerbation rate in Chronic Obstructive Pulmonary Disease to demonstrate the calculations in a step-by-step fashion. The proposed index has intuitive and theoretically sound interpretation and can be estimated with relative ease for a wide class of regression models. Beyond the conceptual developments presented in this work, various aspects of estimation and inference for such metrics need to be pursued in future research.

stat.AP↗