Zach Shahn
YOU?
Author Swipe
View article: Natural History of Self-reported Symptoms Following SARS-CoV-2 Infection: A Target Trial Emulation in a Prospective Community-Based Cohort
Natural History of Self-reported Symptoms Following SARS-CoV-2 Infection: A Target Trial Emulation in a Prospective Community-Based Cohort Open
Background: The natural history of symptoms after SARS-CoV-2 infection remains uncertain because many studies are not representative, ignore background symptom prevalence, lack longitudinal tracking, and omit appropriate controls. Using a …
View article: Structural Nested Mean Models for Modified Treatment Policies
Structural Nested Mean Models for Modified Treatment Policies Open
There is a growing literature on estimating effects of treatment strategies based on the natural treatment that would have been received in the absence of intervention, often dubbed `modified treatment policies' (MTPs). MTPs are sometimes …
View article: Using causal diagrams to assess parallel trends in difference-in-differences studies
Using causal diagrams to assess parallel trends in difference-in-differences studies Open
Difference-in-differences (DID) is popular because it can allow for unmeasured confounding when the key assumption of parallel trends holds. However, there exists little guidance on how to decide a priori whether this assumption is reasona…
View article: Referee report. For: Triangulating Instrumental Variable, confounder adjustment and difference-in-difference methods for comparative effectiveness research in observational data [version 2; peer review: 1 approved, 1 approved with reservations]
Referee report. For: Triangulating Instrumental Variable, confounder adjustment and difference-in-difference methods for comparative effectiveness research in observational data [version 2; peer review: 1 approved, 1 approved with reservations] Open
View article: Uncertainty Quantification for Conditional Treatment Effect Estimation under Dynamic Treatment Regimes.
Uncertainty Quantification for Conditional Treatment Effect Estimation under Dynamic Treatment Regimes. Open
In medical decision-making, clinicians must choose between different time-varying treatment strategies. Counterfactual prediction via g-computation enables comparison of alternative outcome distributions under such treatment strategies. Wh…
View article: Using negative controls to identify causal effects with invalid instrumental variables
Using negative controls to identify causal effects with invalid instrumental variables Open
Summary Many proposals for the identification of causal effects require an instrumental variable that satisfies strong, untestable unconfoundedness and exclusion restriction assumptions. In this paper, we show how one can potentially ident…
View article: Generalizing Difference-in-Differences to Non-Canonical Settings: Identifying an Array of Estimands
Generalizing Difference-in-Differences to Non-Canonical Settings: Identifying an Array of Estimands Open
Consider a general setting in which data on an outcome is collected in two `groups' at two time periods, with certain group-periods deemed `treated' and others `untreated'. A special case is the canonical Difference-in-Differences (DiD) se…
View article: G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes
G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes Open
In the context of medical decision making, counterfactual prediction enables clinicians to predict treatment outcomes of interest under alternative courses of therapeutic actions given observed patient history. In this work, we present G-T…
View article: Structural Nested Mean Models Under Parallel Trends with Interference
Structural Nested Mean Models Under Parallel Trends with Interference Open
Despite the common occurrence of interference in Difference-in-Differences (DiD) applications, standard DiD methods rely on an assumption that interference is absent, and comparatively little work has considered how to accommodate and lear…
View article: The impact of aggressive and conservative propensity for initiation of neuromuscular blockade in mechanically ventilated patients with hypoxemic respiratory failure
The impact of aggressive and conservative propensity for initiation of neuromuscular blockade in mechanically ventilated patients with hypoxemic respiratory failure Open
View article: Estimating Heterogeneous Treatment Effects on Survival Outcomes Using Counterfactual Censoring Unbiased Transformations
Estimating Heterogeneous Treatment Effects on Survival Outcomes Using Counterfactual Censoring Unbiased Transformations Open
Methods for estimating heterogeneous treatment effects (HTE) from observational data have largely focused on continuous or binary outcomes, with less attention paid to survival outcomes and almost none to settings with competing risks. In …
View article: Bias formulas for violations of proximal identification assumptions in a linear structural equation model
Bias formulas for violations of proximal identification assumptions in a linear structural equation model Open
Causal inference from observational data often rests on the unverifiable assumption of no unmeasured confounding. Recently, Tchetgen Tchetgen and colleagues have introduced proximal inference to leverage negative control outcomes and expos…
View article: Subgroup Difference in Differences to Identify Effect Modification Without a Control Group
Subgroup Difference in Differences to Identify Effect Modification Without a Control Group Open
Suppose it is of interest to characterize effect heterogeneity of an intervention across levels of a baseline covariate using only pre- and post- intervention outcome measurements from those who received the intervention, i.e. with no cont…
View article: Efficient estimation of weighted cumulative treatment effects by double/debiased machine learning
Efficient estimation of weighted cumulative treatment effects by double/debiased machine learning Open
In empirical studies with time-to-event outcomes, investigators often leverage observational data to conduct causal inference on the effect of exposure when randomized controlled trial data is unavailable. Model misspecification and lack o…
View article: Effects of aggressive and conservative strategies for mechanical ventilation liberation
Effects of aggressive and conservative strategies for mechanical ventilation liberation Open
View article: A Formal Causal Interpretation of the Case-Crossover Design
A Formal Causal Interpretation of the Case-Crossover Design Open
The case-crossover design of Maclure is widely used in epidemiology and other fields to study causal effects of transient treatments on acute outcomes. However, its validity and causal interpretation have only been justified under informal…
View article: Bias Formulas for Violations of Proximal Identification Assumptions
Bias Formulas for Violations of Proximal Identification Assumptions Open
Causal inference from observational data often rests on the unverifiable assumption of no unmeasured confounding. Recently, Tchetgen Tchetgen and colleagues have introduced proximal inference to leverage negative control outcomes and expos…
View article: When Do Outcome Driven Treatments Break Parallel Trends?
When Do Outcome Driven Treatments Break Parallel Trends? Open
Under what circumstances is it a threat to the parallel trends assumption required for Difference in Differences (DiD) studies if treatment decisions are based on past values of the outcome? We explore via simulation studies whether parall…
View article: Titration of Ventilator Settings to Target Driving Pressure and Mechanical Power
Titration of Ventilator Settings to Target Driving Pressure and Mechanical Power Open
This novel conditional modeling confirmed expected response patterns for ΔP, with the response to adjustments depending on subjects' lung mechanics. Furthermore, a VT-driven approach should be favored over a breathing frequency-…
View article: Systematically exploring repurposing effects of antihypertensives
Systematically exploring repurposing effects of antihypertensives Open
With availability of voluminous sets of observational data, an empirical paradigm to screen for drug repurposing opportunities (i.e., beneficial effects of drugs on nonindicated outcomes) is feasible. In this article, we use a linked claim…
View article: Structural Nested Mean Models Under Parallel Trends Assumptions
Structural Nested Mean Models Under Parallel Trends Assumptions Open
We link and extend two approaches to estimating time-varying treatment effects on repeated continuous outcomes--time-varying Difference in Differences (DiD; see Roth et al. (2023) and Chaisemartin et al. (2023) for reviews) and Structural …
View article: Using negative controls to identify causal effects with invalid instrumental variables
Using negative controls to identify causal effects with invalid instrumental variables Open
Many proposals for the identification of causal effects require an instrumental variable that satisfies strong, untestable unconfoundedness and exclusion restriction assumptions. In this paper, we show how one can potentially identify caus…
View article: Estimating optimal dynamic treatment strategies under resource constraints using dynamic marginal structural models
Estimating optimal dynamic treatment strategies under resource constraints using dynamic marginal structural models Open
Methods for estimating optimal treatment strategies typically assume unlimited access to resources. However, when a health system has resource constraints, such as limited funds, access to medication, or monitoring capabilities, medical de…
View article: Blending Knowledge in Deep Recurrent Networks for Adverse Event Prediction at Hospital Discharge
Blending Knowledge in Deep Recurrent Networks for Adverse Event Prediction at Hospital Discharge Open
Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains. However, these architectures have been limited in their ability to support complex prediction problems using insurance clai…
View article: Blending Knowledge in Deep Recurrent Networks for Adverse Event\n Prediction at Hospital Discharge
Blending Knowledge in Deep Recurrent Networks for Adverse Event\n Prediction at Hospital Discharge Open
Deep learning architectures have an extremely high-capacity for modeling\ncomplex data in a wide variety of domains. However, these architectures have\nbeen limited in their ability to support complex prediction problems using\ninsurance c…
View article: State of the Art Causal Inference in the Presence of Extraneous Covariates: A Simulation Study.
State of the Art Causal Inference in the Presence of Extraneous Covariates: A Simulation Study. Open
The central task of causal inference is to remove (via statistical adjustment) confounding bias that would be present in naive unadjusted comparisons of outcomes in different treatment groups. Statistical adjustment can roughly be broken d…
View article: Efficient Estimation of Optimal Regimes Under a No Direct Effect Assumption
Efficient Estimation of Optimal Regimes Under a No Direct Effect Assumption Open
We derive new estimators of an optimal joint testing and treatment regime under the no direct effect (NDE) assumption that a given laboratory, diagnostic, or screening test has no effect on a patient’s clinical outcomes except through the …
View article: A Formal Causal Interpretation of the Case-Crossover Design
A Formal Causal Interpretation of the Case-Crossover Design Open
The case-crossover design (Maclure, 1991) is widely used in epidemiology and other fields to study causal effects of transient treatments on acute outcomes. However, its validity and causal interpretation have only been justified under inf…
View article: G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes Open
Counterfactual prediction is a fundamental task in decision-making. G-computation is a method for estimating expected counterfactual outcomes under dynamic time-varying treatment strategies. Existing G-computation implementations have most…
View article: Fluid-limiting treatment strategies among sepsis patients in the ICU: a retrospective causal analysis
Fluid-limiting treatment strategies among sepsis patients in the ICU: a retrospective causal analysis Open