Quantifying an Adherence Path-Specific Effect of Antiretroviral Therapy in the Nigeria PEPFAR Program

Caleb H. Miles, Ilya Shpitser, Phyllis Kanki, Seema Meloni, Eric J. Tchetgen Tchetgen

Research output: Contribution to journalArticle

Abstract

Since the early 2000s, evidence has accumulated for a significant differential effect of first-line antiretroviral therapy (ART) regimens on human immunodeficiency virus (HIV) viral load suppression. This finding was replicated in our data from the Harvard President’s Emergency Plan for AIDS Relief (PEPFAR) program in Nigeria. Investigators were interested in finding the source of these differences, that is, understanding the mechanisms through which one regimen outperforms another, particularly via adherence. This question can be naturally formulated via mediation analysis with adherence playing the role of a mediator. Existing mediation analysis results, however, have relied on an assumption of no exposure-induced confounding of the intermediate variable, and generally require an assumption of no unmeasured confounding for nonparametric identification. Both assumptions are violated by the presence of drug toxicity. In this article, we relax these assumptions and show that certain path-specific effects remain identified under weaker conditions. We focus on the path-specific effect solely mediated by adherence and not by toxicity and propose an estimator for this effect. We illustrate with simulations and present results from a study applying the methodology to the Harvard PEPFAR data. Supplementary materials for this article are available online.

Original languageEnglish (US)
Pages (from-to)1443-1452
Number of pages10
JournalJournal of the American Statistical Association
Volume112
Issue number520
DOIs
StatePublished - Oct 2 2017

Fingerprint

Emergency
Therapy
Path
Mediation
Confounding
Toxicity
Nonparametric Identification
Mediator
Virus
Drugs
Estimator
Nigeria
Adherence
Methodology
Line
Simulation

Keywords

  • Human immunodeficiency virus
  • Mediation
  • Nonparametric identification
  • Unobserved confounding

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Quantifying an Adherence Path-Specific Effect of Antiretroviral Therapy in the Nigeria PEPFAR Program. / Miles, Caleb H.; Shpitser, Ilya; Kanki, Phyllis; Meloni, Seema; Tchetgen Tchetgen, Eric J.

In: Journal of the American Statistical Association, Vol. 112, No. 520, 02.10.2017, p. 1443-1452.

Research output: Contribution to journalArticle

Miles, Caleb H. ; Shpitser, Ilya ; Kanki, Phyllis ; Meloni, Seema ; Tchetgen Tchetgen, Eric J. / Quantifying an Adherence Path-Specific Effect of Antiretroviral Therapy in the Nigeria PEPFAR Program. In: Journal of the American Statistical Association. 2017 ; Vol. 112, No. 520. pp. 1443-1452.
@article{e00b1c9444e04922ae43a1d5a3d8b8c9,
title = "Quantifying an Adherence Path-Specific Effect of Antiretroviral Therapy in the Nigeria PEPFAR Program",
abstract = "Since the early 2000s, evidence has accumulated for a significant differential effect of first-line antiretroviral therapy (ART) regimens on human immunodeficiency virus (HIV) viral load suppression. This finding was replicated in our data from the Harvard President’s Emergency Plan for AIDS Relief (PEPFAR) program in Nigeria. Investigators were interested in finding the source of these differences, that is, understanding the mechanisms through which one regimen outperforms another, particularly via adherence. This question can be naturally formulated via mediation analysis with adherence playing the role of a mediator. Existing mediation analysis results, however, have relied on an assumption of no exposure-induced confounding of the intermediate variable, and generally require an assumption of no unmeasured confounding for nonparametric identification. Both assumptions are violated by the presence of drug toxicity. In this article, we relax these assumptions and show that certain path-specific effects remain identified under weaker conditions. We focus on the path-specific effect solely mediated by adherence and not by toxicity and propose an estimator for this effect. We illustrate with simulations and present results from a study applying the methodology to the Harvard PEPFAR data. Supplementary materials for this article are available online.",
keywords = "Human immunodeficiency virus, Mediation, Nonparametric identification, Unobserved confounding",
author = "Miles, {Caleb H.} and Ilya Shpitser and Phyllis Kanki and Seema Meloni and {Tchetgen Tchetgen}, {Eric J.}",
year = "2017",
month = "10",
day = "2",
doi = "10.1080/01621459.2017.1295862",
language = "English (US)",
volume = "112",
pages = "1443--1452",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "520",

}

TY - JOUR

T1 - Quantifying an Adherence Path-Specific Effect of Antiretroviral Therapy in the Nigeria PEPFAR Program

AU - Miles, Caleb H.

AU - Shpitser, Ilya

AU - Kanki, Phyllis

AU - Meloni, Seema

AU - Tchetgen Tchetgen, Eric J.

PY - 2017/10/2

Y1 - 2017/10/2

N2 - Since the early 2000s, evidence has accumulated for a significant differential effect of first-line antiretroviral therapy (ART) regimens on human immunodeficiency virus (HIV) viral load suppression. This finding was replicated in our data from the Harvard President’s Emergency Plan for AIDS Relief (PEPFAR) program in Nigeria. Investigators were interested in finding the source of these differences, that is, understanding the mechanisms through which one regimen outperforms another, particularly via adherence. This question can be naturally formulated via mediation analysis with adherence playing the role of a mediator. Existing mediation analysis results, however, have relied on an assumption of no exposure-induced confounding of the intermediate variable, and generally require an assumption of no unmeasured confounding for nonparametric identification. Both assumptions are violated by the presence of drug toxicity. In this article, we relax these assumptions and show that certain path-specific effects remain identified under weaker conditions. We focus on the path-specific effect solely mediated by adherence and not by toxicity and propose an estimator for this effect. We illustrate with simulations and present results from a study applying the methodology to the Harvard PEPFAR data. Supplementary materials for this article are available online.

AB - Since the early 2000s, evidence has accumulated for a significant differential effect of first-line antiretroviral therapy (ART) regimens on human immunodeficiency virus (HIV) viral load suppression. This finding was replicated in our data from the Harvard President’s Emergency Plan for AIDS Relief (PEPFAR) program in Nigeria. Investigators were interested in finding the source of these differences, that is, understanding the mechanisms through which one regimen outperforms another, particularly via adherence. This question can be naturally formulated via mediation analysis with adherence playing the role of a mediator. Existing mediation analysis results, however, have relied on an assumption of no exposure-induced confounding of the intermediate variable, and generally require an assumption of no unmeasured confounding for nonparametric identification. Both assumptions are violated by the presence of drug toxicity. In this article, we relax these assumptions and show that certain path-specific effects remain identified under weaker conditions. We focus on the path-specific effect solely mediated by adherence and not by toxicity and propose an estimator for this effect. We illustrate with simulations and present results from a study applying the methodology to the Harvard PEPFAR data. Supplementary materials for this article are available online.

KW - Human immunodeficiency virus

KW - Mediation

KW - Nonparametric identification

KW - Unobserved confounding

UR - http://www.scopus.com/inward/record.url?scp=85041138436&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041138436&partnerID=8YFLogxK

U2 - 10.1080/01621459.2017.1295862

DO - 10.1080/01621459.2017.1295862

M3 - Article

AN - SCOPUS:85041138436

VL - 112

SP - 1443

EP - 1452

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 520

ER -