Inferring the Timing of Antiretroviral Therapy by Zero-Inflated Random Change Point Models Using Longitudinal Data Subject to Left-Censoring

Hongbin Zhang; McKaylee Robertson; Sarah L. Braunstein; David B. Hanna; Uriel R. Felsen; Levi Waldron; Denis Nash

doi:10.3390/a18060346

Inferring the Timing of Antiretroviral Therapy by Zero-Inflated Random Change Point Models Using Longitudinal Data Subject to Left-Censoring

Hongbin Zhang
, McKaylee Robertson
, Sarah L. Braunstein
, David B. Hanna
, Uriel R. Felsen
, Levi Waldron
, Denis Nash

Research output: Contribution to journal › Article › peer-review

Abstract

We propose a new random change point model that utilizes routinely recorded individual-level HIV viral load data to estimate the timing of antiretroviral therapy (ART) initiation in people living with HIV. The change point distribution is assumed to follow a zero-inflated exponential distribution for the longitudinal data, which is also subject to left-censoring, and the underlying data-generating mechanism is a nonlinear mixed-effects model. We extend the Stochastic EM (StEM) algorithm by combining a Gibbs sampler with a Metropolis–Hastings sampling. We apply the method to real HIV data to infer the timing of ART initiation since diagnosis. Additionally, we conduct simulation studies to assess the performance of our proposed method.

Original language	English
Article number	346
Journal	Algorithms
Volume	18
Issue number	6
DOIs	https://doi.org/10.3390/a18060346
State	Published - Jun 2025

Bibliographical note

Publisher Copyright:
© 2025 by the authors.

Funding

This work was partially supported by NIH grant R21AI147933. It was also partially supported by the High-Performance Computing Center at the University of Kentucky. The Einstein-Rockefeller-CUNY Center for AIDS Research (P30-AI-124414) is supported by the following NIH Co-Funding and Participating Institutes and Centers: NIAID, NCI, NICHD, NHLBI, NIDA, NIDDK, NIGMS, NIMH, NIMHD, NIA, FIC, and OAR.

Funders	Funder number
National Institute for Child Health and Human Development National Research Service
Fondo de Innovación para la Competitividad
National Institute of General Medical Sciences DP2GM119177 Sophie Dumont National Institute of General Medical Sciences
University of Utah Center for High Performance Computing
National Institute of Diabetes and Digestive and Kidney Diseases
National Institute of Mental Health
Office of AIDS Research
National Institute on Minority Health and Health Disparities (NIMHD)
University of Kentucky
National Institute of Allergy and Infectious F32-AI286447 Cydney N. Johnson Diseases National Institute of Allergy and Infectious R01AI168214 Jason W. Rosch Diseases National Institute of Allergy and Infectious P30 Cydney N. Johnson Diseases National Institute of Allergy and Infectious R00-AI166116 Christopher D. Radka Diseases National Institute of Allergy and Infectious T32-AI106700 Cydney N. Johnson Diseases National Institute of Allergy and Infectious R01AI192221 Jason W. Rosch Diseases National Inst...
National Childhood Cancer Registry – National Cancer Institute
Author National Institute on Drug Abuse DA031791 Mark J Ferris National Institute on Drug Abuse DA006634 Mark J Ferris National Institute on Alcohol Abuse and Alcoholism AA026117 Mark J Ferris National Institute on Alcohol Abuse and Alcoholism AA028162 Elizabeth G Pitts National Institute of General Medical Sciences GM102773 Elizabeth G Pitts Peter McManus Charitable Trust Mark J Ferris National Institute on Drug Abuse
National Heart, Lung, and Blood Institute (NHLBI)
National Institute on Aging
National Institutes of Health (NIH)	R21AI147933
Einstein-Rockefeller-CUNY Center for AIDS Research, Albert Einstein College of Medicine	P30-AI-124414

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Gibbs sampler
Metropolis–Hastings sampling
Stochastic EM
antiretroviral therapy
censored data
nonlinear mixed-effects model
random change point model
zero-inflated exponential distribution

ASJC Scopus subject areas

Theoretical Computer Science
Numerical Analysis
Computational Theory and Mathematics
Computational Mathematics

Access to Document

10.3390/a18060346

Cite this

@article{0c4101cd84ae468fa17d17e41a0495fc,

title = "Inferring the Timing of Antiretroviral Therapy by Zero-Inflated Random Change Point Models Using Longitudinal Data Subject to Left-Censoring",

abstract = "We propose a new random change point model that utilizes routinely recorded individual-level HIV viral load data to estimate the timing of antiretroviral therapy (ART) initiation in people living with HIV. The change point distribution is assumed to follow a zero-inflated exponential distribution for the longitudinal data, which is also subject to left-censoring, and the underlying data-generating mechanism is a nonlinear mixed-effects model. We extend the Stochastic EM (StEM) algorithm by combining a Gibbs sampler with a Metropolis–Hastings sampling. We apply the method to real HIV data to infer the timing of ART initiation since diagnosis. Additionally, we conduct simulation studies to assess the performance of our proposed method.",

keywords = "Gibbs sampler, Metropolis–Hastings sampling, Stochastic EM, antiretroviral therapy, censored data, nonlinear mixed-effects model, random change point model, zero-inflated exponential distribution",

author = "Hongbin Zhang and McKaylee Robertson and Braunstein, \{Sarah L.\} and Hanna, \{David B.\} and Felsen, \{Uriel R.\} and Levi Waldron and Denis Nash",

note = "Publisher Copyright: {\textcopyright} 2025 by the authors.",

year = "2025",

month = jun,

doi = "10.3390/a18060346",

language = "English",

volume = "18",

number = "6",

}

TY - JOUR

T1 - Inferring the Timing of Antiretroviral Therapy by Zero-Inflated Random Change Point Models Using Longitudinal Data Subject to Left-Censoring

AU - Zhang, Hongbin

AU - Robertson, McKaylee

AU - Braunstein, Sarah L.

AU - Hanna, David B.

AU - Felsen, Uriel R.

AU - Waldron, Levi

AU - Nash, Denis

PY - 2025/6

Y1 - 2025/6

N2 - We propose a new random change point model that utilizes routinely recorded individual-level HIV viral load data to estimate the timing of antiretroviral therapy (ART) initiation in people living with HIV. The change point distribution is assumed to follow a zero-inflated exponential distribution for the longitudinal data, which is also subject to left-censoring, and the underlying data-generating mechanism is a nonlinear mixed-effects model. We extend the Stochastic EM (StEM) algorithm by combining a Gibbs sampler with a Metropolis–Hastings sampling. We apply the method to real HIV data to infer the timing of ART initiation since diagnosis. Additionally, we conduct simulation studies to assess the performance of our proposed method.

AB - We propose a new random change point model that utilizes routinely recorded individual-level HIV viral load data to estimate the timing of antiretroviral therapy (ART) initiation in people living with HIV. The change point distribution is assumed to follow a zero-inflated exponential distribution for the longitudinal data, which is also subject to left-censoring, and the underlying data-generating mechanism is a nonlinear mixed-effects model. We extend the Stochastic EM (StEM) algorithm by combining a Gibbs sampler with a Metropolis–Hastings sampling. We apply the method to real HIV data to infer the timing of ART initiation since diagnosis. Additionally, we conduct simulation studies to assess the performance of our proposed method.

KW - Gibbs sampler

KW - Metropolis–Hastings sampling

KW - Stochastic EM

KW - antiretroviral therapy

KW - censored data

KW - nonlinear mixed-effects model

KW - random change point model

KW - zero-inflated exponential distribution

UR - https://www.scopus.com/pages/publications/105009096382

UR - https://www.scopus.com/pages/publications/105009096382#tab=citedBy

U2 - 10.3390/a18060346

DO - 10.3390/a18060346

M3 - Article

AN - SCOPUS:105009096382

SN - 1999-4893

VL - 18

JO - Algorithms

JF - Algorithms

IS - 6

M1 - 346

ER -

Inferring the Timing of Antiretroviral Therapy by Zero-Inflated Random Change Point Models Using Longitudinal Data Subject to Left-Censoring

Abstract

Bibliographical note

Funding

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this