ngoResearch Concentrations 

  • Air Pollution and Health
  • Delirium
  • Cardiology
  • Longitudinal Analysis & Semiparametric Modeling
  • Model Selection
  • Competing Risks

Contact Information


Professional Biography

View Dr. Ngo's biosketch

View Dr. Ngo's complete publication history at PubMed Author Search 

View Dr. Ngo's professional research networking profile at Harvard Catalyst 

Dr. Ngo is the division ’s co-director of biostatistics, and an experienced statistician working on many collaborative projects with investigators in diverse clinical and statistical areas. He is principal investigator (PI) of a NIH-supported project on competing risks which aims to implement the Fine-Gray competing risks method for the Cancer Intervention and Surveillance Modeling Network (CISNET) models. Dr. Ngo is also site PI of a PCORI study of case-only methodology, and a training grant to teach biostatistics to faculty members in Vietnam. Dr. Ngo is co-investigator on several ongoing NIH-supported studies which include the assessment of potential proteomic, metabolomic, and lipidomic biomarkers in elderly patients who undergo elective surgery (PI: Dr. Edward Marcantonio, Dr. Towia Libermann), the modeling of cardiac long term outcomes including mortality using structural and functional imaging parameters from cardiac magnetic resonance technology (PI: Dr. Reza Nezafat), and the estimation of the effect of intranasal insulin treatment on cognitive decline functions in diabetic patients (PI: Dr. Vera Novak). Dr. Ngo also participates in the research training program of fellows, residents, students at the medical school, and the school of public health. Dr. Ngo is the past chairperson of the 9-member national Committee on Statistics and Disability for the American Statistical Association, past member of the Editorial Review Board of the Journal of Clinical Endocrinology and Metabolism, is currently an associate editor for the International Journal of Statistics and Management System, and the Journal of Cardiovascular Magnetic Resonance.

Current Research Support

VEF FS15003M (PI: Ngo) 6/1/2015-12/31/2016 
United States Faculty Scholar Grant 

This project is to provide biostatistics and research methodology training to faculty members and researchers at Hue University of Medicine and Pharmacy in Vietnam. The additional aim of this grant is to serve as a cultural ambassador representing the United States in our effort to learn from Vietnam and to help foster mutual understanding and professional scientific collaborations between the two countries.

NIH R21 CA180793 (PI: McCarthy, Ngo) 9/1/2014-9/1/2017 
Integrating Competing Risks into the CISNET DFCI Breast Cancer Model 

Cancer Intervention and Surveillance Modeling Network (CISNET) is a population-based stochastic model developed at the Dana Farber Cancer Institute (DFCI) to assess cancer screening and treatment effect. The current model does not have a mechanism to handle competing risks. This project aims to implement competing risks estimation into the CISNET models.

PCORI (PI: Mittleman, Site PI: Ngo) 9/1/2016-9/1/2019 
Stratified Regression Models for Case-Only Studies 

The goal of this project is to evaluate the three existing design of case-only studies, and implement estimation methods to extract absolute risks and other measures such as number needed to treat (NNT) from these models. Additional aims include writing software to provide power analysis capability for these case-only methods.

NIH R01 AG051658 (PI: Marcantonio/Libermann) 
Advancing the Understanding of Postoperative Delirium Mechanisms via Multi-Omics 

This project aims to leverage specimens from two recently completed NIA-funded studies, SAGES (Successful Aging after Elective Surgery), and an independent orthopedic cohort, HiPOR (Health ier Postoperative R ecovery) that collected and stored both plasma and preoperative cerebrospinal fluid (CSF). We will apply cutting edge systems level “Omics” methods to define delirium signatures that integrate proteins, lipids, and metabolites from both plasma and CSF. We will seek to confirm and further elucidate the dysfunctional inflammation pathophysiological model for delirium, and probe additional mechanisms for delirium that might interact with, or be independent of the inflammatory pathway. Ultimately, our goal is to translate our findings to the bedside through improved methods of diagnosis and monitoring of delirium, and though the design of targeted, pathophysiologically based interventions. Role: Co-Investigator.

Selected Peer-Reviewed Publications

  1. Ngo L, Wand MP. Smoothing with mixed model software. J of Stat Software 2004; 9(1):1-56.
  2. Ngo L, Ryan LM, Mezzetti M, Bois FY, Smith TJ. Estimating metabolic rate for butadiene at steady state using a Bayesian physiologically-based pharmacokinetic model. Journal of Environmental and Ecological Statistics 2011; Volume 18, Issue 1:131-146
  3. Figuerora RL, Zeng-Treitler Q, Kandula S, Ngo L. Predicting sample size required for classification performance. BMC Medical Informatics and Decision Making 2012 Feb 15; 12(1):1.
  4. Marcantonio ER, Ngo L, O'Connor M, Jones RN, Crane PK, Metzger ED, Inouye SK.3D-CAM: derivation and validation of a 3-minute diagnostic interview for CAM-defined delirium: a cross-sectional diagnostic test study. Ann Intern Med.2014 Oct 21;161(8):554-61.
  5. Schonberg MA, Li VW, Eliassen AH, Davis RB, LaCroix AZ, McCarthy EP, Rosner BA, Chlebowski RT, 
    Hankinson SE, Marcantonio ER, Ngo L. Accounting for individualized competing mortality risks in 
    estimating postmenopausal breast cancer risk. Breast Cancer Res Treat. 2016 Oct 21. [Epub ahead of 
    print] PubMed PMID: 27770283.