1
|
Wyss R, Yanover C, El-Hay T, Bennett D, Platt RW, Zullo AR, Sari G, Wen X, Ye Y, Yuan H, Gokhale M, Patorno E, Lin KJ. Machine learning for improving high-dimensional proxy confounder adjustment in healthcare database studies: an overview of the current literature. Pharmacoepidemiol Drug Saf 2022; 31:932-943. [PMID: 35729705 PMCID: PMC9541861 DOI: 10.1002/pds.5500] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 06/01/2022] [Accepted: 06/05/2022] [Indexed: 11/10/2022]
Abstract
Controlling for large numbers of variables that collectively serve as 'proxies' for unmeasured factors can often improve confounding control in pharmacoepidemiologic studies utilizing administrative healthcare databases. There is a growing body of evidence showing that data-driven machine learning algorithms for high-dimensional proxy confounder adjustment can supplement investigator-specified variables to improve confounding control compared to adjustment based on investigator-specified variables alone. Consequently, there has been a recent focus on the development of data-driven methods for high-dimensional proxy confounder adjustment. In this paper, we discuss the considerations underpinning three areas for data-driven high-dimensional proxy confounder adjustment: 1) feature generation-transforming raw data into covariates (or features) to be used for proxy adjustment; 2) covariate prioritization, selection and adjustment; and 3) diagnostic assessment. We survey current approaches and recent advancements within each area, including the most widely used approach to proxy confounder adjustment in healthcare database studies (the high-dimensional propensity score or hdPS). We also discuss limitations of the hdPS and outline recent advancements that incorporate the principles of proxy adjustment with machine learning extensions to improve performance. We further discuss challenges and avenues of future development within each area. This manuscript is endorsed by the International Society for Pharmacoepidemiology (ISPE). This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Richard Wyss
- Division of Pharmacoepidemioogy and Pharmacoeconomics, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | | | - Tal El-Hay
- KI Research Institute, Kfar Malal, Israel.,IBM Research-Haifa Labs, Haifa, Israel
| | - Dimitri Bennett
- Global Evidence and Outcomes, Takeda Pharmaceutical Company Ltd., Cambridge, MA, USA
| | | | - Andrew R Zullo
- Department of Health Services, Policy, and Practice, Brown University School of Public Health and Center of Innovation in Long-Term Services and Supports, Providence Veterans Affairs Medical Center, Providence, RI, USA
| | - Grammati Sari
- Real World Evidence Strategy Lead, Visible Analytics Ltd, Oxford, UK
| | - Xuerong Wen
- Health Outcomes, Pharmacy Practice, College of Pharmacy, University of Rhode Island, Kingston, RI, USA
| | - Yizhou Ye
- Global Epidemiology, AbbVie Inc. North Chicago, IL, USA
| | - Hongbo Yuan
- Canadian Agency for Drugs and Technologies in Health, Ottawa, Canada
| | - Mugdha Gokhale
- Pharmacoepidemiology, Center for Observational and Real-world Evidence, Merck, PA, USA
| | - Elisabetta Patorno
- Division of Pharmacoepidemioogy and Pharmacoeconomics, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Kueiyu Joshua Lin
- Division of Pharmacoepidemioogy and Pharmacoeconomics, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.,Department of Medicine, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
2
|
Bozorgmehr R, Edalatifard M, Safavi E, Rahimi B, Ghorbani F, Abtahi H, Amini S, Pourdowlat G. Therapeutic effects of nebulized verapamil on chronic obstructive pulmonary disease: A randomized and double‐blind clinical trial. CLINICAL RESPIRATORY JOURNAL 2020; 14:370-381. [DOI: 10.1111/crj.13142] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/26/2019] [Revised: 10/08/2019] [Accepted: 12/09/2019] [Indexed: 01/17/2023]
Affiliation(s)
- Rama Bozorgmehr
- Clinical Research Development Unit Shohadaye Tajrish Hospital Shahid Beheshti University of Medical Sciences Tehran Iran
| | - Maryam Edalatifard
- Thoracic Research Center Tehran University of Medical Sciences Tehran Iran
| | - Enayat Safavi
- Thoracic Research Center Tehran University of Medical Sciences Tehran Iran
| | - Besharat Rahimi
- Thoracic Research Center Tehran University of Medical Sciences Tehran Iran
| | - Fariba Ghorbani
- Tracheal Diseases Research Center National Research Institute of Tuberculosis and Lung DiseaseShahid Beheshti University of Medical Sciences Tehran Iran
| | - Hamidreza Abtahi
- Thoracic Research Center Tehran University of Medical Sciences Tehran Iran
| | - Shahideh Amini
- Faculty of Pharmacy Clinical Pharmacy Department Tehran University of Medical Sciences Tehran Iran
| | - Guitti Pourdowlat
- Chronic Respiratory Diseases Research Center National Research Institute of Tuberculosis and Lung Disease (NRITLD)Shahid Beheshti University of Medical Sciences Tehran Iran
| |
Collapse
|
3
|
Abstract
The use of beta-blockers in patients with chronic obstructive pulmonary disease (COPD) has received much attention. Several observational studies reported important reductions in mortality and exacerbations with these drugs, but the extent of bias in these studies is unclear. Nevertheless, the large ongoing randomized trial (βLOCK-COPD) was initiated specifically to evaluate these effects. We searched the literature to identify all observational studies investigating the effectiveness of beta-blockers in COPD patients on major outcomes, including death and COPD exacerbation. We identified 18 observational studies, with 10 studies affected by confounding bias and six by immortal time bias, while two addressed these biases. Reductions in all-cause mortality with beta-blocker use were observed among the studies with confounding bias (pooled rate ratio 0.72; 95% CI 0.59-0.88) and those with immortal time bias (pooled rate ratio 0.64; 95% CI 0.53-0.77). A large five-database study that addressed these two biases reported hazard ratios of 0.90 (95% CI: 0.78-1.02) for death and 0.54 (95% CI: 0.47-0.61) for COPD hospitalization. However, this latter estimate was the same as for the first 30 days after treatment initiation, thus indicating that important residual confounding cannot be ruled out. Observational studies, important to provide evidence from real-world data on medication effects, are unsupportive for beta-blockers in COPD. Even if immortal time bias is properly avoided, confounding bias cannot be fully controlled due to their relative contraindication in COPD. In the case of beta-blockers, randomized trials such as βLOCK-COPD are necessary to eliminate the uncertainty from residual confounding bias.
Collapse
Affiliation(s)
- Samy Suissa
- a Center for Clinical Epidemiology, Lady Davis Institute - Jewish General Hospital , Montreal , Canada.,b Departments of Epidemiology and Biostatistics and of Medicine , McGill University , Montreal , Canada
| | - Pierre Ernst
- b Departments of Epidemiology and Biostatistics and of Medicine , McGill University , Montreal , Canada
| |
Collapse
|
4
|
Prada-Ramallal G, Takkouche B, Figueiras A. Bias in pharmacoepidemiologic studies using secondary health care databases: a scoping review. BMC Med Res Methodol 2019; 19:53. [PMID: 30871502 PMCID: PMC6419460 DOI: 10.1186/s12874-019-0695-y] [Citation(s) in RCA: 60] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2018] [Accepted: 02/26/2019] [Indexed: 12/17/2022] Open
Abstract
BACKGROUND The availability of clinical and therapeutic data drawn from medical records and administrative databases has entailed new opportunities for clinical and epidemiologic research. However, these databases present inherent limitations which may render them prone to new biases. We aimed to conduct a structured review of biases specific to observational clinical studies based on secondary databases, and to propose strategies for the mitigation of those biases. METHODS Scoping review of the scientific literature published during the period 2000-2018 through an automated search of MEDLINE, EMBASE and Web of Science, supplemented with manually cross-checking of reference lists. We included opinion essays, methodological reviews, analyses or simulation studies, as well as letters to the editor or retractions, the principal objective of which was to highlight the existence of some type of bias in pharmacoepidemiologic studies using secondary databases. RESULTS A total of 117 articles were included. An increasing trend in the number of publications concerning the potential limitations of secondary databases was observed over time and across medical research disciplines. Confounding was the most reported category of bias (63.2% of articles), followed by selection and measurement biases (47.0% and 46.2% respectively). Confounding by indication (32.5%), unmeasured/residual confounding (28.2%), outcome misclassification (28.2%) and "immortal time" bias (25.6%) were the subcategories most frequently mentioned. CONCLUSIONS Suboptimal use of secondary databases in pharmacoepidemiologic studies has introduced biases in the studies, which may have led to erroneous conclusions. Methods to mitigate biases are available and must be considered in the design, analysis and interpretation phases of studies using these data sources.
Collapse
Affiliation(s)
- Guillermo Prada-Ramallal
- Department of Preventive Medicine and Public Health, University of Santiago de Compostela, c/ San Francisco s/n, 15786 Santiago de Compostela, A Coruña Spain
- Health Research Institute of Santiago de Compostela (Instituto de Investigación Sanitaria de Santiago de Compostela - IDIS), Clinical University Hospital of Santiago de Compostela, 15706 Santiago de Compostela, Spain
| | - Bahi Takkouche
- Department of Preventive Medicine and Public Health, University of Santiago de Compostela, c/ San Francisco s/n, 15786 Santiago de Compostela, A Coruña Spain
- Health Research Institute of Santiago de Compostela (Instituto de Investigación Sanitaria de Santiago de Compostela - IDIS), Clinical University Hospital of Santiago de Compostela, 15706 Santiago de Compostela, Spain
- Consortium for Biomedical Research in Epidemiology & Public Health (CIBER en Epidemiología y Salud Pública – CIBERESP), Santiago de Compostela, Spain
| | - Adolfo Figueiras
- Department of Preventive Medicine and Public Health, University of Santiago de Compostela, c/ San Francisco s/n, 15786 Santiago de Compostela, A Coruña Spain
- Health Research Institute of Santiago de Compostela (Instituto de Investigación Sanitaria de Santiago de Compostela - IDIS), Clinical University Hospital of Santiago de Compostela, 15706 Santiago de Compostela, Spain
- Consortium for Biomedical Research in Epidemiology & Public Health (CIBER en Epidemiología y Salud Pública – CIBERESP), Santiago de Compostela, Spain
| |
Collapse
|
5
|
Su TH, Chang SH, Kuo CF, Liu PH, Chan YL. β-blockers after acute myocardial infarction in patients with chronic obstructive pulmonary disease: A nationwide population-based observational study. PLoS One 2019; 14:e0213187. [PMID: 30835781 PMCID: PMC6400336 DOI: 10.1371/journal.pone.0213187] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2018] [Accepted: 02/17/2019] [Indexed: 12/21/2022] Open
Abstract
BACKGROUND Patients with chronic obstructive pulmonary disease (COPD) less often receive β-blockers after acute myocardial infarction (AMI). This may influence their outcomes after AMI. This study evaluated the efficacy of β-blockers after AMI in patients with COPD, compared with non-dihydropyridine calcium channel blockers (NDCCBs) and absence of these two kinds of treatment. METHODS AND RESULTS We conducted a nationwide population-based cohort study using data retrieved from Taiwan National Health Insurance Research Database. We collected 28,097 patients with COPD who were hospitalized for AMI between January 2004 and December 2013. After hospital discharge, 24,056 patients returned to outpatient clinics within 14 days (the exposure window). Those who received both β-blockers and NDCCBs (n = 302) were excluded, leaving 23,754 patients for analysis. Patients were classified into the β-blocker group (n = 10,638, 44.8%), the NDCCB group, (n = 1,747, 7.4%) and the control group (n = 11,369, 47.9%) based on their outpatient prescription within the exposure window. The β-blockers group of patients had lower overall mortality risks (adjusted hazard ratio [95% confidence interval]: 0.91 [0.83-0.99] versus the NDCCB group; 0.88 [0.84-0.93] versus the control group), but the risk of major adverse cardiac events within 1 year was not statistically different. β-blockers decreased risks of re-hospitalization for COPD and other respiratory diseases by 12-32%. CONCLUSIONS The use of β-blockers after AMI was associated with a reduced mortality risk in patients with COPD. β-blockers did not increase the risk of COPD exacerbations.
Collapse
Affiliation(s)
- Tse-Hsuan Su
- Departments of Emergency Medicine, Chang Gung Memorial Hospital Linkou, Taoyuan, Taiwan
| | - Shang-Hung Chang
- Departments of Cardiology, Chang Gung Memorial Hospital Linkou, Taoyuan, Taiwan
| | - Chang-Fu Kuo
- Departments of Rheumatology, Chang Gung Memorial Hospital Linkou, Taoyuan, Taiwan
| | - Pi-Hua Liu
- Clinical Informatics and Medical Statistics Research Center, Chang Gung University, Taoyuan, Taiwan
| | - Yi-Ling Chan
- Departments of Emergency Medicine, Chang Gung Memorial Hospital Linkou, Taoyuan, Taiwan
- * E-mail:
| |
Collapse
|
6
|
Najafzadeh M, Gagne JJ, Schneeweiss S. Synergies From Integrating Randomized Controlled Trials and Real-World Data Analyses. Clin Pharmacol Ther 2017; 102:914-916. [PMID: 29034448 DOI: 10.1002/cpt.873] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2017] [Revised: 09/06/2017] [Accepted: 09/08/2017] [Indexed: 01/24/2023]
Abstract
Analyses using administrative claims databases or national registries provide estimates of benefits and harms of medications in real-world settings for large and diverse patient populations. Whereas claims-based nonrandomized studies and randomized-controlled trials (RCTs) have distinct limitations, their strengths are complementary. Integrating RCT and claims data offers substantial synergies. We propose obtaining routinely collected longitudinal claims data from RCT participants and discuss the added value of the novel evidence that can be derived from this "information overlap."
Collapse
Affiliation(s)
- Mehdi Najafzadeh
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Joshua J Gagne
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Sebastian Schneeweiss
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|