Software Tools to Facilitate Systematic Review Used for Cancer Hazard Identification

Abstract

Objective and systematic methods to search, review, and synthesize published studies are a fundamental aspect of carcinogen hazard classification. Systematic review is a historical strength of the International Agency for Research on Cancer (IARC) Monographs Program and the United States National Toxicology Program (NTP) Office of the Report on Carcinogens (RoC). Both organizations are tasked with evaluating peer-reviewed, published evidence to determine whether specific substances, exposure scenarios, or mixtures pose a cancer hazard to humans. This evidence synthesis is based on objective, transparent, published methods that call for extracting and interpreting data in a systematic manner from multiple domains, including a) human exposure, b) epidemiological evidence, c) evidence from experimental animals, and d) mechanistic evidence. The process involves multiple collaborators and requires an extensive literature search, review, and synthesis of the evidence. Several online tools have been implemented to facilitate these collaborative systematic review processes. Specifically, Health Assessment Workplace Collaborative (HAWC) and Table Builder are custom solutions designed to record and share the results of the systematic literature search, data extraction, and analyses. In addition, a content management system for web-based project management and document submission has been adopted to enable access to submitted drafts simultaneously by multiple co-authors and to facilitate their peer review and revision. These advancements in cancer hazard classification have applicability in multiple systematic review efforts. https://doi.org/10.1289/EHP4224.

Figure 1.

Literature tagging using HAWC. User-defined tags, organized in a hierarchical structure, can be created for each assessment and manually applied to literature identified from searches in HAWC via PubMed or imported from other software platforms. Here, we present a representative image generated by HAWC showing the results of a literature search per the key characteristics of carcinogens (Smith et al., 2016) and other topics relevant to mechanistic data evaluation for lindane (Group 1; IARC 2017b). The far-left node in the figure indicates that a total of 1,081 references were identified from literature searches (also recorded in HAWC). Of these references, 878 relevant references were identified for Section 4 of the IARC monograph, and of those, 626 were included and 252 were excluded. Of note, more than one exclusion criteria may apply to each excluded study, and more than one category may apply to included studies (e.g., if more than one key characteristic, endpoint, species, etc., was evaluated). The visualizations are interactive; tags can be expanded, and child-tags are revealed with the count of references in each tag; other tags may be left unexpanded. Expanded and unexpanded tags are represented by unshaded and shaded circles, respectively.

Figure 2.

Data extraction and summary tables in Table Builder. (A) Data extraction form for the Table Builder software; epidemiological study description as shown for the IARC Monographs including population, exposure characteristics, and strengths and limitations of study. (B) Results view of the same study; a single study can have multiple sets of results, generally defined by organ sites, with potential confounders. (C) The tabular web-view of the data after data entry in the prior panels; this view parallels the Microsoft® Word output reports generated which are subsequently used in final monographs. Users can edit content in rows; rows are locked after quality assessment/quality control (QA/QC) to prevent further changes.

Figure 2.

Data extraction and summary tables in Table Builder. (A) Data extraction form for the Table Builder software; epidemiological study description as shown for the IARC Monographs including population, exposure characteristics, and strengths and limitations of study. (B) Results view of the same study; a single study can have multiple sets of results, generally defined by organ sites, with potential confounders. (C) The tabular web-view of the data after data entry in the prior panels; this view parallels the Microsoft® Word output reports generated which are subsequently used in final monographs. Users can edit content in rows; rows are locked after quality assessment/quality control (QA/QC) to prevent further changes.

Figure 3.

Confounder analysis and forest plot/meta-analysis from data captured in Table Builder. (A) The summary table allows users to identify and view potential confounders in a matrix format and evaluate whether handling of these potential confounders can explain the findings within and across studies. This example displays studies examining the association between exposure to antimony and lung cancer mortality. Below the summary table, pertinent information on potential confounders within each study are extracted and evaluated. (B) A stratified forest plot and random effects meta-analysis from data captured in table builder and generated from table builder exports using R software. Exports can be used in other software packages such as Excel, SAS, or Stata for customized analyses and reformatting.