Selection of appropriate design in the development of interventional and observational research

Shiro Hinotsu

Research output: Contribution to journalReview articlepeer-review

Abstract

Selecting the appropriate study design is crucial when developing clinical research. A fundamental decision is whether to collect data to address the research question using an observational study or to apply an intervention and measure outcomes in a clinical trial. There are two well-known types of observational studies: cohort studies and cross-sectional studies. In the former, a cohort of subjects is observed over time. In prospective cohort studies, observations begin in the present and follow subjects for a given time period. In retrospective cohort studies, information is collected at time intervals in the past. The third potential study design is the case-control study. In such studies, the researcher compares a group of subjects who have a disease or some other outcome with a group without that characteristic. Among clinical trial options, the randomized clinical trial is thought to be higher evidence level than other clinical trials. Developing clinical research begins with the research question, which specifies the primary endpoint, explanatory variables, and the target population. Then, the clinical question and study outline are expanded to the study protocol and case report form. In developing the study protocol, the investigators consider study design, study size, data quality, and feasibility.

Original languageEnglish
Pages (from-to)405-409
Number of pages5
JournalJapanese Journal of Cancer and Chemotherapy
Volume41
Issue number4
Publication statusPublished - Apr 2014
Externally publishedYes

Keywords

  • Interventional research
  • Observational research
  • Study design

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Fingerprint Dive into the research topics of 'Selection of appropriate design in the development of interventional and observational research'. Together they form a unique fingerprint.

Cite this