Research Methods in Health Informatics
Understanding research methods is essential for RHIA professionals who must evaluate published studies, support institutional research activities, manage research-related data, and ensure compliance with research regulations. This topic covers study designs, sampling methods, basic statistical concepts, and the ethical framework governing health research.
Types of Research
Research in health informatics and HIM generally falls into two broad categories:
- Quantitative research: Uses numerical data and statistical analysis to test hypotheses, measure variables, and identify relationships. Results are generalizable when samples are representative.
- Qualitative research: Uses non-numerical data (interviews, focus groups, observations, document analysis) to explore experiences, perceptions, and processes. Results provide depth and context but are not statistically generalizable.
- Mixed methods: Combines quantitative and qualitative approaches to provide both breadth and depth of understanding.
Study Designs
Understanding the hierarchy of evidence and common study designs is critical:
| Design | Type | Description | Strengths/Limitations |
|---|---|---|---|
| Randomized controlled trial (RCT) | Experimental | Participants randomly assigned to intervention or control groups; outcomes compared | Gold standard for establishing causation; expensive and time-consuming |
| Cohort study | Observational | Follows a group over time to see who develops an outcome; can be prospective or retrospective | Can establish temporal relationships; cannot prove causation |
| Case-control study | Observational | Compares individuals with a condition (cases) to those without (controls), looking backward for exposure differences | Efficient for rare diseases; subject to recall bias |
| Cross-sectional study | Observational | Examines a population at a single point in time | Good for prevalence estimates; cannot determine cause and effect |
| Descriptive study | Observational | Describes characteristics of a population or phenomenon (case reports, case series, surveys) | Generates hypotheses; does not test them |
| Systematic review/meta-analysis | Secondary | Systematically identifies, evaluates, and synthesizes all relevant studies on a topic | Highest level of evidence; dependent on quality of included studies |
Sampling Methods
The sampling method determines how representative the study sample is of the target population:
- Probability sampling (each member of the population has a known chance of selection):
- Simple random sampling: Every member has an equal chance of selection.
- Stratified random sampling: Population divided into subgroups (strata); random samples drawn from each stratum.
- Systematic sampling: Every nth member is selected from a list.
- Cluster sampling: Naturally occurring groups (clusters) are randomly selected, and all members within selected clusters are included.
- Non-probability sampling (selection based on criteria other than random chance):
- Convenience sampling: Participants selected based on availability.
- Purposive sampling: Participants selected based on specific characteristics relevant to the research question.
- Snowball sampling: Existing participants recruit additional participants.
Variables and Hypotheses
Understanding variable types is fundamental to research design:
- Independent variable: The variable manipulated or categorized by the researcher (the presumed cause).
- Dependent variable: The outcome variable being measured (the presumed effect).
- Confounding variable: An extraneous variable that correlates with both the independent and dependent variables, potentially distorting the observed relationship.
Hypotheses guide the research:
- Null hypothesis (H0): States there is no significant difference or relationship between variables.
- Alternative hypothesis (H1 or Ha): States there is a significant difference or relationship.
Basic Statistical Concepts
Key statistical concepts for the RHIA exam include:
- p-value: The probability of obtaining results at least as extreme as the observed results, assuming the null hypothesis is true. A p-value less than 0.05 is conventionally considered statistically significant.
- Type I error (alpha): Rejecting the null hypothesis when it is actually true (false positive). The significance level (usually 0.05) represents the acceptable risk of a Type I error.
- Type II error (beta): Failing to reject the null hypothesis when it is actually false (false negative).
- Power: The probability of correctly rejecting a false null hypothesis (1 - beta). Adequate power (typically 0.80) requires sufficient sample size.
- Correlation: Measures the strength and direction of a linear relationship between two variables. Correlation does not imply causation.
Data Collection Instruments
Common data collection methods in health informatics research include:
- Surveys and questionnaires: Self-administered or interviewer-administered tools for collecting standardized data.
- Chart abstraction: Systematic extraction of data from medical records using predefined data elements and coding rules.
- Administrative databases: Secondary analysis of data collected for operational purposes (claims data, registry data).
- Electronic health record data: Extraction of structured and unstructured clinical data for research purposes.
Instrument quality is assessed by reliability (consistency of measurement) and validity (accuracy of measurement - does the instrument measure what it intends to measure?).
Institutional Review Boards (IRBs)
The IRB is a committee that reviews and approves research involving human subjects to protect their rights and welfare. Key principles from the Belmont Report guide IRB review:
- Respect for persons: Individuals should be treated as autonomous agents, and persons with diminished autonomy are entitled to protection. Manifested through informed consent.
- Beneficence: Researchers must maximize benefits and minimize harm.
- Justice: The benefits and burdens of research should be distributed fairly.
Research using de-identified data or limited data sets may qualify for IRB exemption or expedited review. HIM professionals often facilitate research by providing de-identified datasets, managing data use agreements, and serving on IRBs.
Exam Preparation Tips
For the RHIA exam, be able to match study designs with appropriate research questions. Know the difference between probability and non-probability sampling. Understand Type I and Type II errors and what p-values represent. Be familiar with the Belmont Report principles and when IRB review is required versus exempt. Questions may present a research scenario and ask you to identify the study design, the independent and dependent variables, or the appropriate statistical approach.