Maic Methodology

MAIC Methodology

Comprehensive methodological guidance for conducting rigorous Matching-Adjusted Indirect Comparisons following NICE DSU TSD 18.

When to Use This Skill

• Deciding whether to use MAIC vs other ITC methods
• Selecting covariates for matching
• Interpreting weight diagnostics and ESS
• Choosing between anchored and unanchored MAIC
• Reviewing MAIC code or results

Fundamental Assumptions

Key Assumption: Conditional Constancy of Relative Effects

For Anchored MAIC:

• The relative treatment effect (vs common comparator) is the same across populations AFTER adjusting for effect modifiers
• This is untestable - relies on clinical judgment
• Requires all effect modifiers to be included in matching

No Unmeasured Effect Modifiers

Critical: MAIC assumes that adjusting for measured covariates
removes all population differences that modify treatment effects.

If there are unmeasured effect modifiers:
├── Anchored MAIC: Biased indirect comparison
└── Unanchored MAIC: Even more biased

There is NO WAY to test this assumption with available data.

Unanchored MAIC: Additional Assumptions

• All prognostic factors (not just effect modifiers) must be adjusted
• Absolute treatment effects are transportable across populations
• Much stronger, often implausible assumptions
• Should be avoided if anchored is possible

When to Use MAIC

MAIC is Appropriate When:

1. IPD available for one trial (index trial)
2. Only AgD available for comparator trial
3. Important population differences exist between trials
4. Effect modifiers are known and measured
5. Sufficient overlap in covariate distributions

MAIC May Not Be Best When:

• Populations are very similar → Standard ITC may suffice
• Little covariate overlap → ESS will be very low
• Effect modifiers unknown → Cannot ensure adjustment
• Connected network exists → Consider NMA first

Covariate Selection

Selection Criteria

Include covariates that are:
├── Effect modifiers (interact with treatment effect)
│   - Based on clinical evidence
│   - Biological plausibility
│   - Subgroup analyses from trials
├── Available in both trials
│   - IPD: Individual-level data
│   - AgD: Published summary statistics
└── Different between trial populations
    - Check if actually imbalanced
    - No need to match on similar values

What NOT to Include

• Variables balanced between populations (wasteful)
• Pure prognostic factors in anchored MAIC unless they are also effect modifiers or needed for a prespecified sensitivity analysis
• Variables not reported in AgD (impossible to match)
• Too many variables (ESS concerns)

Practical Strategy

1. Start with clinical knowledge - Known effect modifiers
2. Check availability - What's reported in AgD?
3. Assess imbalance - Compare IPD means to AgD targets
4. Start conservative - Fewer variables, check ESS
5. Iterate - Add variables if ESS remains acceptable

Effective Sample Size (ESS)

Definition

ESS = (Σ weights)² / Σ(weights²)

Represents the "equivalent" unweighted sample size
that would give same precision as weighted analysis.

Interpretation Guidelines

| ESS (% of original) | Interpretation | Recommendation | |--------------------|----------------|----------------| | >70% | Good | Proceed with confidence | | 50-70% | Acceptable | Proceed with caution | | 30-50% | Concerning | Reconsider covariates | | 5% of total weight

• ESS 50% of original

- No extreme weights

- Balance achieved

5. Run anchored MAIC

result <- maicanchored( weightsobject = weights, ipd = ipd, pseudoipd = pseudoipd, trtipd = "TreatmentA", trtagd = "TreatmentB", trtcommon = "Placebo", endpointtype = "binary", effmeasure = "OR", bootci_type = "perc" )

6. Report

result$inferential$summary

## Resources

- NICE DSU TSD 18: Population-adjusted indirect comparisons
- Signorovitch et al. (2010): Original MAIC methodology
- Phillippo et al. (2016): Methods review
- maicplus package documentation

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [choxos](https://github.com/choxos)
- **Source:** [choxos/BiostatAgent](https://github.com/choxos/BiostatAgent)
- **License:** MIT

Install and usage instructions live in the source repository linked above.