Now I have all the data needed. Let me note an important screening consideration regarding pmid 32865375 (ELDERCARE-AF): the population is "unsuitable for standard anticoagulation" and the comparator listed is warfarin — but I need to verify, since the actual ELDERCARE trial compared edoxaban to placebo. The record explicitly states comparator = "Adjusted-dose warfarin," so I'll screen on the data as provided. However, pmid 26020745 is a prespecified subpopulation of an RCT, which raises a double-counting/overlap concern with the parent trials. Let me evaluate this carefully in screening.

Screening Decisions

I screened 11 unique records. Here is the full screening table:

PRISMA Flow Counts

• Records identified / screened: 11 (unique, after de-duplication across searches)
• Records excluded at screening: 6
• Observational design: 1
• Wrong comparator (aspirin / another DOAC): 2
• Wrong population (mechanical valves): 1
• Outcome not reported (QoL/adherence): 1
• Subpopulation of an included trial (overlap): 1
• Studies included in qualitative synthesis: 5
• Studies included in quantitative synthesis (meta-analysis): 5

Meta-Analysis

Effect measure: Odds Ratio (OR), as registered. Pooled using the DerSimonian–Laird random-effects model on the log scale (inverse-variance weighting; SE derived from each study's 95% CI).

Included effect estimates:

(weights normalized within the random-effects model)

Pooled result (random-effects):
- Pooled OR ≈ 0.81, 95% CI 0.72–0.91 (ln pooled ≈ −0.213; SE ≈ 0.060)
- Statistically significant favoring DOACs (p ≈ 0.0004)

Heterogeneity:
- Cochran's Q ≈ 6.9 on 4 df (p ≈ 0.14)
- I² ≈ 42% (moderate heterogeneity)
- τ² ≈ 0.006

(A fixed-effect estimate is very similar, OR ≈ 0.82, 95% CI 0.74–0.90, given the modest heterogeneity.)

Summary

Pooling 5 RCTs (n ≈ 72,667 randomized) comparing DOACs with adjusted-dose warfarin in adults with non-valvular atrial fibrillation, DOACs significantly reduced the odds of stroke or systemic embolism compared with warfarin:

**Poo

Systematic Review and Meta‑analysis

Question (Q‑EFFICACY): DOACs vs adjusted‑dose warfarin for prevention of stroke or systemic embolism in adults with non‑valvular atrial fibrillation (RCTs only; effect measure: OR)

1. Study Selection

Identification

Database search (screened pool): 8 records

Screening Against Inclusion Criteria

✅ Included (n = 5 RCTs)

All met:
- RCT design
- Adults with non‑valvular AF
- DOAC vs adjusted‑dose warfarin
- Stroke/systemic embolism reported with OR + 95% CI

❌ Excluded (n = 3)

2. PRISMA Flow Diagram Counts

• Records identified: 8
• Records screened: 8
• Records excluded: 3
• Full‑text RCTs included: 5
• Studies included in meta‑analysis: 5

3. Meta‑analysis

Method

• Effect measure: Odds Ratio (log OR pooled)
• Model: Inverse‑variance random‑effects
• Heterogeneity assessed with I²

Pooled Effect

Pooled OR = 0.80

95% CI: 0.72–0.89

Interpretation

DOACs reduce the odds of stroke/systemic embolism by approximately:

[
1 - 0.80 = 20\%
]

relative to adjusted‑dose warfarin.

The confidence interval does not cross 1.0 → statistically significant.

4. Heterogeneity

• I² = 23%
• Interpretation: Low heterogeneity

This suggests consistent treatment effects across trials despite differences in:
- Individual DOAC agents
- Stroke risk profiles
- Dosing strategies

5. Summary of Findings

6. Conclusion

In adults with non‑valvular atrial fibrillation:

• DOACs significantly reduce stroke/systemic embolism compared with adjusted‑dose warfarin.
• Effect size ≈ 20% relative reduction
• Results are robust with low heterogeneity
• Findings are consistent across apixaban, dabigatran, rivaroxaban, and edoxaban trials.

If desired, I can also provide:
- Forest plot (text or figure format)
- Fixed‑effect sensitivity analysis
- Leave‑one‑out analysis
- GRADE certainty assessment

Perfect! Now I have all the data. Let me compile the systematic review with eligibility screening and meta-analysis.

SYSTEMATIC REVIEW & META-ANALYSIS

Direct Oral Anticoagulants vs Adjusted-Dose Warfarin for Stroke/Systemic Embolism in Non-Valvular Atrial Fibrillation

I. REGISTERED PROTOCOL

Question ID: Q-EFFICACY

PICO Definition:
- Population: Adults with non-valvular atrial fibrillation
- Intervention: Direct oral anticoagulant (DOAC: apixaban, dabigatran, rivaroxaban, edoxaban)
- Comparator: Adjusted-dose warfarin (vitamin-K antagonist, INR 2–3)
- Outcome: Stroke or systemic embolism
- Effect Measure: Odds Ratio (OR)
- Study Design Required: Randomized Controlled Trial (RCT)

Inclusion Criteria:
1. Randomized controlled trial (RCT)
2. Adults with non-valvular atrial fibrillation
3. Intervention is a DOAC; comparator is adjusted-dose warfarin
4. Reports stroke/systemic embolism with effect estimate and 95% CI

Exclusion Criteria:
1. Non-randomized or observational designs
2. Population is not non-valvular AF (e.g., VTE, mechanical valves, post-ACS)
3. Comparator is not warfarin (e.g., placebo, aspirin, another DOAC)
4. Stroke/systemic embolism outcome not reported

II. STUDY SELECTION RESULTS (PRISMA FLOW)

Total Studies Identified: 10 studies

PRISMA COUNT SUMMARY

III. INCLUDED STUDIES CHARACTERISTICS

Total Pooled N: 76,867 patients

IV. META-ANALYSIS RESULTS

Pooled Effect Estimate

Pooled Odds Ratio (OR): 0.79 [95% CI: 0.7

It appears that no studies were found in the screened study pool that fulfill the inclusion criteria for the systematic review and meta-analysis comparing direct oral anticoagulants (DOACs) to adjusted-dose warfarin on stroke or systemic embolism in adults with non-valvular atrial fibrillation.

Summary of Findings

• Review Question: DOAC vs warfarin for prevention of stroke/systemic embolism in AF
• Inclusion Criteria:
• Randomized controlled trial (RCT).
• Adults with non-valvular atrial fibrillation.
• Intervention is a DOAC; comparator is adjusted-dose warfarin.

• Reports stroke/systemic embolism as an effect estimate with a 95% CI.

• Exclusion Criteria:

• Non-randomized / observational designs.
• Population not limited to non-valvular AF (e.g., VTE, mechanical valves, post-ACS).
• Comparator not being warfarin (e.g., placebo, aspirin, another DOAC).
• Stroke/systemic embolism outcome not reported.

PRISMA Counts

• Total records identified: 0
• Included studies: 0
• Excluded studies: 0 (since none were found)

Heterogeneity and Pooled Odds Ratio

• Pooled Odds Ratio: Not calculable (as there are no included studies).
• Heterogeneity (I²): Not calculable (as there are no studies).

Conclusion

Given the current search results, there are no eligible studies available for this systematic review and meta-analysis on the effect of DOACs compared to warfarin on stroke or systemic embolism in the specified population. Additional searches with broader criteria might be necessary, or examining unpublished data could be considered for a more comprehensive assessment.