Bayesian Causal Atlas · Vol. Women’s Health · Pearl Structural Causal Model

Endometriosis — Structural Causal Analysis

Endometriosis affects an estimated ~6.5 million United States women and is a leading cause of pelvic pain, dysmenorrhoea and infertility, with long diagnostic delays. Benign, with essentially no mortality — the burden is chronic pain, quality of life and fertility. This oracle estimates the causal reduction in estrogen-driven lesion activity — the shared mediator — across analgesic, hormonal and surgical options, using effect sizes from named trials. For education, not individual medical advice.

Method. Structural Causal Model (SCM) with backdoor adjustment (Pearl). Interventions are not assumed independent: hormonal options share the estrogen-suppression pathway, so their overlap is removed by an eigenvalue-corrected equicorrelation model at an adjustable mean cross-correlation ρ̄ (default 0.30). NSAIDs are separated as a lesion-independent analgesic path. Robustness to unmeasured confounding is quantified with the E-value. PN / PS / PNS under monotonicity. Every relative risk is cited — no effect size is invented. The front door is resolved through an EXPLICIT mediator cascade (hormonal → symptomatic → surgical → disease state), not one lumped node: each intervention acts on a specific node, so same-node interventions are substitutes that saturate against each other, while different-node interventions are d-separated given the intermediate node and compose in series. The cross-correlation removal thus follows from the graph structure; the residual ρ̄ cleans up only the mediator-independent (direct) effects.
ρ̄ = 0.30
A–D (all)
A high (RCT/meta) · B cohort · C case-series/modelled · D consensus/provisional. Lower-grade interventions are excluded from the DAG, front-door pooling, Pareto, Monte‑Carlo & sensitivity.

Interventions

Tick the interventions to combine. Each shows its trial effect estimate, 95% confidence interval (CI), E-value, mechanism, and citation. ★ = in the current Pareto effective set but not yet ticked.

Combined causal estimate

Headline is the front-door estimate: shared lesion overlap removed via dose-response saturation; residual direct-effect overlap removed via the eigenvalue model at ρ̄.

1.00
Combined RR
0%
Relative risk ↓
Pooled E-value
Interventions selected (k)
0
Effective independent dimensions (n_eff)
0
Redundancy discount applied
0%
Baseline risk (illustrative anchor)
Absolute risk after intervention
Absolute risk difference (RD)
Backdoor-only RR (no front-door)
Mediator (lesion) overlap removed
Number needed to treat (NNT)
ρ-sensitivity band (ρ 0 → 0.6)
Interpretation

Causal attribution

Under monotonicity + exogeneity (E-value bounds the exogeneity assumption).

Probability of Necessity (PN)
Probability of Sufficiency (PS)
Prob. of Necessity & Sufficiency (PNS, lower bound)
Causal DAG
Cross-correlation
Pareto (threshold)
Monte Carlo
Front-door mediation
What-if / If-not-for
Sensitivity
Antithesis

Faithful causal directed acyclic graph (DAG). Each therapy is a node; hormonal and surgical options act through the shared mediator estrogen-driven lesion activity, which drives pelvic pain, fertility/quality-of-life and recurrence — the components of the morbidity burden Y. NSAIDs act independently of lesion activity (prostaglandin-mediated pain). Named confounders — disease stage, central sensitisation, fertility goals — open back-door paths (adjusted). Mediator cascade: interventions attach to the node they act on (hormonal → symptomatic → surgical), which converge on the disease state and thence the endpoint — drawing the intermediate mediators explicitly is what exposes d-separation and per-channel saturation.

Confounders U:age · disease stage/location · fertility goals · prior surgery · adenomyosis · central sensitisation → back-door paths (adjusted)NSAIDCombined hormonalcontraceptiveProgestin(dienogest)LNG-IUSGnRH agonist+ add-backGnRH antagonist(elagolix)Laparoscopicexcision / ablationHormonalsuppressionSymptomatic(prostaglandin)SurgicalexcisionLesionactivity / painPain /burdenFront-door: through lesion suppressionLesion-independent (prostaglandin pain)Back-door confounding (adjusted)

Eigenvalue diagnostics for the selected interventions under an equicorrelation matrix (off-diagonal ρ̄). A large λmax relative to k signals redundancy; n_eff is the effective number of independent interventions actually contributing.

k (selected)
0
λmax
λmin
n_eff = (Σλ)² / Σλ²
Condition number

On mechanistic grounds ρ̄ ≈ 0.30 is defensible: hormonal therapies overwhelmingly share the estrogen-suppression / menstrual-suppression pathway, so combining two hormonal agents is largely redundant. ρ̄ is user-adjustable because a prostaglandin-blocking analgesic and lesion excision share little mechanism. Most of the overlap is now handled structurally by the mediator nodes (same-node substitutes saturate); ρ̄ governs only the residual correlation among direct effects.

Minimum-effective-set analysis. Set a target combined risk reduction; the model finds the smallest set of interventions — accounting for front-door mediator overlap — that reaches it, and highlights them. If the target exceeds what all interventions together can achieve, the full set is shown (never an empty one). "Apply" ticks exactly that set.

Target combined risk ↓ ≥ 50%

Monte Carlo propagation. Each selected intervention's log-effect is sampled from a normal distribution implied by its 95% CI; samples are combined with the same eigenvalue overlap discount. 5,000 draws.

Median combined RR
95% simulation interval
Standard deviation of combined RR
P(combined RR < 0.90)

Antithesis — challenging this oracle's own conclusions

The endpoint is pain, not survival. Endometriosis is a chronic benign disease; there is essentially no mortality. Estimates are surrogates for pelvic pain, quality of life and fertility. Malignant transformation is rare.
Hormonal control reverses and blocks pregnancy. Every hormonal option suppresses lesions only while taken and prevents conception; a woman trying to conceive cannot use them, which is why surgery and expectant/assisted-reproduction pathways dominate that arm. On-treatment relative risks overstate durable benefit.
Pain and lesion burden are poorly correlated. Deep pain can persist despite lesion suppression because of central sensitisation and adenomyosis; a lesion-focused mediator model overstates how much pain any anti-estrogen therapy can remove.
Surgery recurs without suppression. Excision helps, but symptoms and lesions recur in a substantial fraction within 2–5 years unless post-operative hormonal suppression is used; the surgical relative risk is a short-horizon estimate.
GnRH and aromatase agents cost bone. Deep estrogen suppression (GnRH agonist/antagonist, aromatase inhibitor) causes dose-dependent bone-density loss and vasomotor symptoms — competing harms not captured by the pain relative risk, and the reason for add-back and time limits.

What-if — the do-operator: P(Y | do(S))

Intervening on the selected set S with Pearl's do-operator (setting the interventions, not merely observing them). Contrast against do(∅) = no intervention.

P(outcome | do(∅)) — baseline
P(outcome | do(S)) — intervened
Absolute risk reduction (ARR)
Number needed to treat (NNT)

If-not-for — but-for counterfactual (leave-one-out)

For each intervention: "if not for this one, the combined front-door effect would be…". Isolates each intervention's marginal causal contribution after mediator-overlap removal, so shared-pathway agents are not double-credited.

If not for…RR without itRR with full setmarginal RRR lost

One-at-a-time sensitivity. Each intervention's effect is swung across its 95% confidence interval (others held at point estimate); the bar is the resulting swing in the combined front-door effect. A long bar means the combined estimate leans heavily on that single trial's precision.

Optimistic bound (all at CI-low)
Point estimate
Pessimistic bound (all at CI-high)
Pooled E-value (confounding robustness)

Front-door (mediation) decomposition. Hormonal and surgical therapies act through one shared mediator — suppression of estrogen-driven lesion activity. Each log-effect is split into a lesion-mediated (indirect) and a lesion-independent (direct) part. Indirect parts are pooled through the mediator with dose-response saturation, removing the mediator cross-correlation; direct parts keep the residual eigenvalue correlation at ρ̄. NSAIDs, which relieve prostaglandin pain without touching the lesion, are NOT discounted against the hormonal options. Here mediated effects are pooled WITHIN each cascade node (dose-response saturation of substitutes) and composed in SERIES across nodes (d-separated channels), with the per-node reductions reported so the channel structure is visible.

Mediator saturation cap = 55% lesion ↓
Sum of standalone lesion reduction (naive)
Combined lesion reduction after saturation
Mediator overlap removed (1 - saturation)
Direct-effect redundancy removed (1 - n_eff/k)
Front-door combined RR
Backdoor-only combined RR (comparison)
InterventionRR%lesionmed-fracindirect logdirect log

Which % of cross-correlation is appropriate? Not one number. The mediator overlap is fixed empirically by the lesion saturation (currently removing of the summed mediated effect when interventions are stacked). Note a domain caveat: hormonal options are mutually redundant and all prevent pregnancy, so the fertility-desired arm relies on surgery / assisted reproduction. Lesion-mediated fractions are transparent, adjustable priors.

Front-door caveat (antithesis): the endpoint is pelvic pain — a surrogate poorly correlated with lesion burden because of central sensitisation and adenomyosis. Hormonal control reverses on stopping, and surgery recurs without post-operative suppression, so on-treatment relative risks overstate durable benefit.

Executive summary

Select interventions to generate a plain-language summary.