Background Interstitial ectopic pregnancy is rare and carries risks of rupture and severe haemorrhage. Accurate terminology is important because interstitial and cornual pregnancy are often used interchangeably despite representing distinct implantation sites. The primary objective of this five-year audit was to assess compliance with anatomically precise diagnostic terminology. Secondary objectives evaluated ultrasound assessment, escalation of diagnostically uncertain findings, and documented individualisation of management. Methods We retrospectively audited confirmed cases diagnosed between October 2020 and December 2025. Cases identified from Early Pregnancy Assessment Unit clinical and ultrasound records were verified against recognised diagnostic criteria. Five predefined criteria based on the National Institute for Health and Care Excellence (NICE), Royal College of Obstetricians and Gynaecologists (RCOG), and European Society of Human Reproduction and Embryology (ESHRE) guidance assessed transvaginal ultrasonography, compatible anatomical features, escalation of uncertainty, precise terminology in the final ultrasound conclusion, and individualised management. The target was 100% for each applicable criterion. Cases were classified as compliant, non-compliant, or not assessable and analysed descriptively. Results Five cases were identified. All patients underwent transvaginal ultrasonography, with reports documenting anatomical findings compatible with interstitial ectopic pregnancy. Across the five reports, these included an empty uterine cavity, a laterally located gestational sac, a thin surrounding myometrial mantle, and an interstitial line sign. Diagnosis was established on the first scan in three cases, while two diagnostically uncertain cases were confirmed following repeat assessment and lead-sonographer review. All pregnancies were diagnosed before rupture and before eight weeks' gestation. However, all final ultrasound conclusions used the term confirmed cornual ectopic pregnancy, resulting in 0% compliance with anatomically precise terminology. Management was individualised and included methotrexate, hysteroscopic resection, and surgery initiated laparoscopically. No major complications were recorded, and all hospital stays were two days or fewer. Conclusions The principal finding of this five-case retrospective audit was 0% compliance with anatomically precise terminology: all final ultrasound conclusions used the term cornual ectopic pregnancy despite imaging findings compatible with interstitial ectopic pregnancy. This represents a terminology and documentation gap rather than evidence of deficient diagnostic recognition or clinical management. Conversely, compliance was 100% for transvaginal ultrasound assessment, documentation of compatible anatomical features, escalation of diagnostically uncertain findings, and documented individualisation of management. Favourable short-term outcomes were descriptive observations and do not demonstrate the effectiveness or superiority of the diagnostic pathway or any management strategy. Standardised anatomical nomenclature may improve clinical communication, documentation quality, coding accuracy, audit reliability, and future research reporting. Educational initiatives and standardised reporting templates should reinforce the distinction between interstitial, cornual, and angular pregnancies, with re-audit recommended following improvement measures are implemented.

Selective state-space models (SSMs) such as Mamba achieve linear-time sequence modeling through input-dependent recurrence, yet they apply the same dynamics regardless of the latent regime generating the data-a structural mismatch for non-stationary signals whose statistics shift abruptly between regimes. We introduce RC-Mamba, a probabilistic forecaster whose selective-SSM backbone is dynamically conditioned on the posterior over a latent regime variable. Regime posteriors from a Student-t emission Hidden Markov Model with a sticky Dirichlet prior modulate the SSM discretisation step Δ t together with the input and readout matrices B t and C t , so the recurrence adapts its memory decay, input sensitivity, and output emphasis to the prevailing market state. An entropy-based scale-modulation component, the Regime Uncertainty Gate, is evaluated as a route from posterior sharpness to interval width, but matched controls do not identify a performance gain for it over posterior-independent scaling. A hierarchical Feature-wise Linear Modulation (FiLM) embedding captures asset-specific and sector-level structure without an explicit asset-class prediction objective. Evaluated on 18 US-listed ETFs spanning five asset classes under five calendar-aligned expanding-window walk-forward folds (test years 2021-2025), RC-Mamba achieves a mean Continuous Ranked Probability Score (CRPS) of 0.00532, improving on the Vanilla Temporal Fusion Transformer by 4.7 %, DeepAR by 8.9 %, S-Mamba by 15.2 %, and an HMM-conditioned DeepAR by 18.5 %. All models share robust-MAD preprocessing, a common ceiling of 11,450 optimizer updates with validation-based early stopping, and a 30-business-day origin embargo equal to the maximum forecast horizon, so neither preprocessing nor training budget confounds the architectural comparison. Significance is assessed on 1,110 synchronized forecast origins using a moving-block bootstrap that respects serial and cross-sectional dependence rather than treating overlapping horizons as independent; every comparison remains significant after Holm correction (p Holm = 0.006). RC-Mamba also attains the best Winkler80 score (0.0364) with PICP80 = 0.781 and PINAW80 = 0.024, and recovers three interpretable regimes (Calm, Transition, Stress) that assign every one of the 25 observed April 2025 trading days to the Stress state. Matched single-fold ablations show that removing regime conditioning degrades CRPS by 2.05 % in the most volatile test year, although several component contrasts change sign across folds and are therefore reported as design trade-offs rather than identified causal effects. A one-day-lagged long-only backtest over 1,255 out-of-sample trading days returns 8.89 % annualized against 6.56 % for an equal-weight benchmark, but its annualized alpha of 1.18 % is not statistically significant (p = 0.506) and remains insignificant under 1-10 basis-point costs; the economic evidence is therefore suggestive rather than conclusive. Transfer to non-financial domains is left to future work.