Skull Base Meningioma (SBM)

Predicted Outcomes

Each estimate is produced by a model trained and validated specifically for that outcome.

Neurologic Worsening

Probability of a new or worsened neurological status after surgery.

Any Postoperative Complication

Probability of any complication occurring in the postoperative period.

Performance Status Deterioration

Probability of functional status (KPS) deterioration at hospital discharge.

Severe Complication (Ibañez ≥ 3)

Probability of life-threatening adverse events requiring treatment in an intensive care unit (ICU) or death as a result of complications.

Reference

30-Day Mortality

Probability of death within 30 days of surgery.

Methodology

Predictions draw on a multicentre registry of operated skull-base meningiomas. For every outcome, several model families were trained and compared, and the single best-performing model was frozen for use in this tool.

Structured Input

You enter 41 pre-operative variables through one guided form: demographics, comorbidity, functional status, clinical presentation and radiological characteristics.

Frozen Best Model

Each outcome uses the model that performed best under temporal validation. The operating threshold is the one frozen during that validation.

Probability & Band

The model returns an individual probability, placed into an outcome-specific Low / Moderate / High band shown alongside the cohort base rate.

What the number means

How often this outcome occurred in patients with a similar profile, among the cases the model was built on.

Model & Cohort

Skull Base Meningioma (SBM) was developed on a multicentre registry of operated skull-base meningiomas, using a temporal validation design so that models are evaluated on patients treated after those they were trained on.

743

Patients

Tertiary centres

Countries

2010–2025

Study period

Validation Design

Models were trained and internally compared under a temporal split: the earlier patients form the training set and the most recent patients form a held-out temporal test set. Operating thresholds were frozen on a separate validation split before the test set was seen, and are read at runtime by this calculator rather than tuned interactively.

Per-Outcome Performance

Outcome	Model	AUROC	Threshold
Neurologic Worsening	svc@391015d	0.805	0.114
Any Postoperative Complication	lr@c02ab7c	0.755	0.173
Performance Status Deterioration	rf@5e04b27	0.752	0.139
Severe Complication (Ibañez ≥ 3)	lr@2651cac	0.663	0.297
30-Day Mortality	rf@c3a207a	0.898	0.124

30-Day Mortality and Severe Complication (Ibañez ≥ 3) were evaluated on very few test events, so their probabilities are unreliable and are presented with a caveat; the associated factors are the more defensible content on those cards.

Risk Bands

Three bands per outcome. The lower boundary is that outcome's frozen operating threshold; the upper is the 90th percentile of predicted probability in the temporal test set. By construction, High is the top ~10% of cases and Low is the below-threshold group; most cases land in Moderate, which is the correct behaviour for these models.

Outcome	Low	Moderate	High
Neurologic Worsening	< 0.114	0.114 – 0.515	≥ 0.515
Any Postoperative Complication	< 0.173	0.173 – 0.826	≥ 0.826
Performance Status Deterioration	< 0.139	0.139 – 0.366	≥ 0.366
Severe Complication (Ibañez ≥ 3)	< 0.297	0.297 – 0.658	≥ 0.658
30-Day Mortality	< 0.124	0.124 – 0.303	≥ 0.303

Ethics & Governance

Ethics approval: CE-AVEC, Bologna (protocol 19029). For research and educational use; not a medical device and not for clinical decision-making.

Contact & Citation

Contact: the Skull Base Meningioma (SBM) research team (details to be added on publication).

Citation: full citation will be provided once the study is published.

Version

v0.1.5 · models@bdf7266

Risk Assessment Results

Help us improve