NeuroSurg Predict Outcome risk calculators for neurosurgery. Research use only. All calculators
Research decision support

Preoperative risk estimates for anterior clinoidal meningioma surgery

ACM Surgical Risk Calculator estimates the probability of two postoperative outcomes, a systemic or medical complication and a new or worsened motor deficit, from 11 preoperative clinical and radiological variables. The models were developed on multicentre retrospective data and evaluated on an independent external cohort.

2
Predicted outcomes
176
Patients in development
54
Patients in external validation
11
Pre-operative inputs
How it works

Developed in two centres, validated in two others

The models were developed on patients treated in Bologna and Cesena and evaluated on an independent external validation cohort from Liverpool and Nanjing. The predictions are probabilistic estimates derived from historical data, reflecting patterns observed in similar patients.

1

Structured input

You enter 11 preoperative variables through one guided form: patient baseline and symptoms, and radiological characteristics.

2

Published model

Each outcome uses a ridge-penalised logistic regression on eight of those variables, with its published coefficients served unchanged.

3

Probability & band

The model returns an individual probability, placed into one of four bands defined a priori relative to that outcome's event rate in the development cohort.

4

Known limits

The estimates do not account for every factor that may influence outcome, including intraoperative events, surgeon judgement or institution-specific practice. Actual outcomes may differ from the predicted risk.

For research and investigational use only. Not a medical device. Estimates complement, and never replace, clinical judgement, individualised patient evaluation, or the discussion between the treating physician and the patient. Nothing you enter is stored: values are processed in memory and discarded. Our hosting provider sees your IP address briefly for routing and abuse protection; we never record it.
What the tool predicts

Two postoperative outcomes

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

Interactive tool

Risk Calculator

Describe the patient below and calculate the two risk estimates. All fields are pre-filled with a default; change only what applies to this patient.

For research and investigational use only. Not a medical device. Estimates complement, and never replace, clinical judgement. Nothing you enter is stored: values are processed in memory and discarded. Our hosting provider sees your IP address briefly for routing and abuse protection; we never record it. Complete every field before calculating.

2 outcomes are computed together, each with its pinned model.

About

Cohort, validation & performance

ACM Surgical Risk Calculator was developed on a retrospective cohort of patients operated for anterior clinoidal meningioma in Bologna and Cesena, and evaluated on an external cohort from Liverpool and Nanjing.

176
Development cohort
2
Development centres
54
External validation cohort
2
Validation centres

Authors & contributions

To be added on publication.

Validation design

Internal performance was estimated by cross-validation within the development cohort. External performance was measured on the independent Liverpool and Nanjing cohort, on which the published operating points were defined. The coefficients are read at runtime by this calculator rather than refitted.

Per-outcome performance

Outcome Model External AUROC (95% CI) Internal CV AUC (95% CI) Brier Calibration slope Calibration intercept

External AUROC, Brier score and calibration are measured on the Liverpool and Nanjing cohort; the internal AUC by cross-validation on the development cohort.

Risk bands

Risk categories were defined a priori from the predicted probability relative to each model's observed event rate in the development cohort: 22.2% for a systemic or medical complication and 11.4% for a new or worsened motor deficit. Thresholds were selected to preserve clinical interpretability and to reflect meaningful elevation above each outcome's baseline rate.

Contact & citation

Contact: to be added on publication.
Citation: to be added on publication.