Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0600
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-31T06:08:37.511660Z
status: published
lens: trace
sector: health
headline: Development and external validation of a machine learning model for predicting postoperative hydrocephalus in 1,073 posterior fossa tumor patients
dek: Postoperative hydrocephalus is a common complication following posterior fossa tumor resection, affecting 7-40% of patients. Although preoperative cerebrospinal fluid (CSF) diversion may be required in selected patients with hydrocephalus, decisions remain individualized in routine neurosurgical practice. We therefore developed and externally validated a model to provide supplementary preoperative risk stratification using routinely available variables. We retrospectively analyzed 1,073 patients following resect…
gain_title: A preoperative model using Evans index, tumor-fourth ventricle relationship, and preoperative CSF diversion status achieved good external discrimination for postoperative hydrocephalus after posterior fossa tumor resection.
problem_title: Calibration assessment showed dataset shift, so absolute predicted probabilities should be interpreted cautiously and the model should not drive CSF diversion decisions alone without prospective validation.
trace_subject: preoperative prediction of postoperative hydrocephalus after posterior fossa tumor resection using a three-variable machine learning model
gain_reading: A preoperative model using Evans index, tumor-fourth ventricle relationship, and preoperative CSF diversion status achieved good external discrimination for postoperative hydrocephalus after posterior fossa tumor resection.
gain_evidence: showed good external discrimination, with an area under the receiver operating characteristic curve of 0.877 | A concise three-variable preoperative model showed good external discrimination for clinically relevant postoperative hydrocephalus after posterior fossa tumor resection
problem_reading: Calibration assessment showed dataset shift, so absolute predicted probabilities should be interpreted cautiously and the model should not drive CSF diversion decisions alone without prospective validation.
problem_evidence: Calibration assessment suggested dataset shift between the development and external validation cohorts | absolute predicted probabilities should be interpreted cautiously in populations with different baseline risks | should not be used as a stand-alone indication for cerebrospinal fluid diversion
quick_read: Investigators developed and externally validated a machine learning model to stratify risk of postoperative hydrocephalus after posterior fossa tumor resection using data from 1,073 patients treated at five tertiary centers from 2013 to 2024. After screening 30 variables, they built a three-variable preoperative model using Evans index, tumor-fourth ventricle relationship, and preoperative CSF diversion status, with SVM showing AUC 0.877 in the external cohort.

Good external discrimination suggests the tool could help clinicians discuss risk and plan surveillance, but calibration analysis revealed dataset shift, meaning predicted probabilities may not transfer directly to populations with different baseline risks. The authors caution against using it as a sole indication for preoperative CSF diversion and call for prospective validation and recalibration.
limitation: Calibration assessment indicated dataset shift between development and external validation cohorts, so absolute predicted probabilities are uncertain and prospective validation with local recalibration is needed before routine use.
tag: Automated dual reading
key_points: Retrospective analysis of 1,073 patients from five tertiary centers between 2013 and 2024, split into development cohort n=854 and external validation cohort n=219. | Final clinically implementable model restricted to three preoperative variables: Evans index, tumor-fourth ventricle relationship, and preoperative cerebrospinal fluid diversion status. | Support vector machine evaluated among seven ML algorithms; logistic regression achieved comparable discrimination in external validation. | Authors state model may support preoperative risk communication and postoperative surveillance planning but should not be used as stand-alone indication for CSF diversion.
rundown: Researchers screened 30 perioperative variables and selected a clinically implementable model restricted to variables available before tumor resection, ranking feature importance using Shapley additive explanations (SHAP).

In the external validation cohort of 219 patients, the support vector machine model reported AUC 0.877, accuracy 81.3%, sensitivity 80.8%, and specificity 81.7%, with performance measured via ROC, precision-recall curves, and decision curve analysis.

The authors note the model may support preoperative risk communication and postoperative surveillance planning, while emphasizing need for prospective validation and local recalibration before routine clinical implementation.
sources:
- peer_reviewed | Neurosurgical Review | https://doi.org/10.1007/s10143-026-04403-w | 2026-07-30
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

506a89fcc0d85d2cc3e652beb0f613de5f567a32396f88436c9d34b6e17c6070

previous

0000000000000000000000000000000000000000000000000000000000000000