# Lesion Network Mapping of Acute Neurological Deficits and Its Prognostic Value After Ischemic Stroke

## TL;DR

This study found that lesion network mapping, a brain network modeling technique, does not improve predictions of recovery after ischemic stroke compared to traditional clinical factors like age and initial symptom severity.

## Contribution

The study evaluates the clinical utility of lesion network mapping for predicting post-stroke recovery and finds it does not outperform standard clinical variables.

## Key findings

- Lesion network mapping identified distinct symptom-specific brain networks associated with neurological deficits.
- Network damage scores from lesion network mapping did not improve functional outcome prediction compared to age and NIHSS admission score.
- Clinical variables like age and initial NIHSS score were more robust predictors of recovery than lesion network mapping metrics.

## Abstract

•Lesion network mapping (LNM) modeled NIHSS-derived neurological deficits in ischemic stroke.•NIHSS-derived symptom networks were identified for seven clinical categories.•NIHSS-derived network damage scores did not outperform clinical variables for outcomes.•NIHSS admission score and age were the most robust predictors of post-stroke recovery.•These findings suggest limited clinical utility of LNM in terms of outcome prediction of functional recovery after ischemic stroke.

Lesion network mapping (LNM) modeled NIHSS-derived neurological deficits in ischemic stroke.

NIHSS-derived symptom networks were identified for seven clinical categories.

NIHSS-derived network damage scores did not outperform clinical variables for outcomes.

NIHSS admission score and age were the most robust predictors of post-stroke recovery.

These findings suggest limited clinical utility of LNM in terms of outcome prediction of functional recovery after ischemic stroke.

Predicting functional recovery after ischemic stroke is vital for guiding clinical care. This study investigated whether lesion network mapping (LNM), a technique for modeling symptom-specific brain networks, can improve outcome prediction of functional recovery up to one-year post-stroke.

We pooled data from two prospective stroke cohorts (1000Plus and PROSCIS-B; N = 565). Seven NIHSS-derived symptom networks were generated using LNM based on NIHSS sub-scores on admission (i.e., consciousness, language, motor, sensory, vision, neglect and ataxia). Lesion masks derived from MRI (within 7 days) were intersected with each symptom network to calculate individual network damage scores. Functional outcome was defined by the modified Rankin Scale (mRS) at 3 months (1000Plus) or 12 months (PROSCIS-B). Ordinal logistic regression models were performed to evaluate additional predictive value of LNM: Model 1 included age, lesion volume, and presence of selected neurological deficits; Model 2 included age, lesion volume, and NIHSS-derived network damage scores. Models were compared using pseudo-R2 and AIC.

Patients had a mean age of 68 years and a median NIHSS of 3 (IQR 1–5). LNM revealed distinct, symptom-specific networks, with corresponding damage scores that were higher in patients exhibiting the respective deficits compared to those without. However, inclusion of these scores did not enhance the predictive accuracy of functional outcomes beyond that achieved with clinical variables alone (Model 1 vs. Model 2: pseudo-R2: 0.0468 vs. 0.0159; AIC:1730.598 vs. 1769.222).

LNM-derived scores reflected symptom topography but did not enhance prediction of functional recovery. While promising as a mechanistic tool, the clinical utility of LNM-based damage metrics for prognostication remains limited and requires further validation.