Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage
Open Access
- 6 February 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Translational Stroke Research
- Vol. 12 (6), 958-967
- https://doi.org/10.1007/s12975-021-00891-8
Abstract
We hypothesized that imaging-only-based machine learning algorithms can analyze non-enhanced CT scans of patients with acute intracerebral hemorrhage (ICH). This retrospective multicenter cohort study analyzed 520 non-enhanced CT scans and clinical data of patients with acute spontaneous ICH. Clinical outcome at hospital discharge was dichotomized into good outcome and poor outcome using different modified Rankin Scale (mRS) cut-off values. Predictive performance of a random forest machine learning approach based on filter- and texture-derived high-end image features was evaluated for differentiation of functional outcome at mRS 2, 3, and 4. Prediction of survival (mRS ≤ 5) was compared to results of the ICH Score. All models were tuned, validated, and tested in a nested 5-fold cross-validation approach. Receiver-operating-characteristic area under the curve (ROC AUC) of the machine learning classifier using image features only was 0.80 (95% CI [0.77; 0.82]) for predicting mRS ≤ 2, 0.80 (95% CI [0.78; 0.81]) for mRS ≤ 3, and 0.79 (95% CI [0.77; 0.80]) for mRS ≤ 4. Trained on survival prediction (mRS ≤ 5), the classifier reached an AUC of 0.80 (95% CI [0.78; 0.82]) which was equivalent to results of the ICH Score. If combined, the integrated model showed a significantly higher AUC of 0.84 (95% CI [0.83; 0.86], P value P value <0.05). Machine learning–based evaluation of quantitative high-end image features provided the same discriminatory power in predicting functional outcome as multidimensional clinical scoring systems. The integration of conventional scores and image features had synergistic effects with a statistically significant increase in AUC.Keywords
Funding Information
- Projekt DEAL
This publication has 39 references indexed in Scilit:
- Robust Radiomics Feature Quantification Using Semiautomatic Volumetric SegmentationPLOS ONE, 2014
- Intracerebral hemorrhage: toward physiological imaging of hemorrhage risk in acute and chronic bleedingFrontiers in Neurology, 2012
- Semi‐automatic volumetric assessment of perihemorrhagic edema with computed tomographyEuropean Journal of Neurology, 2011
- pROC: an open-source package for R and S+ to analyze and compare ROC curvesBMC Bioinformatics, 2011
- The Path to Personalized MedicineThe New England Journal of Medicine, 2010
- Early care limitations independently predict mortality after intracerebral hemorrhageNeurology, 2007
- The ICH ScoreStroke, 2001
- Volume of intracerebral hemorrhage. A powerful and easy-to-use predictor of 30-day mortality.Stroke, 1993
- Primary intracerebral hemorrhageNeurology, 1984
- Comparison of the predicted and observed secondary structure of T4 phage lysozymeBiochimica et Biophysica Acta (BBA) - Protein Structure, 1975