Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage
Standard
Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage. / Nawabi, Jawed; Kniep, Helge; Elsayed, Sarah; Friedrich, Constanze; Sporns, Peter; Rusche, Thilo; Böhmer, Maik; Morotti, Andrea; Schlunk, Frieder; Dührsen, Lasse; Broocks, Gabriel; Schön, Gerhard; Quandt, Fanny; Thomalla, Götz; Fiehler, Jens; Hanning, Uta.
In: TRANSL STROKE RES, Vol. 12, No. 6, 12.2021, p. 958-967.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage
AU - Nawabi, Jawed
AU - Kniep, Helge
AU - Elsayed, Sarah
AU - Friedrich, Constanze
AU - Sporns, Peter
AU - Rusche, Thilo
AU - Böhmer, Maik
AU - Morotti, Andrea
AU - Schlunk, Frieder
AU - Dührsen, Lasse
AU - Broocks, Gabriel
AU - Schön, Gerhard
AU - Quandt, Fanny
AU - Thomalla, Götz
AU - Fiehler, Jens
AU - Hanning, Uta
PY - 2021/12
Y1 - 2021/12
N2 - 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 <0.05). Accordingly, sensitivities were significantly higher at Youden Index maximum cut-offs (77% vs. 74% sensitivity at 76% specificity, 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.
AB - 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 <0.05). Accordingly, sensitivities were significantly higher at Youden Index maximum cut-offs (77% vs. 74% sensitivity at 76% specificity, 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.
U2 - 10.1007/s12975-021-00891-8
DO - 10.1007/s12975-021-00891-8
M3 - SCORING: Journal article
C2 - 33547592
VL - 12
SP - 958
EP - 967
JO - TRANSL STROKE RES
JF - TRANSL STROKE RES
SN - 1868-4483
IS - 6
ER -