Dataset Information

Location-Specific Radiomics Score: Novel Imaging Marker for Predicting Poor Outcome of Deep and Lobar Spontaneous Intracerebral Hemorrhage.

ABSTRACT: Objective: To derive and validate a location-specific radiomics score (Rad-score) based on noncontrast computed tomography for predicting poor deep and lobar spontaneous intracerebral hemorrhage (SICH) outcome. Methods: In total, 494 SICH patients from multiple centers were retrospectively reviewed. Poor outcome was considered mRS 3-6 at 6 months. The Rad-score was derived using optimal radiomics features. The optimal location-specific Rad-score cut-offs for poor deep and lobar SICH outcomes were identified using receiver operating characteristic curve analysis. Univariable and multivariable analyses were used to determine independent poor outcome predictors. The combined models for deep and lobar SICH were constructed using independent predictors of poor outcomes, including dichotomized Rad-score in the derivation cohort, which was validated in the validation cohort. Results: Of 494 SICH patients, 392 (79%) had deep SICH, and 373 (76%) had poor outcomes. The Glasgow Coma Scale score, haematoma enlargement, haematoma location, haematoma volume and Rad-score were independent predictors of poor outcomes (all P < 0.05). Cut-offs of Rad-score, 82.90 (AUC = 0.794) in deep SICH and 80.77 (AUC = 0.823) in lobar SICH, were identified for predicting poor outcomes. For deep SICH, the AUCs of the combined model were 0.856 and 0.831 in the derivation and validation cohorts, respectively. For lobar SICH, the combined model AUCs were 0.866 and 0.843 in the derivation and validation cohorts, respectively. Conclusion: Location-specific Rad-scores and combined models can identify subjects at high risk of poor deep and lobar SICH outcomes, which could improve clinical trial design by screening target patients.

SUBMITTER: Zhou Z

PROVIDER: S-EPMC8656420 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeWe develop a new risk score to predict patients with stroke-associated pneumonia (SAP) who have an acute intracranial hemorrhage (ICH).MethodWe applied logistic regression to develop a new risk score called ICH-LR2S2. It was derived from examining a dataset of 70,540 ICH patients between 2015 and 2018 from the Chinese Stroke Center Alliance (CSCA). During the training of ICH-LR2S2, patients were randomly divided into two groups - 80% for the training set and 20% for model validation. A prospective test set was developed using 12,523 patients recruited in 2019. To further verify its effectiveness, we tested ICH-LR2S2 on an external dataset of 24,860 patients from the China National Stroke Registration Management System II (CNSR II). The performance of ICH-LR2S2 was measured by the area under the receiver operating characteristic curve (AUROC).ResultsThe incidence of SAP in the dataset was 25.52%. A 24-point ICH-LR2S2 was developed from independent predictors, including age, modified Rankin Scale, fasting blood glucose, National Institutes of Health Stroke Scale admission score, Glasgow Coma Scale score, C-reactive protein, dysphagia, Chronic Obstructive Pulmonary Disease, and current smoking. The results showed that ICH-LR2S2 achieved an AUC = 0.749 [95% CI 0.739-0.759], which outperforms the best baseline ICH-APS (AUC = 0.704) [95% CI 0.694-0.714]. Compared with the previous ICH risk scores, ICH-LR2S2 incorporates fasting blood glucose and C-reactive protein, improving its discriminative ability. Machine learning methods such as XGboost (AUC = 0.772) [95% CI 0.762-0.782] can further improve our prediction performance. It also performed well when further validated by the external independent cohort of patients (n = 24,860), ICH-LR2S2 AUC = 0.784 [95% CI 0.774-0.794].ConclusionICH-LR2S2 accurately distinguishes SAP patients based on easily available clinical features. It can help identify high-risk patients in the early stages of diseases.

Project description:Background and purposeSeizures commonly occur in patients with intracerebral hemorrhage (ICH). Anticonvulsants are commonly used for preventing seizures in patients with ICH. Thus, patients with ICH at high risk of seizures must be identified. The study aims to elucidate whether double the score of cortex involvement in ICH patients can increase accuracy of CAVE score for predicting late seizures.MethodThis retrospective analysis of the medical records of surviving patients admitted between June 1, 2013, and December 31, 2019. Validated the CAVE score and modified it (CAVE2). The main outcome of patients with ICH was seizures. The first seizures occurring within 7 days after a stroke were defined as early seizures. Seizures occurring after 1 week of stroke onset, including patients who had experienced early seizures or patients who had not, were defined as late seizures. CAVE and CAVE2 scores were validated using the cohort. The accuracy and discrimination of those two scores were accessed by the area under the operating characteristic curve. Akaike information criterion, integrated discrimination improvement, and continuous net reclassification improvement were used to assess the performance of the CAVE and CAVE2 scores.ResultsIn the cohort showed that late seizures occurred in 12.7% (52/408) of patients with ICH. Male sex, age > 65 years, cortex involvement, and early seizures were associated with the occurrence of late seizures, with odds ratios of 2.09, 2.04, 4.12, and 3.78, respectively. The risk rate of late seizures was 6.66% (17/255), 14.8% (17/115), and 47.4% (18/38) for CAVE scores ≤ 1, 2, and ≥ 3, and 4.6% (12/258), 18.3% (13/71), and 54.4 (20/37) for CAVE2 scores ≤ 1, 2, and ≥ 3 respectively. The C-statistics for the CAVE and CAVE2 scores were 0.73 and 0.74 respectively.ConclusionThe CAVE score can identify patients with ICH and high risk for late seizures. The CAVE can be modified by changing the score of cortex involvement to 2 points to improve accuracy in predicting late seizures in patients with ICH.

Project description:ObjectiveHematoma enlargement (HE) is associated with clinical outcomes after supratentorial intracerebral hemorrhage (ICH). This study evaluates whether HE characteristics and association with functional outcome differ in deep versus lobar ICH.MethodsPooled analysis of individual patient data between January 2006 and December 2015 from a German-wide cohort study (RETRACE, I + II) investigating ICH related to oral anticoagulants (OAC) at 22 participating centers, and from one single-center registry (UKER-ICH) investigating non-OAC-ICH patients. Altogether, 1954 supratentorial ICH patients were eligible for outcome analyses, which were separately conducted or controlled for OAC, that is, vitamin-K-antagonists (VKA, n = 1186) and non-vitamin-K-antagonist-oral-anticoagulants (NOAC, n = 107). Confounding was addressed using propensity score matching, cox regression modeling and multivariate modeling. Main outcomes were occurrence, extent, and timing of HE (>33%/>6 mL) and its association with 3-month functional outcome.ResultsOccurrence of HE was not different after deep versus lobar ICH in patients with non-OAC-ICH (39/356 [11.0%] vs. 36/305 [11.8%], P = 0.73), VKA-ICH (249/681 [36.6%] vs. 183/505 [36.2%], P = 0.91), and NOAC-ICH (21/69 [30.4%] vs. 12/38 [31.6%], P = 0.90). HE extent did not differ after non-OAC-ICH (deep:+59% [40-122] vs. lobar:+74% [37-124], P = 0.65), but both patients with VKA-ICH and NOAC-ICH showed greater HE extent after deep ICH [VKA-ICH, deep: +94% [54-199] vs. lobar: +56% [35-116], P < 0.001; NOAC-ICH, deep: +74% [56-123] vs. lobar: +40% [21-49], P = 0.001). Deep compared to lobar ICH patients had higher HE hazard during first 13.5 h after onset (Hazard ratio [HR]: 1.85 [1.03-3.31], P = 0.04), followed by lower hazard (13.5-26.5 h, HR: 0.46 [0.23-0.89], P = 0.02), and equal hazard thereafter (HR: 0.96 [0.56-1.65], P = 0.89). Odds ratio for unfavorable outcome was higher after HE in deep (4.31 [2.71-6.86], P < 0.001) versus lobar ICH (2.82 [1.71-4.66], P < 0.001), and only significant after small-medium (1st volume-quarter, deep: 3.09 [1.52-6.29], P < 0.01; lobar: 3.86 [1.35-11.04], P = 0.01) as opposed to large-sized ICH (4th volume-quarter, deep: 1.09 [0.13-9.20], P = 0.94; lobar: 2.24 [0.72-7.04], P = 0.17).InterpretationHE occurrence does not differ among deep and lobar ICH. However, compared to lobar ICH, HE after deep ICH is of greater extent in OAC-ICH, occurs earlier and may be of greater clinical relevance. Overall, clinical significance is more apparent after small-medium compared to large-sized bleedings.

Dataset Information

Location-Specific Radiomics Score: Novel Imaging Marker for Predicting Poor Outcome of Deep and Lobar Spontaneous Intracerebral Hemorrhage.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets