Materiały źródłowe

• #1 Clinical and Radiographic Predictors of Intracerebral Hemorrhage Outcome

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5881146/

  Intracerebral hemorrhage (ICH) represents 10-15% of all stroke cases in the US annually. Fewer than 40% of these patients ever reach long-term functional independence, and mortality rate is roughly 40% at 1 month. […] Due to the high morbidity and mortality rates after ICH, early detection of high-risk patients would be beneficial in directing the management course and goals of care. This review aims to discuss relevant clinical and radiographic characteristics that can serve as predictors of poor prognosis and examine their efficacy in predicting patient outcomes after ICH. […] In this review, we examined clinical and radiographic characteristics that have been found to be significantly associated to a varying degree with poor outcome. Clinical and radiographic predictors of poor patient outcome are invaluable when it comes to identifying high-risk patients and triaging accordingly as well as guiding decision-making.

• #1 Clinical and Radiographic Predictors of Intracerebral Hemorrhage Outcome

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5881146/

  Prognosis depends on the severity of the clinical presentation, speed of diagnosis, and time of intervention. […] The progression from this stage, mainly hematoma expansion and edema, determines patient outcomes. […] Due to the high morbidity and mortality rates after ICH, early detection of high-risk patients would be beneficial in directing the management course and goals of care. […] Given the profound morbidity and mortality associated with ICH, these clinical and radiographic predictors of poor patient outcome are of important prognostic value. Currently, studies show that 40% of patients regain functional independence after ICH, and mortality rate is 40% at 1 month and 54% at 1 year. Indication of patient outcome, based on presentation upon admission, holds value when triaging patients and making care decision.

• #1 Uncertainty-aware deep-learning model for prediction of supratentorial hematoma expansion from admission non-contrast head computed tomography scan | npj Digital Medicine

  https://www.nature.com/articles/s41746-024-01007-w

  Hematoma expansion (HE) is a modifiable risk factor and a potential treatment target in patients with intracerebral hemorrhage (ICH). […] Every 1mL increase in hematoma volume is associated with a 5% higher risk of death or long-term functional dependency. […] As a modifiable predictor of outcome, HE is a potential target for anti-expansion interventions or hemostatic therapies. […] Identification of patients at risk of HE for targeted therapy can increase the chances of treatment benefit from anti-expansion interventions. […] Among patients with high-confidence prediction of HE6mL, the odds ratios of poor outcome and death were 2.92 (p=0.017), and 6.47 (p=0.001), respectively. […] Among patients with high-confidence prediction of HE3mL, the odds ratios of poor outcome and death were 1.69 (p=0.18), and 5.70 (p=0.001), respectively.

• #1 Prognostication after intracerebral hemorrhage: a review | Neurological Research and Practice | Full Text

  https://neurolrespract.biomedcentral.com/articles/10.1186/s42466-021-00120-5

  Approximately half of patients with spontaneous intracerebral hemorrhage (ICH) die within 1 year. Prognostication in this context is of great importance, to guide goals of care discussions, clinical decision-making, and risk stratification. […] Presently available prognostic scores for ICH do not fulfill essential quality standards. Novel prognostic scores need to be developed to inform the design of research studies and improve clinical care in patients with ICH. […] The discrepancy between what prognostic scores offer and what is needed in clinical practice has led physicians to increasingly neglect these scores. […] The max-ICH score was the first ICH prediction score in which the WOC bias was addressed at the level of score creation. […] Despite prediction score fatigue among clinicians, prognostication in patients with ICH remains crucially important. It may improve clinical care by providing information on the most probable outcome, which can then be aligned with what is medically feasible and what the patient wants.

• #1 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://pmc.ncbi.nlm.nih.gov/articles/PMC9961203/

  This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. […] The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with sICH 90 days after surgery. […] The best model predicted an AUC of 0.85 (95%CI, 0.750.94) on the internal test set and 0.81 (95%CI, 0.640.99) and 0.83 (95%CI, 0.680.97) on the two external test sets, respectively. […] The combination of lasso regression feature selection and logistic regression model based on clinical features + radiomics features had the best performance (AUC: 0.87). […] The Shap plot showed that second-order features had a higher contribution than shape features and first-order features in predicting prognosis.

• #1 Using 30-day modified rankin scale score to predict 90-day score in patients with intracranial hemorrhage: Derivation and validation of prediction model | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0303757

  Whether 30-day modified Rankin Scale (mRS) scores can predict 90-day scores is unclear. This study derived and validated a model to predict ordinal 90-day mRS score in an intracerebral hemorrhage (ICH) population using 30-day mRS values and routinely available baseline variables. […] This tool allows practitioners and researchers to utilize clinically available information along with the mRS score 30 days after ICH to reliably predict the mRS score at 90 days. […] In patients with acute ICH, we developed and validated a model to predict the 90-day mRS score using 30-day scores in addition to other routinely available variables. The model was shown to reliably predict mRS score at 90 days on an ordinal and as an EQ-5D weighted (utility weighted) scale. Moreover, it could predict functional independence at 90 days. […] The 30-day mRS score combined with baseline characteristics can reliably predict functional independence and the EQ-5Dweighted 90-day mRS in individuals with ICH.

• #1

  https://link.springer.com/article/10.1007/s00701-022-05216-8

  None of the examined models showed good predictive performance for outcomes after CSDH treatment in our dataset. […] This study confirms the difficulty in predicting outcomes after CSDH and emphasizes the heterogeneity of CSDH patients. […] The importance of developing high-quality models by using unified predictors and relevant outcome measures and appropriate modeling strategies is warranted. […] The prognostic model of Alford predicted that 15% of patients would die within 30 days, whereas the observed proportion in our data was 4%. Thus, it overestimated the proportion of patients dying within 30 days by 11 percentage points. […] The performance of Andersens postoperative model (3-month hematoma recurrence) (A) was assessed with great uncertainty due to a large amount of missing data in postoperative variables.

• #2 Clinical and Radiographic Predictors of Intracerebral Hemorrhage Outcome

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5881146/

  Prognosis depends on the severity of the clinical presentation, speed of diagnosis, and time of intervention. […] The progression from this stage, mainly hematoma expansion and edema, determines patient outcomes. […] Due to the high morbidity and mortality rates after ICH, early detection of high-risk patients would be beneficial in directing the management course and goals of care. […] Given the profound morbidity and mortality associated with ICH, these clinical and radiographic predictors of poor patient outcome are of important prognostic value. Currently, studies show that 40% of patients regain functional independence after ICH, and mortality rate is 40% at 1 month and 54% at 1 year. Indication of patient outcome, based on presentation upon admission, holds value when triaging patients and making care decision.

• #2 Predictors of hematoma expansion predictors after intracerebral hemorrhage | Oncotarget

  https://www.oncotarget.com/article/19366/text/

  Despite years of effort, intracerebral hemorrhage (ICH) remains the most devastating form of stroke with more than 40% 30-day mortality worldwide. Hematoma expansion (HE), which occurs in one third of ICH patients, is strongly predictive of worse prognosis and potentially preventable if high-risk patients were identified in the early phase of ICH. […] Hematoma expansion (HE), which occurs in approximately 33% ICH patients, is identified as one important independent predictor of early neurological deterioration and poor long-term clinical outcomes. […] Therefore, it is important to find those HE predictors to stratify patients and tailor intensive therapies timely and effectively for high-risk patient. […] The definition of HE varied in different literatures with a 40% relative volume increase or 12.6mL absolute volume increase in hematoma size from baseline CT to follow-up CT in one, a 33% relative increase in others, or even a 50% relative increase and 2mL absolute increase in another.

• #2 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://pmc.ncbi.nlm.nih.gov/articles/PMC9961203/

  This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. […] The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with sICH 90 days after surgery. […] The best model predicted an AUC of 0.85 (95%CI, 0.750.94) on the internal test set and 0.81 (95%CI, 0.640.99) and 0.83 (95%CI, 0.680.97) on the two external test sets, respectively. […] The combination of lasso regression feature selection and logistic regression model based on clinical features + radiomics features had the best performance (AUC: 0.87). […] The Shap plot showed that second-order features had a higher contribution than shape features and first-order features in predicting prognosis.

• #2

  https://link.springer.com/article/10.1007/s00701-022-05216-8

  None of the examined models showed good predictive performance for outcomes after CSDH treatment in our dataset. […] This study confirms the difficulty in predicting outcomes after CSDH and emphasizes the heterogeneity of CSDH patients. […] The importance of developing high-quality models by using unified predictors and relevant outcome measures and appropriate modeling strategies is warranted. […] The prognostic model of Alford predicted that 15% of patients would die within 30 days, whereas the observed proportion in our data was 4%. Thus, it overestimated the proportion of patients dying within 30 days by 11 percentage points. […] The performance of Andersens postoperative model (3-month hematoma recurrence) (A) was assessed with great uncertainty due to a large amount of missing data in postoperative variables.

• #3 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://pmc.ncbi.nlm.nih.gov/articles/PMC9961203/

  The top four features of contribution were age, deep ICH, MLS, and GCS on admission, which were all clinical characteristics and correlated with poor prognosis of sICH. […] The AUC of the model fused with ICH score was 0.84. […] By combining radiomics features and clinical features, we established a prognosis prediction model for patients with sICH 90 days after surgery.

• #3 Uncertainty-aware deep-learning model for prediction of supratentorial hematoma expansion from admission non-contrast head computed tomography scan | npj Digital Medicine

  https://www.nature.com/articles/s41746-024-01007-w

  Hematoma expansion (HE) is a modifiable risk factor and a potential treatment target in patients with intracerebral hemorrhage (ICH). […] Every 1mL increase in hematoma volume is associated with a 5% higher risk of death or long-term functional dependency. […] As a modifiable predictor of outcome, HE is a potential target for anti-expansion interventions or hemostatic therapies. […] Identification of patients at risk of HE for targeted therapy can increase the chances of treatment benefit from anti-expansion interventions. […] Among patients with high-confidence prediction of HE6mL, the odds ratios of poor outcome and death were 2.92 (p=0.017), and 6.47 (p=0.001), respectively. […] Among patients with high-confidence prediction of HE3mL, the odds ratios of poor outcome and death were 1.69 (p=0.18), and 5.70 (p=0.001), respectively.

• #3 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://www.mdpi.com/2077-0383/12/4/1580

  This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. […] The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with spontaneous supratentorial intracerebral hemorrhage 90 days after surgery. […] The best model predicted an AUC of 0.85 (95%CI, 0.75–0.94) on the internal test set and 0.81 (95%CI, 0.64–0.99) and 0.83 (95%CI, 0.68–0.97) on the two external test sets, respectively. […] Prognostic prediction for patients with sICH after surgery is helpful for clinicians to classify sICH patients with poor postoperative prognosis early, optimize treatment, achieve individualized precise treatment, and improve the overall prognosis of sICH patients.

• #3

  https://link.springer.com/article/10.1007/s00701-022-05216-8

  The results of complete case analyses were consistent with imputation analyses. […] The study confirms the complexity of predicting outcomes in patients with CSDH and the need for the collection of standard baseline variables and a core outcome set and for improved modeling strategies, which will improve current prognostic models.

• #4 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://www.mdpi.com/2077-0383/12/4/1580

  By combining radiomics features and clinical features, we established a prognosis prediction model for patients with sICH 90 days after surgery. […] The Shap plot showed that second-order features had a higher contribution than shape features and first-order features in predicting prognosis. […] In the prediction model of this study, the top four features of contribution were age, deep ICH, MLS, and GCS on admission, which were all clinical characteristics and correlated with poor prognosis of sICH.

• #4 Uncertainty-aware deep-learning model for prediction of supratentorial hematoma expansion from admission non-contrast head computed tomography scan | npj Digital Medicine

  https://www.nature.com/articles/s41746-024-01007-w

  In our cohort, both HE6mL and HE3mL were associated with higher odds of poor outcomes and death during 3-month follow-up. […] Notably, those identified at risk of HE by the deep-learning model also had higher odds of poor outcome and death, highlighting the clinical relevance of models predictions. […] Overall, deep-learning models were more sensitive in the identification of patients at risk of HE, with a net improvement in risk assessment compared to visual markers.

• #4 Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage | Journal of Translational Medicine | Full Text

  https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-024-04896-3

  Spontaneous intracerebral hemorrhage (sICH) is associated with significant mortality and morbidity. Predicting the prognosis of patients with sICH remains an important issue, which significantly affects treatment decisions. Utilizing readily available clinical parameters to anticipate the unfavorable prognosis of sICH patients holds notable clinical significance. […] We constructed a prediction model based on the results of the RF model incorporating five clinically accessible predictors with reliable predictive efficacy for the short-term prognosis of sICH patients. Meanwhile, the performance of the external validation set was also more stable, which can be used for accurate prediction of short-term prognosis of sICH patients. […] The RF model predicted the short-term prognosis in sICH with an AUC of 0.916, indicating a high predictive performance. Enhanced performance was also observed upon its application to the prediction of an external validation dataset.

• #4 Prognostication after intracerebral hemorrhage: a review | Neurological Research and Practice | Full Text

  https://neurolrespract.biomedcentral.com/articles/10.1186/s42466-021-00120-5

  Approximately half of patients with spontaneous intracerebral hemorrhage (ICH) die within 1 year. Prognostication in this context is of great importance, to guide goals of care discussions, clinical decision-making, and risk stratification. […] Presently available prognostic scores for ICH do not fulfill essential quality standards. Novel prognostic scores need to be developed to inform the design of research studies and improve clinical care in patients with ICH. […] The discrepancy between what prognostic scores offer and what is needed in clinical practice has led physicians to increasingly neglect these scores. […] The max-ICH score was the first ICH prediction score in which the WOC bias was addressed at the level of score creation. […] Despite prediction score fatigue among clinicians, prognostication in patients with ICH remains crucially important. It may improve clinical care by providing information on the most probable outcome, which can then be aligned with what is medically feasible and what the patient wants.

• #5 Uncertainty-aware deep-learning model for prediction of supratentorial hematoma expansion from admission non-contrast head computed tomography scan | npj Digital Medicine

  https://www.nature.com/articles/s41746-024-01007-w

  Hematoma expansion (HE) is a modifiable risk factor and a potential treatment target in patients with intracerebral hemorrhage (ICH). […] Every 1mL increase in hematoma volume is associated with a 5% higher risk of death or long-term functional dependency. […] As a modifiable predictor of outcome, HE is a potential target for anti-expansion interventions or hemostatic therapies. […] Identification of patients at risk of HE for targeted therapy can increase the chances of treatment benefit from anti-expansion interventions. […] Among patients with high-confidence prediction of HE6mL, the odds ratios of poor outcome and death were 2.92 (p=0.017), and 6.47 (p=0.001), respectively. […] Among patients with high-confidence prediction of HE3mL, the odds ratios of poor outcome and death were 1.69 (p=0.18), and 5.70 (p=0.001), respectively.

• #5 Predictors of hematoma expansion predictors after intracerebral hemorrhage | Oncotarget

  https://www.oncotarget.com/article/19366/text/

  Despite years of effort, intracerebral hemorrhage (ICH) remains the most devastating form of stroke with more than 40% 30-day mortality worldwide. Hematoma expansion (HE), which occurs in one third of ICH patients, is strongly predictive of worse prognosis and potentially preventable if high-risk patients were identified in the early phase of ICH. […] Hematoma expansion (HE), which occurs in approximately 33% ICH patients, is identified as one important independent predictor of early neurological deterioration and poor long-term clinical outcomes. […] Therefore, it is important to find those HE predictors to stratify patients and tailor intensive therapies timely and effectively for high-risk patient. […] The definition of HE varied in different literatures with a 40% relative volume increase or 12.6mL absolute volume increase in hematoma size from baseline CT to follow-up CT in one, a 33% relative increase in others, or even a 50% relative increase and 2mL absolute increase in another.

• #5 Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage | Journal of Translational Medicine | Full Text

  https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-024-04896-3

  Our study echoes this by demonstrating a correlation between elevated NIHSS scores and a dismal short-term prognosis, aligning with prior research. Our study also found that patients with higher AST would have poorer prognosis. […] The findings indicate that the AUC of the RF model in the testing set stands at 0.916(95% CI 0.8271.005), surpassing other models. Concurrently, within the external validation dataset, the AUC of the RF model reached 0.817, signaling the robust generalization capability of the RF model, affirming its applicability in clinically predicting sICH short-term prognosis.

• #5 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://www.mdpi.com/2077-0383/12/4/1580

  This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. […] The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with spontaneous supratentorial intracerebral hemorrhage 90 days after surgery. […] The best model predicted an AUC of 0.85 (95%CI, 0.75–0.94) on the internal test set and 0.81 (95%CI, 0.64–0.99) and 0.83 (95%CI, 0.68–0.97) on the two external test sets, respectively. […] Prognostic prediction for patients with sICH after surgery is helpful for clinicians to classify sICH patients with poor postoperative prognosis early, optimize treatment, achieve individualized precise treatment, and improve the overall prognosis of sICH patients.

• #6 Predictors of hematoma expansion predictors after intracerebral hemorrhage | Oncotarget

  https://www.oncotarget.com/article/19366/text/

  The INTERACT1 study categorized absolute and relative HE from minimal change (5mL or 33%) to massive change (12.5mL or 50%). […] One study demonstrates that patients with HE are more likely to have IVH (79% vs 45%) by univariate analysis. IVH is significantly predictive of HE (OR=5.7,95%CI:1.5-20.9). […] One third of ICH patients would may occur HE, which is strongly predictive of worse prognosis and potentially preventable. Potential HE predictors could help clinicians to better stratify patients, who are destined to undergo HE and tailor intensive therapies timely and effectively.

• #6 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://pmc.ncbi.nlm.nih.gov/articles/PMC9961203/

  This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. […] The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with sICH 90 days after surgery. […] The best model predicted an AUC of 0.85 (95%CI, 0.750.94) on the internal test set and 0.81 (95%CI, 0.640.99) and 0.83 (95%CI, 0.680.97) on the two external test sets, respectively. […] The combination of lasso regression feature selection and logistic regression model based on clinical features + radiomics features had the best performance (AUC: 0.87). […] The Shap plot showed that second-order features had a higher contribution than shape features and first-order features in predicting prognosis.

• #6

  https://link.springer.com/article/10.1007/s12975-021-00891-8

  We hypothesized that imaging-only-based machine learning algorithms can analyze non-enhanced CT scans of patients with acute intracerebral hemorrhage (ICH). […] Accurate stratification of ICH prognosis is highly desired regardless of the therapeutic options that are available and remains a clinical research priority. […] Several prognostic tools have been proposed for the prediction of mortality and functional outcome in spontaneous ICH. […] The goal of this study was twofold: First, we hypothesized that quantitative radiomic filter- and texture-derived high-end image features extracted from non-enhanced computed tomography (NECT) brain scans can be used to predict clinical outcome of ICH patients. […] The proposed approach employing quantitative image features derived from NECT scans provided high discriminatory accuracy between good and poor functional outcome of ICH patients at different mRS cut-off values.

• #7 Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

  https://www.mdpi.com/2077-0383/12/4/1580

  By combining radiomics features and clinical features, we established a prognosis prediction model for patients with sICH 90 days after surgery. […] The Shap plot showed that second-order features had a higher contribution than shape features and first-order features in predicting prognosis. […] In the prediction model of this study, the top four features of contribution were age, deep ICH, MLS, and GCS on admission, which were all clinical characteristics and correlated with poor prognosis of sICH.

• #7 Clinical and Radiographic Predictors of Intracerebral Hemorrhage Outcome

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5881146/

  Intracerebral hemorrhage (ICH) represents 10-15% of all stroke cases in the US annually. Fewer than 40% of these patients ever reach long-term functional independence, and mortality rate is roughly 40% at 1 month. […] Due to the high morbidity and mortality rates after ICH, early detection of high-risk patients would be beneficial in directing the management course and goals of care. This review aims to discuss relevant clinical and radiographic characteristics that can serve as predictors of poor prognosis and examine their efficacy in predicting patient outcomes after ICH. […] In this review, we examined clinical and radiographic characteristics that have been found to be significantly associated to a varying degree with poor outcome. Clinical and radiographic predictors of poor patient outcome are invaluable when it comes to identifying high-risk patients and triaging accordingly as well as guiding decision-making.

• #8

  https://link.springer.com/article/10.1007/s12975-021-00891-8

  The predictive value of second-order features is particularly apparent in the high predictive power of the gray level non-uniformity. […] Hence, the proposed approach can be used as supportive tool to augment conventional image analysis and to improve prognostic decision for both radiologists and clinicians. […] The findings support the potential of ML algorithms to augment conventional image analysis, improve prognostic decision, and simplify trial procedures. […] Quantitative imaging features of acute NECT evaluated by ML algorithms provide a high discriminatory power in predicting functional outcome in patients with spontaneous ICH.

• #8 Clinical and Radiographic Predictors of Intracerebral Hemorrhage Outcome

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5881146/

  Prognosis depends on the severity of the clinical presentation, speed of diagnosis, and time of intervention. […] The progression from this stage, mainly hematoma expansion and edema, determines patient outcomes. […] Due to the high morbidity and mortality rates after ICH, early detection of high-risk patients would be beneficial in directing the management course and goals of care. […] Given the profound morbidity and mortality associated with ICH, these clinical and radiographic predictors of poor patient outcome are of important prognostic value. Currently, studies show that 40% of patients regain functional independence after ICH, and mortality rate is 40% at 1 month and 54% at 1 year. Indication of patient outcome, based on presentation upon admission, holds value when triaging patients and making care decision.

• #9

  https://link.springer.com/article/10.1007/s12975-021-00891-8

  We hypothesized that imaging-only-based machine learning algorithms can analyze non-enhanced CT scans of patients with acute intracerebral hemorrhage (ICH). […] Accurate stratification of ICH prognosis is highly desired regardless of the therapeutic options that are available and remains a clinical research priority. […] Several prognostic tools have been proposed for the prediction of mortality and functional outcome in spontaneous ICH. […] The goal of this study was twofold: First, we hypothesized that quantitative radiomic filter- and texture-derived high-end image features extracted from non-enhanced computed tomography (NECT) brain scans can be used to predict clinical outcome of ICH patients. […] The proposed approach employing quantitative image features derived from NECT scans provided high discriminatory accuracy between good and poor functional outcome of ICH patients at different mRS cut-off values.

• #9 Prognostication after intracerebral hemorrhage: a review | Neurological Research and Practice | Full Text

  https://neurolrespract.biomedcentral.com/articles/10.1186/s42466-021-00120-5

  Approximately half of patients with spontaneous intracerebral hemorrhage (ICH) die within 1 year. Prognostication in this context is of great importance, to guide goals of care discussions, clinical decision-making, and risk stratification. […] Presently available prognostic scores for ICH do not fulfill essential quality standards. Novel prognostic scores need to be developed to inform the design of research studies and improve clinical care in patients with ICH. […] The discrepancy between what prognostic scores offer and what is needed in clinical practice has led physicians to increasingly neglect these scores. […] The max-ICH score was the first ICH prediction score in which the WOC bias was addressed at the level of score creation. […] Despite prediction score fatigue among clinicians, prognostication in patients with ICH remains crucially important. It may improve clinical care by providing information on the most probable outcome, which can then be aligned with what is medically feasible and what the patient wants.

• #10

  https://link.springer.com/article/10.1007/s12975-021-00891-8

  The predictive value of second-order features is particularly apparent in the high predictive power of the gray level non-uniformity. […] Hence, the proposed approach can be used as supportive tool to augment conventional image analysis and to improve prognostic decision for both radiologists and clinicians. […] The findings support the potential of ML algorithms to augment conventional image analysis, improve prognostic decision, and simplify trial procedures. […] Quantitative imaging features of acute NECT evaluated by ML algorithms provide a high discriminatory power in predicting functional outcome in patients with spontaneous ICH.

• #10

  https://link.springer.com/article/10.1007/s00701-022-05216-8

  The results of complete case analyses were consistent with imputation analyses. […] The study confirms the complexity of predicting outcomes in patients with CSDH and the need for the collection of standard baseline variables and a core outcome set and for improved modeling strategies, which will improve current prognostic models.

• #11 Prognostication after intracerebral hemorrhage: a review | Neurological Research and Practice | Full Text

  https://neurolrespract.biomedcentral.com/articles/10.1186/s42466-021-00120-5

  Approximately half of patients with spontaneous intracerebral hemorrhage (ICH) die within 1 year. Prognostication in this context is of great importance, to guide goals of care discussions, clinical decision-making, and risk stratification. […] Presently available prognostic scores for ICH do not fulfill essential quality standards. Novel prognostic scores need to be developed to inform the design of research studies and improve clinical care in patients with ICH. […] The discrepancy between what prognostic scores offer and what is needed in clinical practice has led physicians to increasingly neglect these scores. […] The max-ICH score was the first ICH prediction score in which the WOC bias was addressed at the level of score creation. […] Despite prediction score fatigue among clinicians, prognostication in patients with ICH remains crucially important. It may improve clinical care by providing information on the most probable outcome, which can then be aligned with what is medically feasible and what the patient wants.

Zobacz więcej