Explore the vast range of titles available.

Acute gastrointestinal (GI) bleed is a common reason for hospitalization with 2%-10% risk of mortality. In this study, we developed a machine learning (ML) model to calculate the risk of mortality in intensive care unit patients admitted for GI bleed and compared it with APACHE IVa risk score. We used explainable ML methods to provide insight into the model's prediction and outcome. We analyzed the patient data in the Electronic Intensive Care Unit Collaborative Research Database and extracted data for 5,691 patients (mean age = 67.4 years; 61% men) admitted with GI bleed. The data were used in training a ML model to identify patients who died in the intensive care unit. We compared the predictive performance of the ML model with the APACHE IVa risk score. Performance was measured by area under receiver operating characteristic curve (AUC) analysis. This study also used explainable ML methods to provide insights into the model's outcome or prediction using the SHAP (SHapley Additive exPlanations) method. The ML model performed better than the APACHE IVa risk score in correctly classifying the low-risk patients. The ML model had a specificity of 27% (95% confidence interval [CI]: 25-36) at a sensitivity of 100% compared with the APACHE IVa score, which had a specificity of 4% (95% CI: 3-31) at a sensitivity of 100%. The model identified patients who died with an AUC of 0.85 (95% CI: 0.80-0.90) in the internal validation set, whereas the APACHE IVa clinical scoring systems identified patients who died with AUC values of 0.80 (95% CI: 0.73-0.86) with P value <0.001. We developed a ML model that predicts the mortality in patients with GI bleed with a greater accuracy than the current scoring system. By making the ML model explainable, clinicians would be able to better understand the reasoning behind the outcome.

BackgroundHaemoglobin E (HbE)-β-thalassaemia has a very variable clinical presentation. The management of severe cases that are often transfusion dependent is similar to that of cases of β-thalassaemia major; however, this is often not possible in India because of its high cost and the lack of availability of safe blood at many places. Thus there was a need for a drug such as hydroxyurea, which is known to reduce the transfusion requirements of patients with thalassaemia intermedia. This study was undertaken to evaluate the response of Indian patients with HbE-β-thalassaemia to hydroxyurea.Materials and methods11 patients with HbE-β-thalassaemia receiving regular transfusion plus two less frequently transfused patients were selected for hydroxyurea therapy. Clinical and haematological evaluation was performed before and after treatment for 2 years. Molecular studies included β-globin genotype, β-globin gene haplotype, Xmn I polymorphism and α-genotyping.ResultsFour clinically severe patients became transfusion independent (responders) after hydroxyurea therapy, four patients showed a reduction in their transfusion requirements (partial responders), and three patients were non-responders. Responders showed a statistically significant increase in Hb, mean corpuscular volume, mean cell Hb, fetal Hb and F cells with a reduction in their transfusion requirements. A reduction in serum ferritin concentration was also seen in responders and non-responders.ConclusionsGenetic markers such as Xmn I polymorphism and α-gene deletions were not always beneficial for the response to hydroxyurea therapy. Thus many more markers and a larger cohort need to be studied to predict the response in these patients.

Background: Hydroxyurea, which induces Fetal hemoglobin (HbF) synthesis, is the only drug widely used in different hemoglobinopathies; however, the response is very variable. We compared the efficacy of hydroxyurea in-vitro in erythroid cultures and in-vivo in the same patients with different hemoglobinopathies to induce HbF production and enhance γ-messenger RNA expression. Materials and Methods: A total of 24-patients with different Hemoglobinopathies were given hydroxyurea and their response was studied in-vivo and in-vitro on mononuclear cells collected from them simultaneously. Results: A total of 57.7% of patients (responders) showed no further crisis or transfusion requirements after hydroxyurea therapy with a mean increase in fetal cells (F-cells) of 63.8 ± 59.1% and γ-mRNA expression of 205.5 ± 120.8%. In-vitro results also showed a mean increase in F-cells of 27.2 ± 24.7% and γ-mRNA expression of 119.6% ± 65.4% among the treated cells. Nearly 19.0% of the partial-responders reduced their transfusion requirements by 50% with a mean increase in F-cells of 61.2 ± 25.0% and 28.4 ± 25.3% and γ-mRNA-expression of 21.0% ± 1.4% and 80.0% ± 14.1% in-vivo and in-vitro respectively. The non-responders (15.3%) showed no change in their clinical status and there was no significant increase in F-cells levels and γ-mRNA expression in-vivo or in-vitro. Conclusion: Thus, this method may help to predict the in-vivo response to hydroxyurea therapy; however, a much larger study is required.

Background: Hydroxyurea, which induces Fetal hemoglobin (HbF) synthesis, is the only drug widely used in different hemoglobinopathies; however, the response is very variable. We compared the efficacy of hydroxyurea in-vitro in erythroid cultures and in-vivo in the same patients with different hemoglobinopathies to induce HbF production and enhance γ-messenger RNA expression. Materials and Methods: A total of 24-patients with different Hemoglobinopathies were given hydroxyurea and their response was studied in-vivo and in-vitro on mononuclear cells collected from them simultaneously. Results: A total of 57.7% of patients (responders) showed no further crisis or transfusion requirements after hydroxyurea therapy with a mean increase in fetal cells (F-cells) of 63.8 +- 59.1% and γ-mRNA expression of 205.5 +- 120.8%. In-vitro results also showed a mean increase in F-cells of 27.2 +- 24.7% and γ-mRNA expression of 119.6% +- 65.4% among the treated cells. Nearly 19.0% of the partial-responders reduced their transfusion requirements by 50% with a mean increase in F-cells of 61.2 +- 25.0% and 28.4 +- 25.3% and γ-mRNA-expression of 21.0% +- 1.4% and 80.0% +- 14.1% in-vivo and in-vitro respectively. The non-responders (15.3%) showed no change in their clinical status and there was no significant increase in F-cells levels and γ-mRNA expression in-vivo or in-vitro. Conclusion: Thus, this method may help to predict the in-vivo response to hydroxyurea therapy; however, a much larger study is required.

Background Haemoglobin E (HbE)-β-thalassaemia has a very variable clinical presentation. The management of severe cases that are often transfusion dependent is similar to that of cases of β-thalassaemia major; however, this is often not possible in India because of its high cost and the lack of availability of safe blood at many places. Thus there was a need for a drug such as hydroxyurea, which is known to reduce the transfusion requirements of patients with thalassaemia intermedia. This study was undertaken to evaluate the response of Indian patients with HbE-β-thalassaemia to hydroxyurea. Materials and methods 11 patients with HbE-β-thalassaemia receiving regular transfusion plus two less frequently transfused patients were selected for hydroxyurea therapy. Clinical and haematological evaluation was performed before and after treatment for 2 years. Molecular studies included β-globin genotype, β-globin gene haplotype, Xmn I polymorphism and α-genotyping. Results Four clinically severe patients became transfusion independent (responders) after hydroxyurea therapy, four patients showed a reduction in their transfusion requirements (partial responders), and three patients were non-responders. Responders showed a statistically significant increase in Hb, mean corpuscular volume, mean cell Hb, fetal Hb and F cells with a reduction in their transfusion requirements. A reduction in serum ferritin concentration was also seen in responders and non-responders. Conclusions Genetic markers such as Xmn I polymorphism and α-gene deletions were not always beneficial for the response to hydroxyurea therapy. Thus many more markers and a larger cohort need to be studied to predict the response in these patients.