Female ; Heart Atria ; pathology ; Humans ; Middle Aged ; Pleural Effusion ; diagnosis ; diagnostic imaging ; Radiography ; Rheumatic Heart Disease ; diagnosis ; diagnostic imaging

INTRODUCTION: Nontraumatic acute abdomen (NTAA) in dialysis patients is a challenging issue. The aetiologies of NTAA vary considerably depending on the renal replacement therapy (RRT) modality. Although haematological parameters and contributing factors have been reported to be associated with outcomes for dialysis patients, their clinical effect on the length of hospital stay (LOS) remains unknown. METHODS: We retrospectively analysed 52 dialysis patients (peritoneal dialysis [PD], n = 33; haemodialysis [HD], n = 19) and 30 non-dialysis patients (as controls) between January 2011 and December 2014. To attenuate the selection bias, non-dialysis patients with NTAA were matched to cases at a ratio of 1:1 by age, gender and comorbidities (diabetes mellitus and hypertension). Their demographic characteristics, laboratory data, clinical assessment scores and LOS were analysed. RESULTS: The PD group exhibited a significantly higher neutrophil percentage, neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR); longer LOS; and lower lymphocyte percentage and absolute lymphocyte count than the control group. After multivariate analysis adjustment, female gender, longer RRT duration and higher intact parathyroid hormone (iPTH) levels were associated with a lower probability of being discharged home. In the dialysis group, a higher iPTH level (> 313 μg/mL) was positively correlated with longer LOS. iPTH level combined with NLR can be used as a surrogate marker for predicting longer LOS (p < 0.001). CONCLUSION NTAA dialysis patients with female gender, longer RRT duration and higher iPTH levels are prone to experiencing longer LOS. In addition, the combination of iPTH and NLR is a significant determinant for LOS in NTAA dialysis patients.

Background/Aims: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1–3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. Methods: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. Results: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. Conclusions Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.