OBJECTIVES: To review cases of peritonsillar abscess and investigate the initial clinical factors that may influence the duration of hospitalization. To determine the predictive factors of prolonged hospital stay in adult patients with peritonsillar abscess. METHODS: Subjects were adults hospitalized with peritonsillar abscess. We retrospectively reviewed 377 medical records from 1990 to 2013 in a tertiary medical center in southern Taiwan. The association between clinical characteristics and the length of hospital stay was analyzed with independent t-test, univariate linear regression and multiple linear regression analysis. RESULTS: The mean duration of hospitalization was 6.2±6.0 days. With univariate linear regression, a prolonged hospital stay was associated with several variables, including female gender, older ages, nonsmoking status, diabetes mellitus, hypertension, band forms in white blood cell (WBC) counts, and lower hemoglobin levels. With multiple linear regression analysis, four independent predictors of hospital stay were noted: years of age (P<0.001), history of diabetes mellitus (P<0.001), ratio of band form WBC (P<0.001), and hemoglobin levels (P<0.001). CONCLUSION: In adult patients with peritonsillar abscess, older ages, history of diabetes mellitus, band forms in WBC counts and lower hemoglobin levels were independent predictors of longer hospitalization.
Adult* ; Diabetes Mellitus ; Female ; Hospitalization ; Humans ; Hypertension ; Length of Stay* ; Leukocytes ; Linear Models ; Medical Records ; Peritonsillar Abscess* ; Retrospective Studies ; Taiwan

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.