clozapine and Healthcare-Associated-Pneumonia

Few researchers have investigated the incidence of and risk factors for hospital-acquired pneumonia (HAP) among inpatients with mental disorders in a general hospital.. This study included patients with mental disorders hospitalized in a large mental health center (situated in a general hospital) between January 1, 2017, and July 31, 2021 (excluding January 1, 2020- May 31, 2020). Risk factors for HAP were identified by logistic regression analysis after propensity score matching (PSM, 1:4) for gender, age, duration of observation, and hospital ward.. The study included 16,864 patients. HAP incidence rate was 1.15% overall, 2.11% in closed wards, 0.75% in open wards, 4.45% in patients with organic mental disorders, 1.80% in patients with schizophrenia spectrum disorders, and 0.84% in patients with mood disorders. Risk factors for HAP after PSM were hypoproteinemia, chronic liver disease, use of clozapine, hospitalization during the previous 180 days, body mass index (BMI) ≤18.5 kg/m. HAP was common among inpatients with mental disorders. Risk factors for HAP in patients with mental disorders include hypoproteinemia, chronic liver disease, hospitalization during the past 180 days, BMI ≤18.5 kg/m

Topics: Clozapine; Cross Infection; Healthcare-Associated Pneumonia; Hospitals, General; Humans; Hypoproteinemia; Inpatients; Mental Disorders; Mental Health; Pneumonia; Risk Factors

Medications are frequently used for treating schizophrenia, however, anti-psychotic drug use is known to lead to cases of pneumonia. The purpose of our study is to build a model for predicting hospital-acquired pneumonia among schizophrenic patients by adopting machine learning techniques.. Data related to a total of 185 schizophrenic in-patients at a Taiwanese district mental hospital diagnosed with pneumonia between 2013 ~ 2018 were gathered. Eleven predictors, including gender, age, clozapine use, drug-drug interaction, dosage, duration of medication, coughing, change of leukocyte count, change of neutrophil count, change of blood sugar level, change of body weight, were used to predict the onset of pneumonia. Seven machine learning algorithms, including classification and regression tree, decision tree, k-nearest neighbors, naïve Bayes, random forest, support vector machine, and logistic regression were utilized to build predictive models used in this study. Accuracy, area under receiver operating characteristic curve, sensitivity, specificity, and kappa were used to measure overall model performance.. Among the seven adopted machine learning algorithms, random forest and decision tree exhibited the optimal predictive accuracy versus the remaining algorithms. Further, six most important risk factors, including, dosage, clozapine use, duration of medication, change of neutrophil count, change of leukocyte count, and drug-drug interaction, were also identified.. Although schizophrenic patients remain susceptible to the threat of pneumonia whenever treated with anti-psychotic drugs, our predictive model may serve as a useful support tool for physicians treating such patients.

Topics: Adult; Aged; Aged, 80 and over; Antipsychotic Agents; Clozapine; Comorbidity; Decision Trees; Female; Healthcare-Associated Pneumonia; Hospitals, Psychiatric; Humans; Machine Learning; Male; Middle Aged; Risk Factors; Schizophrenia