1.
Predicting psoriasis using routine laboratory tests with random forest.
Zhou, J, Li, Y, Guo, X
PloS one. 2021;(10):e0258768
Abstract
Psoriasis is a chronic inflammatory skin disease that affects approximately 125 million people worldwide. It has significant impacts on both physical and emotional health-related quality of life comparable to other major illnesses. Accurately prediction of psoriasis using biomarkers from routine laboratory tests has important practical values. Our goal is to derive a powerful predictive model for psoriasis disease based on only routine hospital tests. We collected a data set including 466 psoriasis patients and 520 healthy controls with 81 variables from only laboratory routine tests, such as age, total cholesterol, HDL cholesterol, blood pressure, albumin, and platelet distribution width. In this study, Boruta feature selection method was applied to select the most relevant features, with which a Random Forest model was constructed. The model was tested with 30 repetitions of 10-fold cross-validation. Our classification model yielded an average accuracy of 86.9%. 26 notable features were selected by Boruta, among which 15 features are confirmed from previous studies, and the rest are worth further investigations. The experimental results demonstrate that the machine learning approach has good potential in predictive modeling for the psoriasis disease given the information only from routine hospital tests.
2.
Hepatic and renal functions and blood cell counts in brain tumor patients during the perioperative period.
Zhang, F, Guo, X, Xing, B, Yang, Y, Xu, Z
Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia. 2019;:190-197
Abstract
We aimed to investigate the correlations between biochemical and hematological markers and the clinical conditions of brain tumor patients before and after craniotomy. A retrospective study was conducted in 90 brain tumor patients. Age, gender, underlying diseases, tumor size and intraoperative blood loss were recorded. Red blood cell counts and hepatic and renal markers were analyzed preoperatively and postoperatively. Albumin decreased by 5.6 g/L after surgery (p < 0.001). Older patients (>52 years) and females had lower albumin levels than younger patients and males did. Red blood cell counts and hemoglobin levels decreased significantly on the 1st and increased on the 3rd postoperative day. The blood glucose level increased on the 1st postoperative day and then decreased. Older patients had higher blood glucose levels than younger patients did (p < 0.05). The postoperative serum sodium, potassium and calcium levels were within the normal ranges; 37 patients had hypocalcemia (41.1%) and patients with hypokalemia and hyponatremia increased postoperatively. Albumin and hemoglobin levels were linearly correlated (correlation coefficient 0.559, p < 0.001). Intraoperative blood loss was correlated with tumor size (p < 0.05) but did not affect the decrease in hematological markers. In brain tumor patients, red blood cell counts and hemoglobin and serum albumin levels were significantly decreased after craniotomy; these effects were influenced by gender and age instead of intraoperative blood loss. The postoperative blood glucose level peaked and then decreased; it was affected by age and diabetes mellitus. Electrolytes remained relatively stable. These findings have implications for patient management and postoperative complication prevention.