ABSTRACT
Objective:To investigate the application value of establishing the differential diagnosis model of pulmonary tuberculosis using routine laboratory data.Methods:The retrospective study was conducted. The routine laboratory data of newly diagnosed patients with pulmonary tuberculosis and other pulmonary diseases in Beijng Jishuitan Hospital and Beijing Hepingli Hospital from May 2015 to November 2021were collected. According to the random numbers showed in the computer, all the 11516 patients were divided into training dataset and test dataset with a ratio of 9∶1. Four machine learning algorithms, Support Vector Machine, Random Forest, K-Nearest Neighbor and Logistic Regression, were used to build models and select features. The diagnostic accuracy of each model was verified by using the 10-fold cross-validation method and the performance of each model was evaluated by using the receptor operator of characteristic (ROC) curve.Results:Random Forest was selected as the optimal machine learning algorithm to build the best feature model in the study. According to importance scale of factors, the differential diagnosis model of pulmonary tuberculosis consisting of 37 non-specific test indexes. In the validation set and test set the accuracy and area under curve (AUC) of the models were 0.747 and 0.736, the sensitivity, specificity and accuracy were 68.03% and 68.75%, 70.91% and 67.90%, 70.30% and 68.12%, respectively.Conclusion:A key tool in the differential diagnosis model of pulmonary tuberculosis was established by routine laboratory data in combination with machine learning. The results of this study need to be further verified by more data from medical institutions.
ABSTRACT
Objective To evaluate the effect of serratus plane block (SPB) combined with general anesthesia and SPB with patient-controlled nerve analgesia (PCNA) after surgery on the early postoperative quality of recovery in the patients undergoing radical mastectomy.Methods Sixty American Society of Anesthesiologists physical status Ⅰ or Ⅱ female patients,aged 18-64 yr,weighing 45-70 kg,scheduled for elective unilateral modified radical mastectomy under general anesthesia,were assigned into 3 groups (n=20 each) using a computer software:SPB and general anesthesia plus patient-controlled intravenous analgesia (PCIA) group (SG+PCIA group),SPB and general anesthesia plus SPB with PCNA group (SG+PCNA group),and general anesthesia plus PCIA group (G+PCIA group).Ultrasound-guided ipsilateral SPB was performed before anesthesia induction.Analgesia was maintained with propofol-remifentanilsevoflurane,rocuronium or vecuronium was intermittently injected to maintain muscle relaxation.PCIA solution contained tramadol 800 mg and flurbiprofen axetil 100 mg in 54 ml of normal saline,and the PCA pump was set up to deliver a 2 ml bolus dose,with a 15 min lockout interval and background infusion at a rate of 0.5 ml/h after a loading dose of 5 ml.The location of the indwelling catheter was confirmed again using ultrasound at the end of surgery,PCNA solution contained 1％ ropivacaine 500 mg in 250 ml of normal saline,and the PCA pump was set up to deliver a 5 ml bolus dose,with a 45 min lockout interval and background infusion at a rate of 5 ml/h after a loading dose of 5 ml.The PCA pumps were used until 48 h after surgery.The automatic key was pressed when pain scores (numerical rating scale [NRS] scores) ≥ 4 at rest or during activity (at 45° ipsilateral upper extremity-up tilt).Quality of Recovery-40 (QoR-40) score was used to assess the early postoperative quality of recovery at 24 and 48 h after surgery.NRS scores at rest or during activity were recorded at 6,8,12,24 and 48 h after surgery.The total pressing times of PCA and occurrence of adverse reactions such as respiratory depression,pruritus,infection at the puncture site or pneumothorax were also recorded.Results Compared with group G+PCIA,the postoperative QoR40 scores were significantly increased,NRS scores at rest or during activity were decreased at each time point after surgery,and the total pressing times of PCA were reduced in SG+PCIA and SG+PCNA groups,the incidence of nausea and vomiting was significantly decreased in group SG+PCIA,and the incidence of nausea and vomiting and dizziness was significantly decreased in group SG+PCNA (P＜0.05 or 0.01).Compared with group SG+PCIA,the postoperative QoR-40 scores were significantly increased at 24 h after surgery,and NRS scores at rest or during activity were decreased after surgery in group SG+PCNA (P＜ 0.05 or 0.01).Conclusion SPB combined with general anesthesia and SPB with PCNA after surgery can raise the early postoperative quality of recovery in the patients undergoing modified radical mastectomy.