Postoperative delirium prediction after cardiac surgery using machine learning models.

OBJECTIVE: Postoperative delirium (POD) is a common postoperative complication in elderly patients, especially those undergoing cardiac surgery, which seriously affects the short- and long-term prognosis of patients. Early identification of risk factors for the development of POD can help improve the perioperative management of surgical patients. In the present study, five machine learning models were developed to predict patients at high risk of delirium after cardiac surgery and their performance was compared. METHODS: A total of 367 patients who underwent cardiac surgery were retrospectively included in this study. Using single-factor analysis, 21 risk factors for POD were selected for inclusion in machine learning. The dataset was divided using 10-fold cross-validation for model training and testing. Five machine learning models (random forest (RF), support vector machine (SVM), radial based kernel neural network (RBFNN), K-nearest neighbour (KNN), and Kernel ridge regression (KRR)) were compared using area under the receiver operating characteristic curve (AUC-ROC), accuracy (ACC), sensitivity (SN), specificity (SPE), and Matthews coefficient (MCC). RESULTS: Among 367 patients, 105 patients developed POD, the incidence of delirium was 28.6 %. Among the five ML models, RF had the best performance in ACC (87.99 %), SN (69.27 %), SPE (95.38 %), MCC (70.00 %) and AUC (0.9202), which was far superior to the other four models. CONCLUSION: Delirium is common in patients after cardiac surgery. This analysis confirms the importance of the computational ML models in predicting the occurrence of delirium after cardiac surgery, especially the outstanding performance of the RF model, which has practical clinical applications for early identification of patients at risk of developing POD.

Ultrafast Microfluidic PCR Thermocycler for Nucleic Acid Amplification.

The polymerase chain reaction (PCR) is essential in nucleic acid amplification tests and is widely used in many applications such as infectious disease detection, tumor screening, and food safety testing; however, most PCR devices have inefficient heating and cooling ramp rates for the solution, which significantly limit their application in special scenarios such as hospital emergencies, airports, and customs. Here, we propose a temperature control strategy to significantly increase the ramp rates for the solution temperature by switching microfluidic chips between multiple temperature zones and excessively increasing the temperature difference between temperature zones and the solution; accordingly, we have designed an ultrafast thermocycler. The results showed that the ramp rates of the solution temperature are a linear function of temperature differences within a range, and a larger temperature difference would result in faster ramp rates. The maximum heating and cooling ramp rates of the 25 µL solution reached 24.12 °C/s and 25.28 °C/s, respectively, and the average ramp rate was 13.33 °C/s, 6-8 times higher than that of conventional commercial PCR devices. The thermocycler achieved 9 min (1 min pre-denaturation + 45 PCR cycles) ultrafast nucleic acid amplification, shortening the time by 92% compared to the conventional 120 min nucleic acid amplification, and has the potential to be used for rapid nucleic acid detection.

Identification of D Modification Sites Using a Random Forest Model Based on Nucleotide Chemical Properties.

Dihydrouridine (D) is an abundant post-transcriptional modification present in transfer RNA from eukaryotes, bacteria, and archaea. D has contributed to treatments for cancerous diseases. Therefore, the precise detection of D modification sites can enable further understanding of its functional roles. Traditional experimental techniques to identify D are laborious and time-consuming. In addition, there are few computational tools for such analysis. In this study, we utilized eleven sequence-derived feature extraction methods and implemented five popular machine algorithms to identify an optimal model. During data preprocessing, data were partitioned for training and testing. Oversampling was also adopted to reduce the effect of the imbalance between positive and negative samples. The best-performing model was obtained through a combination of random forest and nucleotide chemical property modeling. The optimized model presented high sensitivity and specificity values of 0.9688 and 0.9706 in independent tests, respectively. Our proposed model surpassed published tools in independent tests. Furthermore, a series of validations across several aspects was conducted in order to demonstrate the robustness and reliability of our model.

Overexpression of CHD1L is associated with poor survival and aggressive tumor biology in esophageal carcinoma.

Esophageal carcinoma (EC) is a malignancy with high metastatic potential. Chromosomal helicase/ATPase DNA binding protein 1-like (CHD1L) gene is a newly identified oncogene located at Chr1q21, and it is amplified in many solid tumors. However, the status of CHD1L protein expression in EC and its clinical significance is uncertain. This study was designed to investigate the significance of CHD1L expression in human EC and its biological function in EC cells. The expression of CHD1L was examined by immunohistochemistry in 191 surgically resected ECs. The associations between CHD1L expression and clinical pathological parameters and the prognostic value of CHD1L were analyzed. Western blot analysis showed that CHD1L was overexpressed in EC cell lines. In addition, positive CHD1L expression was strongly related to advanced clinical stage (P<0.01), and lymph node metastasis (P<0.01) of EC. The Kaplan-Meier curve indicated that high expression of CHD1L may result in poor prognosis of EC patients (P<0.01), and multivariate analysis showed that CHD1L overexpression was an independent predictor of overall survival. Furthermore, suppression of CHD1L in EC cells increased apoptosis and decreased cell proliferation invasion ability. Our results suggest that CHD1L is a target oncogene with the potential to serve as a novel prognostic biomarker in EC pathogenesis.

Vitexin suppresses autophagy to induce apoptosis in hepatocellular carcinoma via activation of the JNK signaling pathway.

Vitexin, a flavonoids compound, is known to exhibit broad anti-oxidative, anti-inflammatory, analgesic, and antitumor activity in many cancer xenograft models and cell lines. The purpose of this study was to investigate the antitumor effects and underlying mechanisms of vitexin on hepatocellular carcinoma. In this study, we found that vitexin suppressed the viability of HCC cell lines (SK-Hep1 and Hepa1-6 cells) significantly. Vitexin showed cytotoxic effects against HCC cell lines in vitro by inducing apoptosis and inhibiting autophagy. Vitexin induced apoptosis in a concentration-dependent manner, and caused up-regulations of Caspase-3, Cleave Caspase-3, and a down-regulation of Bcl-2. The expression of autophagy-related protein LC3 II was significantly decreased after vitexin treatment. Moreover, western blot analysis presented that vitexin markedly up-regulated the levels of p-JNK and down-regulated the levels of p-Erk1/2 in SK-Hep1 cells and Hepa1-6 cells. Cotreatment with JNK inhibitor SP600125, we demonstrated that apoptosis induced by vitexin was suppressed, while the inhibition of autophagy by vitexin was reversed. The results of colony formation assay and mouse model confirmed the growth inhibition role of vitexin on HCC in vitro and in vivo. In conclusion, vitexin inhibits HCC growth by way of apoptosis induction and autophagy suppression, both of which are through JNK MAPK pathway. Therefore, vitexin could be regarded as a potent therapeutic agent for the treatment of HCC.