In general, bioassay-guided fractionation and isolation of bioactive constituents from botanical materials frequently ended up with the reward of a single compound. However, botanical materials typically exert their therapeutic actions through multi-pathway effects due to the intrinsic complex nature of chemical constituents. In addition, the content of bioactive compounds in botanical materials is largely dependent on humidity, temperature, soil, especially geographical origins, from which rapid and accurate identification of plant materials is pressingly needed. These long-standing obstacles collectively impede the deep exploitation and application of these versatile natural sources. To address the challenges, a new paradigm integrating biogravimetric analyses and machine learning-driven origin classification (BAMLOC) was developed. The biogravimetric analyses are based on absolute qHNMR quantification and in vivo zebrafish model-assisted activity index calculation, by which bioactive substance groups jointly responsible for the bioactivities in all fractions are pinpointed before any isolation effort. To differentiate origin-different botanical materials varying in the content of bioactive substance groups, principal component analysis, linear discriminant analysis, and hierarchical cluster analysis in conjunction with supervised support vector machine are employed to classify and predict production areas based on the detection of volatile organic compounds by E-nose and GC-MS. Expanding BAMLOC to Codonopsis Radix enables the identification of polyacetylenes and pyrrolidine alkaloids as the bioactive substance group for immune restoration effect and accurately determines the origins of plants. This study advances the toolbox for the discovery of bioactive compounds from complex mixtures and lays a more definitive foundation for the in-depth utilization of botanical materials.

Current epilepsy prediction methods are not effective in characterizing the multi-domain features of complex long-term electroencephalogram (EEG) data, leading to suboptimal prediction performance. Therefore, this paper proposes a novel multi-scale sparse adaptive convolutional network based on multi-head attention mechanism (MS-SACN-MM) model to effectively characterize the multi-domain features. The model first preprocesses the EEG data, constructs multiple convolutional layers to effectively avoid information overload, and uses a multi-layer perceptron and multi-head attention mechanism to focus the network on critical pre-seizure features. Then, it adopts a focal loss training strategy to alleviate class imbalance and enhance the model's robustness. Experimental results show that on the publicly created dataset (CHB-MIT) by MIT and Boston Children's Hospital, the MS-SACN-MM model achieves a maximum accuracy of 0.999 for seizure prediction 10 ~ 15 minutes in advance. This demonstrates good predictive performance and holds significant importance for early intervention and intelligent clinical management of epilepsy patients.
Humans ; Electroencephalography/methods* ; Epilepsy/physiopathology* ; Neural Networks, Computer ; Seizures/physiopathology* ; Signal Processing, Computer-Assisted ; Algorithms

Non-small cell lung cancer(NSCLC)is the most common form of lung cancer,and patients with advanced disease generally have a poor prognosis.In recent years,immune checkpoint inhibitors(ICIs)have been approved as first-line therapy for patients with NSCLC lacking actionable driver mutations.Emerging evidence indicates that ICIs reduce tumor burden in some patients and may affect pulmonary ventila-tion and diffusion capacity,which are associated with clinical outcomes.This review summarizes baseline pulmonary function characteristics in advanced NSCLC,outlines in the impact of ICI therapy on lung function,and discusses potential mechanisms through which immunother-apy can influence pulmonary function,with the aim of guiding lung function monitoring and individualized management during ICI treat-ment.

Non-small cell lung cancer(NSCLC)is the most common form of lung cancer,and patients with advanced disease generally have a poor prognosis.In recent years,immune checkpoint inhibitors(ICIs)have been approved as first-line therapy for patients with NSCLC lacking actionable driver mutations.Emerging evidence indicates that ICIs reduce tumor burden in some patients and may affect pulmonary ventila-tion and diffusion capacity,which are associated with clinical outcomes.This review summarizes baseline pulmonary function characteristics in advanced NSCLC,outlines in the impact of ICI therapy on lung function,and discusses potential mechanisms through which immunother-apy can influence pulmonary function,with the aim of guiding lung function monitoring and individualized management during ICI treat-ment.

The problem of drug resistance resulting from the long-term use of antimicrobials is a serious threat to global health,and the emergence of multidrug-resistant bacteria,in particular,has greatly limited therapeutic op-tions.Therefore,the development of new or alternative antimicrobial agents has become an urgent need.Antimi-crobial peptides(AMPs)have been regarded as good alternatives to antibacterial drugs due to their strong antibac-terial activity and unique mechanism of action.At present,some AMPs have completed preclinical studies on drug-resistant bacterial infections and entered the clinical trial stage,while their stability and targeting have been signifi-cantly improved through the optimisation of amino acid modification,nano-delivery system and other technolo-gies,which have gradually become a research hotspot in this field.Therefore,this paper discusses the importance of AMPs in bacterial drug resistance from the biological properties of AMPs,the mechanism of regulating bacteri-al drug resistance and the application of AMPs in the treatment of drug-resistant bacterial infections,with a view to providing a reference for the development of drugs against drug-resistant bacteria and clinical application.

The problem of drug resistance resulting from the long-term use of antimicrobials is a serious threat to global health,and the emergence of multidrug-resistant bacteria,in particular,has greatly limited therapeutic op-tions.Therefore,the development of new or alternative antimicrobial agents has become an urgent need.Antimi-crobial peptides(AMPs)have been regarded as good alternatives to antibacterial drugs due to their strong antibac-terial activity and unique mechanism of action.At present,some AMPs have completed preclinical studies on drug-resistant bacterial infections and entered the clinical trial stage,while their stability and targeting have been signifi-cantly improved through the optimisation of amino acid modification,nano-delivery system and other technolo-gies,which have gradually become a research hotspot in this field.Therefore,this paper discusses the importance of AMPs in bacterial drug resistance from the biological properties of AMPs,the mechanism of regulating bacteri-al drug resistance and the application of AMPs in the treatment of drug-resistant bacterial infections,with a view to providing a reference for the development of drugs against drug-resistant bacteria and clinical application.

Objective To establish a diagnostic model for depression in insomnia patients by mining polysomnography (PSG) data of insomnia patients with machine learning algorithms,and to provide a scientific basis for the diagnosis of depression in insomnia patients. Methods According to the inclusion and exclusion criteria,2162 insomnia inpatients and outpatients who attended the Inner Mongolia Autonomous Region Mental Health Center from January to December 2023 and underwent polysomnographic monitoring were included,and depression was diagnosed using the International Statistical Classification of Diseases and Related Health Problems,10th version (ICD-10). The general condition and PSG data of the patients were collected. Six algorithms—logistic regression (LR),Support vector machines (SVM),Random forest (RF),Adaptive Boosting (AdaBoost),Extreme Gradient Boosting (XGBoost) and Naive Bayes (NB)—were used to build the diagnostic model of depression in insomnia patients after the patients' general condition and PSG data were gathered. Results Among the enrolled patients with insomnia,40.1％ had comorbid depression. Among the six models,LR and RF exhibited the highest values of area under the curve (AUC) of receiver operating characteristic (ROC),at 0.825 and 0.823,respectively,indicating superior overall classification performance. Conclusion Logistic regression and random forest modeling have good diagnostic efficacy in the population of insomniacs with depression.

Objective To establish a diagnostic model for depression in insomnia patients by mining polysomnography (PSG) data of insomnia patients with machine learning algorithms,and to provide a scientific basis for the diagnosis of depression in insomnia patients. Methods According to the inclusion and exclusion criteria,2162 insomnia inpatients and outpatients who attended the Inner Mongolia Autonomous Region Mental Health Center from January to December 2023 and underwent polysomnographic monitoring were included,and depression was diagnosed using the International Statistical Classification of Diseases and Related Health Problems,10th version (ICD-10). The general condition and PSG data of the patients were collected. Six algorithms—logistic regression (LR),Support vector machines (SVM),Random forest (RF),Adaptive Boosting (AdaBoost),Extreme Gradient Boosting (XGBoost) and Naive Bayes (NB)—were used to build the diagnostic model of depression in insomnia patients after the patients' general condition and PSG data were gathered. Results Among the enrolled patients with insomnia,40.1％ had comorbid depression. Among the six models,LR and RF exhibited the highest values of area under the curve (AUC) of receiver operating characteristic (ROC),at 0.825 and 0.823,respectively,indicating superior overall classification performance. Conclusion Logistic regression and random forest modeling have good diagnostic efficacy in the population of insomniacs with depression.

Using syringaldehyde as raw material, the phosphine ylide intermediate was efficiently synthesized through acetylated hydroxyl protection, aldehyde group reduction, chlorination and reaction with triphenylphosphine. On this basis, moscatilin (MST) and its 12 analogs (MST-1-MST-12) were synthesized by wittig reaction, deacetylation and double bond reduction. All the structures were confirmed by 1H NMR, 13C NMR and ESI-MS. Bacterial lipopolysaccharide-induced mouse macrophage RAW264.7 inflammation model was used to conduct preliminary anti-inflammatory activity tests in vitro for the target compounds. Results showed that all compounds could inhibit the production of inflammatory factor NO, and that MST-5 exhibited the strongest anti-inflammatory activity (IC50= 0.428 μmol/L).Further exploration is expected for the study of the anti-inflammatory mechanism of MST-5.

Objective:To explore the predictive value of quantitative electroencephalogram (qEEG) in the poor outcome of children with non-traumatic disturbance of consciousness (DoC) in the pediatric intensive care unit (PICU).Methods:A prospective study was conducted. From January 2019 to May 2019, a total of 62 patients aged from 1 month to 11 years with non-traumatic DoC in the PICU of the First Affiliated Hospital of Bengbu Medical College were enrolled. Bedside monitoring with NicoletOne monitor was performed within 24 hours after admission, and qEEG parameters, including amplitude-integrated electroencephalogram (aEEG), relative alpha variability (RAV), relative band power (RBP), and spectral entropy (SE) were recorded. The state of consciousness was assessed with modified pediatric Glasgow coma scale (MPGCS) before monitoring. According to the pediatric cerebral performance category score at 1 year after discharge, the enrolled subjects were divided into good and poor outcome groups. The association between these variables and the poor outcome was analyzed by univariate and multivariate logistic regression analysis, and the predictive performance was analyzed by receiver operator characteristic (ROC) curve.Results:There were 39 males and 23 females, with the age of 12.0 (5.8, 24.0) months. Fifty patients (81%) were in the good outcome group and 12 patients (19%) in the poor outcome group. The univariate Logistic regression analysis showed that age ( OR=1.037, 95% CI 1.001-1.074, P=0.041), severe abnormal aEEG ( OR=128.000, 95% CI 10.274-1 594.656, P<0.01), RAV ( OR=0.877, 95% CI 0.810-0.949, P=0.001), SE ( OR=0.892, 95% CI 0.814-0.978, P=0.015), and MPGCS score ( OR=0.511, 95% CI 0.349-0.747, P=0.001) were significantly associated with the poor outcome. However, the multivariate Logistic regression analysis showed that only severe abnormal aEEG ( OR=315.692, 95% CI 6.091-16 362.298, P=0.004) and RAV ( OR=0.808, 95% CI 0.664-0.983, P=0.033) were significantly associated with the poor outcome. The area under the curve (AUC) of the aEEG and RAV in predicting the poor outcome were 0.848 (95% CI 0.735-0.927, P<0.01) and 0.847 (95% CI 0.733-0.926, P<0.01), respectively. The optimal cut-off value was severe abnormal for the aEEG and 38% for the RAV, with sensitivity of 67% and 83%, specificity of 98% and 84%, positive predictive value of 89% and 55%, negative predictive value of 92% and 95%, and Youden index of 0.647 and 0.673, respectively. The AUC of the novel combined index of aEEG and RAV for predicting the poor outcome was 0.974 (95% CI 0.898-0.998, P<0.01). Conclusions:The aEEG and RAV are reliable predictors for the poor outcome of children with non-traumatic DoC, and the novel combined index of aEEG and RAV can improve the predictive performance. The qEEG can be used as a routine method for outcome assessment due to its good objectivity.