Due to its high sensitivity and non-destructive nature, Raman spectroscopy has become an essential analytical tool in biopharmaceutical analysis and drug development. Despite of the computational demands, data requirements, or ethical considerations, artificial intelligence (AI) and particularly deep learning algorithms has further advanced Raman spectroscopy by enhancing data processing, feature extraction, and model optimization, which not only improves the accuracy and efficiency of Raman spectroscopy detection, but also greatly expands its range of application. AI-guided Raman spectroscopy has numerous applications in biomedicine, including characterizing drug structures, analyzing drug forms, controlling drug quality, identifying components, and studying drug-biomolecule interactions. AI-guided Raman spectroscopy has also revolutionized biomedical research and clinical diagnostics, particularly in disease early diagnosis and treatment optimization. Therefore, AI methods are crucial to advancing Raman spectroscopy in biopharmaceutical research and clinical diagnostics, offering new perspectives and tools for disease treatment and pharmaceutical process control. In summary, integrating AI and Raman spectroscopy in biomedicine has significantly improved analytical capabilities, offering innovative approaches for research and clinical applications.

Atrial fibrillation(AF)is the most common cardiac arrhythmia.Many medical conditions,including hypertension,diabetes,obesity,sleep apnea,and heart failure(HF),increase the risk for AF.Car-diomyocytes have unique metabolic characteristics to maintain adenosine triphosphate production.Significant changes occur in myocardial metabolism in AF.Glucagon-like peptide-1 receptor agonists(GLP-1 RAs)have been used to control blood glucose fluctuations and weight in the treatment of type 2 diabetes mellitus(T2DM)and obesity.GLP-1 RAs have also been shown to reduce oxidative stress,inflammation,autonomic nervous system modulation,and mitochondrial function.This article reviews the changes in metabolic characteristics in cardiomyocytes in AF.Although the clinical trial outcomes are unsatisfactory,the findings demonstrate that GLP-1 RAs can improve myocardial metabolism in the presence of various risk factors,lowering the incidence of AF.

Objective To investigate the value of intravoxel incoherent motion diffusion weighted imaging(IVIM-DWI)in quantitatively evaluating the involved muscle in idiopathic inflammatory myopathies(IIM).Methods Totally,50 patients with clinically diagnosed IIM(IIM group)and 15 healthy controls(control group)were selected for bilateral thigh MRI examination,including IVIM-DWI sequences.The right quadriceps(vastus lateralis,vastus intermedius,vastus medialis,and rectus femoris)of all subjects were selected as region of interest(ROI).Single-exponential and double-exponential analysis were employed to quantitatively measure IVIM-DWI parameters,including apparent diffusion coefficient(ADC),D,f,and D*.Based on T1WI and T2WI fat-suppressed images of the right quadriceps,these muscles were divided into affected and unaffected groups.One-way analysis of variance was used to compare IVIM-DWI parameters between affected group,unaffected group,and control group.Receiver operating characteristic(ROC)curve was performed to analyze the differences in IVIM-DWI parameters among the above groups.Results The D and ADC values were significantly higher in the affected group compared to the unaffected group and the control group(P＜0.001).ROC curve analysis revealed that D and ADC values had moderate diagnostic significance with area under the curve(AUC)of 0.794 and 0.882,respec-tively.The cutoff values for D values and ADC values were 1.63×10-3 mm2/s and 1.44×10-3 mm2/s,respectively.Additionally,MRI follow-up performed one year after treatment in three patients with IIM showed significant resolution of inflammatory edema in thigh muscles,accompanied by a marked decrease in IVIM-DWI parameter values,particularly D values and ADC values.Conclusion The affected muscle in IIM show distinctive diffusion characteristics,and IVIM-DWI parameters,especially D values and ADC val-ues,show a higher diagnostic value for assessing muscle status in IIM.In addition,IVIM-DWI parameters also demonstrate a promis-ing value in the follow-up of IIM,which requires further confirmation in larger cohorts.

Background::Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.Methods::This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Na?ve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.Results::The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726. Conclusions::Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Objective:To investigate the values of two-dimensional and three-dimensional echocardiographic parameters in predicting pulmonary vascular resistance (PVR) in chronic pulmonary thromboembolic pulmonary hypertension (CTEPH).Methods:A total of 141 patients diagnosed with CTEPH in China-Japan Friendship Hospital from November 2015 to December 2022 were included. Two-dimensional echocardiographic indicators reflecting PVR were constructed according to the calculation formula of PVR: echocardiographic estimated systolic pulmonary artery pressure (sPAP Echo)/left ventricular end-diastolic diameter (LVIDd), echocardiographic estimated mean pulmonary artery pressure (mPAP Echo)/LVIDd. sPAP Echo/left ventricular end-diastolic volume (LVEDV), sPAP Echo/left ventricular cardiac output (LVCO) were measured by three-dimensional echocardiography. The correlations between two-dimensional and three-dimensional echocardiographic ratios and invasive PVR were then analyzed using the Spearman correlation method. Using receiver operating characteristic curve analysis, cut-off values for the ratios were generated to identify patients with PVR>1 000 dyn·s -1·cm -5. Pre- and postoperative hemodynamics and echocardiographic data were analyzed, as well as the correlation between the reduction rate of the echocardiographic index and PVR in 54 patients who underwent pulmonary endarterectomy (PEA). Results:sPAP Echo/LVIDd, sPAP Echo/LVEDV and sPAP Echo/LVCO were moderately correlated with PVR( rs=0.62, 0.52, 0.63, both P<0.001). The ratio of sPAP Echo to LVEDV, when greater than or equal to 1.41, had a sensitivity of 0.800 and a specificity of 0.930 for determining PVR >1 000 dyn·s -1·cm -5 (AUC=0.860, P<0.001). Similarly, the ratio of sPAP Echo to LVIDd, when greater than or equal to 2.14, had a sensitivity of 0.647 and a specificity of 0.861 for determining PVR >1000 dyn·s -1·cm -5 (AUC=0.830, P<0.001). The sPAP Echo/LVIDd and mPAP Echo/LVIDd significantly decreased after PEA (both P<0.001). The sPAP Echo/LVIDd and mPAP Echo/LVIDd reduction rate (ΔsPAP Echo/LVIDd and ΔmPAP Echo/LVIDd) were significantly correlated with PVR reduction rate (ΔPVR), respectively ( rs=0.61, 0.63, both P<0.05). Conclusions:Two-dimensional ratio sPAP Echo/LVIDd and three-dimensional ratio sPAP Echo/LVEDV can be used to noninvasively estimate PVR in CTEPH patients. The conventional ratio sPAP Echo/LVIDd is convenient and reproducibly suitable for monitoring the improvement of PVR before and after treatment, and its ratio of 2.14 can predict the significant increase of PVR in CTEPH patients (>1 000 dyn·s -1·cm -5).

Objective:This paper summarized the practical experience in the construction of a scientific research platform in a large comprehensive hospital and discusses the innovative management model of the scientific research platform.Methods:This paper introduced the development history and construction status of a scientific research platform in a large comprehensive hospital, and analyzes the contradictions and difficulties existing in equipment sharing, resource allocation and other aspects during the development of the scientific research platform and its countermeasures.Results:Building a strong scientific research platform was of great significance to the hospital's discipline development, talent cultivation, and improvement of academic influence and core competitiveness. The hospital should continue to increase investment in the construction of scientific research platforms and strengthen system layout, cooperation, exchanges, and resource sharing.Conclusions:Large comprehensive hospitals need to build a highly open and efficient scientific research platform system to empower technological innovation.

Objective:To analyze the curative effect of sandwich cheiloplasty for the treatment of macrocheilia secondary to port-wine stain (PWS).Methods:A total of 43 patients, including 20 males and 23 females, aged 37.0 years (ranged from 4 to 69 years), who underwent sandwich cheiloplasty for the treatment of macrocheilia secondary to PWS from March 2008 to March 2022 were retrospectively enrolled. According to the location of the lesions, they were divided into two groups: upper lip group (21 cases) and lower lip group (22 cases). Pathological examinations were performed in all excised specimens. Postoperative attentions should be paid to keeping incisions locally clean, observing the blood supplying, and taking care of fluid accumulation or incision split. After discharge, the lip appearance and function were evaluated every six months in the outpatient department, and the long-term efficacy was further divided into three levels: grade Ⅰ (poor), grade Ⅱ (moderate), and grade Ⅲ (good). The comparison of grade data named long-term efficacy between the two groups was conducted by Mann-Whitney U test.Results:All 43 patients underwent sandwich cheiloplasty, of which 40 patients received one operation, whereas the other 3 received two due to recurrences. One-stage incision healing was achieved in 43 cases, whereas partial mucosal necrosis appeared in 2 cases, and slight incision dehiscence occurred in 1 case, which healed well after local dressing change. The pathological examination results of 43 excised tissue specimens all showed capillary malformations. After follow-up for 1 to 10 years, long-term efficacy evaluation was made up as follows: 36 cases were evaluated as grade Ⅲ, 7 cases as grade Ⅱ, and 0 case as grade Ⅰ. There were 18 cases of grade Ⅲ, and 3 cases of grade Ⅱ in group A, compared to 18 cases of grade Ⅲ, and 4 cases of grade Ⅱ in group B. By rank sum test, there was no significant difference in overal efficacy between the two groups ( Z=0.342, P>0.05). Conclusions:Sandwich cheiloplasty for the treatment of macrocheilia secondary to PWS effectively removes malformed vascular lesions, and consequently, it can achieve a good long-term therapeutic effect.

Objective:To study the regulatory effect of miR-200a on mesenchymal-epithelial transition factor (MET) and its impact on the biological behavior of hepatoma carcinoma cells.Method:A luciferase reporter assay was used to determine miR-200a's regulatory impact on MET. Human hepatoma HepG2 cells were divided into a control group, a miR-200a group, a MET overexpression group, and a co-transfection group (miR-200a+MET). After culture, cell proliferation ability, cell migration ability, apoptosis, cell invasion ability, and the expression of MET and apoptosis-related (Bcl-2, Caspase-3, Bax) proteins were detected and observed by cell counting kit-8 (CCK-8), scratch assay, Annexin V-FITC staining, transwell chambers, and western blotting. The two groups were compared using the independent sample t-test. The multiple groups were statistically analyzed using one-way ANOVA.Results:The luciferase experiment showed that miR-200a had target MET. The proliferation rate, number of invasions in cells (55.00 ± 7.21, 85.00 ± 7.94, 164.67 ± 19.22, 104.00± 12.29), scratch healing rate (28.33% ± 5.03%, 61.67% ± 4.04%, 74.67% ± 7.02%, 49.33% ± 9.02%), and expression levels of MET, Bcl-2, and Caspase-3 proteins were lower in the miR-200a group than those in the control group, MET overexpression group, and co-transfection group, while the MET overexpression group had higher indexes than the other three groups, with statistically significant differences between the groups ( P <0.05). The apoptosis rate of HepG2 cells and the expression level of Bax protein were higher in the miR-200a group than those in the control group, MET overexpression group, and co-transfection group (19.25% ± 2.98%, 6.80% ± 1.15%, 3.42% ±0.76%, 9.90% ± 2.72%), while the levels of various indexes in the MIF overexpression group were lower than those in the other three groups. The control group and co-transfection group were between the two groups, and the difference between the groups was statistically significant ( P <0.05). Conclusion:HepG2 cell proliferation, migration, invasion, and cell apoptosis induction can be inhibited by miR-200a, and the functional mechanism for this may be associated with the miR-200a target’s ability to down-regulate MET expression in HepG2 cells.