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.

Objective To investigate extended high-frequency hearing in young adults and to analyse its char-acteristics.Methods A total of 230 freshmen(101 males and 129 females,aged 17-19 years old)from the class of 2023 at the Air Force Medical University underwent audiometric tests,including acoustic impedance,conventional frequency and extended high-frequency audiometry,and distortion product otoacoustic emissions(DPOAE).Ac-cording to the results of extended high-frequency audiometry,the students were divided into normal and abnormal groups,and the hearing thresholds at conventional frequencies were compared between the two groups.Results Of the 230 students,47.83％(110/230)showed abnormal extended high-frequency hearing.The hearing thresholds of the right ear were 1 to 3 dB higher than those of the left ear at most frequencies.The hearing thresholds of the ab-normal group were higher than those of the normal group in the conventional frequencies(P＜0.05).The difference in extended high-frequency thresholds between the two groups increased with higher frequency.Conclusion Ex-tended high-frequency hearing loss occurs earlier,and has a higher prevalence in young adults,and right ear hearing is worse than that of left ear.Extended high-frequency audiometry can be used as a predictive tool for detecting con-ventional frequency hearing loss.

Objective To investigate extended high-frequency hearing in young adults and to analyse its char-acteristics.Methods A total of 230 freshmen(101 males and 129 females,aged 17-19 years old)from the class of 2023 at the Air Force Medical University underwent audiometric tests,including acoustic impedance,conventional frequency and extended high-frequency audiometry,and distortion product otoacoustic emissions(DPOAE).Ac-cording to the results of extended high-frequency audiometry,the students were divided into normal and abnormal groups,and the hearing thresholds at conventional frequencies were compared between the two groups.Results Of the 230 students,47.83％(110/230)showed abnormal extended high-frequency hearing.The hearing thresholds of the right ear were 1 to 3 dB higher than those of the left ear at most frequencies.The hearing thresholds of the ab-normal group were higher than those of the normal group in the conventional frequencies(P＜0.05).The difference in extended high-frequency thresholds between the two groups increased with higher frequency.Conclusion Ex-tended high-frequency hearing loss occurs earlier,and has a higher prevalence in young adults,and right ear hearing is worse than that of left ear.Extended high-frequency audiometry can be used as a predictive tool for detecting con-ventional frequency hearing loss.

METHODS: We retrospectively collected CT scan data from 276 patients with pathologically confirmed primary bone tumors from 4 medical centers in Guangdong Province between January, 2010 and August, 2021. A convolutional neural network (CNN) was employed as the deep learning architecture. The optimal baseline deep learning model (R-Net) was determined through transfer learning, and an optimized model (S-Net) was obtained through algorithmic improvements. Multivariate logistic regression analysis was used to screen the clinical features such as sex, age, mineralization location, and pathological fractures, which were then connected with the imaging features to construct the deep learning fusion model (SC-Net). The diagnostic performance of the SC-Net model and machine learning models were compared with radiologists' diagnoses, and their classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) and F1 score. RESULTS: In the external test set, the fusion model (SC-Net) achieved the best performance with an AUC of 0.901 (95% CI: 0.803-1.00), an accuracy of 83.7% (95% CI: 69.3%-93.2%) and an F1 score of 0.857, and outperformed the S-Net model with an AUC of 0.818 (95% CI: 0.694-0.942), an accuracy of 76.7% (95% CI: 61.4%-88.2%), and an F1 score of 0.828. The overall classification performance of the fusion model (SC-Net) exceeded that of radiologists' diagnoses. CONCLUSIONS The deep learning fusion model based on multi-center CT images and clinical features is capable of accurate classification of osseous and chondroid matrix mineralization and may potentially improve the accuracy of clinical diagnoses of osteogenic versus chondrogenic primary bone tumors.
Humans ; Deep Learning ; Bone Neoplasms/diagnostic imaging* ; Retrospective Studies ; Tomography, X-Ray Computed/methods* ; Neural Networks, Computer ; Male ; Female ; ROC Curve ; Algorithms

Objective To minimize variations in treatment outcomes of L5/S1 percutaneous intervertebral radiofrequency thermocoagulation(PIRFT)arising from physician proficiency and achieve precise quantitative risk assessment of the puncture paths.Methods We used a self-developed deep neural network DWT-UNet for automatic segmentation of the magnetic resonance(MR)images of the L5/S1 segments into 7 key structures:L5,S1,Ilium,Disc,N5,Dura mater,and Skin,based on which a needle insertion path planning environment was modeled.Six hard constraints and 6 soft constraints were proposed based on clinical criteria for needle insertion,and the physician's experience was quantified into weights using the analytic hierarchy process and incorporated into the risk function for needle insertion paths to enhance individual case adaptability.By leveraging the proposed skin entry point sampling sub-algorithm and Kambin's triangle projection area sub-algorithm in conjunction with the analytic hierarchy process,and employing various technologies such as ray tracing,CPU multi-threading,and GPU parallel computing,a puncture path was calculated that not only met clinical hard constraints but also optimized the overall soft constraints.Results A surgical team conducted a subjective evaluation of the 21 needle puncture paths planned by the algorithm,and all the paths met the clinical requirements,with 95.24%of them rated excellent or good.Compared with the physician's planning results,the plans generated by the algorithm showed inferior DIlium,DS1,and Depth(P<0.05)but much better DDura,DL5,DN5,and AKambin(P<0.05).In the 21 cases,the planning time of the algorithm averaged 7.97±3.73 s,much shorter than that by the physicians(typically beyond 10 min).Conclusion The multi-constraint optimal puncture path planning algorithm offers an efficient automated solution for PIRFT of the L5/S1 segments with great potentials for clinical application.

Background::Atopic dermatitis (AD) affects approximately 10% of adults worldwide. CM310 is a humanized monoclonal antibody targeting interleukin-4 receptor alpha that blocks interleukin-4 and interleukin-13 signaling. This trial aimed to evaluate the efficacy and safety of CM310 in Chinese adults with moderate-to-severe AD.Methods::This multicenter, randomized, double-blind, placebo-controlled, phase 2b trial was conducted in 21 medical institutions in China from February to November 2021. Totally 120 eligible patients were enrolled and randomized (1:1:1) to receive subcutaneous injections of 300 mg CM310, 150 mg CM310, or placebo every 2 weeks for 16 weeks, followed by an 8-week follow-up period. The primary endpoint was the proportion of patients achieving ≥75% improvement in the Eczema Area and Severity Index (EASI-75) score from baseline at week 16. Safety and pharmacodynamics were also studied.Results::At week 16, the proportion of EASI-75 responders from baseline was significantly higher in the CM310 groups (70% [28/40] for high-dose and 65% [26/40] for low-dose) than that in the placebo group (20%[8/40]). The differences in EASI-75 response rate were 50% (high vs. placebo, 95% CI 31%–69%) and 45% (low vs. placebo, 95% CI 26%–64%), with both P values <0.0001. CM310 at both doses also significantly improved the EASI score, Investigator’s Global Assessment score, daily peak pruritus Numerical Rating Scale, AD-affected body surface area, and Dermatology Life Quality Index compared with placebo. CM310 treatment reduced levels of thymus and activation-regulated chemokine, total immunoglobulin E, lactate dehydrogenase, and blood eosinophils. The incidence of treatment-emergent adverse events (TEAEs) was similar among all three groups, with the most common TEAEs reported being upper respiratory tract infection, atopic dermatitis, hyperlipidemia, and hyperuricemia. No severe adverse events were deemed to be attributed to CM310. Conclusion::CM310 at 150 mg and 300 mg every 2 weeks demonstrated significant efficacy and was well-tolerated in adults with moderate-to-severe AD.Trial Registration::ClinicalTrials.gov, NCT04805411.

Objective To minimize variations in treatment outcomes of L5/S1 percutaneous intervertebral radiofrequency thermocoagulation(PIRFT)arising from physician proficiency and achieve precise quantitative risk assessment of the puncture paths.Methods We used a self-developed deep neural network DWT-UNet for automatic segmentation of the magnetic resonance(MR)images of the L5/S1 segments into 7 key structures:L5,S1,Ilium,Disc,N5,Dura mater,and Skin,based on which a needle insertion path planning environment was modeled.Six hard constraints and 6 soft constraints were proposed based on clinical criteria for needle insertion,and the physician's experience was quantified into weights using the analytic hierarchy process and incorporated into the risk function for needle insertion paths to enhance individual case adaptability.By leveraging the proposed skin entry point sampling sub-algorithm and Kambin's triangle projection area sub-algorithm in conjunction with the analytic hierarchy process,and employing various technologies such as ray tracing,CPU multi-threading,and GPU parallel computing,a puncture path was calculated that not only met clinical hard constraints but also optimized the overall soft constraints.Results A surgical team conducted a subjective evaluation of the 21 needle puncture paths planned by the algorithm,and all the paths met the clinical requirements,with 95.24%of them rated excellent or good.Compared with the physician's planning results,the plans generated by the algorithm showed inferior DIlium,DS1,and Depth(P<0.05)but much better DDura,DL5,DN5,and AKambin(P<0.05).In the 21 cases,the planning time of the algorithm averaged 7.97±3.73 s,much shorter than that by the physicians(typically beyond 10 min).Conclusion The multi-constraint optimal puncture path planning algorithm offers an efficient automated solution for PIRFT of the L5/S1 segments with great potentials for clinical application.

Pulmonary blast injury has become the main type of trauma in modern warfare, characterized by externally mild injuries but internally severe injuries, rapid disease progression, and a high rate of early death. The injury is complicated in clinical practice, often with multiple and compound injuries. Currently, there is a lack of effective protective materials, accurate injury detection instrument and portable monitoring and transportation equipment, standardized clinical treatment guidelines in various medical centers, and evidence-based guidelines at home and abroad, resulting in a high mortality in clinlcal practice. Therefore, the Trauma Branch of Chinese Medical Association and the Editorial Committee of Chinese Journal of Trauma organized military and civilian experts in related fields such as thoracic surgery and traumatic surgery to jointly develop the Clinical treatment guideline for pulmonary blast injury ( version 2023) by combining evidence for effectiveness and clinical first-line treatment experience. This guideline provided 16 recommended opinions surrounding definition, characteristics, pre-hospital diagnosis and treatment, and in-hospital treatment of pulmonary blast injury, hoping to provide a basis for the clinical treatment in hospitals at different levels.

OBJECTIVE To investigate the mechanism of Fuke duanhongyin capsule in improving dysfunctional uterine bleeding （DUB） in rats. METHODS Pregnant SD rats were randomly divided into blank control group （distilled water）， model control group （distilled water） and Fuke duanghongyin capsule group （1.296 g/kg）， with 6 rats in each group. Except for blank control group， DUB model was established in other groups. After modeling， they were given relevant medicine/distilled water 10 mL/kg intragastrically， once a day， for consecutive 14 d. After medication， uterine index， ovary index and hemorheology indexes （whole blood high shear relative index， whole blood low shear relative index， erythrocyte aggregation index， Carson viscosity） of rats were all determined. The pathological changes of uterus and ovary tissues were observed； mRNA relative expression levels of epidermal growth factor （EGF）， hypoxia-inducible factor 1α （HIF-1α）， epidermal growth factor receptor （EGFR） and serine/ threonine-protein kinase 1（AKT1）， and protein relative expression levels of EGF and EGFR in uterine tissue were all measured. RESULTS Compared with model control group， the uterine index， ovary index， erythrocyte aggregation index were all decreased significantly in Fuke duanghongyin capsule group （P＜0.05 or P＜0.01）； whole blood high shear relative indexes， mRNA relative expression levels of EGF， HIF-1α and EGFR and protein relative expression levels of EGF and EGFR in uterine tissue were all increased significantly （P＜0.05 or P＜0.01）. The pathological changes of ovary and uterus were improved. CONCLUSIONS Fuke duanhongyin capsule can improve DUB in rat， the mechanism of which may be related to the activation of EGF-EGFR signaling pathway.

Objective:To investigate the application value of contrast-enhanced ultrasound combined with serum CXC chemokine ligand 8 (CXCL8) and CXC chemokine receptor 2 (CXCR2) levels detection in the efficacy evaluation of patients with primary liver cancer after transcatheter arterial chemoembolization (TACE) .Methods:A total of 80 patients with primary liver cancer who were diagnosed and treated in Huanggang Central Hospital of Hubei Province from June 2019 to January 2022 were selected as the research objects. The therapeutic efficacy was evaluated 2 months after TACE treatment. According to the pathological diagnosis, the patients were divided into complete inactivation group ( n=30) and residual lesion group ( n=50) . The levels of serum CXCL8 and CXCR2 were measured by enzyme linked immunosorbent assay (ELISA) double antibody sandwich method, and contrast-enhanced ultrasonography was performed on the patients. Receiver operating characteristic (ROC) curve was applied to analyze the value of serum CXCL8 and CXCR2 in evaluating the efficacy of TACE in patients with primary liver cancer. Kappa test was applied to test the consistency of contrast-enhanced ultrasound and contrast-enhanced ultrasound combined with serum CXCL8 and CXCR2 in evaluating the efficacy of TACE in patients with primary liver cancer and the results of pathological diagnosis. Results:Compared with the complete inactivation group, the levels of serum CXCL8 [ (7.12±1.68) ng/ml vs. (5.07±1.25) ng/ml] and CXCR2 [ (3.62±0.79) ng/ml vs. (2.43±0.67) ng/ml] in the residual lesion group were obviously higher ( t=5.79, P<0.001; t=6.89, P<0.001) . The areas under the curve of CXCL8 and CXCR2 in evaluating the efficacy of TACE in patients with primary liver cancer were 0.827 and 0.801 respectively, the specificities were 73.3% and 76.7%, and the sensitivities were 70.0% and 72.0% respectively. The concordance between contrast-enhanced ultrasound and pathological diagnosis was moderate, and the Kappa value was 0.49 ( P<0.001) . The concordance between contrast-enhanced ultrasound combined with serum CXCL8 and CXCR2 and pathological diagnosis was high, and the Kappa value was 0.62 ( P<0.001) . The sensitivity of contrast-enhanced ultrasound combined with serum CXCL8 and CXCR2 in evaluating the efficacy of TACE in patients with primary liver cancer was 90.0%, which was higher than the sensitivity of contrast-enhanced ultrasound (72.0%, χ2=5.26, P=0.022) , CXCL8 (70.0%, χ2=6.25, P=0.012) and CXCR2 (72.0%, χ2=5.26, P=0.022) . Conclusion:Contrast-enhanced ultrasound can detect residual lesions after TACE in patients with primary liver cancer to a certain extent, and its combination with serum CXCL8 and CXCR2 can effectively improve the evaluation efficiency of the efficacy of TACE treatment in patients with primary liver cancer.