Objective To observe the value of 18F-D3FSP PET/CT machine learning(ML)models for evaluating subjective cognitive decline(SCD).Methods Thirty-two SCD patients(SCD group)and 16 healthy volunteers(control group)who received 18F-D3FSP PET/CT were selected from Sino Longitudinal Study on Cognitive Decline(SILCODE)and divided into training set(n=34)and test set(n=14)at a ratio of 7∶3.Support vector machine(SVM),random forest(RF)and logistic regression(LR)models were constructed based on Hamilton anxiety scale(HAMA)and standard uptake value ratio(SUVR)of brain regions being significantly different between groups to evaluate SCD.Then PET/CT data were amplified by format conversion and divided into training set(including 8 775 CT images and 1 833 PET images)and test set(including 2 025 CT images and 423 PET images)at the ratio of 8∶2.VGG16 models were constructed based on CT and PET images to evaluate SCD,respectively.Results The area under the receiver operating characteristic curve(AUC)of SVM,RF and LR model for evaluating SCD in training set was all 1.000,while was 0.863,0.872 and 1.000 in test set,respectively.LR model was overfitting,and RF model had better performance.The accuracy of VGG16 model for evaluating SCD based on CT and PET images tended to be stable after the 175th and 150th iterations,with the highest accuracy of 67.11％ and 65.35％ in training set,which tended to be stable after the 165th and 145th iterations,with the highest accuracy of 62.43％ and 59.16％ in test set,respectively.Conclusion 18F-D3FSP PET/CT ML models could be used to evaluate SCD.

To address the issue of reduced signal quality of photoplethysmography caused by local fluctuation,an approach called locally orthogonal weighted polynomial fitting(LOWPF)is proposed for signal smoothing.After determining the positions of the fluctuation sequences using the forward-backward difference XOR method,weighted polynomial fitting is applied to these sequences,and the fitted values are used to replace the fluctuation sequences to achieve signal smoothing.By constructing orthogonal basis functions,the condition number of the coefficient matrix is reduced,and the stability of the equation system solution for higher-order fitting is improved.Simulation results demonstrate that the smoothed signal's XOR smoothness of the proposed method surpasses that of the moving average algorithm and the empirical mode decomposition reconstruction algorithm.The smoothing results on 241 sets of measured PPG signals show that LOWPF achieves an efficiency of smoothness of 89.10%,significantly higher than the 78.05%of empirical mode decomposition and the 59.13%of the 5-point moving average algorithm.LOWPF has promising application prospects for smoothing signals with significant local fluctuations.

To address the issue of reduced signal quality of photoplethysmography caused by local fluctuation,an approach called locally orthogonal weighted polynomial fitting(LOWPF)is proposed for signal smoothing.After determining the positions of the fluctuation sequences using the forward-backward difference XOR method,weighted polynomial fitting is applied to these sequences,and the fitted values are used to replace the fluctuation sequences to achieve signal smoothing.By constructing orthogonal basis functions,the condition number of the coefficient matrix is reduced,and the stability of the equation system solution for higher-order fitting is improved.Simulation results demonstrate that the smoothed signal's XOR smoothness of the proposed method surpasses that of the moving average algorithm and the empirical mode decomposition reconstruction algorithm.The smoothing results on 241 sets of measured PPG signals show that LOWPF achieves an efficiency of smoothness of 89.10%,significantly higher than the 78.05%of empirical mode decomposition and the 59.13%of the 5-point moving average algorithm.LOWPF has promising application prospects for smoothing signals with significant local fluctuations.

Objective To observe the value of 18F-D3FSP PET/CT machine learning(ML)models for evaluating subjective cognitive decline(SCD).Methods Thirty-two SCD patients(SCD group)and 16 healthy volunteers(control group)who received 18F-D3FSP PET/CT were selected from Sino Longitudinal Study on Cognitive Decline(SILCODE)and divided into training set(n=34)and test set(n=14)at a ratio of 7∶3.Support vector machine(SVM),random forest(RF)and logistic regression(LR)models were constructed based on Hamilton anxiety scale(HAMA)and standard uptake value ratio(SUVR)of brain regions being significantly different between groups to evaluate SCD.Then PET/CT data were amplified by format conversion and divided into training set(including 8 775 CT images and 1 833 PET images)and test set(including 2 025 CT images and 423 PET images)at the ratio of 8∶2.VGG16 models were constructed based on CT and PET images to evaluate SCD,respectively.Results The area under the receiver operating characteristic curve(AUC)of SVM,RF and LR model for evaluating SCD in training set was all 1.000,while was 0.863,0.872 and 1.000 in test set,respectively.LR model was overfitting,and RF model had better performance.The accuracy of VGG16 model for evaluating SCD based on CT and PET images tended to be stable after the 175th and 150th iterations,with the highest accuracy of 67.11％ and 65.35％ in training set,which tended to be stable after the 165th and 145th iterations,with the highest accuracy of 62.43％ and 59.16％ in test set,respectively.Conclusion 18F-D3FSP PET/CT ML models could be used to evaluate SCD.

Anaplastic lymphoma kinase(ALK)fusion is commonly observed in lung adenocarcinoma,with an incidence rate of 5%-7%.Due to the tumor heterogeneity in advanced non-small cell lung cancer,ALK fusion can also occur in lung squamous cell carcinoma.A mul-tidisciplinary team(MDT)combines various professional opinions and evidence-based medical principles to provide personalized treatment recommendations,particularly for complex cases.This study presents the MDT diagnostic and treatment approach for a patient with lung squamous cell carcinoma with an ALK mutation.Following initial diagnosis at stage ⅢB,the patient exhibited rapid disease progression with liver and brain metastases after sequence chemoradiotherapy.After genetic testing revealed ALK fusion,the patient was treated with the ALK inhibitor,lorlatinib,which resulted in tumor regression and a persistent partial response.

ObjectiveTo investigate the prevalence and influencing factors of overweight， obesity and central obesity among elderly residents in Xuhui District， and to analyze the epidemiological status of central obesity in elderly people with different body mass indexes. MethodsThe third round of health status and health service utilization monitoring data in Xuhui District was used. The information collected from questionnaire survey and physical examination were analyzed. SPSS 20.0 software was used for χ² test， trend χ² test and multinominal logistic regression analysis. Results5 096 survey subjects were included. The prevalence of overweight， general obesity， and central obesity in the residents aged 60 and above in Xuhui District were 34.3%， 6.5%， and 29.2%， respectively. There was gender difference in the rates of overweight， obesity， and central obesity among the residents. The overweight and central obesity rates in males were higher than those in females， while the obesity rate was lower than that in females （P<0.05）. Multinominal logistic regression analysis showed that in comparison with the normal weight non-central obesity group drinking only at party （OR=1.729， 95%CI： 1.184‒2.525）， and hypertension （OR=1.637， 95%CI： 1.305‒2.053）， were highly associated with normal weight with central obesity. Aged 60‒ years （OR=1.589， 95%CI： 1.190‒2.120）， aged 70‒ years （OR=1.763， 95%CI： 1.327‒2.342）， male （OR=1.379， 95%CI： 1.134‒1.676）， hypertension （OR=2.231， 95%CI： 1.878‒2.649）， former smokers （OR=1.437， 95%CI： 1.027‒2.011）， drinking at party only （OR=1.491， 95%CI： 1.107‒2.006）， and drinking ≥3 times per week （OR=1.611， 95%CI： 1.116‒2.325）， were highly associated with overweight combined with central obesity. Aged 60‒ years （OR=3.817， 95%CI： 2.251‒6.474）， aged 70‒ years （OR=3.084， 95%CI： 1.838‒5.175）， hypertension （OR=3.683， 95%CI： 2.753‒4.929）， diabetes （OR=2.085， 95%CI： 1.511‒2.878）， former smokers （OR=1.835， 95%CI： 1.043‒3.226）， were highly associated with compound obesity. Central obesity was found in the elderly residents with different BMI categories， and the rate of central obesity increased with the increase of BMI grade. ConclusionThe prevalence of overweight， obesity and central obesity among the elderly aged 60 years and above in Xuhui District is not optimistic. Attention should be paid to the elderly under 80 years old who are with hypertension and/or diabetes， alcohol consumption， low educational level and not doing physical exercise. Especially for the central obesity population with normal BMI， measures should be taken to prevent and intervene the occurrence of obesity and related diseases.

Objective:To evaluate the effectiveness and feasibility of 3D ResSE-Unet-based intelligent delineation of clinical target volume (CTV) in postoperative adjuvant radiotherapy for breast cancer.Methods:A total of 974 cases of breast cancer treated in the Cancer Diagnosis and Treatment Center of the Fourth Affiliated Hospital of Guangxi Medical University from September 2018 to June 2022 were enrolled in this study, including 614 cases receiving total mastectomy and 360 cases treated with breast-conserving surgery. They were divided into a training set, a validation set, and a testing set. The training set consisted of 874 cases and was used to build a model of 3D ResSE-Unet-based intelligent CTV delineation. The validation set comprised 40 cases and was used to evaluate the feasibility and effectiveness of the clinical application of AI-based CTV design in the radiotherapy for breast cancer. The testing set was composed of 60 cases and was used to test the accuracy of intelligent CTV. The Wilcoxon rank test was used to compare the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) obtained using the intelligent delineation model.Results:The intelligent delineation model showed high precision. The CTV of cases treated with total mastectomy (CTV cw) and the CTV of cases treated with breast-conserving surgery (CTV b) had DSCs greater than 0.80 and greater than 0.88, respectively. Therefore, compared with CTV cw, CTV b had a higher DSC (0.91 ± 0.03 vs.0.83 ± 0.05, t = 7.11, P < 0.05). Both CTV cw and CTV b had lower HD 95 [(7.56 ± 3.42) mm vs.(8.77 ± 5.89) mm] and ASD [(1.85 ± 0.71) mm vs.(1.86 ± 0.83)mm], without statistically significant difference ( P > 0.05). The left/right supraclavicular and infraclavicular CTV (CTV2) had DSCs greater than 0.8. CTV2 also had low average HD95 and ASD, without statistically significant difference ( P > 0.05). Conclusions:The 3D ResSE-Unet-based intelligent CTV delineation has better consistency and feasibility in postoperative adjuvant radiotherapy for breast cancer, especially the CTVs after breast-conserving surgery.

Non-small cell lung cancer (NSCLC) is the most common type of lung cancer, and immunotherapy has become a relatively common treatment for NSCLC. The use of biomarkers to screen out people with high benefit from immunotherapy could help to timely grasp the therapeutic information of NSCLC patients and meet the current challenges faced by immunotherapy. Compared with traditional markers such as programmed death-ligand protein 1(PD-L1) expression fraction, circulating biomarkers have the characteristics of non-invasion, convenient collection of materials, and dynamically evaluating the prognosis of patients and observing the efficacy of immunotherapy in the process of immunotherapy, which has a broad application prospect.

With the progress of gene detection technology and the speed-up in new drug development, biological target therapy has fully covered the first-line treatment of advanced NSCLC. Immunotherapy has significantly improved the survival of advanced NSCLC patients with negative driven genes, and the median OS reaches about 2 years (15.6-30 months). EGFR is the most common driven gene. According to different EGFR mutation subtypes (L858R or 19del), different treatment mode (EGFR-TKI single drug, TKI combined with anti-vascular drugs and TKI combined with chemotherapy) is selected as the first-line treatment, which has become a consensus. Depending on the data of median PFS, the treatment efficacy against rare targets is more prominent, which has exceeded the efficacy of standard chemotherap:ALK (alectinib, PFS=34.8 months), ROS1 (ceritinib, PFS=19.3 months), RET (selpercatinib, PFS=18.4 months), BRAF (dabrafenib plus trametinib, PFS=14.6 months), NTRK (larotrectinib, PFS≥12 months) and MET (savolitinib, PFS=9.7 months). In conclusion, the first-line treatment of advanced NSCLC has entered the era of“precision-targeted treatment”based on different molecular typing, and it has become a consensus that high-throughput sequencing is required for newly diagnosed patients.

Objective To investigate the effects of simulated microgravity by rotary cell culture system (RCCS) on expression profiles of miRNA in mouse fibroblasts L929 cell line.Methods L929 cells were cultured in vitro and divided into simulated microgravity (SMG) group and normal gravity (NG) group according to the simple random method.Samples of two groups were collected on 7th day of culture and the total RNAs were extracted,labeled,and hybridized in sequence.Feature Extraction Software was used to collect the array images and get raw data,which were analyzed by Genespring Software.Differentially expressed miRNAs were identified and then validated by qRT-PCR.Target genes of differentially expressed miRNAs were predicted by the databases of Targetscan and microRNAorg,and the intersections of databases were identified as potential regulatory target genes.Gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG) analysis were applied to determine the roles of these target genes.Relevant biological functions and/or signaling pathways of the regulated genes especially related with wound healing process were categorized based on their enrichments.Then integration predictions of the miRNA and mRNA expression profiles had been proposed to refine the functional miRNA-mRNA relationships.The miRNA-mRNA functional network and miRNA-mRNA control network were constructed.Results Four miRNA genes were up-regulated significantly including mmumiR-669j,-122-5p,-30a-3p,-6516-3p,among which mmu-miR-669j was up-regulated at 52.84 folds with the greatest significance (P ＜ 0.05).Seventeen miRNA genes were down-regulated significantly including mmu-miR-21a-3p,-miR-28a-5p,-218-5p,-210-3p,-miR-19a-3p,-miR-31-3p,and-miR-19b-3p,among which mmu-miR-28a-5p was down-regulated at 15.47 folds with the greatest significance (P ＜ 0.05).The qRT-PCR showed a high concordance with the microarray results (P ＜ 0.05).Target gene prediction and functional enrichment analysis suggested that a variety of biological processes and signaling pathways involved in wound repair were significantly enriched (P ＜ 0.05).Function network and regulation network of miRNA-mRNA covered all the differentially expressed miRNAs,which suggested that miR-21 a-3p and predicted target gene Smad3 might play an important role in wound healing under microgravity.Conclusions Simulated microgravity by RCCS can significantly affect the expression of stress-related miRNAs in mouse fibroblasts L929.The miRNA target gene prediction and functional enrichment analysis based on gene chip technology may provide theoretical basis for illustrating the mechanism and management of weightlessness stress injury.