In recent years, cardiovascular disease has become a common disease. With the development of machine learning and big data technologies, the processing ability of electrocardiogram (ECG) signals has been greatly enhanced through new computer technologies, enabling the auxiliary diagnosis technology for cardiovascular disease (CVD) to achieve new improvements. This article discusses the application of machine learning in ECG processing, especially in the auxiliary diagnosis of diseases. Firstly, the conventional signal preprocessing methods are introduced, and then the EEG signal processing methods based on feature extraction and fuzzy classification are explored. Secondly, the application of auxiliary diagnosis in CVD is further summarized. Finally, the advantages and disadvantages of the two methods are analyzed, and based on this, a design of an auxiliary diagnostic system compatible with the two methods is proposed, providing a new perspective for similar applied researches in the future.
Machine Learning ; Cardiovascular Diseases/diagnosis* ; Humans ; Electrocardiography ; Signal Processing, Computer-Assisted ; Diagnosis, Computer-Assisted ; Fuzzy Logic ; Electroencephalography

Objective:To evaluate the diagnostic value of MRI findings in differentiating between tophus and giant cell tumors of the tendon sheath (GCTTS) in the knee.Methods:The study was a case-control study. The clinical and MRI data of patients diagnosed with knee tophus or GCTTS was retrospectively analyzed at the Affiliated Hospital of Qingdao University from September 2018 to September 2024. The study included 23 cases of tophus and 22 cases of GCTTS. MRI sequences, including T 1WI, fat-suppressed T 2WI, and proton density weighted imaging, were evaluated. Parameters including lesion signal intensity and homogeneity, margin, maximum diameter, location (inside or outside the synovial cavity), ligament/tendon involvement, ligament/tendon parenchymal changes, adjacent bone erosion, bone marrow edema, synovial hyperplasia, joint effusion, and periarticular soft tissue swelling were recorded. Independent sample t-tests, χ2 tests, or Fisher exact tests were used to compare MRI findings between the two groups. Multivariate logistic regression was performed to identify independent predictive factors. Results:Significant differences in terms of maximum diameter, location (inside or outside the synovial cavity), ligament/tendon involvement, ligament/tendon parenchymal changes, adjacent bone erosion, bone marrow edema, and periarticular soft tissue swelling between the two groups were found (all P<0.05). No significant differences for other parameters were observed (all P>0.05). Lesion location and ligament/tendon parenchymal involvement demonstrated the highest sensitivity and specificity for distinguishing the two diseases. The sensitivity and specificity values for lesion location were 0.78 and 0.95. The sensitivity and specificity values for ligament/tendon involvement were 0.78 and 1.00. Multivariate logistic regression identified lesion location (inside or outside the synovial cavity) as an independent predictor for differentiating tophus from GCTTS ( OR=31.48, 95% CI 1.58-625.69, P=0.024). Conclusion:The location of the lesion (inside or outside the synovial cavity) and involvement of ligament/tendon parenchyma are critical factors in differentiating knee tophus from GCTTS. Additionally, lesion location serves as an independent predictor for distinguishing between the two conditions.

Objective To investigate the effects of different anesthesia depths on stress states and inflammatory mediators in patients undergoing video-assisted thoracoscopic lobectomy.Methods A total of 89 lung cancer patients who underwent video-assisted thoracoscopic lobectomy were selected as study subjects.Based on intraoperative bispectral index(BIS)range,the patients were divided into deep anesthesia group(BIS of 40 to＜50,n=45)and shallow anesthesia group(BIS of 50 to＜60,n=44).Vital signs(mean arterial pressure,heart rate and blood oxygen saturation),anesthesia re-covery time,extubation time,dosage of vasoactive drugs,postoperative pain intensity[Visual Ana-logue Scale(VAS)],postoperative analgesic dosage,perioperative stress state[prostaglandin E2(PGE2),nerve growth factor(NGF)and substance P(SP)],levels of inflammatory mediators[neuron-specific enolase(NSE),tumor necrosis factor-α(TNF-α)and S100β protein]at different time points(before anesthesia induction,immediately after intubation,before lesion resection and at the end of surgery)and the incidence of anesthesia-related adverse reactions were compared between the two groups.Results Before lesion resection and at the end of surgery,the mean arterial pressure and heart rate in the deep anesthesia group were significantly lower than those in the shallow anesthe-sia group(P＜0.05).The anesthesia recovery time and extubation time in the deep anesthesia group were significantly longer than those in the shallow anesthesia group(P＜0.05).At the end of surgery and on postoperative day one,the levels of PGE2,NGF and SP in the deep anesthesia group were significantly lower than those in the shallow anesthesia group,while the levels f NSE,TNF-α and S100β protein were significantly higher than those in the shallow anesthesia group(P＜0.05).There were no significant differences in the dosage of vasoactive drugs,VAS scores,sufentanil dos-age and the incidence of anesthesia-related adverse reactions between thetwo groups(P＞0.05).Conclusion During one-lung ventilation in patients undergoing video-assisted thoracoscopic surgery lobectomy,deep anesthesia can effectively control surgical stress and maintain stability of intraopera-tive hemodynamics,but it is associated with delayed postoperative awakening and more pronounced inflammatory response.Shallow anesthesia results in faster postoperative awakening and lower levels of inflammatory mediators,but it is associated with more significant intraoperative stress response and unstable hemodynamics.

Objective:To explore the predictive value of preoperative CT angiography (CTA) for incomplete endothelialization of the occluder after left atrial appendage closure (LAAC) in patients with atrial fibrillation.Methods:The clinical data of 92 atrial fibrillation patients underwent LAAC in the Tangdu Hospital of Air Force Military Medical University from January 2022 to June 2024 were retrospectively analyzed. CTA examinations were performed both before operation and 3 months after operation. Before operation, the long diameter of left atrial appendage opening, short diameter of left atrial appendage opening, area of left atrial appendage opening, diameter of anchoring area and effective depth were measured. After operation, the condition of occluder endothelialization was evaluated, and the patients were divided into the completely endothelialization group and the incomplete endothelialization group. Multivariate Logistic regression analysis was used to analyze the independent risk factors of occluder incomplete endothelialization after LAAC in patients with atrial fibrillation. The predictive value of independent risk factors was evaluated by the receiver operating characteristic (ROC) curve.Results:Among the 92 patients, CTA 3 months after the operation showed that 58 cases had complete occluder endothelialization (complete endothelialization group), and 34 cases had occluder incomplete endothelialization (incomplete endothelialization group). Before operation, the long diameter of left atrial appendage opening, short diameter of left atrial appendage opening, area of left atrial appendage opening and diameter of anchoring area in incomplete endothelialization group were significantly larger than those in complete endothelialization group: (28.35 ± 1.77) mm vs. (26.21 ± 2.21) mm, (22.09 ± 2.01) mm vs. (20.86 ± 1.75) mm, (512.76 ± 63.35) mm 2 vs. (453.83 ± 75.39) mm 2 and (24.71 ± 2.50) mm vs. (23.12 ± 2.40) mm, and there were statistical differences ( P<0.01); there was no statistical difference in effective depth between the two groups ( P>0.05). Multivariate Logistic regression analysis result showed that the long diameter of left atrial appendage opening before operation was an independent risk factor for occluder incomplete endothelialization after LAAC in patients with atrial fibrillation ( OR = 2.141, 95% CI 1.217 to 3.768, P<0.01). ROC curve analysis result showed that the area under the curve of the long diameter of left atrial appendage opening before operation for predicting occluder incomplete endothelialization after LAAC in patients with atrial fibrillation was 0.768 (95% CI 0.674 to 0.862, P<0.01), the optimal cut-off value was 26.5 mm, the sensitivity was 88.2%, and the specificity was 55.2%. Conclusions:A larger long diameter of left atrial appendage opening before operation can lead to occluder incomplete endothelialization after LAAC in patients with atrial fibrillation.

Objective:To compare the mid- to long-term clinical outcomes of arthrolysis versus revision arthroplasty for arthrofibrosis-related stiffness following total knee arthroplasty (TKA).Methods:A retrospective analysis was conducted of the 20 patients (26 knees) with post-TKA arthrofibrosis who had been treated at Department of Orthopedics, The Fourth Medical Center of Chinese PLA General Hospital between January 2004 and January 2020. The patients were divided into 2 groups based on their treatment: an arthrolysis group of 8 cases (10 knees) [1 male (2 knees)and 7 females (8 knees); median age: 44.0 (21.0, 62.0) years] and a revision arthroplasty group of 13 cases (16 knees) [4 males (6 knees)and 9 females (10 knees); median age: 41.5 (30.0, 56.0) years]. The knee range of motion (ROM) and the American Hospital for Special Surgery (HSS) knee score as well as their improvements were compared between preoperation and the last follow-up, as well as between the 2 groups; the satisfaction of the patients at the last follow-up was compared between the 2 groups.Results:No significant differences in the baseline characteristics were observed between the 2 groups, indicating comparability ( P>0.05). The preoperative knee ROM [55.0° (48.8°, 61.3°)] and HSS knee score [54.0 (47.0, 61.8) points] in the arthrolysis group were significantly higher than those in the revision group [27.5° (6.3°, 50.0°), 33.0 (27.3, 47.8) points] ( P<0.05). In the arthrolysis and revision arthroplasty groups, the knee ROMs [90.0° (65.0°, 100.0°), 90.0° (63.5°, 98.8°)] and HSS knee scores [(69.8±19.9) points, (77.6±11.3) points] at the last follow-up were significantly improved compared with those before operation ( P<0.05). In the revision arthroplasty group, the improvement in knee ROM (48.9°±21.7°) was insignificantly larger than that in the arthrolysis group (34.5°±13.2°) ( P>0.05), but the improvement in HSS knee score [39.5 (25.3, 57.0) points] was significantly larger than that in the arthrolysis group [16.0 (10.5, 25.3) points] ( P<0.05). Respectively, 14 and 3 knees in the revision arthroplasty group and the arthrolysis group resulted in patient satisfaction, showing a significant difference between the 2 groups ( P<0.05). Conclusions:Both arthrolysis and revision arthroplasty can significantly improve knee ROM and HSS knee score in post-TKA arthrofibrosis. However, since revision arthroplasty demonstrates superior improvements in HSS knee score and patient satisfaction, it is preferable for patients with lower preoperative knee ROM.

Objective To explore the influencing factors of immune-associated thyroid dysfunction caused by sintilimab treatment in solid tumors and construct a prediction model.Methods Medical records of patients diagnosed with solid tumors and treated with sintilimab at Peking University People's Hospital(Xizhimen Campus,Tongzhou Campus,Shijiazhuang Campus)from January 2023 to September 2024 were collected to explore the influencing factors that caused immune-related thyroid dysfunction using univariate and multifactorial binary logistic regression analyses and to establish a prediction model.The predictive effect of the model was assessed using the receiver operating characteristic(ROC)curve.Results A total of 120 patients were included,and 33 presented with immune-related thyroid dysfunction.Multifactorial logistic regression analysis revealed that thyroid-stimulating hormone(TSH)[OR=2.470,95%CI=(1.279,4.771)]and treatment cycles[OR=1.298,95%CI=(1.117,1.509)]were independent risk factors for the occurrence of immune-associated thyroid dysfunction,and the difference was statistically significant(P＜0.05).The area under the ROC curve was(0.897±0.043)[95%CI=(0.813,0.981)],the Yoden index was 0.703,and the model prediction accuracy was 86.5%.Conclusion The risk of immune-related thyroid dysfunction caused by sintilimab is high,and TSH and treatment cycle are the influencing factors,and the constructed model has certain predictive value and is of reference significance.

Aim To investigate the effect of Zhenwu decoction on inflammation,oxidative stress and apopto-sis of human glomerular epithelial cells(HGEC)in-duced by lipopolysaccharide(LPS)based on Nrf2/HO-1 signaling pathway,and to explore the underlying mechanism.Methods HGEC were treated with LPS(1.0 mg·L-1)for 24 h to construct an oxidative damage model.On this basis,2.5％,5％and 10％Zhenwu decoction-containing serum were added to the low,medium and high dose groups of Zhenwu decoc-tion,and a normal group was set up.The changes of cell activity were assessed by MTT method and LDH method.The contents of TNF-α,IL-6,IL-10,SOD,CAT,GSH-Px,ROS and MDA in each group were de-tected by ELISA.The apoptosis of each group was de-tected by flow cytometry.The mRNA and protein ex-pressions of Bax,Bcl-2,caspase-3,caspase-9 and Nrf2/HO-1 pathway were detected by RT-qPCR and Western blot,respectively.Results Compared to the normal group,the model group of HGEC exhibited increased levels of inflammatory cytokines,enhanced oxidative stress response and aggravated apoptosis;after inter-vention with various doses of Zhenwu decoction,the in-flammatory levels in HGEC were reduced,oxidative damage and apoptosis were effectively ameliorated,and the mRNA and protein expression levels of the Nrf2/HO-1 signaling pathway were upregulated.Conclu-sions Zhenwu decoction can protect HGEC from LPS-induced inflammation and oxidative damage and im-prove apoptosis.The mechanism may be related to the activation of Nrf2/HO-1 signaling pathway.

Aim To investigate the effect of Zhenwu decoction on inflammation,oxidative stress and apopto-sis of human glomerular epithelial cells(HGEC)in-duced by lipopolysaccharide(LPS)based on Nrf2/HO-1 signaling pathway,and to explore the underlying mechanism.Methods HGEC were treated with LPS(1.0 mg·L-1)for 24 h to construct an oxidative damage model.On this basis,2.5％,5％and 10％Zhenwu decoction-containing serum were added to the low,medium and high dose groups of Zhenwu decoc-tion,and a normal group was set up.The changes of cell activity were assessed by MTT method and LDH method.The contents of TNF-α,IL-6,IL-10,SOD,CAT,GSH-Px,ROS and MDA in each group were de-tected by ELISA.The apoptosis of each group was de-tected by flow cytometry.The mRNA and protein ex-pressions of Bax,Bcl-2,caspase-3,caspase-9 and Nrf2/HO-1 pathway were detected by RT-qPCR and Western blot,respectively.Results Compared to the normal group,the model group of HGEC exhibited increased levels of inflammatory cytokines,enhanced oxidative stress response and aggravated apoptosis;after inter-vention with various doses of Zhenwu decoction,the in-flammatory levels in HGEC were reduced,oxidative damage and apoptosis were effectively ameliorated,and the mRNA and protein expression levels of the Nrf2/HO-1 signaling pathway were upregulated.Conclu-sions Zhenwu decoction can protect HGEC from LPS-induced inflammation and oxidative damage and im-prove apoptosis.The mechanism may be related to the activation of Nrf2/HO-1 signaling pathway.

Objective To explore the influencing factors of immune-associated thyroid dysfunction caused by sintilimab treatment in solid tumors and construct a prediction model.Methods Medical records of patients diagnosed with solid tumors and treated with sintilimab at Peking University People's Hospital(Xizhimen Campus,Tongzhou Campus,Shijiazhuang Campus)from January 2023 to September 2024 were collected to explore the influencing factors that caused immune-related thyroid dysfunction using univariate and multifactorial binary logistic regression analyses and to establish a prediction model.The predictive effect of the model was assessed using the receiver operating characteristic(ROC)curve.Results A total of 120 patients were included,and 33 presented with immune-related thyroid dysfunction.Multifactorial logistic regression analysis revealed that thyroid-stimulating hormone(TSH)[OR=2.470,95%CI=(1.279,4.771)]and treatment cycles[OR=1.298,95%CI=(1.117,1.509)]were independent risk factors for the occurrence of immune-associated thyroid dysfunction,and the difference was statistically significant(P＜0.05).The area under the ROC curve was(0.897±0.043)[95%CI=(0.813,0.981)],the Yoden index was 0.703,and the model prediction accuracy was 86.5%.Conclusion The risk of immune-related thyroid dysfunction caused by sintilimab is high,and TSH and treatment cycle are the influencing factors,and the constructed model has certain predictive value and is of reference significance.

Objective:To explore the predictive value of preoperative CT angiography (CTA) for incomplete endothelialization of the occluder after left atrial appendage closure (LAAC) in patients with atrial fibrillation.Methods:The clinical data of 92 atrial fibrillation patients underwent LAAC in the Tangdu Hospital of Air Force Military Medical University from January 2022 to June 2024 were retrospectively analyzed. CTA examinations were performed both before operation and 3 months after operation. Before operation, the long diameter of left atrial appendage opening, short diameter of left atrial appendage opening, area of left atrial appendage opening, diameter of anchoring area and effective depth were measured. After operation, the condition of occluder endothelialization was evaluated, and the patients were divided into the completely endothelialization group and the incomplete endothelialization group. Multivariate Logistic regression analysis was used to analyze the independent risk factors of occluder incomplete endothelialization after LAAC in patients with atrial fibrillation. The predictive value of independent risk factors was evaluated by the receiver operating characteristic (ROC) curve.Results:Among the 92 patients, CTA 3 months after the operation showed that 58 cases had complete occluder endothelialization (complete endothelialization group), and 34 cases had occluder incomplete endothelialization (incomplete endothelialization group). Before operation, the long diameter of left atrial appendage opening, short diameter of left atrial appendage opening, area of left atrial appendage opening and diameter of anchoring area in incomplete endothelialization group were significantly larger than those in complete endothelialization group: (28.35 ± 1.77) mm vs. (26.21 ± 2.21) mm, (22.09 ± 2.01) mm vs. (20.86 ± 1.75) mm, (512.76 ± 63.35) mm 2 vs. (453.83 ± 75.39) mm 2 and (24.71 ± 2.50) mm vs. (23.12 ± 2.40) mm, and there were statistical differences ( P<0.01); there was no statistical difference in effective depth between the two groups ( P>0.05). Multivariate Logistic regression analysis result showed that the long diameter of left atrial appendage opening before operation was an independent risk factor for occluder incomplete endothelialization after LAAC in patients with atrial fibrillation ( OR = 2.141, 95% CI 1.217 to 3.768, P<0.01). ROC curve analysis result showed that the area under the curve of the long diameter of left atrial appendage opening before operation for predicting occluder incomplete endothelialization after LAAC in patients with atrial fibrillation was 0.768 (95% CI 0.674 to 0.862, P<0.01), the optimal cut-off value was 26.5 mm, the sensitivity was 88.2%, and the specificity was 55.2%. Conclusions:A larger long diameter of left atrial appendage opening before operation can lead to occluder incomplete endothelialization after LAAC in patients with atrial fibrillation.