Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health. Research on electrocardiogram (ECG) signals offers valuable opportunities to address these issues. However, existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks. To address these challenges, this study developed a multi-resolution feature encoding network based on residual networks, which effectively extracted local morphological features and global rhythm features of ECG signals, thereby enhancing feature representation. Furthermore, a model compression-based continual learning method was proposed, enabling the structured transfer of knowledge from simpler tasks to more complex ones, resulting in improved performance in downstream tasks. The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets, including tasks such as ECG QRS complex detection, arrhythmia classification, and emotion classification. The continual learning method achieved significant improvements over conventional training approaches in cross-domain, cross-task, and incremental data scenarios. These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.
Humans ; Electrocardiography/methods* ; Mental Health ; Algorithms ; Signal Processing, Computer-Assisted ; Machine Learning ; Arrhythmias, Cardiac/diagnosis* ; Cardiovascular Diseases ; Neural Networks, Computer ; Mental Disorders

In order to realize the diagnosis of slit lamp in cross-regional patients and improve the real-time and convenience of diagnosis,a remote slit lamp diagnosis platform based on Internet of Things(IoT)technology is designed.Firstly,the feasibility of remote slit lamp is analyzed.Secondly,the IoT platform architecture of doctor/server/facility(D/S/F)is proposed and a remote slit lamp is designed.Finally,the performance of the remote slit lamp diagnostic platform is tested.The platform solves the communication problem of distributed slit lamps and realizes respectively numerical control of multi-area slit lamp by multi-eye experts.The test results show that the remote control delay of the platform is less than 20 ms,which supports multiple experts to diagnose multiple patients separately.

Objective:To investigate the effect of long-term oral aspirin on the changes in the aneurysm sac and persistent type Ⅱ endoleak after endovascular aortic repair (EVAR) of infrarenal abdominal aortic aneurysms based on propensity score-matched analysis.Methods:A retrospective cohort study was used to analyze the clinical data of 133 patients with infrarenal abdominal aortic aneurysms treated with EVAR from January 2019 to December 2021 in the Department of Vascular Surgery, Nanjing Drum Tower Hospital. There were 113 males and 20 females, aged (74.8±7.2) years (range: 59 to 95 years). Patients were divided into the group receiving aspirin ( n=80) and the group not taking aspirin ( n=53) based on whether they took aspirin regularly for a long time after surgery. The two groups were matched in a 1∶1 ratio using propensity score matching and the caliper value was 0.05. Cumulative probability curve was plotted using the Kaplan-Meier method and the Log-rank test was used to compare the differences in primary endpoint events (enlargement of the aneurysm sac, occurrence of persistent type Ⅱ endoleak) and secondary endpoint events (adverse cardiovascular events and clinically relevant bleeding events) between the two groups. Results:The follow-up time was (38.4±11.8) months (range: 30 to 58 months). Among the 133 patients, a total of 25 cases (18.8%) suffered enlargement of the aneurysm sac, including 20 cases in the group receiving aspirin and 5 cases in the group not taking aspirin; 35 cases (26.3%) suffered persistent type Ⅱ endoleak, including 26 cases in the group receiving aspirin and 9 cases in the group not taking aspirin. Adverse cardiovascular events occurred in 11 cases (8.3%) and clinically relevant bleeding events were reported in 5 cases (3.8%). A matched cohort was established after propensity score matching, resulting in 32 cases per group. The survival analysis found that the rate of aneurysm sac enlargement was significantly higher in the group receiving aspirin than that in the group not taking aspirin (Log-rank test: P=0.010), and the incidence of persistent type Ⅱ endoleak was significantly higher than that in the group not taking aspirin (Log-rank test: P=0.019). The incidence of adverse cardiovascular events and clinically relevant bleeding events were not significantly different in two groups (Log-rank test: P=0.061, P=0.286). Conclusions:The risk of aneurysm sac expansion and persistent type Ⅱ endoleak were significantly higher in patients taking long-term aspirin after EVAR than in the group not taking asprin. Therefore, high-risk abdominal aortic aneurysm patients who are prone to aneurysm sac expansion should be evaluated in advance so that the risks and benefits of surgery can be comprehensively evaluated and treatment strategies can be optimized.

Objective:To investigate the effect of long-term oral aspirin on the changes in the aneurysm sac and persistent type Ⅱ endoleak after endovascular aortic repair (EVAR) of infrarenal abdominal aortic aneurysms based on propensity score-matched analysis.Methods:A retrospective cohort study was used to analyze the clinical data of 133 patients with infrarenal abdominal aortic aneurysms treated with EVAR from January 2019 to December 2021 in the Department of Vascular Surgery, Nanjing Drum Tower Hospital. There were 113 males and 20 females, aged (74.8±7.2) years (range: 59 to 95 years). Patients were divided into the group receiving aspirin ( n=80) and the group not taking aspirin ( n=53) based on whether they took aspirin regularly for a long time after surgery. The two groups were matched in a 1∶1 ratio using propensity score matching and the caliper value was 0.05. Cumulative probability curve was plotted using the Kaplan-Meier method and the Log-rank test was used to compare the differences in primary endpoint events (enlargement of the aneurysm sac, occurrence of persistent type Ⅱ endoleak) and secondary endpoint events (adverse cardiovascular events and clinically relevant bleeding events) between the two groups. Results:The follow-up time was (38.4±11.8) months (range: 30 to 58 months). Among the 133 patients, a total of 25 cases (18.8%) suffered enlargement of the aneurysm sac, including 20 cases in the group receiving aspirin and 5 cases in the group not taking aspirin; 35 cases (26.3%) suffered persistent type Ⅱ endoleak, including 26 cases in the group receiving aspirin and 9 cases in the group not taking aspirin. Adverse cardiovascular events occurred in 11 cases (8.3%) and clinically relevant bleeding events were reported in 5 cases (3.8%). A matched cohort was established after propensity score matching, resulting in 32 cases per group. The survival analysis found that the rate of aneurysm sac enlargement was significantly higher in the group receiving aspirin than that in the group not taking aspirin (Log-rank test: P=0.010), and the incidence of persistent type Ⅱ endoleak was significantly higher than that in the group not taking aspirin (Log-rank test: P=0.019). The incidence of adverse cardiovascular events and clinically relevant bleeding events were not significantly different in two groups (Log-rank test: P=0.061, P=0.286). Conclusions:The risk of aneurysm sac expansion and persistent type Ⅱ endoleak were significantly higher in patients taking long-term aspirin after EVAR than in the group not taking asprin. Therefore, high-risk abdominal aortic aneurysm patients who are prone to aneurysm sac expansion should be evaluated in advance so that the risks and benefits of surgery can be comprehensively evaluated and treatment strategies can be optimized.

BACKGROUND:Artificial intelligence-assisted bone age assessment has become a research hotspot.Domestic and foreign studies have shown that the rapid development of artificial intelligence technology in the field of medical imaging provides the possibility of more accurate and rapid assessment of bone age. OBJECTIVE:To investigate the consistency between a domestically developed artificial intelligent Greulich-Pyle(GP)bone age assessment system and an expert manually assessed GP(expert GP),and to provide a basis for the feasibility of applying an artificial intelligent GP in clinical practice or in other fields. METHODS:Wrist radiographs were sampled from children and adolescents aged 6-15 years,of whom 672 were male and 650 were female.Bone age assessment of the same wrist radiograph was performed using the artificial intelligent GP and the expert GP.The accuracy of the artificial intelligent GP reading results was assessed by the absolute value of the difference.The consistency of the bone age results was assessed by Pearson correlation and Bland-Altamn distribution;and the consistency of the assessment was checked by Kappa test. RESULTS AND CONCLUSION:The absolute value of the difference(95%confidence interval)of the difference between artificial intelligent GP and expert GP for male and female was 0.39 years(0.37-0.41 years)and 0.32 years(0.29-0.34 years),respectively.The deviation of Bland-Altamn values for male and female was(-0.096±0.482)years and(0.014±0.415)years,respectively.The correlation results between artificial intelligent GP bone age and expert GP bone age for male and female were r=0.991 and r=0.992,respectively(P<0.000 1).The median difference between all age groups for male and female was within 0.5 years.Kappa test values were greater than 0.4 for both sexes at all ages except for the 9-year age group for male.Overall Kappa values were 0.603 and 0.659 for male and female respectively.To conclude,there is a high degree of consistency between the artificial intelligence and expert evaluation results of GP bone age values in children and adolescents aged 6-15 years.

With the increasing incidence of diabetes mellitus in recent years， cardiomyopathy caused by diabetes mellitus has aroused wide concern and this disease is characterized by high insidiousness and high mortality. The early pathological changes of diabetic cardiomyopathy （DCM） are mitochondrial structural disorders and loss of myocardial metabolic flexibility. The turbulence of mitochondrial quality control （MQC） is a key mechanism leading to the accumulation of damaged mitochondria and loss of myocardial metabolic flexibility， which， together with elevated levels of oxidative stress and inflammation， trigger changes in myocardial structure and function. Qi deficiency and stagnation is caused by the loss of healthy Qi， and the dysfunction of Qi transformation results in the accumulation of pathogenic Qi， which further triggers injuries. According to the theory of traditional Chinese medicine （TCM）， DCM is rooted in Qi deficiency of the heart， spleen， and kidney. The dysfunction of Qi transformation leads to the generation and lingering of turbidity， stasis， and toxin in the nutrient-blood and vessels， ultimately damaging the heart. Therefore， Qi deficiency and stagnation is the basic pathologic mechanism of DCM. Mitochondria， similar to Qi in substance and function， are one of the microscopic manifestations of Qi. The role of MQC is consistent with the defense function of Qi. In the case of MQC turbulence， mitochondrial structure and function are impaired. As a result， Qi deficiency gradually emerges and triggers pathological changes， which make it difficult to remove the stagnant pathogenic factor and aggravates the MQC turbulence. Ultimately， DCM occurs. Targeting MQC to treat DCM has become the focus of current research， and TCM has the advantages of acting on multiple targets and pathways. According to the pathogenesis of Qi deficiency and stagnation in DCM and the modern medical understanding of MQC， the treatment should follow the principles of invigorating healthy Qi， tonifying deficiency， and regulating Qi movement. This paper aims to provide ideas for formulating prescriptions and clinical references for the TCM treatment of DCM by targeting MQC.

Objective:To explore the surgical treatment strategy of stent graft infection after interventional treatment of major iliac artery related diseases.Methods:Retrospective analysis was performed on the clinical data of 6 patients with secondary stent graft infection after interventional treatment for major iliac artery related diseases admitted to the Department of Vascular Surgery,Affiliated Drum Tower Hospital,Medical School of Nanjing University from November 2021 to August 2022.There were 5 males and 1 female,with a mean age of 64 years (range:49 to 79 years).The infection time was 53 days to 3 165 days.All the 6 patients received surgical treatment,including 3 patients who underwent anatomic bypass grafting (axillary arterial-femoral artery bypass,femoral arterial-femoral artery bypass) using artificial vessels,and 3 patients who underwent in situ abdominal aorta reconstruction using bovine pericardium.The perioperative situation,postoperative infection and the occurrence of serious adverse events were recorded,and the safety of different treatment methods and materials was evaluated.Results:All patients successfully completed the operation and no death occurred during hospitalization.Intraoperative blood loss was 2 000 to 5 000 ml,and intraoperative blood transfusion was 1 600 to 5 350 ml.All the patients were followed up for 81 to 395 days after surgery,and the incision healed well,and no reinfection occurred.Postoperative gastrointestinal bleeding occurred in 1 patient,secondary surgery (retroperitoneal hematoma removal) was performed in 1 patient due to postoperative bleeding at the vascular anastomosis,both lower limb amputations were performed in 1 patient due to postoperative lower limb ischemia,and intermittent claudication occurred in 2 patients.All patients were alive at the last follow-up.Conclusion:For patients with aortic stent graft infection,when the infection is not serious and there is enough space to block the proximal and distal aorta,in situ aortic reconstruction is an effective treatment,and different materials can achieve satisfactory results in a short period of time.

Objective:To investigate the study of the correlation between C-reactive protein to albumin ratio (CAR) and restenosis after stenting in patients with lower extremity atherosclerotic occlusive disease(LEASO).Methods:The clinical data of 95 patients with LEASO admitted to the Department of Vascular Surgery of Nanjing Drum Tower Hospital from June 2020 to December 2022 were retrospectively analyzed. There were 67 males and 28 females,aged (73.1±9.4) years (range:51 to 92 years). The patients were classified into the restenosis group ( n=61) and the patency group ( n=34) according to the CT angiography results. Independent sample t test,Mann-Whitney U test and χ2 test were used to compare the data between two groups. Risk factors for restenosis after femoropopliteal artery stenting in patients with LEASO were analyzed using multivariate Cox regression. The relationship between preoperative CAR level and restenosis after stent placement was analyzed. Subject operating characteristic(ROC) curves of CAR were plotted to assess the predictive value of CAR for restenosis after stenting,and the results were expressed as area under the curve (AUC). Results:The aortoiliac calcification grade,number of stents,length of stents,C-reactive protein and CAR levels in restenosis group were higher than those in the patency group,and the serum albumin level was lower than that in the patency group(all P<0.05). And the results of multifactorial Cox regression analysis showed that higher pre-procedure CAR level and lower ABI value was an independent risk factor for in-stent restenosis. The AUC of the ROC curve for restenosis was 0.737(95% CI:0.617 to 0.856),the AUC of the ROC curve for 12-month restenosis was 0.709(95% CI:0.602 to 0.815), and the AUC of the ROC curve for 24-month restenosis was 0.702(95% CI:0.594 to 0.811). Conclusion:Higher pre-procedural CAR levels in patients with LEASO is risk factor for in-stent restenosis,and CAR has a predictive value for restenosis after lower extremity arterial stent dilatation and angioplasty.

Objective:To explore the surgical treatment strategy of stent graft infection after interventional treatment of major iliac artery related diseases.Methods:Retrospective analysis was performed on the clinical data of 6 patients with secondary stent graft infection after interventional treatment for major iliac artery related diseases admitted to the Department of Vascular Surgery,Affiliated Drum Tower Hospital,Medical School of Nanjing University from November 2021 to August 2022.There were 5 males and 1 female,with a mean age of 64 years (range:49 to 79 years).The infection time was 53 days to 3 165 days.All the 6 patients received surgical treatment,including 3 patients who underwent anatomic bypass grafting (axillary arterial-femoral artery bypass,femoral arterial-femoral artery bypass) using artificial vessels,and 3 patients who underwent in situ abdominal aorta reconstruction using bovine pericardium.The perioperative situation,postoperative infection and the occurrence of serious adverse events were recorded,and the safety of different treatment methods and materials was evaluated.Results:All patients successfully completed the operation and no death occurred during hospitalization.Intraoperative blood loss was 2 000 to 5 000 ml,and intraoperative blood transfusion was 1 600 to 5 350 ml.All the patients were followed up for 81 to 395 days after surgery,and the incision healed well,and no reinfection occurred.Postoperative gastrointestinal bleeding occurred in 1 patient,secondary surgery (retroperitoneal hematoma removal) was performed in 1 patient due to postoperative bleeding at the vascular anastomosis,both lower limb amputations were performed in 1 patient due to postoperative lower limb ischemia,and intermittent claudication occurred in 2 patients.All patients were alive at the last follow-up.Conclusion:For patients with aortic stent graft infection,when the infection is not serious and there is enough space to block the proximal and distal aorta,in situ aortic reconstruction is an effective treatment,and different materials can achieve satisfactory results in a short period of time.

Objective:To investigate the study of the correlation between C-reactive protein to albumin ratio (CAR) and restenosis after stenting in patients with lower extremity atherosclerotic occlusive disease(LEASO).Methods:The clinical data of 95 patients with LEASO admitted to the Department of Vascular Surgery of Nanjing Drum Tower Hospital from June 2020 to December 2022 were retrospectively analyzed. There were 67 males and 28 females,aged (73.1±9.4) years (range:51 to 92 years). The patients were classified into the restenosis group ( n=61) and the patency group ( n=34) according to the CT angiography results. Independent sample t test,Mann-Whitney U test and χ2 test were used to compare the data between two groups. Risk factors for restenosis after femoropopliteal artery stenting in patients with LEASO were analyzed using multivariate Cox regression. The relationship between preoperative CAR level and restenosis after stent placement was analyzed. Subject operating characteristic(ROC) curves of CAR were plotted to assess the predictive value of CAR for restenosis after stenting,and the results were expressed as area under the curve (AUC). Results:The aortoiliac calcification grade,number of stents,length of stents,C-reactive protein and CAR levels in restenosis group were higher than those in the patency group,and the serum albumin level was lower than that in the patency group(all P<0.05). And the results of multifactorial Cox regression analysis showed that higher pre-procedure CAR level and lower ABI value was an independent risk factor for in-stent restenosis. The AUC of the ROC curve for restenosis was 0.737(95% CI:0.617 to 0.856),the AUC of the ROC curve for 12-month restenosis was 0.709(95% CI:0.602 to 0.815), and the AUC of the ROC curve for 24-month restenosis was 0.702(95% CI:0.594 to 0.811). Conclusion:Higher pre-procedural CAR levels in patients with LEASO is risk factor for in-stent restenosis,and CAR has a predictive value for restenosis after lower extremity arterial stent dilatation and angioplasty.