Objective·To explore the predictive capability of retinal vascular features in preeclampsia(PE)based on artificial intelligence(AI)models.Methods·This retrospective study enrolled 789 pregnant women who registered from June 2020 to January 2021 at Shanghai First Maternity and Infant Hospital of Tongji University in the first 16 weeks of gestation.These women underwent regular prenatal examinations,had retinal fundus images captured,and delivered singleton live births at the hospital.According to whether they developed hypertensive disorders of pregnancy(HDP),they were divided into unaffected group(n=685)and HDP group(n=104).Within the HDP group,pregnancies were further categorized into gestational hypertension(GH)group(n=36)and PE group(n=68)based on the occurrence of PE.Based on the gestational age at onset,the PE group was further divided into early-onset PE group(gestational age<34 weeks)and late-onset PE group(gestational age≥34 weeks).Fundus images of the pregnant women were obtained,and an AI algorithm was utilized to diagnose retinal lesions and quantify retinal vascular features.Comparative analyses were conducted on fundus features and retinal vascular features.Univariate Logistic regression model was employed to analyze the influencing factors of PE occurrence,and multivariate Logistic regression model was further utilized to assess the correlation between retinal vascular features and the occurrence of PE.The predictive capability of retinal vascular features for PE(both early-and late-onset PE)was analyzed by using area under the curve(AUC)of receiver operator characteristic curve(ROC curve).Results·The comparative analysis of fundus features and retinal vascular features demonstrated statistically significant differences between the unaffected group and PE group in terms of central retinal artery equivalent(CRAE),central retinal vein equivalent(CRVE),arteriole-to-venular ratio(AVR),retinal artery tortuosity and retinal artery fractal dimension(all P<0.05).Univariate Logistic regression analysis indicated that second-trimester mean arterial pressure(MAP),second-trimester estimated fetal weight(EFW),CRAE,CRVE,AVR,retinal artery tortuosity and retinal artery fractal dimension were the influencing factors for PE occurrence(all P<0.05).Multivariate Logistic regression analysis revealed that second-trimester EFW,CRAE,CRVE,AVR,retinal artery tortuosity and retinal artery fractal dimension were the protective factors for the occurrence of PE,while second-trimester MAP was the risk factor for PE(all P<0.05).The analysis of ROC curves revealed that maternal risk factors along with second-trimester prenatal examination data(including MAP and EFW)and retinal vascular features model had good predictive ability for PE[AUC(95%CI)=0.784(0.725-0.843),and this model exhibited better predictive capability for early-onset PE,with an AUC(95%CI)of 0.840(0.756-0.924).Conclusion·The integration of quantified retinal vascular features based on AI models with maternal risk factors and second-trimester prenatal examination data(including MAP and EFW)enables a more effective prediction of PE occurrence,particularly early-onset PE.

Objective:To investigate the surgical treatment methods of femoral artery pseudoaneurysm combined with infectious wounds and to evaluate the clinical effects.Methods:The retrospective observational research method was used. Twelve patients with femoral artery pseudoaneurysm combined with infectious wounds who met the inclusion criteria were admitted to Nanjing University of Chinese Medicine Wuxi Integrated Traditional Chinese and Western Medicine Hospital (Affiliated Hospital of Jiangnan University) from October 2014 to September 2022, including 6 males and 6 females, aged from 46 to 78 years. In the primary operation, debridement, tumor resection, and artery suture/venous grafting to repair the artery/artery ligation were performed, and the wound area after tumor resection ranged from 4.0 cm×1.5 cm to 12.0 cm×6.5 cm. Wounds that could be sutured were treated with tension reduction suture and extracutaneous continuous vacuum sealing drainage (VSD), while large wounds that could not be sutured were treated with VSD to control infection. In the secondary operation, tension reduction suture was performed to repair the wounds that could be sutured; large wounds were repaired with adjacent translocated flaps with area of 9.0 cm×5.0 cm to 15.0 cm×7.0 cm. Additionally, when the length of the exposed femoral artery was equal to or over 3.0 cm, the wounds were repaired with additional rectus femoris muscle flap with length of 15.0 to 18.0 cm. The donor areas of the flaps were directly sutured. The wound with artery ligation was treated with stamp skin grafting and continuous VSD. The bacterial culture results of the wound exudate samples on admission were recorded. The intraoperative blood loss, the location of femoral artery rupture, the artery treatment method, and the wound repair method in the primary operation were recorded, and the durations of catheter lavage, catheter drainage, and VSD treatment, and the drainage volume after the operation were recorded. The repair method of wounds in the secondary operation, the durations of catheter drainage and VSD treatment, and the total drainage volume after the operation were recorded. The survivals of flap/muscle flap/stamp skin grafts were observed, and the wound healing time was recorded. Follow-up after discharge was performed to evaluate the quality of wound healing and the walking function and to check whether the pulsatile mass disappeared. B-ultrasound or computed tomography angiography (CTA) was performed again to observe potential pseudoaneurysm recurrence and evaluate the patency of blood flow of the femoral artery.Results:The bacterial culture results of wound exudate samples of all the patients were positive on admission. The blood loss was 150 to 750 mL in the primary operation. The arterial ruptures were located in the femoral artery in 8 cases, in the external iliac artery in 2 cases, and in the femoral arteriovenous fistula in 2 cases. Six cases received direct artery suture, 4 cases received autologous great saphenous vein grafting to repair the artery, 1 case received autologous great saphenous vein bypass surgery, and 1 case received artery ligation. The primary wound suture was performed in 4 cases, along with catheter lavage for 3 to 5 days, catheter drainage for 4 to 6 days, VSD treatment for 5 to 7 days, and a total drainage volume of 80 to 450 mL after the surgery. In the secondary operation, the wounds were sutured directly in 3 cases along with catheter drainage for 2 to 3 days, the wound was repaired with scalp stamp skin graft and VSD treatment for 5 days in 1 case, the wounds were repaired with adjacent translocated flaps in 2 cases with catheter drainage for 2 to 3 days, and the wounds were repaired with rectus femoris muscle flaps+adjacent translocated flaps in 2 cases with catheter drainage for 3 to 5 days . The total drainage volume after the secondary operation ranged from 150 to 400 mL. All the skin flaps/muscle flaps/skin grafts survived after operation. The wound healing time ranged from 15 to 36 days after the primary operation. Follow-up of 2 to 8 months after discharge showed that the wounds of all patients healed well. One patient who underwent femoral artery ligation had calf amputation due to foot ischemic necrosis, and the rest of the patients regained normal walking ability. The pulsatile mass disappeared in inguinal region of all patients. B-ultrasound or CTA re-examination in 6 patients showed that the blood flow of femoral artery had good patency, and there was no pseudoaneurysm recurrence.Conclusions:Early debridement, tumor resection, and individualized artery treatment should be performed in patients with femoral artery pseudoaneurysm combined with infected wounds. Besides, proper drainage and personalized repair strategy should be conducted according to the wound condition to achieve a good outcome.