[A deep-learning model for the assessment of coronary heart disease and related risk factors via the evaluation of retinal fundus photographs].

Objective: To develop and validate a deep learning model based on fundus photos for the identification of coronary heart disease (CHD) and associated risk factors. Methods: Subjects aged>18 years with complete clinical examination data from 149 hospitals and medical examination centers in China were included in this retrospective study. Two radiologists, who were not aware of the study design, independently evaluated the coronary angiography images of each subject to make CHD diagnosis. A deep learning model using convolutional neural networks (CNN) was used to label the fundus images according to the presence or absence of CHD, and the model was proportionally divided into training and test sets for model training. The prediction performance of the model was evaluated in the test set using monocular and binocular fundus images respectively. Prediction efficacy of the algorithm for cardiovascular risk factors (e.g., age, systolic blood pressure, gender) and coronary events were evaluated by regression analysis using the area under the receiver operating characteristic curve (AUC) and R2 correlation coefficient. Results: The study retrospectively collected 51 765 fundus images from 25 222 subjects, including 10 255 patients with CHD, and there were 14 419 male subjects in this cohort. Of these, 46 603 fundus images from 22 701 subjects were included in the training set and 5 162 fundus images from 2 521 subjects were included in the test set. In the test set, the deep learning model could accurately predict patients' age with an R2 value of 0.931 (95%CI 0.929-0.933) for monocular photos and 0.938 (95%CI 0.936-0.940) for binocular photos. The AUC values for sex identification from single eye and binocular retinal fundus images were 0.983 (95%CI 0.982-0.984) and 0.988 (95%CI 0.987-0.989), respectively. The AUC value of the model was 0.876 (95%CI 0.874-0.877) with either monocular fundus photographs and AUC value was 0.885 (95%CI 0.884-0.888) with binocular fundus photographs to predict CHD, the sensitivity of the model was 0.894 and specificity was 0.755 with accuracy of 0.714 using binocular fundus photographs for the prediction of CHD. Conclusion: The deep learning model based on fundus photographs performs well in identifying coronary heart disease and assessing related risk factors such as age and sex.

[Radical vulvectomy and inguinal lymphadenectomy using a single incision for the treatment of vulvar malignancy].

Objective: To describe a novel procedure of radical vulvectomy and inguinal lymphadenectomy using a single incision (RVIL-SI) for the treatment of vulvar malignancy. Methods: In March, 2019, two cases affected with vulvar cancer (the first one is stage ⅢA squamous cell carcinoma and the second one is stage ⅠB with malignant melanoma) underwent this novel procedure, which was characterized by the combination of radical vulvectomy and bilateral inguinal lymphadenectomy without making additional incisions in groin areas. The boundaries of femoral triangle could be exposed perfectly using the initial incision of radical vulvectomy and the combined superficial and deep groin lymph node dissection were done subcutaneously from medial to lateral. Preoperative data and short term follow-up outcomes were collected. Results: The RVIL-SI was successfully conducted in two patients without any incisions of groin. The great saphenous veins were all spared. The operative time, average blood loss and median total regional lymph nodes of two cases were close. No major intraoperative complications occurred. Micrometastasis in one right superficial inguinal node was found in the first case with ipsilateral huge cancer lesion. No drain tube was left in inguinal areas intraoperatively. On postoperative day 3, the second case suffered mild lymphocele of right groin, which was resolved via repeated percutaneous needle puncture followed by elastic compression. Postoperative hospital stay of two cases were 10 and 11 days, respectively. With no skin complication at the time of writing this report. Conclusion: Our preliminary experience with the RVIL-SI has confirmed the reproducibility and minimal invasive therapeutic potential in the treatment for patients with vulvar cancer. But this novel procedure is in its infancy stage. Although short-term results are encouraging, a larger series with longer follow-up are required to fully evaluate the therapeutic efficacy.

Extracorporeal shock wave lithotripsy. Experience in treating 245 patients with gallbladder stones.

An EDAP LT-01 lithotripter was used to treat 245 patients with functioning gallbladders containing one to three radiolucent stones of less than 20 mm in diameter. Ursodeoxycholic acid was administrated as adjuvant litholytic therapy. The gallbladder stones disintegrated in 98.8% of patients and disappeared completely in 21.2% within 1 month after lithotripsy, in 26.5% within 2 months, in 33.9, 40, 46.5, 48.6 and 53.9% within 3, 4, 6, 9, and 12 months, respectively. Adverse effects after lithotripsy were dull abdominal pain (49.4%), biliary colic (13.1%), jaundice (1.2%), and pancreatitis (0.4%). Extracorporeal shock wave lithotripsy combined with litholytic therapy is a non-invasive, painless, safe, and effective treatment in selected patients. Patients with solitary radiolucent stone less than 20 mm in diameter are considered candidates for extracorporeal shock wave lithotripsy (ESWL). The key to success of ESWL lies in the strict selection of patients, careful monitoring throughout the lithotriptic procedure, and enough litholytic therapy. The disadvantages of this method include strict selection of patients and high costs, poor curative effect, and recurrence of stones (11.4% of patients).

EDAP piezoelectric shock wave lithotripsy for gallbladder stones.

EDAP piezoelectric shock wave lithotripsy combined with oral ursodeoxycolic acid dissolution of stones was used to treat 1055 patients with gallbladder stones. 926 of them (87.8%) were followed up for more than 1 year. The patients were divided into two groups: Group I, 637 patients with functioning gallbladders containing one radiolucent stone less than or equal to 20 mm in diameter or 2 to 3 stones each less than or equal to 12 mm, and Group II: 289 patients with stones exceeding the above criteria. The stone fragmentation rate was 96.2% and 94.1% respectively in Group I and in Group II. Gallbladder stones disappeared in 18.5%, 35.0%, 46.2% and 52.4% of the patients in Group I in 1, 3, 6, and 12 months after treatment and 7.3%, 11.4%, 20.1%, and 27.7% in Group II. The treatment was more effective for solitary stones less than or equal to 20 mm in diameter. No serious complications were noted. The midterm curative effect was satisfactory. Further study is required to raise the curative effect and prevent stone recurrence.

Effectiveness of green tea tannin on rats with chronic renal failure.

The effects of green tea tannin on nephrectomized rats were examined. There were increases in blood urea nitrogen, serum creatinine, and urinary protein, and a decrease in creatinine clearance in the nephrectomized control rats, whereas better results for these parameters were obtained in rats given green tea tannin after nephrectomy, demonstrating a suppressed progression of the renal failure. When the renal parenchyma was partially resected, the remnant kidney showed a decrease in the activity of radical scavenger enzymes. Green tea tannin, however, was found to lighten the kidney under such oxidative stress. Mesangial proliferation and glomerular sclerotic lesions, which were conspicuous in the rats that were not given green tea tannin after nephrectomy, were also relieved.