Prediction of pathological staging and grading of renal clear cell carcinoma based on deep learning algorithms.

OBJECTIVE: Deep learning algorithms were used to develop a model for predicting the staging and grading of renal clear cell carcinoma to inform clinicians' treatment plans. METHODS: Clinical and pathological information was collected from 878 patients diagnosed with renal clear cell carcinoma in the Department of Urology, Peking University First Hospital. The patients were randomly assigned to the test set (n = 702) or the verification set (n = 176). Pathological staging and grading of renal clear cell carcinoma were predicted by preoperative clinical variables using deep learning algorithms. Receiver operating characteristic curves were used to evaluate the predictive accuracy as measured by the area under the receiver operating characteristic curve (AUC). RESULTS: For tumor pathological staging, AUC values of 0.933, 0.947, and 0.948 were obtained using the BiLSTM, CNN-BiLSTM, and CNN-BiGRU models, respectively. For tumor pathological grading, the AUC values were 0.754, 0.720, and 0.770, respectively. CONCLUSIONS: The proposed model for predicting renal clear cell carcinoma allows for accurate projection of the staging and grading of renal clear cell carcinoma and helps clinicians optimize individual treatment plans.

Clinical and neurocognitive outcomes after transcatheter aortic valve implantation (TAVI) with cerebral protection: initial experience with a novel dual-filter device in Southeast Asia.

INTRODUCTION: Transcatheter aortic valve implantation (TAVI) is increasingly performed in patients with severe aortic stenosis. A novel dual-filter system to reduce cerebral embolism during TAVI recently became available. We aimed to assess the feasibility, safety, and clinical and neurocognitive outcomes of TAVI with cerebral protection in Asian patients. METHODS: 40 consecutive patients undergoing TAVI with cerebral protection were enrolled. All procedures were performed via femoral access using the self-expanding Evolut R/PRO or Portico, or the balloon-expandable SAPIEN 3 bioprostheses. Baseline characteristics, procedural and clinical outcomes were recorded. Cognition was assessed at baseline and 30 days using the abbreviated mental test (AMT). RESULTS: The mean age of the patients (75% male) was 76.4 ± 8.4 years. TAVI was uncomplicated in all patients. The filter device was successfully deployed in 38 (95.0%) patients without safety issues. There was no stroke or death at 30 days, and the survival rate at nine months was 95.0%. There was no overall cognitive change (baseline vs. 30-day AMT: 9.2 ± 1.1 vs. 9.0 ± 1.5, p = 0.12), and only 1 (2.5%) patient developed impaired cognition at 30 days. Patients with a decreased AMT score at 30 days were significantly older than those without (82.1 ± 4.5 vs. 74.4 ± 7.7 years, p = 0.019). All patients with decreased AMT scores were aged ≥ 76 years. CONCLUSION: In this early Asian experience of TAVI under cerebral protection, the filter device was successfully deployed in 95% of patients, with 100% procedural success. There were no filter-related complications and no stroke or mortality at 30 days. Overall cognition was preserved, although increased age was associated with a decline in AMT score.

Combined fibrinolysis using reduced-dose alteplase plus abciximab with immediate rescue angioplasty versus primary angioplasty with adjunct use of abciximab for the treatment of acute myocardial infarction: Asia-Pacific Acute Myocardial Infarction Trial (APAMIT) pilot study.

We conducted a randomized feasibility pilot study comparing combined fibrinolysis with immediate rescue angioplasty vs. primary angioplasty with adjunctive abciximab in patients with acute myocardial infarction (AMI). Seventy patients with ST segment elevation AMI of