RESUMEN
BACKGROUND: Addressing intraoperative bleeding remains a significant challenge in the field of robotic surgery. This research endeavors to pioneer a groundbreaking solution utilizing convolutional neural networks (CNNs). The objective is to establish a system capable of forecasting instances of intraoperative bleeding during robot-assisted radical prostatectomy (RARP) and promptly notify the surgeon about bleeding risks. METHODS: To achieve this, a multi-task learning (MTL) CNN was introduced, leveraging a modified version of the U-Net architecture. The aim was to categorize video input as either "absence of blood accumulation" (0) or "presence of blood accumulation" (1). To facilitate seamless interaction with the neural networks, the Bleeding Artificial Intelligence-based Detector (BLAIR) software was created using the Python Keras API and built upon the PyQT framework. A subsequent clinical assessment of BLAIR's efficacy was performed, comparing its bleeding identification performance against that of a urologist. Various perioperative variables were also gathered. For optimal MTL-CNN training parameterization, a multi-task loss function was adopted to enhance the accuracy of event detection by taking advantage of surgical tools' semantic segmentation. Additionally, the Multiple Correspondence Analysis (MCA) approach was employed to assess software performance. RESULTS: The MTL-CNN demonstrated a remarkable event recognition accuracy of 90.63%. When evaluating BLAIR's predictive ability and its capacity to pre-warn surgeons of potential bleeding incidents, the density plot highlighted a striking similarity between BLAIR and human assessments. In fact, BLAIR exhibited a faster response. Notably, the MCA analysis revealed no discernible distinction between the software and human performance in accurately identifying instances of bleeding. CONCLUSION: The BLAIR software proved its competence by achieving over 90% accuracy in predicting bleeding events during RARP. This accomplishment underscores the potential of AI to assist surgeons during interventions. This study exemplifies the positive impact AI applications can have on surgical procedures.
RESUMEN
BACKGROUND: Angiotensin Converting Enzyme inhibitors (ACEis) and beta-blockers (BB) are suggested to prevent and treat trastuzumab-related cardiac toxicity. We performed a prospective clinical trial in women experiencing mild cardiac toxicity (MCT) while on adjuvant treatment with trastuzumab. METHODS: MCT was defined as an asymptomatic absolute decrease in LVEF of ≥ 10 percentage units to >50%. Treatment consisted of enalapril 2.5 mg bid and carvedilol 3.75 mg bid, which were up-titrated to 10 mg bid for the enalapril and 6,25 mg bid of carvedilol. In patients receiving study drug, the primary study end-point was LVEF recovery, which was defined as a post-trastuzumab LVEF returning to no less than -5 percentage points of the baseline value. RESULTS: 103 patients were enrolled, 100 started trastuzumab, and 98 completed the planned treatment. Sixteen patients (16%) had MCT and received study drugs until trastuzumab completion. None of these patients achieved a post-trastuzumab LVEF recovery. Nevertheless, treated patients had significantly higher median LVEF recovery from nadir to post-trastuzumab LVEF in (8% points vs. 4% points, respectively, p = 0.004), resulting in no difference in post-treatment LVEF values compared to patients without MCT. CONCLUSION: Treatment of MCT with ACEis and BB allows faster LVEF recovery from nadir values and should be further studied in this setting.
