Background Despite the role of surgery in the management of left ventricular (LV) thrombi remaining controversial, robotic LV thrombectomy has emerged as a viable treatment option. This study aimed to present our successful experience with a robotic mitral program, detailing the operative technique. Materials and Methods We conducted a retrospective analysis of our institutional database to identify patients who underwent LV thrombectomy using the da Vinci robot system. Subsequently, serial echocardiograms and short- and long-term outcomes were reviewed and analyzed using descriptive statistics. Results A total of five patients (median age: 46 years) were included in this study. All patients presented with a floating LV thrombus and a history of embolization. Among them, four patients experienced reduced heart function, none had coronary artery disease, three experienced dilated cardiomyopathy. Complete resection was achieved in all cases, with no postoperative deaths, strokes, or major complications. Additionally, LV function showed improvement during follow-up periods. Postoperative anticoagulation was continued for two years in one patient and one year in the remaining patients. No recurrence or further embolic events were observed during the median follow-up period of 6 years. Conclusion Robotic LV thrombectomy yields excellent outcomes and should be considered early for patients with floating LV thrombi. However, further investigation is warranted to determine the optimal timing of this intervention and its role in the treatment paradigm, including whether these results can be extrapolated to patients with other forms of mobile thrombus and/or to support surgery as the primary prevention of systemic embolization. © 2024, CC BY.

pecialised pre-trained language models are becoming more frequent in Natural language Processing (NLP) since they can potentially outperform models trained on generic texts. BioBERT (Sanh et al., Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv: 1910.01108, 2019) and BioClinicalBERT (Alsentzer et al., Publicly available clinical bert embeddings. In Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp. 72–78, 2019) are two examples of such models that have shown promise in medical NLP tasks. Many of these models are overparametrised and resource-intensive, but thanks to techniques like knowledge distillation, it is possible to create smaller versions that perform almost as well as their larger counterparts. In this work, we specifically focus on development of compact language models for processing clinical texts (i.e. progress notes, discharge summaries, etc). We developed a number of efficient lightweight clinical transformers using knowledge distillation and continual learning, with the number of parameters ranging from 15 million to 65 million. These models performed comparably to larger models such as BioBERT and ClinicalBioBERT and significantly outperformed other compact models trained on general or biomedical data. Our extensive evaluation was done across several standard datasets and covered a wide range of clinical text-mining tasks, including natural language inference, relation extraction, named entity recognition and sequence classification. To our knowledge, this is the first comprehensive study specifically focused on creating efficient and compact transformers for clinical NLP tasks. The models and code used in this study can be found on our Huggingface profile at https://huggingface.co/nlpie and Github page at https://github.com/nlpieresearch/Lightweight-Clinical-Transformers, respectively, promoting reproducibility of our results. © The Author(s), 2024.

Pei-Lin Lee serves as Clinical Associate Professor, School of Medicine, National Taiwan University; Consultant, Center of Sleep Disorder, National Taiwan University Hospital. Her current academic positions at international sleep societies include American Academy of Sleep Medicine Fellow and Co-Chair International Assembly; Asian Society of Sleep Medicine, Sleep Medicine Education Task Force committee member. Her current research focuses on the era of new technology and big data in sleep medicine; and intervention on sleep and metabolism in sleep disordered breathing.