No abstract

Aiming the problems that the clinical data of different patients is difficult for reasonable representation and the time interval between medical events is different, which lead to the difficulty of clinical prediction, a clinical prediction model based on the long short-term memory (LSTM) network optimized by fruit fly optimization algorithm in health time series data is proposed. First, FastText method is used to represent the interpretable vector of medical events, which can extract the concept relationship rich in medical information more effectively. Then, considering the strong dependence of clinical data on time stamp, LSTM network is used to model clinical events for better extraction of long-term and short-term information, so as to improve the prediction performance of the model. Finally, the fruit fly optimization algorithm is used to find the optimal super parameters of LSTM network, which can improve the training efficiency and prediction precision of the network. Experimental results on MIMIC datasets show that the prediction precision, Recall@k and MAP@k of the proposed model are better than those of other models. The validity of the model is proved.INDEX TERMS Fruit fly optimization algorithm, LSTM network, FastText method, clinical prediction, health time series data, MIMIC dataset.

Background: Traumatic lymphatic leakage is a rare but potentially life-threatening complication. The purpose of this study was to introduce the technique of ultrasound-guided intranodal lymphangiography and embolization in the postoperative lymphatic leakage in patients with cancer.Methods: During January 2018 and June 2020, seven cancer patients (three males, four females, aged 59-75 years [mean 67.57 ± 6.11 years]) developed lymphatic leakage after abdominal or pelvic surgery, with drainage volume ranging from 550 to 1200 mL per day. The procedure and follow-up of ultrasound-guided intranodal lymphangiography and embolization were recorded. This study retrospectively analysed the technical success rate, operation time, hospital stay, clinical efficacy, and complications.Results：The operation was technically successful in all patients. Angiography revealed leakage and embolization was performed in all the seven patients (7/7, 100%). The operative time of angiography and embolization was 41 to 68 minutes, with an average time of 53.29 ± 10.27 minutes. The mean length of stay was 3.51±1.13 days. Lymph node embolization was finally clinically successful in five patients (5/7, 71.43%), with a significant reduction in or disappearance of chylous ascites. The other two patients received surgical treatment 2 weeks later due to poor results after embolization. All patients were followed-up for 2 weeks. No serious complications or only minor complications were found in all the patients.Conclusions：Ultrasound-guided intranodal lymphangiography and embolization are easy to tolerance, with a low incidence of complications. Early intervention is recommended for cancer patients with postoperative lymphatic leakage.

Background: Traumatic lymphatic leakage is a rare but potentially life-threatening complication. The purpose of this study was to introduce ultrasound-guided intranodal lymphangiography and embolisation techniques for postoperative lymphatic leakage in patients with cancer.Methods: From January 2018 through June 2020, seven cancer patients (three males, four females, aged 59-75 years [mean 67.57 ± 6.11 years]) developed lymphatic leakage after abdominal or pelvic surgery, with drainage volumes ranging from 550 to 1200 mL per day. The procedure and follow-up of ultrasound-guided intranodal lymphangiography and embolisation were recorded. This study retrospectively analysed the technical success rate, operative time, length of hospital stay, clinical efficacy, and complications.Results: The operation was technically successful in all patients. Angiography revealed leakage and embolisation was performed in all seven patients (7/7, 100%). The operative time of angiography and embolisation was 41 to 68 minutes, with an average time of 53.29 ± 10.27 minutes. The mean length of stay was 3.51±1.13 days. Lymph node embolisation was clinically successful in five patients (5/7, 71.43%), who had a significant reduction in or disappearance of chylous ascites. The other two patients received surgical treatment two weeks later due to poor results after embolisation. All patients were followed for two weeks. No serious complications or only minor complications were found in all the patients.Conclusions: Ultrasound-guided intranodal lymphangiography and embolisation were well tolerated by the patients, who experienced a low incidence of complications. Early intervention is recommended for cancer patients with postoperative lymphatic leakage.