Search

Efficient retrieval is one of the crucial services of digital library, and sorting is the core issue of efficient information retrieval. Given a list of candidate book titles, the sorting model is used to generate a sorted list of book titles. When learning-based sorting algorithms are applied in the filed of information retrieval, they often optimize the sorting model by minimizing the value of the pairwise loss function. However, existing analysis shows that minimizing the pairwise loss value does not necessarily lead to the optimal sorting performance of the listwise algorithm. It is also very difficult to combine the online learning sorting algorithm with the listwise algorithm. This paper proposes an online learning sorting algorithm based on listwise, which aims to realize the online learning sorting algorithm under the premise of ensuring the performance advantage of listwise algorithm, thereby reducing the retrieval complexity. Firstly, the problem of combining the online learning sorting algorithm with the listwise algorithm is solved. Secondly, the sorting model is optimized by minimizing the loss function based on the predicted list and the real list. Finally, an adaptive learning rate based on the online-listwise algorithm is proposed. Experimental results show that the proposed algorithm has better retrieval performance and speed. [ABSTRACT FROM AUTHOR]

Background: Complete resection (CR) serves as the standard of surgical treatment for retroperitoneal liposarcoma (RPLS). Unfortunately, even at referral centers, recurrence rates are high, and CR may not address multifocal diseases, which are a common phenomenon in RPLS. We sought to retrospectively compare the clinical outcomes of RPLS patients treated with total (ipsilateral) retroperitoneal lipectomy (TRL) and CR. Because TRL remove potentially multifocal tumors in the fat, patients may have a better prognosis than CR., Methods: Patients with primary/first-recurrent RPLS who had been treated at 5 referral centers were recruited from December 2014 to June 2018. Multivariable Cox regression analyses were conducted to determine the effects of demographic, operative, and clinicopathological variables on the following primary endpoints: local recurrence (LR), local recurrence-free survival (LRFS), and overall survival (OS)., Results: A total of 134 patients were enrolled in this retrospective study, 53 of whom underwent TRL, and 81 of whom underwent CR. The 2 groups were comparable in terms of age, gender, presentation (primary vs. first-recurrent RPLS), number of tumors (unifocal vs. multifocal) at presentation, and Fédération Nationale des Centres de Lutte Contre le Cancer (FNCLCC) grade. The TRL group had higher levels of preoperative hemoglobin (Hb) (13 vs. 12.5 g/dL; P=0.008) and a lower amount of intraoperative blood loss (400 vs. 500 mL; P=0.034), but there were no significant differences in the length of hospital stay (23 vs. 22 d; P=0.47) or complications (32 vs. 30; P=0.82) between the 2 groups. In a subset of patients with multifocal tumors at initial presentation, OS was more prolonged in those treated with TRL than those treated with CR (P=0.0272). Based on the multivariable analysis, primary liposarcoma and a low FNCLCC grade were associated with decreased LR and improved OS., Conclusions: TRL is a safe procedure that positively affects the OS of patients with multifocal RPLS. This novel strategy deserves further investigation in prospective studies., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://atm.amegroups.com/article/view/10.21037/atm-22-3332/coif). GKZ and HYY are from HBR Data Science Ltd. The other authors have no conflicts of interest to declare., (2022 Annals of Translational Medicine. All rights reserved.)