RESUMEN
Chimonanthus praecox is a famous traditional flower in China with high ornamental value. It has numerous varieties, yet its classification is highly disorganized. The distinctness, uniformity, and stability (DUS) test enables the classification and nomenclature of various species; thus, it can be used to classify the Chimonanthus varieties. In this study, flower traits were quantified using an automatic system based on pattern recognition instead of traditional manual measurement to improve the efficiency of DUS testing. A total of 42 features were quantified, including 28 features in the DUS guidelines and 14 new features proposed in this study. Eight algorithms were used to classify wintersweet, and the random forest (RF) algorithm performed the best when all features were used. The classification accuracy of the outer perianth was the highest when the features of the different parts were used for classification. A genetic algorithm was used as the feature selection algorithm to select a set of 22 reduced core features and improve the accuracy and efficiency of the classification. Using the core feature set, the classification accuracy of the RF model improved to 99.13%. Finally, K-means was used to construct a pedigree cluster tree of 23 varieties of wintersweet; evidently, wintersweet was clustered into a single class, which can be the basis for further study of genetic relationships among varieties. This study provides a novel method for DUS detection, variety identification, and pedigree analysis.
RESUMEN
BACKGROUND: There are no current standardized and accepted methods to characterize the surgical complexity of a laparoscopic hysterectomy. This leads to challenges when trying to understand the relationship between the patient and the surgical features and outcomes. The development of core feature sets for laparoscopic hysterectomy studies would enable future trials to measure the similar meaningful variables that can contribute to surgical complexity and outcomes. OBJECTIVE: The purpose of this study was to develop a core feature set for the surgical complexity of a laparoscopic hysterectomy. STUDY DESIGN: This was an international Delphi consensus study. A comprehensive literature review was conducted to identify the features that were reported in studies on laparoscopic hysterectomy complexity. All the features were presented for evaluation and prioritization to key experts in 3 rounds of online surveys. A priori consensus criteria were used to reach agreement on the final outcomes for inclusion in the core feature set. RESULTS: Experts represented North America, South America, Europe, Africa, Asia, and Oceania. Most of them had fellowship training in minimally invasive gynecologic surgery. Sixty-four potential features were entered into round 1. Experts reached a consensus on 7 features to be included in the core feature set. These features were grouped under the following domains: 1) patient features, 2) uterine features, and 3) nonuterine pelvic features. The patient features include obesity and other nonobesity comorbidities that alter or limit the ability of a surgeon to perform the basic or routine steps in a laparoscopic hysterectomy. The uterine features include the size and presence of fibroids. The nonuterine pelvic features include endometriosis, ovarian cysts, and adhesions (bladder-to-uterus, rectouterine pouch, and other adhesions). CONCLUSION: Using robust consensus science methods, an international consortium of experts has developed a core feature set that should be assessed and reported in all future studies that aim to assess the relationship between the patient features and surgical outcomes of laparoscopic hysterectomy.