RESUMEN
BACKGROUND: We aimed to investigate the value of a machine learning (ML) algorithm in the preoperative prediction of lymph node metastasis in patients with rectal cancer. METHODS: Based on the histopathological results, 126 rectal cancer patients were divided into two groups: lymph node metastasis-positive and metastasis-negative groups. We collected clinical and laboratory data, three-dimensional endorectal ultrasound (3D-ERUS) findings, and parameters of the tumor for between-group comparisons. We constructed a clinical prediction model based on the ML algorithm, which demonstrated the best diagnostic performance. Finally, we analyzed the diagnostic results and processes of the ML model. RESULTS: Between the two groups, there were significant differences in serum carcinoembryonic antigen (CEA) levels, tumor length, tumor breadth, circumferential extent of the tumor, resistance index (RI), and ultrasound T-stage (P < 0.05). The extreme gradient boosting (XGBoost) model had the best comprehensive diagnostic performance for predicting lymph node metastasis in patients with rectal cancer. Compared with experienced radiologists, the XGBoost model showed significantly higher diagnostic value in predicting lymph node metastasis; the area under curve (AUC) value of the receiver operating characteristic (ROC) curve of the XGBoost model and experienced radiologists was 0.82 and 0.60, respectively. CONCLUSIONS: Preoperative predictive utility in lymph node metastasis was demonstrated by the XGBoost model based on the 3D-ERUS finding and related clinical information. This could be useful in guiding clinical decisions on the selection of different treatment strategies.
Asunto(s)
Endosonografía , Neoplasias del Recto , Humanos , Endosonografía/métodos , Metástasis Linfática/diagnóstico por imagen , Modelos Estadísticos , Pronóstico , Estadificación de Neoplasias , Neoplasias del Recto/diagnóstico por imagen , Neoplasias del Recto/cirugía , Neoplasias del Recto/patología , Algoritmos , Aprendizaje Automático , Estudios RetrospectivosRESUMEN
Arbuscular mycorrhizal (AM) fungi are an alternative to chemical insecticides or fertilizers, and there is an urgent need to extend the application of AM fungi to woody plants. This study aims to investigate the growth and resistance against the gypsy moth larvae (Lymantria dispar) in Glomus intraradices-colonized Populus alba × P. berolinensis seedlings, and to unravel the transcriptome and metabolome phenotypes recruited by AM fungus colonization that affect plant growth and insect resistance. Our results showed a positive mycorrhizal growth response, i.e., growth and biomass of mycorrhizal seedlings were enhanced. However, AM fungus inoculation reduced the resistance of poplar to gypsy moth larvae, as evidenced by the decreased carbon/nitrogen ratio in leaves, as well as the increased larval growth and shortened larval developmental duration. Transcriptome analysis revealed that in both auxin and gibberellin signaling transductions, all nodes were responsive to AM symbiosis and most differentially expressed genes belonging to effectors were up-regulated in mycorrhizal seedlings. Furthermore, the two key enzymes (4-coumarate-CoA ligase and trans-cinnamate 4-monooxygenase) involved in the synthesis of p-Coumaroyl-CoA, an initial metabolite in flavonoid biosynthesis and the first rate-limiting enzyme (chalcone synthase) in flavonoid biosynthesis, were down-regulated at the transcriptional level. Consistent with the transcriptome results, metabolome analysis found that the amounts of all differentially accumulated flavonoid compounds (e.g., catechin and quercetin) identified in mycorrhizal seedlings were decreased. Taken together, these findings highlight the diverse outcomes of AM fungi-host plant-insect interaction and reveal the regulatory network of the positive mycorrhizal growth response and mycorrhizal-induced reduction of insect resistance in poplar.