RÉSUMÉ
BACKGROUND: This study aimed to use artificial intelligence (AI) to integrate various radiological and clinical pathological data to identify effective predictors of contralateral cervical lymph node metastasis (CCLNM) in patients with papillary thyroid carcinoma (PTC) and to establish a clinically applicable model to guide the extent of surgery. METHODS: This prospective cohort study included 603 patients with PTC from three centers. Clinical, pathological, and ultrasonographic data were collected and utilized to develop a machine learning (ML) model for predicting CCLNM. Model development at the internal center utilized logistic regression along with other ML algorithms. Diagnostic efficacy was compared among these methods, leading to the adoption of the final model (random forest). This model was subject to AI interpretation and externally validated at other centers. RESULTS: CCLNM was associated with multiple pathological factors. The Delphian lymph node metastasis ratio, ipsilateral cervical lymph node metastasis number, and presence of ipsilateral cervical lymph node metastasis were independent risk factors for CCLNM. Following feature selection, a Delphian lymph node-CCLNM (D-CCLNM) model was established using the Random forest algorithm based on five attributes. The D-CCLNM model demonstrated the highest area under the curve (AUC; 0.9273) in the training cohort and exhibited high predictive accuracy, with AUCs of 0.8907 and 0.9247 in the external and validation cohorts, respectively. CONCLUSIONS: We developed a new, effective method that uses ML to predict CCLNM in patients with PTC. This approach integrates data from Delphian lymph nodes and clinical characteristics, offering a foundation for guiding surgical decisions, and is conveniently applicable in clinical settings.
RÉSUMÉ
Hepatocellular carcinoma (HCC) is one of the most deadly malignancies in the world, with strong invasiveness, low cure rate, high metastasis rate and poor prognosis. Sorafenib is the most important and effective first-line drug for the treatment of advanced hepatocellular carcinoma, but its clinical efficacy is severely limited by primary and acquired drug resistance. Mi-crornas ( micrornas) are small non-coding Rnas that play a key regulatory role in the occurrence and development of hepatocellular carcinoma and the progression of sorafenib resistance. This paper summarizes the role of micrornas in the initiation and development of sorafenib resistance in hepatocellular carcinoma, in order to further understand the mechanism of sorafenib anti-hep-atocellular carcinoma, and to provide valuable theoretical basis for clinical targeted therapy and prognosis improvement in hepatocellular carcinoma.
RÉSUMÉ
<p><b>Background</b>Despite recent advances that have improved the pregnancy success rates that can be achieved via in vitro fertilization (IVF) therapy, it is not yet clear which blastocyst morphological parameters best predict the outcomes of single blastocyst transfer. In addition, most of the previous studies did not exclude the effect of embryo aneuploidy on blastocysts transfer. Thus, the present study investigated the predictive value of various parameters on the pregnancy outcomes achieved via the transfer of frozen euploid blastocysts.</p><p><b>Methods</b>The study retrospectively analyzed 914 single euploid blastocyst transfer cycles that were performed at the Peking University Third Hospital Reproductive Medical Center between June 2011 and May 2016. The expansion, trophectoderm (TE), and inner cell mass (ICM) quality of the blastocysts were assessed based on blastocyst parameters, and used to differentiate between "excellent", "good", "average", and "poor"-quality embryos. The relationship between these embryo grades and the achieved pregnancy outcomes was then analyzed via the Chi-square and logistic regression tests.</p><p><b>Results</b>For embryo grades of excellent, good, average and poor, the clinical pregnancy rates were 65.0%, 59.3%, 50.3% and 33.3%, respectively; and the live-birth rates were 50.0%, 49.7%, 42.3% and 25.0%, respectively. Both the clinical pregnancy rate (χ = 21.28, P = 0.001) and live-birth rate (χ = 13.50, P < 0.001) increased with the overall blastocyst grade. Both rates were significantly higher after the transfer of a blastocyst that exhibited either an A-grade or B-grade TE, and similarly, an A-grade ICM, than after the transfer of a blastocyst that exhibited a C-grade TE and/or ICM. The degree of blastocyst expansion had no apparent effect on the clinical pregnancy or live-birth rate. All odds ratio were adjusted for patient age, body mass index, length (years) of infertility history, and infertility type.</p><p><b>Conclusions</b>A higher overall euploid blastocyst quality is shown to correlate most strongly with optimal pregnancy outcomes. The study thus supports the use of the described TE and ICM morphological grades to augment current embryo selection criteria.</p>