Search

Abstract Background To provide a preoperative prediction model for lymph node metastasis in pancreatic cancer patients and provide molecular information of key radiomic features. Methods Two cohorts comprising 151 and 54 pancreatic cancer patients were included in the analysis. Radiomic features from the tumor region of interests were extracted by using PyRadiomics software. We used a framework that incorporated 10 machine learning algorithms and generated 77 combinations to construct radiomics-based models for lymph node metastasis prediction. Weighted gene coexpression network analysis (WGCNA) was subsequently performed to determine the relationships between gene expression levels and radiomic features. Molecular pathways enrichment analysis was performed to uncover the underlying molecular features. Results Patients in the in-house cohort (mean age, 61.3 years ± 9.6 [SD]; 91 men [60%]) were separated into training (n = 105, 70%) and validation (n = 46, 30%) cohorts. A total of 1,239 features were extracted and subjected to machine learning algorithms. The 77 radiomic models showed moderate performance for predicting lymph node metastasis, and the combination of the StepGBM and Enet algorithms had the best performance in the training (AUC = 0.84, 95% CI = 0.77–0.91) and validation (AUC = 0.85, 95% CI = 0.73–0.98) cohorts. We determined that 15 features were core variables for lymph node metastasis. Proliferation-related processes may respond to the main molecular alterations underlying these features. Conclusions Machine learning-based radiomics could predict the status of lymph node metastasis in pancreatic cancer, which is associated with proliferation-related alterations.

For French cochlear implant (CI) recipients, in-person clinical auditory rehabilitation is typically provided during the first few years post-implantation. However, this is often inconvenient, it requires substantial time resources and can be problematic when appointments are unavailable. In response, we developed a computer-based home training software (French AngelSound™) for French CI recipients. We recently conducted a pilot study to evaluate the newly developed French AngelSound™ in 15 CI recipients (5 unilateral, 5 bilateral, 5 bimodal). Outcome measures included phoneme recognition in quiet and sentence recognition in noise. Unilateral CI users were tested with the CI alone. Bilateral CI users were tested with each CI ear alone to determine the poorer ear to be trained, as well as with both ears (binaural performance). Bimodal CI users were tested with the CI ear alone, and with the contralateral hearing aid (binaural performance). Participants trained at home over a one-month period (10 hours total). Phonemic contrast training was used; the level of difficulty ranged from phoneme discrimination in quiet to phoneme identification in multi-talker babble. Unilateral and bimodal CI users trained with the CI alone; bilateral CI users trained with the poorer ear alone. Outcomes were measured before training (pre-training), immediately after training was completed (post-training), and one month after training was stopped (follow-up). For all participants, post-training CI-only vowel and consonant recognition scores significantly improved after phoneme training with the CI ear alone. For bilateral and bimodal CI users, binaural vowel and consonant recognition scores also significantly improved after training with a single CI ear. Follow-up measures showed that training benefits were largely retained. These preliminary data suggest that the phonemic contrast training in French AngelSound™ may significantly benefit French CI recipients and may complement clinical auditory rehabilitation, especially when in-person visits are not possible.

Providing appropriate feedback is important when learning to program. However, it is still unclear how different feedback strategies affect learning outcomes in programming. This study designed four different two-step programming feedback strategies and explored their impact on novice programmers' academic achievement, learning motivations, and self-efficacy. A quasi-experimental study was conducted for four classes of freshmen (261 students, average age = 19) in computer science over six weeks. The students received four different feedback strategies including "programming template and correct code without comments", "programming template and correct code with comments", "flowchart and correct code without comments", and "flowchart and correct code with comments" during their C language programming course. The results showed that none of the feedback strategies can promote novice programmers' learning motivations and self-efficacy, but using "programming template and correct code without comments" can improve academic achievement of these novice programmers. Further analysis of students' reflection demonstrated that providing "programming template and correct code without comments" had advantage in helping students interpret code, thereby guiding the students to think comprehensively and face challenges positively, as well as promoting student success when learning to program.

Online education has made it possible to implement the "classes suspended but learning continues" policy during the COVID-19 outbreak. However, the intangible sense of the online educational setting requires self-directed learning (SDL) and may force students to know the goals of learning that may impact their engagement. To understand the effect, based on situated expectancy-value theory, this study considered SDL as attitude and approach and constructed a research model to explore the mediating power of perceived value of knowing learning goals (PVKLG) related to participants' online learning engagement during the COVID-19 lockdown. Data were collected from 497 higher education students in China. After the confirmatory factor analysis with structural equation modeling, the results reported that SDL attitude and approach positively predicted learning engagement mediated by PVKLG. The results suggest that only when students have a high level of PVKLG will they be able to regulate their learning process through the two types of SDL and enhance their engagement in online learning contexts during the COVID-19 lockdown.

Enlarging the lateral space of drip tubes saves irrigation equipment costs (drip tubes and bypass), but it will lead to an increased risk of grain yield heterogeneity between wheat rows. Adjusting wheat row spacing is an effective cultivation measure to regulate a row’s yield heterogeneity. During a 2-year field experiment, we investigated the variations in yield traits and photosynthetic physiology by utilizing two different water- and fertilizer-demanding spring wheat cultivars (NS22 and NS44) under four kinds of drip irrigation patterns with different drip tube lateral spacing and wheat row spacing [① TR4, drip tube spacing (DTS) was 60 cm, wheat row horizontal spacing (WRHS) was 15 cm; ② TR6, DTS was 90 cm, WRHS was 15 cm; ③ TR6L, DTS was 90 cm, WRHS was 10 cm, inter-block spacing (IBS) was 35 cm; and ④ TR6S, DTS was 80 cm, WRHS was 10 cm, IBS was 25 cm]. The results showed that under 15-cm equal row spacing condition, after the number of wheat rows served by a single tube increased from four (TR4, control) to six (TR6), NS22 and NS44 exhibited a marked decline in yield. The decline of NS22 (9.93%) was higher than that of NS44 (9.04%), and both cultivars also showed a greater decrease in grain weight and average grain-filling rate (AGFR) of inferior grains (NS22: 23.19%, 13.97%; NS44: 7.78%, 5.86%) than the superior grains (NS22: 10.60%, 8.33%; NS44: 4.89%, 4.62%). After the TR6 was processed to narrow WRHS (from 15 to 10 cm) and add IBS (TR6L: 35 cm; TR6S: 25 cm), the grain weight per panicle (GWP) and AGFR of superior and inferior grains in the third wheat row (RW3) of NS22 and NS44 under TR6L increased significantly by 26.05%, 8.22%, 14.05%, 10.50%, 5.09%, and 5.01%, respectively, and under TR6S, they significantly increased by 20.78%, 9.91%, 16.19%, 9.28%, 5.01%, and 4.14%, respectively. The increase in GWP and AGFR was related to the increase in flag leaf area, net photosynthetic rate, chlorophyll content, relative water content, actual photochemical efficiency of PSII, and photochemical quenching coefficient. Among TR4, TR6, TR6L, and TR6S, for both NS22 and NS44, the yield of TR6S was significantly higher than that of TR6 and TR6L. Furthermore, TR6S showed the highest economic benefit.