Automated Classification of 6-n-Propylthiouracil Taster Status with Machine Learning

Several studies have used taste sensitivity to 6-n-propylthiouracil (PROP) to evaluate interindividual taste variability and its impact on food preferences, nutrition, and health. We used a supervised learning (SL) approach for the automatic identification of the PROP taster categories (super taster (ST); medium taster (MT); and non-taster (NT)) of 84 subjects (aged 18–40 years). Biological features determined from subjects were included for the training system. Results showed that SL enables the automatic identification of objective PROP taster status, with high precision (97%). The biological features were classified in order of importance in facilitating learning and as prediction factors. The ratings of perceived taste intensity for PROP paper disks (50 mM) and PROP solution (3.2 mM), along with fungiform papilla density, were the most important features, and high estimated values pushed toward ST prediction, while low values leaned toward NT prediction. Furthermore, TAS2R38 genotypes were significant features (AVI/AVI, PAV/PAV, and PAV/AVI to classify NTs, STs, and MTs, respectively). These results, in showing that the SL approach enables an automatic, immediate, scalable, and high-precision classification of PROP taster status, suggest that it may represent an objective and reliable tool in taste physiology studies, with applications ranging from basic science and medicine to food sciences.     

Seminar联合病案导入式教学法在耳鼻咽喉科临床见习中的应用

目的研究Seminar联合病案导入式教学法在耳鼻咽喉头颈外科临床见习中的应用效果。 方法将2018年来首都医科大学宣武医院耳鼻咽喉头颈外科见习的七年制学生48人作为研究对象,随机分为两组,将采取传统教学法的设为对照组（n=24）,Seminar联合病案导入式教学法的设为实验组(n=24)。对比两组学生的理论考核成绩、基本检查操作成绩、教学满意度。结果实验组学员理论考核成绩为（93.00±3.13）分,基本检查操作成绩为( 90.25±2.97)分,高于对照组学生的( 87.70±3.57)分、( 85.92±4.68)分,组间比较差异具有统计学意义 (P<0.01);实验组学生的教学质量满意度( 95.80%) 高于对照组学生( 70.80%),组间比较差异具有统计学意义(P<0.05)。结论Seminar联合病案导入式教学法比传统教学法更能提高学生的学习力和操作动手能力,激发学生的兴趣,扩展临床思维,有助于学生对知识系统的掌握,教学效果显著。     

EczemaPred: A computational framework for personalised prediction of eczema severity dynamics

BackgroundAtopic dermatitis (AD) is a chronic inflammatory skin disease leading to substantial quality of life impairment with heterogeneous treatment responses. People with AD would benefit from personalised treatment strategies, whose design requires predicting how AD severity evolves for each individual.ObjectiveThis study aims to develop a computational framework for personalised prediction of AD severity dynamics.MethodsWe introduced EczemaPred, a computational framework to predict patient‐dependent dynamic evolution of AD severity using Bayesian state‐space models that describe latent dynamics of AD severity items and how they are measured. We used EczemaPred to predict the dynamic evolution of validated patient‐oriented scoring atopic dermatitis (PO‐SCORAD) by combining predictions from the models for the nine severity items of PO‐SCORAD (six intensity signs, extent of eczema, and two subjective symptoms). We validated this approach using longitudinal data from two independent studies: a published clinical study in which PO‐SCORAD was measured twice weekly for 347 AD patients over 17 weeks, and another one in which PO‐SCORAD was recorded daily by 16 AD patients for 12 weeks.ResultsEczemaPred achieved good performance for personalised predictions of PO‐SCORAD and its severity items daily to weekly. EczemaPred outperformed standard time‐series forecasting models such as a mixed effect autoregressive model. The uncertainty in predicting PO‐SCORAD was mainly attributed to that in predicting intensity signs (75% of the overall uncertainty).ConclusionsEczemaPred serves as a computational framework to make a personalised prediction of AD severity dynamics relevant to clinical practice. EczemaPred is available as an R package.     

Machine learning-based screening of the diagnostic genes and their relationship with immune-cell infiltration in patients with lung adenocarcinoma

BackgroundLung adenocarcinoma (LUAD) is the most common type of lung cancer, and has a dismal mortality rate of 80%, mainly due to diagnosis at an advanced stage. Biomarkers with high specificity and sensitivity for the early diagnosis of LUAD are sparse. This study aimed to identify markers for the early diagnosis of LUAD.MethodsThe {"type":"entrez-geo","attrs":{"text":"GSE32863","term_id":"32863"}}GSE32863 and {"type":"entrez-geo","attrs":{"text":"GSE75037","term_id":"75037"}}GSE75037 data sets were standardized and merged to screen for differentially expressed genes (DEGs). Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were conducted. The intersected DEGs from the least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM) regression analyses were considered the hub genes. Then the diagnostic ability and expression of hub genes was tested in {"type":"entrez-geo","attrs":{"text":"GSE63459","term_id":"63459"}}GSE63459 data set, Finally, CIBERSORT was used to analyze the correlation between the immune-infiltrating cells and hub genes.ResultsThe following 7 DEGs were intersected by the LASSO and SVM regression analyses: Locus 401286 (LOC401286), flavin-containing monooxygenase 2 (FMO2), XLKD1, Ras homolog family member J (RHOJ), scavenger receptor Class A member 5 (SCARA5), heat shock protein beta-2 (HSPB2), and serine incorporator 2 (SERINC2). The area under the receiver operating characteristic curve (AUC) of LOC401286, FMO2, XLKD1, RHOJ, SCARA5, HSPB2, and SERINC2 was 0.99, 1.00, 0.99, 1.00, 0.99, 0.99, and 0.98, respectively in the training groups. The AUC of LOC401286, FMO2, XLKD1, RHOJ, SCARA5, HSPB2, and SERINC2 was 0.97, 0.96, 0.94, 0.88, 0.85, 0.94 and 0.89, respectively in the validation group. The immune-cell infiltrations of naive B cells, memory B cells, plasma cells, naive cluster of differentiation (CD) 4 T cells, T follicular helper cells, regulatory T cells, gamma delta T cells, monocytes, M0 macrophages, M1 macrophages, resting mast cells, activated mast cells, and neutrophils were different between the normal and tumor tissues. Notably, these immune cells were correlated with the above-mentioned 7 diagnostic genes.ConclusionsWe identified 7 DEGs in LUAD tissue that can be considered diagnostic genes based on 2 machine-learning regression methods, which could be very helpful for the early diagnosis of LUAD in clinical practice.     

Teacher–student neural coupling during teaching and learning

Human communication is remarkably versatile, enabling teachers to share highly abstracted and novel information with their students. What neural processes enable such transfer of information across brains during naturalistic teaching and learning? Here, a teacher was scanned in functional magnetic resonance imaging while giving an oral lecture with slides on a scientific topic followed by a review lecture. Students were then scanned while watching either the intact Lecture and Review (N = 20) or a temporally scrambled version of the lecture (N = 20). Using intersubject correlation, we observed widespread Teacher–Student neural coupling spanning sensory cortex and language regions along the superior temporal sulcus as well as higher-level regions including posterior medial cortex (PMC), superior parietal lobule, and dorsolateral and dorsomedial prefrontal cortex. Teacher–student alignment in higher-level areas was not observed when learning was disrupted by temporally scrambling the lecture. Moreover, teacher–student coupling in PMC was significantly correlated with learning: the more closely the student’s brain mirrored the teacher’s brain, the more the student improved their learning score. Together, these results suggest that the alignment of neural responses between teacher and students may reflect effective communication of complex information across brains in classroom settings.     

小组学习和SPOC混合教学在医学院校程序设计类课程中的实践研究

分析传统教学存在的问题,提出针对医学院校程序设计类课程实施小组合作学习和SPOC混合教学模式,详细阐述该模式学习内容、教学实践情况及教学效果,指出该模式有助于提高学生学习效果、成绩以及自主学习能力。     

深度学习在生物医学数据中的应用

介绍深度学习方法常用模型结构,包括卷积神经网络和循环神经网络模型,总结目前生物医学数据分析中深度学习的最新应用情况,分析其在数据处理、模型构建和训练方法等方面共有问题的解决方法,指出深度学习方法应用于生物医学数据分析中仍需解决的问题。     

基于电子病历数据的临床表型提取及其应用进展

在介绍临床表型提取技术的基础上,利用临床决策支持技术、自然语言处理技术和机器学习方法,就从糖尿病相关电子病历中提取临床表型等方面进行系统综述,表明深度学习方法可以更高效准确地从电子病历数据中提取出临床表型,帮助临床研究人员更好地进行临床试验,提高医疗护理水平。