Registries,Databases and Repositories for Developing Artificial Intelligence in Cancer Care

Modern artificial intelligence techniques have solved some previously intractable problems and produced impressive results in selected medical domains. One of their drawbacks is that they often need very large amounts of data. Pre-existing datasets in the form of national cancer registries, image/genetic depositories and clinical datasets already exist and have been used for research. In theory, the combination of healthcare Big Data with modern, data-hungry artificial intelligence techniques should offer significant opportunities for artificial intelligence development, but this has not yet happened. Here we discuss some of the structural reasons for this, barriers preventing artificial intelligence from making full use of existing datasets, and make suggestions as to enable progress. To do this, we use the framework of the 6Vs of Big Data and the FAIR criteria for data sharing and availability (Findability, Accessibility, Interoperability, and Reuse). We share our experience in navigating these barriers through The Brain Tumour Data Accelerator, a Brain Tumour Charity-supported initiative to integrate fragmented patient data into an enriched dataset. We conclude with some comments as to the limits of such approaches.     

Development of a Simulation-Based Mastery Learning Curriculum for Breaking Bad News

Introduction

Physician communication impacts patient outcomes. However, communication skills, especially around difficult conversations, remain suboptimal, and there is no clear way to determine the validity of entrustment decisions. The aims of this study were to 1) describe the development of a simulation-based mastery learning (SBML) curriculum for breaking bad news (BBN) conversation skills and 2) set a defensible minimum passing standard (MPS) to ensure uniform skill acquisition among learners.

Increased alpha suppression with age during involuntary memory retrieval

Recent work suggests that while voluntary episodic memory declines with age, involuntary episodic memory, which comes to mind spontaneously without intention, remains relatively intact. However, the neurophysiology underlying these differences has yet to be established. The current study used electroencephalography (EEG) to investigate voluntary and involuntary retrieval in older and younger adults. Participants first encoded sounds, half of which were paired with pictures, the other half unpaired. EEG was then recorded as they listened to the sounds, with participants in the involuntary group performing a sound localization cover task, and those in the voluntary group additionally attempting to recall the associated pictures. Participants later reported which sounds brought the paired picture to mind during the localization task. Reaction times on the localization task were slower for voluntary than involuntary retrieval and for paired than unpaired sounds, possibly reflecting increased attentional demands of voluntary retrieval and interference from reactivation of the associated pictures respectively. For the EEG analyses, young adults showed greater alpha event-related desynchronization (ERD) during voluntary than involuntary retrieval at frontal and occipital sites, while older adults showed pronounced alpha ERD regardless of intention. Additionally, older adults showed greater ERD for paired than unpaired sounds at occipital sites, likely reflecting visual reactivation of the associated pictures. Young adults did not show this alpha ERD memory effect. Taken together, these data suggest that involuntary memory is largely preserved with age, but this may be due to older adults' greater recruitment of top-down control even when demand for such control is limited.     

亚慢性硝酸钇暴露对雌性大鼠学习记忆能力的影响

目的：观察稀土化合物硝酸钇[Y（NO₃）₃]亚慢性（90 d）暴露对大鼠学习记忆能力的影响，并探究其可能的机制，为全面评估稀土元素钇的健康风险提供科学依据。方法：选用刚离乳（PND21）SD雌性大鼠，根据质量随机分为4组，分别为对照组（ddH₂O），Y（NO₃）₃低剂量组[10 mg/（kg·d）]、中剂量组[40 mg/（kg·d）]和高剂量组[160 mg/（kg·d）]，每组15只。连续灌胃受试物90 d后进行旷场实验、高架十字迷宫实验、转棒实验、Morris水迷宫实验。水迷宫检测后，每组取5只雌鼠心脏原位灌注，进行脑组织病理学检查。每组剩余10只雌鼠摘取脑组织，紫外分光光度计检测雌鼠大脑皮质和海马中谷氨酸（Glu）的含量；Western blot检测海马组织中N-甲基-D-天冬氨酸（NMDA）受体蛋白表达情况。结果：与对照组相比，硝酸钇90 d暴露后，转棒实验中160 mg/（kg·d）剂量组大鼠在棒时间、在棒圈数、掉落速度明显升高（P<0.05）。在Morris水迷宫定位航向实验第4天时，40、160 mg/（kg·d）剂量组大鼠逃避潜伏期明显降低（P<0.05）；Morris水迷宫空间探索实验中，40 mg/（kg·d）剂量组大鼠穿越平台次数、目标象限游泳时间明显增加（P<0.05）；160 mg/（kg·d）剂量组穿越平台次数、进入目标象限次数、目标象限游泳时间明显增加（P<0.05）；160 mg/（kg·d）剂量组大鼠东北、东南、西南象限的逃避潜伏期明显低于西北象限的逃避潜伏期（P<0.05）。160 mg/（kg·d）剂量组大鼠海马中Glu含量和NMDA受体NR1含量均明显低于对照组（P<0.05）。40和160 mg/（kg·d）剂量组大鼠海马中NMDA受体NR2A含量明显低于对照组（P<0.05）。结论：硝酸钇亚慢性（90 d）暴露可以引起雌性大鼠空间学习记忆能力增强；硝酸钇可能通过降低海马组织神经元细胞外Glu含量，抑制NMDA受体激活，增强雌性大鼠的空间学习记忆能力。     

慕课在医学生假期课前预习中的应用探讨

高校医学生会利用假期时间对将要学习的科目进行预习,力求提前了解或掌握,以利于日后对知识的充分理解。预习对于医学科目学习有一定必要性,然而传统的假期预习模式常存在缺乏引导、效率难以提升等问题。目前,慕课在医学教育领域的应用有所发展。对于医学生,其自主学习的模式、课程设计等契合医学课程的预习需求和假期学习的特点,有助于提升医学生的学习能力和假期预习效果。医学生将慕课作为假期预习资源可有多种学习模式选择。慕课平台的功能拓展和学校教师的辅助可以有效深入慕课在医学生假期预习中的应用,为医学生带来更合理的假期学习安排。     

Rethinking PICO in the Machine Learning Era: ML-PICO

Background  Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers. Objective  We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes). We describe how the ML-PICO framework can be applied toward appraising literature describing ML models for health care. Conclusion  The relevance of ML to practitioners of clinical medicine is steadily increasing with a growing body of literature. Therefore, it is increasingly important for clinicians to be familiar with how to assess and best utilize these tools. In this paper we have described a practical framework on how to read ML papers that create a new ML model (or diagnostic test): ML-PICO. We hope that this can be used by clinicians to better evaluate the quality and utility of ML papers.