Deep learning for intelligent diagnosis in thyroid scintigraphy

ObjectiveTo construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy.MethodsWe constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model’s performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents.ResultsThe recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided “diagnostic assistance” to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents.ConclusionDL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves’ disease and subacute thyroiditis.     

跨平台移动卵巢癌患者远程管理系统建设

建立跨平台移动卵巢癌患者远程管理系统，介绍系统开发相关技术、总体架构、各功能模块，包括病史采集、复查内容管理、医患交流管理等，指出该系统能够实现医患双方及时沟通，提供智能化服务。     

丰台区256名小学生体内重金属含量与智力和神经行为的相关性分析

目的:了解丰台区学龄儿童体内重金属分布现状及其与儿童智力发育和神经行为的相关性.方法:采用整群随机抽样的方法,抽取丰台区3所小学校的9 ～12岁的学龄儿童256名作为研究对象,进行瑞文智力测验和神经行为测验,检测血样和尿样中铬、镍、砷、硒、镉、汞、铊、铅含量.结果:256名儿童血铅、血硒、尿砷检出率为100％,铊检出率为0,其他金属的检出率在10.3％ ～71.1％之间,儿童血铬、血硒、血铅,尿硒含量与IQ呈正相关(P＜0.05);血汞、尿汞与IQ呈负相关(P＜0.05);儿童血砷、尿砷、尿铬、尿铅、尿硒与神经行为呈负相关(P＜0.05).结论:研究区域儿童体内各种金属均有检出应引起重视;汞对儿童的智商发育有不良的影响;硒对儿童智商有保护作用;金属砷、铬、硒、铊、铅对儿童神经行为发育有不良影响.     

医学院校物联网工程专业应用型人才培养的探索与实践

医学院校物联网工程专业作为新兴战略产业中的一个分支,既具有普通高校该专业的普遍性,又具有一定的特殊性,本文从实施卓越计划、智慧医疗、“211质量工程”三个方面探索了培养方案的制定策略,在实际教育过程中,从更新教育观念、改革课程教学、强化实践能力、重视科技创新四个方面进行了实践。     

智能化辅助NICU发育支持护理的实施

目的 探讨利用信息手段减少对患儿不良刺激及促进发育支持护理规范化执行的效果。方法 在移动护理终端增加医护人员刺激行为的监控提示及为护理人员按发育支持护理进行评估干预提供辅助决策的功能。对我院NICU出生胎龄<32周,体重<1500g的早产儿共73例进行随机分组,观察组37例借助信息系统进行干预,对照组36例行常规照护使用纸质的发育支持护理表格进行干预,比较两组患儿的操作刺激频次、开始经口喂养时间、完全经口喂养时间、每日体重增长情况、行为神经测定（neonatal behavioral neurological assessment,NBNA）,全身运动评估(general movements,GMs)。结果 观察组的日平均干扰频次明显低于对照组（P<0.05）; 纠正胎龄40周NBNA评分干预组高于对照组（P<0.05）,两组全GMs异常发生率无统计学意义（P>0.05）;干预组开始经口喂养时的纠正胎龄和完全经口喂养时的纠正胎龄均小于对照组（P<0.05）;干预组的平均住院天数低于对照组、体重增长速度明显高于对照组（P<0.05）。　结论 发育支持护理的智能化手段应用,可降低护理对患儿不良刺激的干扰频次,缩短住院时间、促进体重增长,改善早产儿预后。     

掌上智能用药系统的开发与应用

目的 提高患者用药的正确性与依从性,保障患者安全、有效、合理、经济的用药。方法 介绍我院研发的掌上智能用药系统的架构、设计特点及工作流程,详细论述该系统的创建用药计划、用药提醒、用药完成、用药后效应四大模块的功能与应用。结果 该系统采用移动手机应用,构建图文并茂的智能用药信息,能提醒患者按时服药,正确辨识药物,提高用药依从性与正确性。结论 信息化建设有利于促进药品的合理应用,保障患者用药安全,成为现阶段药学服务不可或缺的重要内容。     

传染病智慧化症状监测的进展与挑战

智慧化症状监测是我国传染病智慧化预警多点触发和多渠道预警体系的重要组成部分,是传统症状监测在新技术发展下的必然路径。智慧化症状监测不仅包括医院就诊患者的大量医疗数据,还囊括未在医院就诊、海量的非医疗数据。然而,发展的同时也迎来了挑战,如信息爆炸、成本-效益问题以及数据共享、数据安全和隐私问题。本文通过对智慧化症状监测相关概念发展的思考和总结,为传染病智慧化预警方法与技术的发展提供参考,为我国和全球传染病防控提供新思路。     

Intrapartum translabial ultrasound with pushing used to predict the difficulty in vacuum-assisted delivery of fetuses in non-occiput posterior position

Objective: Our aim is to evaluate the capacity of intrapartum translabial ultrasound (ITU) with pushing in the prediction of difficulty of fetal extraction in vacuum assisted deliveries. Prospective, observational study performed (2/2015–8/2015) on 75 nulliparous women, ≥37 weeks with singleton pregnancies at full dilatation who had ITU-with-pushing performed, previous to vacuum-placement for fetal extraction. Working on the translabial sagittal-plane, we assessed: Angle-Progression (AoP), Progression-Distance (PD) and Head-Direction (HD); in the axial plane we evaluated: Midline-Angle (MLA) and Head-Perineum-Distance (HPD). Vacuum extractions were classified as easy-difficulty (ED) (≤3 vacuum-pulls), difficult-unsuccessful (DD) (>3 vacuum-pulls). We did not assess occipito-posterior-presentations.

Results: Seventy nulliparous were studied (44-ED,26-DD). We observed no differences in obstetric, neonatal or intrapartum characteristics between the two study groups, with the following exceptions: newborn weight (3272?±?438?g versus 3540?±?372?g; p?=?0.011) and number of vacuum-pulls (1.4-ED-vs-4.4-DD; p?<?0.0005). AoP-pushing was 143.9°?±?14.6° in ED and 115.1°±?12.9° in DD (p?<?0.0005); Head-Up was 79.5% versus 38.4% (p?<?0.0005); PD-Pushing was 42.7?±?11.3?mm versus 30.4?±?9.8?mm (p?<?0.0005); MLA-Pushing was 27.6°±?26.6° versus 57.5°±26.5°(p=0.025); HPD-Pushing was 40.8?±?10.0?mm versus 47.4?±?10.9?mm (p?=?0.039).

Conclusion: We identified that the presence of an AoP-Pushing?>?128° predicts an Easy-Vacuum-Delivery (≤3 Vacuum-Pulls) in >85% of cases (Sen 80%–FPR 9.3%).