|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/healthcare-data-literacy
课程评论：没有评论
课程名称: 医疗数据素养 概述: 本课程将帮助您打下医疗数据之旅的基础，提供在医疗行业作为数据科学家所需的知识和技能。医疗行业的特点在于其与健康管理和医疗护理相关的不断发展的复杂过程。我们将学习医疗中的许多方面，确定数据分析师在医疗中的价值和日益增长的需求。课程将介绍“三重目标”等数据驱动的医疗动力，涵盖医疗数据的不同概念和类别，并描述本体论及相关术语如分类法和术语如何组织概念以便于计算。我们将讨论医疗系统中常见的数据临床表示，包括ICD-10、SNOMED、LOINC、药物词汇（如RxNorm）和临床数据标准。此外，我们还将讨论各种类型的医疗数据，并评估在汇集不同类型数据以辅助决策时所面临的复杂性。我们将分析各种医疗数据类型和来源，包括临床、运营索赔和患者生成的数据，以及在健康数据上下文中区分非结构化、半结构化和结构化数据。课程还将深入探讨数据的内在运作，提供解决数据整合问题的一些解决方案，定义在该领域重要的一些概念、方法和应用。 课程大纲: 1. 医疗101 描述: 本模块将让您识别生物体系和社会体系在个人健康与福祉中的特征，描述美国医疗系统中的重要组织，并讨论具体示例来证明美国医疗系统中的高成本和可能的浪费。您将能够识别和讨论知识与行动之间的差距，并描述基于证据的努力如何将零散的护理过程转变为以患者为中心的协调活动。 2. 概念与类别 描述: 本模块将让您比较不同的交流形式，描述人们为何使用本体论来描述世界。您将能够描述美国标准化铁路的演变，并认识到铁路轨道的演变如何适用于医疗术语。您将分析疾病编码的数据集，并选择特定疾病所对应的编码。同时，您将能够将不同的术语与不同的描述域匹配，比较将信息组织为层级或其他类别的不同方式。 3. 医疗数据 描述: 本模块将让您识别不同类型的医疗流程，并解释为何这些多样化流程产生了特定的数据格式。您将列出电子健康记录（EHRs）中的多种数据类型，并关联生成这些输出的具体临床流程。此外，您将能够追溯为何收集各种行政数据，并描述这些数据在分析中的价值，同时识别基因序列常见的计算机可读文件存储方式，并描述大数据格式与普通关系数据库技术的不同之处。 4. 数据与概念和谐 描述: 本模块将让您向领导和同事们说明为何应该投入时间创建数据字典及其他元数据。您将描述某一烧伤登记处的数据片段化问题，以及各种标准化和集中化过程是如何帮助实现数据和谐的。您将回答为何有必要整合来自不同来源的数据。最后，您将能够进行数据映射，并沟通描述和执行记录链接时使用的技术术语。
Name:Healthcare 101
Description:In this module, you will be able to identify how biological and social systems are features of human well-being and health. You'll be able to describe important organizations in the US healthcare system and be able to discuss specific examples that document high cost and possible waste in the US healthcare system. You'll be able to identify and discuss the knowing-doing gap and be able to describe evidence-based efforts to transform fragmented care processes into coordinated patient-centered activities.
Name:Concepts and Categories
Description:In this module, you will be able to compare forms of communication and describe why people us ontologies to describe the world. You'll be able to describe the evolution of standardized railroads in the US and recognize why the evolution of railroad tracks also applies to medical terminologies. You'll be able to analyze a dataset with disease codes and also be able to select which codes refer to specific diseases. You'll be able to match different terminologies with different descriptive domains as well as be able to contrast the different ways of organizing information into hierarchies or other categories.
Name:Healthcare Data
Description:In this module, you will be able to identify different types of medical processes and be able to explain why specific data formats emerged from these varied processes. You'll be able to list numerous data types that are found within EHRs and link specific clinical processes that created these outputs. You'll be able to trace why various types of administrative data are collected and describe the value of this data for analytics. You'll be able to identify the common ways that gene sequences are stored in computer readable files and be able to describe how big data formats are different than common relational database technologies that require a lot of data modeling and planning.
Name:Data and Conceptual Harmony
Description:In this module, you will be able to tell leaders and coworkers why they should invest time in creating data dictionaries and other meta-data. You'll be able to describe why one burn registry had data fragmentation issues, and how a variety of standardization and centralization processes helped to achieve data harmony. You'll be able to answer why it is necessary to integrate data, even though the data is coming from disparate sources. You'll be able to perform data mapping as well as communicate the technical terms used to describe and perform record linkages.
This course will help lay the foundation of your healthcare data journey and provide you with knowledge and skills necessary to work in the healthcare industry as a data scientist. Healthcare is unique because it is associated with continually evolving and complex processes associated with health management and medical care. We'll learn about the many facets to consider in healthcare and determine the value and growing need for data analysts in healthcare. We'll learn about the Triple Aim and other data-enabled healthcare drivers. We'll cover different concepts and categories of healthcare data and describe how ontologies and related terms such as taxonomy and terminology organize concepts and facilitate computation. We'll discuss the common clinical representations of data in healthcare systems, including ICD-10, SNOMED, LOINC, drug vocabularies (e.g., RxNorm), and clinical data standards. We’ll discuss the various types of healthcare data and assess the complexity that occurs as you work with pulling in all the different types of data to aid in decisions. We will analyze various types and sources of healthcare data, including clinical, operational claims, and patient generated data as well as differentiate unstructured, semi-structured and structured data within health data contexts. We'll examine the inner workings of data and conceptual harmony offer some solutions to the data integration problem by defining some important concepts, methods, and applications that are important to this domain.
