|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/healthcare-decoded-data-analytics/
课程评论：没有评论
课程名称：医疗保健信息技术解读 - 数据分析 课程概述：您是否希望学习如何在医疗数据中应用机器学习算法，并且使用Excel进行操作？如果是的话，这门课程非常适合您。课程的设计考虑了多种因素，结合了我在医疗信息技术领域22年的经验和12年的教学经历，面向技术和非技术背景的学生。 在本课程中，您将学习以下内容： - 理解患者旅程与收入周期管理工作流程，包括前台、中台和后台的内容。 - 数据可视化之旅，从数据源系统到报告的制作。 - 理解描述性、诊断性、预测性和处方性分析。 当前课程详细介绍的算法包括： - 简单线性回归 - 多元线性回归 - 加权线性回归 - 逻辑回归 - 多项式回归 - 有序回归 - KNN分类 - K均值聚类 - 经典时间序列ARIMA 课程中还详细解释了以下关键概念： - 同方差性与异方差性 - Breusch-Pagan和White检验 - 混淆矩阵 - 名义数据与有序数据 - AUC和ROC曲线 - 时间序列中的自相关函数(ACF)与偏自相关函数(PACF) - 时间序列差分 使用的医疗数据集包括： - 医疗保险数据 - 新冠病例 - 哮喘数据 - 肥胖会员注册 - 药品销售 - 前列腺癌 - 乳腺癌 - 妇产健康风险 **课程封面图像使用了来自Freepik网站的资产设计。**
Are you Interested in learning how to apply some machine learning algorithms using Healthcare data and that too using Excel? Yes, then look no further. This course has been designed considering various parameters. I combine my experience of twenty two years in Health IT and twelve years in teaching the same to students of various backgrounds (Technical as well as Non-Technical).In this course you will learn the following:Understand the Patient Journey via the Revenue Cycle Management Workflow - Front, Middle and Back OfficeThe Data Visualization Journey - Moving from Source System to creating ReportsUnderstand Descriptive, Diagnostic, Predictive and Prescriptive Analytics At present I have explained below AlgorithmsSimple Linear Regression Multiple Linear Regression Weighted Linear Regression Logistic Regression Multinomial Regression Ordinal Regression KNN Classification KMeans Clustering Classic Time Series ARIMA Some of the concepts key explained are listed below Homoscedasticity vs HeteroskedasticityBreusch-Pagan & White TestConfusion MatrixNominal vs Ordinal DataAUC & ROC CurveACF & PACF in Time SeriesDifferencing in Time Series Healthcare Datasets to create the algorithms.I have listed a the healthcare datasets used belowHealth Insurance DataCovid CasesAsthma DataObesity Member Enrollment Pharma SalesProstate CancerBreast CancerMaternal Health Risk**Course Image cover has been designed using assets from Freepik website.
