How can healthcare organizations use their big data assets into actionable clinical intelligence? To lower costs and improve outcomes, healthcare organizations have invested heavily in pooling in as much big data as they can get their hands on. From customer service call logs and clinical documentation to satisfaction surveys and patient-generated health data from the Internet of Things, providers of every size and speciality have fully accepted the notion that no scrap of information will go to waste in the era of machine learning, artificial intelligence, and semantic data lakes.
医疗保健组织如何将其大数据资产用于可行的临床情报中？ 为了降低成本并改善结果，医疗保健组织已投入大量资金来汇集尽可能多的大数据。 从客户服务呼叫日志和临床文档，到满意度调查和来自物联网的患者生成的健康数据，各种规模和专业的提供商都完全接受以下观点：在机器学习时代，不会浪费任何信息，人工智能和语义数据湖。
1.描述性分析 (1. Descriptive analytics)
This is the most common type of analytics. The majority of healthcare data, including clinical documentation, claims data, patient surveys, and lab tests, falls under this category. They tell clinicians what has already happened. The data describes events in the past to answer basic questions such as: “How many patients acquired an infection in the ICU the last month?” “When is the busiest time of day for the walk-in clinic?” “How many individuals in a given population have a diabetes diagnosis in their records?”
这是最常见的分析类型。 大多数医疗保健数据(包括临床文档，理赔数据，患者调查和实验室检查)都属于此类。 他们告诉临床医生已经发生了什么。 数据描述了过去发生的事件，以回答以下基本问题： “上个月有多少患者在ICU中感染？” “全天候诊所最繁忙的时间是什么时候？” “给定人口中有多少个人有糖尿病诊断记录？”
For most businesses, descriptive analytics is the heart of their everyday reporting. This includes simple reports such as inventory, workflow, warehousing, and sales, which can be compiled easily and provide a clear picture of a company’s operations.
对于大多数企业而言，描述性分析是其日常报告的核心。 这包括简单的报告，例如库存，工作流，仓储和销售，可以轻松地对其进行汇编并提供公司运营的清晰画面。
While this information is a good first step, and it can be valuable for clinical and operational management, there is only so much one can glean from a historical record. Descriptive analytics does not include forecasting or trending. It simply turns raw data into a report or other format that we can consume.
尽管此信息是很好的第一步，并且对于临床和操作管理可能是有价值的，但从历史记录中可以收集到的信息太多了。 描述性分析不包括预测或趋势。 它只是将原始数据转换成我们可以使用的报告或其他格式。
Tells you what happened.
告诉你发生了什么。
2.预测分析 (2. Predictive analytics)
The ability to extrapolate the course of future events from descriptive data. In order to tell a provider what is likely to happen in the near future, predictive analytics typically requires large volumes of real-time data, or something close to it, to generate an accurate, detailed, and precise trend line or risk score.
从描述性数据推断未来事件过程的能力。 为了告诉提供商不久的将来可能发生的情况，预测分析通常需要大量的实时数据或其附近的数据，以生成准确，详细和精确的趋势线或风险评分。
Predictive analytics aims to alert healthcare providers of the likelihood of events and outcomes before they occur. Driven by the rise of Artificial Intelligence (AI) and the Internet of Things (IoT), we now have algorithms that can be fed with historical as well as real-time data to make meaningful predictions. These predictive algorithms can be used both to support clinical decision making for individual patients and to inform interventions on a cohort or population level.
预测分析旨在在事件和结果发生之前提醒医疗保健提供者。 在人工智能(AI)和物联网(IoT)兴起的推动下，我们现在拥有可与历史数据和实时数据结合使用的算法，可以做出有意义的预测。 这些预测算法既可用于支持单个患者的临床决策，又可在队列或人群水平上为干预提供信息。
Tells you what will happen.
告诉你会发生什么。
3.规范分析 (3. Prescriptive analytics)
It doesn’t just answer the question of what is probably going to happen. Prescriptive analytics can tell a user what course of action would produce the highest likelihood of maximum benefit when a predicted event does occur.
它不仅回答了可能发生的问题。 规范分析可以告诉用户，当预测事件确实发生时，哪种行动方针将产生最大的最大收益可能性。
This is the aim of clinical decision support applications and many of the artificial intelligence initiatives that are currently cropping up across the industry.
这是临床决策支持应用程序和目前在整个行业中兴起的许多人工智能计划的目标。
Prescriptive analytics is starting to emerge most strongly in precision medicine, where algorithms can suggest a therapy that is most likely to produce a positive response based on the patient’s unique genetic makeup and clinical situation.
在精密医学中，规范分析开始出现最强劲的趋势，在该算法中，算法可以根据患者独特的基因组成和临床情况，提出最有可能产生积极React的疗法。
Tells you what can be done.
告诉您可以做什么。
Eshan Samaranayake
埃山·萨马拉纳亚克(Eshan Samaranayake)
获得访问专家视图的权限-订阅DDI Intel (Gain Access to Expert View — Subscribe to DDI Intel)
翻译自: https://medium.com/datadriveninvestor/descriptive-predictive-and-prescriptive-analytics-explained-f8a0393900cc