Big Data in Healthcare
Joseph Woodside shares examples of applied experimental learning in healthcare from his book, "Applied Health Analytics and Informatics Using SAS".
Uncategorized
How next-best-action could transform health care
Teenagers. I have three boys, and two of them are teenagers. 15 year-old Kav is my middle son, and he gave me permission to share his story here. When he was five, Kav was diagnosed with Type I Diabetes, and I'm in awe of how he's accepted this challenging, lifelong
Create and compare ROC curves for any predictive model
An ROC curve graphically summarizes the tradeoff between true positives and true negatives for a rule or model that predicts a binary response variable. An ROC curve is a parametric curve that is constructed by varying the cutpoint value at which estimated probabilities are considered to predict the binary event.
Georgia health department uses analytics to stop fraud in WIC program
In many grocery stores throughout the country, the acronym “WIC” accompanies a number of the food items on the shelves. The letters stand for the federal “Women, Infants and Children” program that provides nutritional food to pregnant women and their young children who are in need. While this is a
Check out the SAS Student Series during winter break
SAS is launching the SAS Student Series, which bundles thousands of dollars’ worth of training and certification materials into an affordable package for university students and recent graduates.
The digital utility era is now: The customer/grid nexus
Note: Today’s utility industry is in upheaval. All of the assumptions the business has run on have been turned on their heads. This post is the third in a three-part series looking at how analytics are helping utilities navigate this challenging landscape and find new opportunities for improvements in operations,
인공지능(AI)이 헬스케어 산업에 불러올 혁신적인 변화는?
인공지능(AI)이 우리에게 미치는 영향이 나날이 커지면서 일자리를 대체할 것이라는 우려도 높아지고 있습니다. 이를 위해서 인공지능의 윤리 방안과 규제에 대한 논의가 이루어지고, 기업이 알고리즘으로 인해 일자리를 빼앗긴 직원에게 재교육을 제공해야 한다는 목소리가 나오고 있는데요. 하지만 이러한 모든 내용은 인공지능이 미치는 부정적인 면에만 치우쳐 있습니다. 그렇다면 인공지능이 우리의 삶에 주는 혜택으로는 무엇이 있을까요? 인공지능,
5 principles of data management for analytics
Joyce Norris-Montanari cites five things she considers essential to data management for analytics.
Define custom color ramps by using the RANGEATTRMAP statement in GTL
The SGPLOT procedure enables you to use the value of a response variable to color markers or areas in a graph. For example, you can use the COLORRESPONSE= option to define a variable whose values will be used to color markers in a scatter plot or cells in a heat
SAS Government Leadership Forum highlights analytics in government innovation...and Pokemon?
One would expect analytics in government to be a hot topic at a SAS government event. What the crowd didn't see coming was Margaret Weichert, Acting Director of the US Office of Personnel Management and Deputy Director for Management at the Office of Management and Budget, touting her ability to
사물인터넷(IoT)은 보험 산업을 어떻게 발전시킬까요? ‘인슈어테크’ 실현을 위해 고려해야 할 5가지 과제
보험 업계는 변화에 느리다는 평을 받는 보수적인 산업이지만 지난 5년간 엄청난 변화와 혁신을 경험하고 있습니다. 보험사들은 고객과 유통 관계에서 혁신을 모색하며 디지털 이니셔티브에 많은 투자를 하고 있는데요. 이와 함께 데이터 분석, 인공지능 등의 정보기술(IT)을 활용해 기존 보험 산업을 혁신하는 인슈어테크(insurtech)가 디지털 기회를 활용할 수 있는 보험 업계의 새로운 분야로 떠오르고
Enhancing a congressional district map - one layer at a time
With the recent midterm elections here in the US, I frequently saw congressional district maps popping up in the news. And being a GraphGuy, I wanted to fully understand these maps, to see if I might could improve them. If you're interested in congressional district maps, follow along as I
Making life easier for your data scientists
Phil Simon chimes in with some tips on how to set these folks loose.
A Time of Giving
Fall…it’s my favorite time of year. The air is crisp, the leaves are colorful and exercising outdoors is once again appealing. Most of all, its this time of year that I turn my attention to one of my favorite events of the year: #GivingTuesday. While Cyber Monday and Black
Visualize the feasible region for a constrained optimization
When solving optimization problems, it is harder to specify a constrained optimization than an unconstrained one. A constrained optimization requires that you specify multiple constraints. One little typo or a missing minus sign can result in an infeasible problem or a solution that is unrelated to the true problem. This
Creating a custom 'I Voted' sticker
With today being an election day here in the US, I see a lot of people wearing the 'I Voted' sticker. This got me wondering if I could create my own sticker ... using SAS software and simple graphics primitives. :-) So I started by using Proc Gslide to create
Reporting on accelerometer data with SAS Visual Analytics
I've collected accelerometer data with a third-party app. I've used some SAS tricks to import all of my data readings in a single step. Now I'm ready to create a report of these data in SAS Visual Analytics.
인공지능(AI)이 재정의하는 윤리는? 윤리적인 인공지능 시스템 관리를 위한 4가지 핵심요소
인공지능(AI)은 1950년대부터 머신러닝, 링크 걸기 시작 딥러닝(deep learning), 인지 컴퓨팅(cognitive computing)이 점차 발전하면서 우리와 꽤 오랜 시간을 함께 해왔습니다. 최근 달라진 점이 있다면 아마 활용할 수 있는 데이터의 양이 어마어마하게 늘었다는 것인데요. 방대한 양의 데이터 덕분에 오늘날 과거에는 불가능했던 방식으로 인공지능 기반의 모델을 학습시킬 수 있게 되었습니다. 이러한 인공지능은 지금의 세상과 거대한 데이터를 이해하는
Maps, models, and analytic problem framing
What’s the most important component of analytic analysis? The data? The model? The deployment? Getting the business problem right? All the above? Or does it simply depend on who you ask? While the model gets all the attention, and the data requires most of the effort, there is that step
Fit the Pareto distribution in SAS
Will the real Pareto distribution please stand up? SAS supports three different distributions that are named "Pareto." The Wikipedia page for the Pareto distribution lists five different "Pareto" distributions, including the three that SAS supports. This article shows how to fit the two-parameter Pareto distribution in SAS and discusses the
Visualizing cities as constellations in the night sky
Who says technical people can't have fun!?! Similar to Throwback Thursday / #TBT (when people post one of their old/nostalgic photos on social media), I like the tradition of Fun Friday when I use a fun data topic to test our software - a test can be just as rigorous using
The myths and realities of AI in health care
Health care is facing an unprecedented need to reform, drive quality and cut costs. Growth in targeted, specific treatments and diagnostic technology, coupled with a rise in people with long-term and multiple chronic conditions, is creating unsustainable demand on the system. To thrive – or even merely survive – health
Mein Vater hat den spannendsten Job der Welt, denn er ist ein Data Scientist!
Mein Name ist Daniel und ich bin in der vierten Klasse. Diese Woche wurden die Eltern in meine Schule eingeladen, um uns etwas über ihre Arbeit zu erzählen. Und mein Vater war mit dabei. Am Anfang war ich etwas unsicher, ob ich mich darüber freuen sollte. Denn wenn sein Vortrag
SAS Viya：Python API向けパッケージ：DLPyの最新版1.0拡張機能概要紹介
SASでは、従来からオープン・AIプラットフォームであるSAS Viyaの機能をPythonから効率的に活用いただくためのハイレベルなPython向けAPIパッケージであるDLPyを提供してきました。 従来のDLPyは、Viya3.3以降のディープラーニング（CNN）と画像処理（image action set）のために作成された、Python API向けハイレベルパッケージです。 DLPyではKerasに似たAPIを提供し、より簡潔なコーディングで高度な画像処理やCNNモデリングが可能でした。 そして、この度、このDLPyが大幅に機能拡張されました。 最新版DLPy1.0では、以下の機能が拡張されています。 ■ 従来からの画像データに加え、テキスト、オーディオ、そして時系列データを解析可能 ■ 新たなAPIの提供: ・ RNN に基づくタスク: テキスト分類、テキスト生成、そして 系列ラベリング（sequence labeling） ・ 一般物体検出（Object Detection） ・ 時系列処理とモデリング ・ オーディオファイルの処理と音声認識モデル生成 ■ 事前定義ネットワーク（DenseNet, DarkNet, Inception, and Yolo）の追加 ■ データビジュアライゼーションとメタデータハンドリングの拡張 今回はこれらの拡張機能の中から「一般物体検出（Object Detection）」機能を覗いてみましょう。 SAS Viyaでは従来から画像分類（資料画像1.の左から２番目：Classification）は可能でした。例えば、画像に映っている物体が「猫」なのか「犬」なのかを認識・分類するものです。 これに加えて、DLPy1.0では、一般物体検出（資料画像1.の左から３番目：Object Detection）が可能になりました。 資料画像１. (引用：Fei-Fei Li & Justin Johnson & Serena Yeung’s Lecture
Why SAS?
I've worked at SAS for over 27 years and have often been asked: What does SAS do? or Why should I choose SAS? It all boils down to one question: Why SAS? While there are many approaches to answering this question, I recently came up with three short, yet powerful,
Improving model interpretability with LIME
We have updated our software for improved interpretability since this post was written. For the latest on this topic, read our new series on model-agnostic interpretability. While some machine learning models – like decision trees – are transparent, the majority of models used today – like deep neural networks, random forests, gradient boosting
Unasked fraud questions answered by AI
Artificial intelligence often seems misunderstood, especially in fraud. The same is true of machine learning. One of the amazing things about them is they ask the unasked questions. This occurs as artificial intelligence (AI) and machine learning (ML) go about their daily work. So, what is the unasked question? Too
Tracking Trump's approval rating
President Donald Trump - people seem to either love him or hate him. Which makes for an interesting data-analysis topic ... tracking Trump's approval rating. Follow along as I explore some data! I'll start with what I consider the 'best' approval-rating graph I've found so far. Here's a screen-capture of
Data is not the only decision maker
Jim Harris says people still play a pivotal role in data-driven decision making.
Teaching analytics: Advice from two experts
What skills will students need in order to pursue a lucrative career in analytics? I recently interviewed two professors to find out. In my first post, the professors discussed the importance of teaching and learning analytics. Today, we'll hear their top advice for students studying analytics, such as: get a