US Hospitals: Timely and Effective Care

Connie Zhang
Posted on Nov 6, 2016

Overview

Health care spending has increased dramatically over past decades in the United States, affecting individuals, companies and the government.  Many factors have an impact on the spending, and the major ones include actions of patients, doctors and hospitals. Increasing effort has been made by insurance companies and the government over the years to keep costs under control, while the public pays more attention to the healthcare performance as well.

In this project, we will investigate one of the major players of the healthcare system: the hospital.  The primary functions of hospitals consist of three parts:

  • Medical - treatment and management of patients
  • Patient Support - patient care includes nursing, dietary diagnostics, therapy, pharmacy and laboratory service
  • Administrative - execution of policies related to the hospital governing discharge of support services

We will focus on patient support, and try to shed some insight on how hospitals performed in a timely and effective manner.

The Data and Scope

The data used for this project is from the following link:

https://catalog.data.gov/dataset/timely-and-effective-care-hospital-e4aad

This dataset includes provider-level data for measures of  the following cares:

children's asthma care, colonoscopy care, heart failure care, pneumonia care, pregnancy/delivery care, preventive care

And the measurement for those type of care are listed as following:

Children's asthma care :
Home Management Plan of Care Document

Colonoscopy care:
[1] Endoscopy/polyp surveillance: appropriate follow-up interval for normal colonoscopy in average risk patients
[2] Endoscopy/polyp surveillance: colonoscopy interval for patients with a history of adenomatous polyps - avoidance of inappropriate use

Heart failure care:
Evaluation of LVS Function

Pneumonia care:
Initial antibiotic selection for CAP in immunocompetent patient

Preventive care:
[1] Healthcare workers given influenza vaccination
[2] Immunization for influenza

Pregnancy/delivery care:
Percent of newborns whose deliveries were scheduled early (1-3 weeks early), when a scheduled delivery was not medically necessary

 

The goal of the project is to supply a tool for users interested in the care list above to find information on the hospitals nationwide and ranking within state. The tool was built as a Shiny application using R.

Results

Here are the average score distribution across states for Children Asthma Care, Colonoscopy Care, Heart Failure Care.

childnation                                             colonnation

heartnation

The horizontal axis is the score range from 0 to 100. The plots show how many states fall within each score range. The plots also show that Children Asthma Care scores are in a wider range which indicates that the quality of care for this medical condition varies greatly across United States hospitals.

The other three score distributions of Pneumonia Care, Preventive Care and Pregnancy/Delivery Care are the following:

pnumination                                         preventnation

pregnation

The distribution of Pregnancy/Delivery Care shows the lowest score across the nation compared with the others.  These six plots will supply users with information about overall quality for each medical condition across states.

Besides the distributions above, we also supply the distribution through a map format and the top, bottom  , and average ranking on a state level. Here is a snapshot for Children Asthma Care:

children

 

We also supply the rankings of hospitals within each state for each care based on requests from users. Here is a snapshot of the function

stateranking

 

It will supply users with the available hospital names, addresses, and phone numbers based on the medical care chosen and the state a user selects. The top ranking hospital for each state is supplied upon user request.

Conclusion

We have investigated the quality of healthcare for six medical conditions and provided the distribution of the scores across the United States. We have seen some big variation across different states for some type of care and the data also showed that some states did not have many hospitals participate on some type of care, especially in Children's Asthma Care.

 

About Author

Connie Zhang

Connie Zhang

Connie Zhang, a marketing specialist, has been working in the field of data analysis since 2010. She holds a Ph.D. in Engineering,MBA and an Associateship of the Society of Actuary in United States.
View all posts by Connie Zhang >

Leave a Comment

No comments found.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp