Monitoring Patient Health -- R Shiny Dashboard


Real time monitoring of patients in the intensive care units (ICUs) is paramount as it provides nurses and physicians a timely warning or alert of a significant change in the health status of the patient. Here, we are going to use a simple algorithm to determine the health status of a patient. In reality, patient deterioration monitoring algorithms are complex and normally requires realtime data from bedside monitors, lab results, patient health history from EMRs, and experts' judgment ... more.




Comparison of Median Salary by State and Visa-type


The salary of a given position depends on several factors such as years or experience, educational background, the cost of living of the city, visa type of the candidate. This Shiny app compares the annual median salaries of some professions by the state the job is located and the visa type of the candidate ... more.




Predicting Sentiment of Tweets: Analysis of 2016 Presidential Candidates


This post analyzes sentiment of tweets towards the 2016 presidatial candidate front runners and predicts the sentiment of tweets. CART and random forest classification models are also developed to classify tweets as Positive, Neutral, or Negative.Tweets containing the names of Bernie Sanders, Donald Trump, Hillary Clinton, and Ted Cruz were mined and analyzed... read more.



Text Mining and Sentiment Analysis Using R: Analysis of 2016 Presidential Candidates


This post analyzes sentiment of tweets towards the 2016 presidatial candidate front runners using R. Tweets containing the names of Bernie Sanders, Donald Trump, Hillary Clinton, and Ted Cruz were mined and analyzed ... read more.


Logistic Regression Model to Predict the Risk of Readmission for Diabetic Patients


Hospital readmissions are among the challenge that hospitals are facing today. Most of the readmission are believed to be preventable. Predictive models can be used to assess the chance of readmission of a patient within a given period. If the risk of readmission is high, patients can receive extended care before ... read more.


Multi-class Classification in R


Often the cost of classifying a high-risk patient is higher than the cost predicting a low-risk patient as a high-risk patient. Here claims data for groups of people in the Medicare program is used to predict hospital costs. ... read more.


Classification Tree for Court Decision


Classification trees have advantage over logistic regression models in that they are easy to interpret. ... read more.


Linear Regression Model to Analyze Energy Efficiency


This project performs energy efficency analysis using 12 different building shapes simulated in Ecotect. The buildings differ with respect to the glazing area, the glazing area distribution, and the orientation, amongst other parameters. Various settings are simulated as functions of the afore-mentioned characteristics. ... read more.



Exploratory Data Visualization in R


This subsection applies the plotting tools in R (including ggplot) to explore different sets of data.


Tutorial on the dplyr Package


The dplyr package is among the most important packages that make data analysis easier. This subsection use the dplyr package to analysis data... read more.