Patient satisfaction survey.

Data courtesy of http://www.hcahpsonline.org. Centers for Medicare & Medicaid Services, Baltimore, MD.

Stroke prediction based on a random sample of the approximately 6 million patient records from GE Medical Quality Improvement Consortium (MQIC) database.

Source:

• http://www.visualizing.org/datasets/mqic-patient-data-100k-sample

In the U.K 2.6 million people have diabetes.It can have serious health consequences if not diagnosed immediately. A new improved way of detecting Diabetes which can change lives with this model. Data UCI

Medical charges in the USA. Average total payment based on state demographic data and 2012 elections winner in the state.

Source

• Demographics from Esri at Azure Datamarket

• Medical data from cms.gov

Model predicting hospital readmissions, by Major Diagnostic Category (MDC) and age.

Data sourced from HCUPnet - a services of the US Department of Health & Human Services: http://hcupnet.ahrq.gov/HCUPnet.jsp.

Model that predicts which percentage of patients will rate a hospital at 9 or 10, based on a dataset of hospital patient surveys. It shows which survey items and which scores are important for a good overall result. The data is from a list of hospital ratings for the Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS). HCAHPS is a national, standardized survey of hospital patients about their experiences during a recent inpatient hospital stay. https://data.medicare.gov/dataset/Survey-of-Patients-Hospital-Experiences-HCAHPS-/rj76-22dk

The aim is to distinguish between the presence and absence of cardiac arrhythmia and to classify it in one of the 16 groups:

• Class 01 refers to 'normal' ECG
• Classes 02 to 15 refers to different classes of arrhythmia
• Class 16 refers to the rest of unclassified ones.

For the time being, there exists a computer program that makes such a classification. However there are differences between the cardiolog's and the programs classification. Taking the cardiolog's as a gold standard we aim to minimise this difference by means of machine learning tools.

Source

Arrhythmia Data Set at UCI Machine Learning Repository

This model predicts one of three spinal statuses: normal, Hernia or Spondylolisthesis, based on a number of metrics.

The source is taken from UCI Machine learning Repository, from the Vertebral Column Dataset

Standardized data from Protos---An Exemplar-Based Learning Apprentice.

"Professional training for clinical audiology typically requires two years of graduate school culminating in a Master degree. Before becoming practicing clinicians, students must pass a national examination and serve a clinical-fellowship year following graduation. In the course of their graduate training, students see between 150-200 cases and then an additional 900-1200 cases in their clinical-fellowship year. To be consistent with this amount of training, a learning system should learn to perform demonstrably well given a training set of 200 cases. "

Bareiss, E. Ray, & Porter, Bruce (1987). Protos: An Exemplar-Based Learning Apprentice. In the Proceedings of the 4th International Workshop on Machine Learning, 12-23, Irvine, CA: Morgan Kaufmann.

Sources:

- Original Owner: Professor Jergen at Baylor College of Medicine

Donor: Bruce Porter

Standardized Version:

• Donor: Ross Quinlan

Taken from http://archive.ics.uci.edu/ml/machine-learning-databases/audiology/