Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact


Repository Web            Google
View ALL Data Sets

× Check out the beta version of the new UCI Machine Learning Repository we are currently testing! Contact us if you have any issues, questions, or concerns. Click here to try out the new site.

Sepsis survival minimal clinical records Data Set
Download: Data Folder, Data Set Description

Abstract: This dataset collection contains minimal health records of 110,204 admissions (primary cohort), 19,051 admissions (study cohort), and 137 admissions (validation cohort) of patients who had sepsis.

Data Set Characteristics:  

Multivariate

Number of Instances:

110341

Area:

Life

Attribute Characteristics:

Integer

Number of Attributes:

4

Date Donated

2020-10-23

Associated Tasks:

Classification

Missing Values?

N/A

Number of Web Hits:

7993


Source:

The original dataset version of the primary cohort was collected by Siri Tandberg Knoop, Steinar Skrede, Nina Langeland, Hans Kristian Flaatten and made available by them on FigShare under the Attribution 4.0 International (CC BY 4.0: freedom to share and adapt the material) copyright in November 2017.

The original dataset version of the validation cohort was collected by Seung Hwan Lee, Jin Young Lee, Tae Hwa Hong, Bo Ok Kim, Yeon Ju Lee, Jae Gil Lee and made available by them on FigShare under the Attribution 4.0 International (CC BY 4.0: freedom to share and adapt the material) copyright in July 2018.

The current version of the datasets was elaborated by Davide Chicco and donated to the University of California Irvine Machine Learning Repository under the same Attribution 4.0 International (CC BY 4.0) copyright in October 2020. Davide Chicco can be reached at <davidechicco '@' davidechicco.it>


Data Set Information:

Primary cohort from Norway:
4 features for 110,204 patient admissions
file: 's41598-020-73558-3_sepsis_survival_primary_cohort.csv'

Study cohort (subset of the primary cohort) from Norway:
4 features for 19,051 patient admissions
file: 's41598-020-73558-3_sepsis_survival_study_cohort.csv'

Validation cohort from South Korea:
4 features for 137 patients
file: 's41598-020-73558-3_sepsis_survival_validation_cohort.csv'

A detailed description of the datasets can be found in the Datasets section of the following article:

Davide Chicco, Giuseppe Jurman, “Survival prediction of patients with sepsis from age, sex, and septic episode number alone”. Scientific Reports 10, 17156 (2020). [Web Link]


Attribute Information:

Four (4) clinical features:
- age_years: integer
- sex_0male_1female: binary
- episode_number: integer
- hospital_outcome_1alive_0dead: boolean

A detailed description of the datasets features can be found in the Datasets section of the following article:

Davide Chicco, Giuseppe Jurman, “Survival prediction of patients with sepsis from age, sex, and septic episode number alone”. Scientific Reports 10, 17156 (2020). [Web Link]


Relevant Papers:

Original study cohort dataset version:

Siri Tandberg Knoop, Steinar Skrede, Nina Langeland, and Hans Kristian Flaatten, 'Epidemiology and impact on all-cause mortality of sepsis in Norwegian hospitals: A national retrospective study'. PLoS ONE 12(11): e0187990. [Web Link]

Original validation cohort dataset version:

Seung Hwan Lee, Jin Young Lee, Tae Hwa Hong, Bo Ok Kim, Yeon Ju Lee, and Jae Gil Lee, 'Severe persistent hypocholesterolemia after emergency gastrointestinal surgery predicts in-hospital mortality in critically ill patients with diffuse peritonitis', PLoS ONE 13(7): e0200187. [Web Link]

Current dataset version on the UCI ML Repository:

Davide Chicco, Giuseppe Jurman, “Survival prediction of patients with sepsis from age, sex, and septic episode number alone”. Scientific Reports 10, 17156 (2020). [Web Link]



Citation Request:

Davide Chicco, Giuseppe Jurman, “Survival prediction of patients with sepsis from age, sex, and septic episode number alone”. Scientific Reports 10, 17156 (2020). [Web Link]


Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML