Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Survival Tree01:19

Survival Tree

138
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
138
Introduction To Survival Analysis01:18

Introduction To Survival Analysis

352
Survival analysis is a statistical method used to study time-to-event data, where the "event" might represent outcomes like death, disease relapse, system failure, or recovery. A unique feature of survival data is censoring, which occurs when the event of interest has not been observed for some individuals during the study period. This requires specialized techniques to handle incomplete data effectively.
The primary goal of survival analysis is to estimate survival time—the time...
352

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Obesity in Late Adolescence and Healthcare Costs in Young to Mid-Adulthood.

Diabetes, obesity & metabolism·2026
Same author

Falls Among Residents Living in Care Homes Using Real-Time Data Collection: A Large UK Case-Control Study.

Health science reports·2026
Same author

Correction to: Glucagon‑like peptide‑1 analogs activate AMP kinase leading to reversal of the Warburg metabolic switch in breast cancer cells.

Medical oncology (Northwood, London, England)·2026
Same author

Visualization of associative exploration of temporal concepts via frequent patterns.

Patterns (New York, N.Y.)·2025
Same author

Drug adherence, glycemic control, and weight reduction with subcutaneous semaglutide in real-world management of type 2 diabetes.

Diabetes research and clinical practice·2025
Same author

Sleep apnea test prediction based on Electronic Health Records.

Journal of biomedical informatics·2024

Related Experiment Video

Updated: Aug 28, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.8K

Temporal patterns selection for All-Cause Mortality prediction in T2D with ANNs.

Pavel Novitski1, Cheli Melzer Cohen2, Avraham Karasik2

  • 1Software and Information Systems Engineering, Ben Gurion University, Beer-Sheva, Israel.

Journal of Biomedical Informatics
|September 13, 2022
PubMed
Summary

Predicting mortality in elderly patients with type 2 diabetes and chronic kidney disease is possible using electronic health records. Novel methods for representing and selecting temporal patterns improve deep learning model performance for risk assessment.

Keywords:
Deep learningPattern miningTemporal data prediction

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Related Experiment Videos

Last Updated: Aug 28, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Area of Science:

  • Medical Informatics
  • Computational Biology
  • Gerontology

Background:

  • Elderly patients with type 2 diabetes (T2D) and chronic kidney disease (CKD) face high mortality risks.
  • Accurate mortality prediction is crucial for proactive interventions and improved patient outcomes.
  • Electronic Health Records (EHRs) offer rich data for predictive modeling but present challenges due to heterogeneity and temporal complexity.

Purpose of the Study:

  • To investigate the predictive capability of heterogeneous EHR data for mortality in elderly T2D patients with CKD.
  • To develop novel methods for representing and selecting temporal patterns from EHR data to enhance deep learning models.
  • To improve the accuracy and efficiency of mortality risk assessment in this vulnerable population.

Main Methods:

  • Temporal abstraction was used to convert multivariate temporal EHR data into symbolic time intervals.
  • Novel representations, integer TIRPs (iTirps) and binary TIRPs (bTirps), were introduced for Time Intervals Related Patterns (TIRPs).
  • A TIRP Ranking Criteria (TRC) method, including TRC Redundant TIRP Removal (TRC-RTR), was developed for selecting informative TIRPs. Deep learning models (RNN, CNN) and a predictive committee were employed.

Main Results:

  • The proposed iTirps and bTirps representations enabled the incorporation of temporal patterns into deep learning networks.
  • The TRC-RTR method effectively reduced the number of TIRPs, mitigating model under-performance.
  • iTirps-based models utilizing the TRC-RTR selected subset significantly outperformed models using raw data or the full set of discovered TIRPs.

Conclusions:

  • Novel TIRP representations (iTirps, bTirps) and selection methods (TRC, TRC-RTR) enhance the predictive power of deep learning models for mortality in elderly T2D patients with CKD.
  • This approach offers a promising strategy for improving risk stratification and personalized care in complex chronic disease populations.
  • Optimizing feature selection from temporal EHR data is key to achieving high accuracy in mortality prediction models.