Skip to main navigation
Skip to search
Skip to main content
Icahn School of Medicine at Mount Sinai Home
Help & FAQ
Link opens in a new tab
Search content at Icahn School of Medicine at Mount Sinai
Home
Profiles
Research units
Publications & Research Outputs
Press/Media
Fairness in Predicting Cancer Mortality Across Racial Subgroups
Teja Ganta
,
Arash Kia
, Prathamesh Parchure
, Min Heng Wang
,
Melanie Besculides
,
Madhu Mazumdar
, Cardinale B. Smith
Icahn School of Medicine at Mount Sinai
Anesthesiology, Perioperative, and Pain Medicine
Population Health Science and Policy
Brookdale Department of Geriatrics and Palliative Medicine
CTSA ConduITS - Institutes for Translational Sciences
Graduate School of Biomedical Sciences
KL2
Medicine
Medicine - Hematology and Medical Oncology
Research output
:
Contribution to journal
›
Article
›
peer-review
8
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Fairness in Predicting Cancer Mortality Across Racial Subgroups'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Cancer Mortality
100%
Black Men
100%
White Patients
50%
Fairness Metrics
50%
Rate Ratio
37%
Racial Groups
37%
F1 Score
37%
Racial Bias
37%
Race Categories
37%
Disparate Impact
37%
Equal Opportunities
37%
Equalized Odds
37%
Mortality Risk
25%
Machine Learning Models
25%
Area under the Receiver Operating Characteristic (AUROC)
25%
Native American
25%
Clinical Application
12%
Clinical Setting
12%
Pairwise Comparison
12%
Patient Care
12%
Odds Ratio
12%
Electronic Health Records
12%
Health Systems
12%
Machine Learning
12%
Racial Disparities
12%
Mount Sinai
12%
Asian Patients
12%
Validation Data
12%
Cancer Registry
12%
Area under the Receiver Operating Characteristic Curve
12%
Model Prediction
12%
Random Forest Algorithm
12%
Social Security Death Index
12%
Cancer Care
12%
False Positive Rate
12%
Test Validity
12%
Positive Rate
12%
Performance Metrics
12%
Retrospective Data
12%
True Positive Rate
12%
Performance Areas
12%
True Positive
12%
Predictive Machine Learning
12%
Serious Illness Communication
12%
Discriminative Performance
12%
True-false
12%
Malignant Solid Tumors
12%
Impact Ratio
12%
Nursing and Health Professions
Cancer Mortality
100%
Rate Ratio
75%
Racial Group
75%
Malignant Neoplasm
50%
Cohort Analysis
50%
Odds Ratio
25%
Receiver Operating Characteristic
25%
Electronic Health Record
25%
Patient Care
25%
False Positive Result
25%
Solid Malignant Neoplasm
25%
Cancer Registry
25%
Random Forest
25%
Diseases
25%
Medicine and Dentistry
Cancer Mortality
100%
Racial Group
75%
Malignant Neoplasm
50%
Cohort Analysis
50%
Solid Malignant Neoplasm
25%
Clinician
25%
Patient Care
25%
Electronic Health Record
25%
Health System
25%
Racial Disparity
25%
Cancer Registry
25%
False Positive Result
25%
Odds Ratio
25%
Diseases
25%
Primary Outcome
25%
Mathematics
Positive Rate
100%
Characteristic Curve
50%
False Positive Rate
50%
Pairwise Comparison
50%
Validation Dataset
50%
Odds Ratio
50%
Pharmacology, Toxicology and Pharmaceutical Science
Cancer Mortality
100%
Malignant Neoplasm
50%
Cohort Study
50%
Cancer Registry
25%
Solid Malignant Neoplasm
25%
Diseases
25%
Agricultural and Biological Sciences
Malignant Neoplasm
100%
Learning System
37%
Machine Learning
37%
Ethnic Group
37%
Americans
25%
Patient Care
12%
Odds Ratio
12%