Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

TMPM-ICD9: a trauma mortality prediction model based on ICD-9-CM codes.

Laurent G Glance¹, Turner M Osler, Dana B Mukamel

¹Department of Anesthesiology, University of Rochester School of Medicine, Rochester, New York 14642, USA. Laurent_Glance@urmc.rochester.edu

Annals of Surgery

|May 29, 2009

Summary

A new regression-based injury model, the Trauma Mortality Prediction Model (TMPM-ICD9), significantly improves upon the International Classification of Diseases ninth Edition Injury Severity Score (ICISS) for predicting trauma mortality. TMPM-ICD9 offers better discrimination and calibration for risk adjustment in trauma care.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

A Novel Method to Apply Race and Ethnicity Observation for Nursing Home Residents Using Multiple Medicare Administrative Datasets.

Medical care·2026

Same author

Nondialytic Care vs Dialysis Transition on Hospitalization: Outcomes in Veterans With Advanced Chronic Kidney Disease.

Mayo Clinic proceedings·2026

Same author

Hospital-Level Variation in Transcatheter vs Surgical Aortic Valve Replacement Among Patients Younger Than 65 Years.

The Annals of thoracic surgery·2026

Same author

Exploring online and in-person mental healthcare access and app use in a cohort of people living with disability: results from the 2019 and 2020 California Health Interview Survey.

Internet interventions·2026

Same author

When AI Writes Back: Ethical Considerations by Physicians on AI-Drafted Patient Message Replies.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026

Same author

Impact of Adverse Childhood Experiences (ACEs) on Mental Health Help-Seeking Among Asian American Adults: Findings from the 2021 California Health Interview Survey.

Journal of immigrant and minority health·2026

Area of Science:

Trauma research
Medical informatics
Public health

Background:

The American College of Surgeons mandates ICD-9-CM codes for trauma injury coding.
The International Classification of Diseases ninth Edition Injury Severity Score (ICISS) is widely used for risk adjustment but has calibration issues.
Accurate injury severity modeling is crucial for hospital trauma report cards.

Purpose of the Study:

To develop and validate a novel ICD-9 injury model using regression.
To estimate empiric injury severities for all ICD-9-CM codes.
To compare the performance of the new model against existing models like ICISS and the Single-Worst Injury (SWI) model.

Main Methods:

A regression-based approach was used to estimate injury severities for ICD-9-CM codes.

Related Experiment Videos

Data from 749,374 patients in the National Trauma Databank (version 7.0) were utilized.

Model performance was evaluated using ROC, Hosmer-Lemeshow, and Akaike information criterion statistics.

Main Results:

The new Trauma Mortality Prediction Model (TMPM-ICD9) demonstrated superior discrimination (ROC 0.880) and calibration (HL 29.3) compared to ICISS (ROC 0.850, HL 231) and SWI (ROC 0.862, HL 462).
Inclusion of age, gender, and mechanism of injury improved all models.
TMPM-ICD9 maintained superior performance even after incorporating these additional variables.

Conclusions:

TMPM-ICD9 uniformly outperforms both ICISS and the SWI model.
TMPM-ICD9 is recommended for risk-adjusting trauma outcomes when using ICD-9-CM codes.
This new model offers improved accuracy for trauma severity assessment and reporting.