Predicting in-hospital mortality of traffic victims: A comparison between AIS-and ICD-9-CM-related injury severity scales when only ICD-9-CM is reported

Belleghem, Griet Van; Devos, Stefanie; Wit, Liesbet De; Hubloue, Ives; Lauwaert, Door; Pien, Karen; Putman, Koen

doi:10.1016/j.injury.2015.08.025

Cited by 29 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Importantly, the ability of AIS-ICD mapped injury severity scores had only slightly lower performance in mortality prediction compared to registry calculated TRISS scores, which does suggest that EMR based datasets could be used to benchmark performance with respect to in-patient mortality for moderate to severe trauma across facilities using ICD based injury severity scores. The AUROC for mortality prediction associated with TRISS was much lower than previously reported [20] and may be related to the threshold for major trauma being an ISS greater than 12 in this study, rather than 16.…”

Section: Discussioncontrasting

confidence: 89%

“…Nevertheless, the ability to flag the majority of major trauma in terms of trauma volume using EMR based ICD diagnoses does open up possibilities for the use of ICD based injury severity scores (ICISS), which have been shown to be more predictive of in-hospital mortality [19,20]. Past analyses using ICISS were predicated on the ability of administrative and EMR datasets to adequately capture injury diagnoses with an established threshold for injury severity to define the population of major trauma.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Correlating injury severity scores and major trauma volume using a state-wide in-patient administrative dataset linked to trauma registry data—A retrospective analysis from New South Wales Australia

Dinh

Singh

Sarrami

et al. 2020

Injury

View full text Add to dashboard Cite

Section: Discussioncontrasting

confidence: 89%

Section: Discussionmentioning

confidence: 99%

Correlating injury severity scores and major trauma volume using a state-wide in-patient administrative dataset linked to trauma registry data—A retrospective analysis from New South Wales Australia

Dinh

Singh

Sarrami

et al. 2020

Injury

View full text Add to dashboard Cite

“…Despite the ability of ICDPIC to calculate numerous severity scores of historical interest, some of them arguably more accurate than ISS for hospitalized patients (Van Belleghem et al, 2016; Meredith et al, 2002), researchers have primarily used it to obtain an approximate AIS and/or ISS. The initial methodology for ICDPIC to perform this function was developed using ICD-9-CM codes and ISS data from the 2008 American College of Surgeons (ACS) National Trauma Data Bank (NTDB), and it has been validated by several independent researchers (Sears et al, 2014; Greene et al, 2015; Fleischman et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…There has been an ongoing debate about whether injury severity should be predicted based on expert opinion or derived from a reference database (Van Belleghem et al, 2016; Committee on Trauma, ACS, 2017). The former approach has generally been used for AIS and ISS, but the development of ICDPIC-R provides an opportunity to combine the familiar ISS format with a data-driven approach.…”

Section: Introductionmentioning

confidence: 99%

Open-access programs for injury categorization using ICD-9 or ICD-10

et al. 2018

View full text Add to dashboard Cite

BackgroundThe article introduces Programs for Injury Categorization, using the International Classification of Diseases (ICD) and R statistical software (ICDPIC-R). Starting with ICD-8, methods have been described to map injury diagnosis codes to severity scores, especially the Abbreviated Injury Scale (AIS) and Injury Severity Score (ISS). ICDPIC was originally developed for this purpose using Stata, and ICDPIC-R is an open-access update that accepts both ICD-9 and ICD-10 codes.MethodsData were obtained from the National Trauma Data Bank (NTDB), Admission Year 2015. ICDPIC-R derives CDC injury mechanism categories and an approximate ISS (“RISS”) from either ICD-9 or ICD-10 codes. For ICD-9-coded cases, RISS is derived similar to the Stata package (with some improvements reflecting user feedback). For ICD-10-coded cases, RISS may be calculated in several ways: The “GEM” methods convert ICD-10 to ICD-9 (using General Equivalence Mapping tables from CMS) and then calculate ISS with options similar to the Stata package; a “ROCmax” method calculates RISS directly from ICD-10 codes, based on diagnosis-specific mortality in the NTDB, maximizing the C-statistic for predicting NTDB mortality while attempting to minimize the difference between RISS and ISS submitted by NTDB registrars (ISSAIS). Findings were validated using data from the National Inpatient Survey (NIS, 2015).ResultsNTDB contained 917,865 cases, of which 86,878 had valid ICD-10 injury codes. For a random 100,000 ICD-9-coded cases in NTDB, RISS using the GEM methods was nearly identical to ISS calculated by the Stata version, which has been previously validated. For ICD-10-coded cases in NTDB, categorized ISS using any version of RISS was similar to ISSAIS; for both NTDB and NIS cases, increasing ISS was associated with increasing mortality. Prediction of NTDB mortality was associated with C-statistics of 0.81 for ISSAIS, 0.75 for RISS using the GEM methods, and 0.85 for RISS using the ROCmax method; prediction of NIS mortality was associated with C-statistics of 0.75–0.76 for RISS using the GEM methods, and 0.78 for RISS using the ROCmax method. Instructions are provided for accessing ICDPIC-R at no cost.ConclusionsThe ideal methods of injury categorization and injury severity scoring involve trained personnel with access to injured persons or their medical records. ICDPIC-R may be a useful substitute when this ideal cannot be obtained.

show abstract

“…[93] A limitation of this work is use of International Classification of Disease codes (ICD) for constructing ontological feature classes for Heart Failure. Despite known reliability concerns and systematic variations in their use, [94] ICD codes are still frequently used in biomedical research [95][96][97][98][99][100][101] and can convey valuable temporal information. [102] Nevertheless, utilizing more reliable ontologies, such as PheWAS, [103,104] may result in more precise feature generation and thus improve classification performance.…”

Section: Discussionmentioning

confidence: 99%

High-throughput Phenotyping with Temporal Sequences

Estiri

McCoy

Wagholikar

et al. 2019

Preprint

View full text Add to dashboard Cite

Electronic health records (EHRs) contain important temporal information about progression of disease and treatment outcomes. The objective of this paper is to propose and test a high-throughput approach for phenotyping using temporal sequences of EHR observations to derive predictive and interpretable data representations. Using expert labeled clinical data from a congestive heart failure (CHF) cohort, we applied a four-phase framework to mine new data representations from temporal sequences of EHR observations, reduce dimensionality of the feature space, evaluate feature importance, and classify CHF patients with CHF. We found that sequenced features significantly outperform raw EHR features in classifying heart failure patients. Compared to the gold standard created by a panel of domain experts, the best classifier using sequences of diagnosis and medication observations classified heart failure status with a receiver operating characteristic area under the curve of 0.926. Compared with their raw counterparts, the top sequenced features have lower prevalence in medical records, but present more useful information for classification as the majority of those who have the sequences are likely to have the disease. Raw EHR data are not direct reflections of true health states as they also reflect various healthcare processes. Our results demonstrated that data representations obtained from sequencing EHR observations can present novel insight about the progression of disease that is difficult to discern when clinical observation histories are treated independently. Harnessing knowledge of disease progression through temporal sequencing of EHR observations can improve computational disease classification or phenotyping.

show abstract

Predicting in-hospital mortality of traffic victims: A comparison between AIS-and ICD-9-CM-related injury severity scales when only ICD-9-CM is reported

Cited by 29 publications

References 14 publications

Correlating injury severity scores and major trauma volume using a state-wide in-patient administrative dataset linked to trauma registry data—A retrospective analysis from New South Wales Australia

Correlating injury severity scores and major trauma volume using a state-wide in-patient administrative dataset linked to trauma registry data—A retrospective analysis from New South Wales Australia

Open-access programs for injury categorization using ICD-9 or ICD-10

High-throughput Phenotyping with Temporal Sequences

Contact Info

Product

Resources

About