Validation of ICD-10-CM surveillance codes for traumatic brain injury inpatient hospitalizations.
Ontology highlight
ABSTRACT:
SUBMITTER: Warwick J
PROVIDER: S-EPMC7808251 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background:The International Classification of Diseases, Ninth Edition, Clinical Modification (ICD-9-CM) Injury Severity Score (ICISS) is a risk adjustment model when injuries are recorded using ICD-9-CM coding. The trauma mortality prediction model (TMPM-ICD9) provides better calibration and discrimination compared with ICISS and injury severity score (ISS). Though TMPM-ICD9 is statistically rigorous, it is not precise enough mathematically and has the tendency to overestimate injury severity. The purpose of this study is to develop a new ICD-10-CM injury model which estimates injury severities for every injury in the ICD-10-CM lexicon by a combination of rigorous statistical probit models and mathematical properties and improves the prediction accuracy. Methods:We developed an injury mortality prediction (IMP-ICDX) using data of 794,098 patients admitted to 738 hospitals in the National Trauma Data Bank from 2015 to 2016. Empiric measures of severity for each of the trauma ICD-10-CM codes were estimated using a weighted median death probability (WMDP) measurement and then used as the basis for IMP-ICDX. ISS (version 2005) and the single worst injury (SWI) model were re-estimated. The performance of each of these models was compared by using the area under the receiver operating characteristic (AUC), the Hosmer-Lemeshow (HL) statistic, and the Akaike information criterion statistic. Results:IMP-ICDX exhibits significantly better discrimination (AUCIMP-ICDX, 0.893, and 95% confidence interval (CI), 0.887 to 0.898; AUCISS, 0.853, and 95% CI, 0.846 to 0.860; and AUCSWI, 0.886, and 95% CI, 0.881 to 0.892) and calibration (HLIMP-ICDX, 68, and 95% CI, 36 to 98; HLISS, 252, and 95% CI, 191 to 310; and HLSWI, 92, and 95% CI, 53 to 128) compared with ISS and SWI. All models were improved after the extension of age, gender, and injury mechanism, but the augmented IMP-ICDX still dominated ISS and SWI by every performance. Conclusions:The IMP-ICDX has a better discrimination and calibration compared to ISS. Therefore, we believe that IMP-ICDX could be a new viable trauma research assessment method.
| S-EPMC6787998 | biostudies-literature
Project description:Various assessment methods based on the International Classification of Diseases, Tenth Edition, Clinical Modification (ICD-10-CM), such as ICD-10-CM Injury Severity Score (ICISS), trauma mortality prediction model (TMPM-ICD10), and injury mortality prediction (IMP-ICDX), are purely anatomic trauma assessment, which need to be further improved. Traumatic injury mortality prediction (TRIMP-ICDX) is a comprehensive assessment method based on anatomic injuries and incorporating available information to determine whether it is superior to Trauma and Injury Severity Score (TRISS) and IMP-ICDX in predicting trauma outcomes. This retrospective cohort study was based on data from 704,287 trauma patients admitted to 710 trauma centers in the National Trauma Data Bank of the United States in 2016. The TRIMP-ICDX was established using anatomical injury, physiological reserves, and physiological response indicators. Its performance was compared with the IMP-ICDX and TRISS by examining the area under the receiver operating characteristic curve (AUC), calibration (Hosmer-Lemeshow goodness-of-fit test, HL), and the Akaike information criterion (AIC). The TRIMP-ICDX showed significantly better discrimination (AUCTRIMP-ICDX 0.968; 95% confidence interval (CI), 0.966–0.970, AUCTRISS 0.922; 95% CI, 0.918–0.925, and AUCIMP-ICDX 0.894; 95% CI, 0.890–0.899), better calibration (HLTRIMP-ICDX 5.6; 95% CI, 3.0–8.0, HLTRISS 72.7; 95% CI, 38.4–104.5, and HLIMP-ICDX 53.1; 95% CI, 26.6–77.8), and a lower AIC (AICTRIMP-ICDX 24,774, AICTRISS 30,753, and AICIMP-ICDX 32,780) compared with TRISS and IMP-ICDX. Similar results were found in statistical comparisons among different body regions. As a comprehensive evaluation method based on the ICD-10-CM lexicon TRIMP-ICDX is significantly better than IMP-ICDX and TRISS with respect to both discriminative power and calibration. The TRIMP-ICDX should become a research method for the comprehensive evaluation of trauma severity.
| S-EPMC9351923 | biostudies-literature
Project description:BACKGROUND:The phecode system was built upon the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) for phenome-wide association studies (PheWAS) using the electronic health record (EHR). OBJECTIVE:The goal of this paper was to develop and perform an initial evaluation of maps from the International Classification of Diseases, 10th Revision (ICD-10) and the International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) codes to phecodes. METHODS:We mapped ICD-10 and ICD-10-CM codes to phecodes using a number of methods and resources, such as concept relationships and explicit mappings from the Centers for Medicare & Medicaid Services, the Unified Medical Language System, Observational Health Data Sciences and Informatics, Systematized Nomenclature of Medicine-Clinical Terms, and the National Library of Medicine. We assessed the coverage of the maps in two databases: Vanderbilt University Medical Center (VUMC) using ICD-10-CM and the UK Biobank (UKBB) using ICD-10. We assessed the fidelity of the ICD-10-CM map in comparison to the gold-standard ICD-9-CM phecode map by investigating phenotype reproducibility and conducting a PheWAS. RESULTS:We mapped >75% of ICD-10 and ICD-10-CM codes to phecodes. Of the unique codes observed in the UKBB (ICD-10) and VUMC (ICD-10-CM) cohorts, >90% were mapped to phecodes. We observed 70-75% reproducibility for chronic diseases and <10% for an acute disease for phenotypes sourced from the ICD-10-CM phecode map. Using the ICD-9-CM and ICD-10-CM maps, we conducted a PheWAS with a Lipoprotein(a) genetic variant, rs10455872, which replicated two known genotype-phenotype associations with similar effect sizes: coronary atherosclerosis (ICD-9-CM: P<.001; odds ratio (OR) 1.60 [95% CI 1.43-1.80] vs ICD-10-CM: P<.001; OR 1.60 [95% CI 1.43-1.80]) and chronic ischemic heart disease (ICD-9-CM: P<.001; OR 1.56 [95% CI 1.35-1.79] vs ICD-10-CM: P<.001; OR 1.47 [95% CI 1.22-1.77]). CONCLUSIONS:This study introduces the beta versions of ICD-10 and ICD-10-CM to phecode maps that enable researchers to leverage accumulated ICD-10 and ICD-10-CM data for PheWAS in the EHR.
| S-EPMC6911227 | biostudies-literature
Project description:The Sentinel Distributed Database (SDD) is a large database of patient-level medical and prescription records, primarily derived from insurance claims and electronic health records, and is sponsored by the U.S. Food and Drug Administration for drug safety assessments. In this chart validation study, we report on the positive predictive value (PPV) of inpatient ICD-9-CM acute ischemic stroke (AIS) administrative diagnosis codes (433.x1, 434.xx, and 436) in the SDD.As part of an assessment of the risk of thromboembolic adverse events following treatment with intravenous immune globulin (IGIV), charts were obtained for 131 potential post-IGIV AIS cases. Charts were abstracted by trained nurses and then adjudicated by stroke experts using pre-specified diagnostic criteria.Case status could be determined for 128 potential AIS cases, of which 34 were confirmed. The PPVs for the inpatient AIS diagnoses recorded in the SDD were 27% overall [95% confidence interval (95% CI): 19-35], 60% (95% CI: 32-84) for principal-position diagnoses, 42% (95% CI: 28-57) for secondary diagnoses, and 6% (95% CI: 2-15) for position-unspecified diagnoses (which in the SDD generally originate from separate physician claims associated with an inpatient stay).Position-unspecified diagnoses were unlikely to represent true AIS cases. PPVs for principal and secondary inpatient diagnosis codes were higher, but still meaningfully lower than estimates from prior chart validation studies. The low PPVs may be specific to the IGIV user study population. Additional research is needed to assess the validity of AIS administrative diagnosis codes in other study populations within the SDD.
| S-EPMC6392785 | biostudies-literature
Project description:ObjectiveTo develop, test, and validate the performance of ICD-10-CM claims-based case definitions for identifying children with sickle cell anemia (SCA).Data sourcesMedicaid administrative claims (2016) for children <18 years with potential SCA (any D57x diagnosis code) and newborn screening records from Michigan and New York State.Study designThis study is a secondary data analysis.Data collection/extraction methodsUsing specific SCA-related (D5700, D5701, and D5702) and nonspecific (D571) diagnosis codes, 23 SCA case definitions were applied to Michigan Medicaid claims (2016) to identify children with SCA. Measures of performance (sensitivity, specificity, area under the ROC curve) were calculated using newborn screening results as the gold standard. A parallel analysis was conducted using New York State Medicaid claims and newborn screening data.Principal findingsIn Michigan Medicaid, 1597 children had ≥1 D57x claim; 280 (18 percent) were diagnosed with SCA. Measures of performance varied, with sensitivities from 0.02 to 0.97 and specificities from 0.88 to 1.0. The case definition of ≥1 outpatient visit with a SCA-related or D571 code had the highest area under the ROC curve, with a sensitivity of 95 percent and specificity of 92 percent. The same definition also had the highest performance in New York Medicaid (n = 2454), with a sensitivity of 94 percent and specificity of 86 percent.ConclusionsChildren with SCA can be accurately identified in administrative claims using this straightforward case definition. This methodology can be used to monitor trends and use of health services after transition to ICD-10-CM.
| S-EPMC7080376 | biostudies-literature
Project description:BACKGROUND:Many public health surveillance programs utilize hospital discharge data in their estimation of disease prevalence. These databases commonly use the International Classification of Diseases (ICD) coding scheme, which transitioned from the ICD-9 clinical modification (ICD-9-CM) to ICD-10-CM on October 1, 2015. This study examined this transition's impact on the prevalence of major birth defects among infant hospitalizations. METHODS:Using data from the Agency for Health Care Research and Quality-sponsored National Inpatient Sample, hospitalizations during the first year of life with a discharge date between January 1, 2012 and December 31, 2016 were used to estimate the monthly national hospital prevalence of 46 birth defects for the ICD-9-CM and ICD-10-CM timeframes separately. Survey-weighted Poisson regression was used to estimate 95% confidence intervals for each hospital prevalence. Interrupted time series framework and corresponding segmented regression was used to estimate the immediate change in monthly hospital prevalence following the ICD-9-CM to ICD-10-CM transition. RESULTS:Between 2012 and 2016, over 21 million inpatient hospitalizations occurred during the first year of life. Among the 46 defects studied, statistically significant decreases in the immediate hospital prevalence of five defects and significant increases in the immediate hospital prevalence of eight defects were observed after the ICD-10-CM transition. CONCLUSIONS:Changes in prevalence were expected based on changes to ICD-10-CM. Observed changes for some conditions may result from variation in monthly hospital prevalence or initial unfamiliarity of coders with ICD-10-CM. These findings may help birth defects surveillance programs evaluate and interpret changes in their data related to the ICD-10-CM transition.
| S-EPMC7194333 | biostudies-literature
Project description:Craniofacial microsomia (CFM) is a congenital condition characterized by microtia and mandibular underdevelopment. Healthcare databases and birth defects surveillance programs could be used to improve knowledge of CFM. However, no specific International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) code exists for this condition, which makes standardized data collection challenging. Our aim was to evaluate the validity of existing ICD-9-CM codes to identify individuals with CFM.Study sample eligibility criteria were developed by an expert panel and matched to 11 ICD-9-CM codes. We queried hospital discharge data from two craniofacial centers and identified a total of 12,254 individuals who had ?1 potentially CFM-related code(s). We reviewed all (n = 799) medical records identified at the University of North Carolina (UNC) and 500 randomly selected records at Seattle Children's Hospital (SCH). Individuals were classified as a CFM case or non-case.Thirty-two individuals (6%) at SCH and 93 (12%) at UNC met the CFM eligibility criteria. At both centers, 59% of cases and 95% of non-cases had only one code assigned. At both centers, the most frequent codes were 744.23 (microtia), 754.0 and 756.0 (nonspecific codes), and the code 744.23 had a positive predictive value (PPV) >80% and sensitivity >70%. The code 754.0 had a sensitivity of 3% (PPV <1%) at SCH and 36% (PPV = 5%) at UNC, whereas 756.0 had a sensitivity of 38% (PPV = 5%) at SCH and 18% (PPV = 26%) at UNC.These findings suggest the need for a specific CFM code to facilitate CFM surveillance and research.
| S-EPMC3522759 | biostudies-literature
Project description:BackgroundMost current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions.ObjectiveWe aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods.MethodsWe compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the three-character-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted.ResultsIn medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698).ConclusionsThe word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.
| S-EPMC6683650 | biostudies-literature
Project description:BACKGROUND:The Sentinel Distributed Database (SDD) is a large database of patient-level administrative health care records, primarily derived from insurance claims and electronic health records, and is sponsored by the US Food and Drug Administration for medical product safety evaluations. Acute myocardial infarction (AMI) is a common study endpoint for drug safety studies that rely on health records from the SDD and other administrative databases. PURPOSE:In this chart validation study, we report on the positive predictive value (PPV) of inpatient International Classification of Diseases, Ninth Revision, Clinical Modification AMI administrative diagnosis codes (410.x1 and 410.x0) in the SDD. METHODS:As part of an assessment of thromboembolic adverse event risk following treatment with intravenous immune globulin, charts were obtained for 103 potential post-intravenous immune globulin AMI cases. Charts were abstracted by trained nurses and physician-adjudicated based on prespecified diagnostic criteria. RESULTS:Acute myocardial infarction status could be determined for 89 potential cases. The PPVs for the inpatient AMI diagnoses recorded in the SDD were 75% overall (95% CI, 65-84%), 93% (95% CI, 78-99%) for principal-position diagnoses, 88% (95% CI, 72-97%) for secondary diagnoses, and 38% (95% CI, 20-59%) for position-unspecified diagnoses (eg, diagnoses originating from separate physician claims associated with an inpatient stay). Of the confirmed AMI cases, demand ischemia was the suspected etiology more often for those coded in secondary or unspecified positions (72% and 40%, respectively) than for principal-position AMI diagnoses (21%). CONCLUSIONS:The PPVs for principal and secondary AMI diagnoses were high and similar to estimates from prior chart validation studies. Position-unspecified diagnosis codes were less likely to represent true AMI cases.
| S-EPMC6410350 | biostudies-literature
Project description:BackgroundImplementation of the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) in the U.S. on October 1, 2015 was a significant policy change with the potential to affect established injury morbidity trends. This study used data from a single state to demonstrate 1) the use of a statistical method to estimate the effect of this coding transition on injury hospitalization trends, and 2) interpretation of significant changes in injury trends in the context of the structural and conceptual differences between ICD-9-CM and ICD-10-CM, the new ICD-10-CM-specific coding guidelines, and proposed ICD-10-CM-based framework for reporting of injuries by intent and mechanism. Segmented regression analysis was used for statistical modeling of interrupted time series monthly data to evaluate the effect of the transition to ICD-10-CM on Kentucky hospitalizations' external-cause-of-injury completeness (percentage of records with principal injury diagnoses supplemented with external-cause-of-injury codes), as well as injury hospitalization trends by intent or mechanism, January 2012-December 2017.ResultsThe segmented regression analysis showed an immediate significant drop in external-cause-of-injury completeness during the transition month, but returned to its pre-transition levels in November 2015. There was a significant immediate change in the percentage of injury hospitalizations coded for unintentional (3.34%) and undetermined intent (- 3.39%). There were immediate significant changes in the level of injury hospitalization rates due to poisoning, suffocation, struck by/against, other transportation, unspecified mechanism, and other specified not elsewhere classifiable mechanism. Significant change in slope after the transition (without immediate level change) was identified for assault, firearm, cut/pierce, and motor vehicle traffic injury rates. The observed trend changes reflected structural and conceptual features of ICD-10-CM coding (e.g., poisoning and suffocations are now captured via diagnosis codes only), new coding guidelines (e.g., requiring coding of injury intent as "accidental" if it is unknown or unspecified), and CDC proposed external-cause-of-injury code groupings by injury intent and mechanism. Researchers can replicate this methodology assessing trends in injuries or other ICD-10-CM-coded conditions using administrative billing data sets.ConclusionsThe CDC 's Proposed Framework for Presenting Injury Data Using ICD-10-CM External Cause of Injury Codes provided a logical transition from the ICD-9-CM-based matrix on injury hospitalization trends by intent and mechanism. Our findings are intended to raise awareness that changes in the ICD-10-CM coding system must be understood to assure accurate interpretation of injury trends.
| S-EPMC6165830 | biostudies-literature