Validation of Case Finding Algorithms for Hepatocellular Cancer From Administrative Data and Electronic Health Records Using Natural Language Processing
Bibliographic Data
| ID | 9101117 |
|---|---|
| Authors | Yvonne Sada, Yvonne H Sada (0000-0002-3196-2398, Baylor College of Medicine, corresponding author), Jason Hou, Jason K Hou (0000-0003-0644-6778, Michael E. DeBakey VA Medical Center, corresponding author), Peter Richardson (0000-0002-3349-345X, Health Services Research & Development, corresponding author), Hashem El-Serag, Hashem B El‐Serag (0000-0001-5964-7579, Health Services Research & Development, corresponding author), Jessica Davila, Jessica A Davila (Michael E. DeBakey VA Medical Center, corresponding author) |
| Year | 2016 |
| Volume | 54 |
| Issue | 2 |
| Pages | e9-e14 |
| Publication date | 2016-02-01 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Medical Care (JOURNAL) |
| Journal identifiers | ISSN: 0025-7079 • E-ISSN: 1537-1948 |
| Publisher | Ovid Technologies (Wolters Kluwer Health) (PUBLISHER) |
| DOI | 10.1097/mlr.0b013e3182a30373 |
| PMID | 23929403 |
| PMCID | PMC3875602 |
| OpenAlex | W2329011065 |
| Language | EN |
| Citations received | 1 |
| References cited | 14 |
BACKGROUND: Accurate identification of hepatocellular cancer (HCC) cases from automated data is needed for efficient and valid quality improvement initiatives and research. We validated HCC International Classification of Diseases, 9th Revision (ICD-9) codes, and evaluated whether natural language processing by the Automated Retrieval Console (ARC) for document classification improves HCC identification. METHODS: We identified a cohort of patients with ICD-9 codes for HCC during 2005-2010 from Veterans Affairs administrative data. Pathology and radiology reports were reviewed to confirm HCC. The positive predictive value (PPV), sensitivity, and specificity of ICD-9 codes were calculated. A split validation study of pathology and radiology reports was performed to develop and validate ARC algorithms. Reports were manually classified as diagnostic of HCC or not. ARC generated document classification algorithms using the Clinical Text Analysis and Knowledge Extraction System. ARC performance was compared with manual classification. PPV, sensitivity, and specificity of ARC were calculated. RESULTS: A total of 1138 patients with HCC were identified by ICD-9 codes. On the basis of manual review, 773 had HCC. The HCC ICD-9 code algorithm had a PPV of 0.67, sensitivity of 0.95, and specificity of 0.93. For a random subset of 619 patients, we identified 471 pathology reports for 323 patients and 943 radiology reports for 557 patients. The pathology ARC algorithm had PPV of 0.96, sensitivity of 0.96, and specificity of 0.97. The radiology ARC algorithm had PPV of 0.75, sensitivity of 0.94, and specificity of 0.68. CONCLUSIONS: A combined approach of ICD-9 codes and natural language processing of pathology and radiology reports improves HCC case identification in automated data
Algorithm · Diagnosis code · Machine learning · Population · Radiology · AI in cancer detection · Artificial Intelligence · Artificial Intelligence in Healthcare · Computer Science · Medical Coding and Health Information · Medicine
| Unique citing works | 1 |
|---|---|
| Citations per year | 0,1 |
| Citation span | 2016 - 2016 (1) |
| Citation velocity | historical |
| Highly cited | No |