ObjectiveTo compare three groupings of Electronic Health Record (EHR) billing codes for their ability to represent clinically meaningful phenotypes and to replicate known genetic associations. The three tested coding systems were the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes, the Agency for Healthcare Research and Quality Clinical Classification Software for ICD-9-CM (CCS), and manually curated “phecodes” designed to facilitate phenome-wide association studies (PheWAS) in EHRs.Methods and materialsWe selected 100 disease phenotypes and compared the ability of each coding system to accurately represent them without performing additional groupings. The 100 phenotypes included 25 randomly-chosen clinical phenotypes pursued in prior genome-wide association studies (GWAS) and another 75 common disease phenotypes mentioned across free-text problem lists from 189,289 individuals. We then evaluated the performance of each coding system to replicate known associations for 440 SNP-phenotype pairs.ResultsOut of the 100 tested clinical phenotypes, phecodes exactly matched 83, compared to 53 for ICD-9-CM and 32 for CCS. ICD-9-CM codes were typically too detailed (requiring custom groupings) while CCS codes were often not granular enough. Among 440 tested known SNP-phenotype associations, use of phecodes replicated 153 SNP-phenotype pairs compared to 143 for ICD-9-CM and 139 for CCS. Phecodes also generally produced stronger odds ratios and lower p-values for known associations than ICD-9-CM and CCS. Finally, evaluation of several SNPs via PheWAS identified novel potential signals, some seen in only using the phecode approach. Among them, rs7318369 in PEPD was associated with gastrointestinal hemorrhage.ConclusionOur results suggest that the phecode groupings better align with clinical diseases mentioned in clinical practice or for genomic studies. ICD-9-CM, CCS, and phecode groupings all worked for PheWAS-type studies, though the phecode groupings produced superior results.
Genetic association studies often examine features independently, potentially missing subpopulations with multiple phenotypes that share a single cause. We describe an approach that aggregates phenotypes on the basis of patterns described by Mendelian diseases. We mapped the clinical features of 1204 Mendelian diseases into phenotypes captured from the electronic health record (EHR) and summarized this evidence as phenotype risk scores (PheRSs). In an initial validation, PheRS distinguished cases and controls of five Mendelian diseases. Applying PheRS to 21,701 genotyped individuals uncovered 18 associations between rare variants and phenotypes consistent with Mendelian diseases. In 16 patients, the rare genetic variants were associated with severe outcomes such as organ transplants. PheRS can augment rare-variant interpretation and may identify subsets of patients with distinct genetic causes for common diseases.
Background: Natural language processing models such as ChatGPT can generate text-based content and are poised to become a major information source in medicine and beyond. The accuracy and completeness of ChatGPT for medical queries is not known.
Methods: Thirty-three physicians across 17 specialties generated 284 medical questions that they subjectively classified as easy, medium, or hard with either binary (yes/no) or descriptive answers. The physicians then graded ChatGPT-generated answers to these questions for accuracy (6-point Likert scale; range 1 – completely incorrect to 6 – completely correct) and completeness (3-point Likert scale; range 1 – incomplete to 3 - complete plus additional context). Scores were summarized with descriptive statistics and compared using Mann-Whitney U or Kruskal-Wallis testing.
Results: Across all questions (n=284), median accuracy score was 5.5 (between almost completely and completely correct) with mean score of 4.8 (between mostly and almost completely correct). Median completeness score was 3 (complete and comprehensive) with mean score of 2.5. For questions rated easy, medium, and hard, median accuracy scores were 6, 5.5, and 5 (mean 5.0, 4.7, and 4.6; p=0.05). Accuracy scores for binary and descriptive questions were similar (median 6 vs. 5; mean 4.9 vs. 4.7; p=0.07). Of 36 questions with scores of 1-2, 34 were re-queried/re-graded 8-17 days later with substantial improvement (median 2 vs. 4; p<0.01).
Conclusions: ChatGPT generated largely accurate information to diverse medical queries as judged by academic physician specialists although with important limitations. Further research and model development are needed to correct inaccuracies and for validation.
PURPOSE Because of expanding interoperability requirements, structured patient data are increasingly available in electronic health records. Many oncology data elements (eg, staging, biomarkers, documentation of adverse events and cancer outcomes) remain challenging. The Minimal Common Oncology Data Elements (mCODE) project is a consensus data standard created to facilitate transmission of data of patients with cancer. METHODS In 2018, mCODE was developed through a work group convened by ASCO, including oncologists, informaticians, researchers, and experts in terminologies and standards. The mCODE specification is organized by 6 high-level domains: patient, laboratory/vital, disease, genomics, treatment, and outcome. In total, 23 mCODE profiles are composed of 90 data elements. RESULTS A conceptual model was published for public comment in January 2019 and, after additional refinement, the first public version of the mCODE (version 0.9.1) Fast Healthcare Interoperability Resources (FHIR) implementation guide (IG) was presented at the ASCO Annual Meeting in June 2019. The specification was approved for balloting by Health Level 7 International (HL7) in August 2019. mCODE passed the HL7 ballot in September 2019 with 86.5% approval. The mCODE IG authors worked with HL7 reviewers to resolve all negative comments, leading to a modest expansion in the number of data elements and tighter alignment with FHIR and other HL7 conventions. The mCODE version 1.0 FHIR IG Standard for Trial Use was formally published on March 18, 2020. CONCLUSION The mCODE project has the potential to offer tremendous benefits to cancer care delivery and research by creating an infrastructure to better share patient data. mCODE is available free from www.mCODEinitiative.org . Pilot implementations are underway, and a robust community of stakeholders has been assembled across the oncology ecosystem.
PURPOSE: The use of telemedicine expanded dramatically in March 2020 following the COVID-19 pandemic. We sought to assess oncologist perspectives on telemedicine's present and future roles (both phone and video) for patients with cancer. METHODS: The National Comprehensive Cancer Network (NCCN) Electronic Health Record (EHR) Oncology Advisory Group formed a Workgroup to assess the state of oncology telemedicine and created a 20-question survey. NCCN EHR Oncology Advisory Group members e-mailed the survey to providers (surgical, hematology, gynecologic, medical, and radiation oncology physicians and clinicians) at their home institution. RESULTS: Providers (N = 1,038) from 26 institutions responded in Summer 2020. Telemedicine (phone and video) was compared with in-person visits across clinical scenarios (n = 766). For reviewing benign follow-up data, 88% reported video and 80% reported telephone were the same as or better than office visits. For establishing a personal connection with patients, 24% and 7% indicated video and telephone, respectively, were the same as or better than office visits. Ninety-three percent reported adverse outcomes attributable to telemedicine visits never or rarely occurred, whereas 6% indicated they occasionally occurred (n = 801). Respondents (n = 796) estimated 46% of postpandemic visits could be virtual, but challenges included (1) lack of patient access to technology, (2) inadequate clinical workflows to support telemedicine, and (3) insurance coverage uncertainty postpandemic. CONCLUSION: Telemedicine appears effective across a variety of clinical scenarios. Based on provider assessment, a substantial fraction of visits for patients with cancer could be effectively and safely conducted using telemedicine. These findings should influence regulatory and infrastructural decisions regarding telemedicine postpandemic for patients with cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.