Validation of an internationally derived patient severity phenotype to support COVID-19 analytics from electronic health record data.

OBJECTIVE: The Consortium for Clinical Characterization of COVID-19 by EHR (4CE) is an international collaboration addressing coronavirus disease 2019 (COVID-19) with federated analyses of electronic health record (EHR) data. We sought to develop and validate a computable phenotype for COVID-19 severity. MATERIALS AND METHODS: Twelve 4CE sites participated. First, we developed an EHR-based severity phenotype consisting of 6 code classes, and we validated it on patient hospitalization data from the 12 4CE clinical sites against the outcomes of intensive care unit (ICU) admission and/or death. We also piloted an alternative machine learning approach and compared selected predictors of severity with the 4CE phenotype at 1 site. RESULTS: The full 4CE severity phenotype had pooled sensitivity of 0.73 and specificity 0.83 for the combined outcome of ICU admission and/or death. The sensitivity of individual code categories for acuity had high variability-up to 0.65 across sites. At one pilot site, the expert-derived phenotype had mean area under the curve of 0.903 (95% confidence interval, 0.886-0.921), compared with an area under the curve of 0.956 (95% confidence interval, 0.952-0.959) for the machine learning approach. Billing codes were poor proxies of ICU admission, with as low as 49% precision and recall compared with chart review. DISCUSSION: We developed a severity phenotype using 6 code classes that proved resilient to coding variability across international institutions. In contrast, machine learning approaches may overfit hospital-specific orders. Manual chart review revealed discrepancies even in the gold-standard outcomes, possibly owing to heterogeneous pandemic conditions. CONCLUSIONS: We developed an EHR-based severity phenotype for COVID-19 in hospitalized patients and validated it at 12 international sites.

The dark matter of the cancer genome: aberrations in regulatory elements, untranslated regions, splice sites, non-coding RNA and synonymous mutations.

Cancer is a disease of the genome caused by oncogene activation and tumor suppressor gene inhibition. Deep sequencing studies including large consortia such as TCGA and ICGC identified numerous tumor-specific mutations not only in protein-coding sequences but also in non-coding sequences. Although 98% of the genome is not translated into proteins, most studies have neglected the information hidden in this "dark matter" of the genome. Malignancy-driving mutations can occur in all genetic elements outside the coding region, namely in enhancer, silencer, insulator, and promoter as well as in 5'-UTR and 3'-UTR Intron or splice site mutations can alter the splicing pattern. Moreover, cancer genomes contain mutations within non-coding RNA, such as microRNA, lncRNA, and lincRNA A synonymous mutation changes the coding region in the DNA and RNA but not the protein sequence. Importantly, oncogenes such as TERT or miR-21 as well as tumor suppressor genes such as TP53/p53, APC, BRCA1, or RB1 can be affected by these alterations. In summary, coding-independent mutations can affect gene regulation from transcription, splicing, mRNA stability to translation, and hence, this largely neglected area needs functional studies to elucidate the mechanisms underlying tumorigenesis. This review will focus on the important role and novel mechanisms of these non-coding or allegedly silent mutations in tumorigenesis.