Framework of the Centralized Interactive Phenomics Resource (CIPHER) standard for electronic health data-based phenomics knowledgebase

Ho, Yuk‐Lam; Fontin, Francesca; Gosian, Jeffrey; Maripuri, Monika; Murray, Michael T.; Sangar, Rahul; Galloway, Ashley; Zimolzak, Andrew J.; Whitbourne, Stacey B.; Casas, Juan P.; Ramoni, Rachel; Gagnon, David; Cai, Tianxi; Liao, Katherine P.; Gaziano, J. Michael; Muralidhar, Sumitra; Cho, Kelly

doi:10.1093/jamia/ocad030

Cited by 12 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The laboratory results and records of individual patients were linked to Logical Observation Identifiers Names and Codes (LOINC) codes for laboratory tests, MVP Core Data Team’s ’ShortNames’ for 108 of the most common laboratory tests 59 , and a customized mapping based on the VA’s LabChemTestName, VA station, and a substantial amount of hand curation. Although LOINC codes were found to be missing and mis-assigned to laboratory results in the VA EMRs, we recorded the frequency with which LOINC codes were associated with each of our laboratory results (A1c, Glucose, HDLC, LDLC, Total Cholesterol, Triglycerides, Hemoglobin, and eGFR) in the fifth tab of Supplementary Information SI-5 , the ModelStats.xlsx spreadsheet.…”

Section: Methodsmentioning

confidence: 99%

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

Dhaubhadel,

Ganguly,

Ribeiro

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of $$\sim$$ ∼ 4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics.

show abstract

Section: Methodsmentioning

confidence: 99%

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

Dhaubhadel,

Ganguly,

Ribeiro

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The analysis involved a series of GWAS across 2,068 traits, covering a deep catalog of phenotypes extracted from EHR-derived diagnosis codes, clinical laboratory tests, vital signs, and survey responses. As previously described (13, 19, 20, 21, 22), the analysis was performed using data from 635,969 participants from MVP Genomics Release 4 (23) ( Table 1 ) classified into four population groups based on genetic similarity (GIA) to the 1000 Genomes Project (24, 25) African (AFR, n = 121,177), Admixed Americans (AMR, n = 59,048), East Asian (EAS, n = 6,702), and European (EUR, n = 449,042) superpopulations. After imputation and quality control (QC) filtering, > 44.3M variants (minor allele count (MAC) ≥ 40) were included for analysis.…”

Section: Methodsmentioning

confidence: 99%

Accelerating Genome- and Phenome-Wide Association Studies using GPUs – A case study using data from the Million Veteran Program

Rodriguez,

Kim,

Nandi

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The expansion of biobanks has significantly propelled genomic discoveries yet the sheer scale of data within these repositories poses formidable computational hurdles, particularly in handling extensive matrix operations required by prevailing statistical frameworks. In this work, we introduce computational optimizations to the SAIGE (Scalable and Accurate Implementation of Generalized Mixed Model) algorithm, notably employing a GPU-based distributed computing approach to tackle these challenges. We applied these optimizations to conduct a large-scale genome-wide association study (GWAS) across 2,068 phenotypes derived from electronic health records of 635,969 diverse participants from the Veterans Affairs (VA) Million Veteran Program (MVP). Our strategies enabled scaling up the analysis to over 6,000 nodes on the Department of Energy (DOE) Oak Ridge Leadership Computing Facility (OLCF) Summit High-Performance Computer (HPC) resulting in a 20-fold acceleration compared to the baseline model. We also provide a Docker container with our optimizations that was successfully used on multiple cloud infrastructures on UK Biobank and All of Us datasets where we showed significant time and cost benefits over the baseline SAIGE model.

show abstract

“…We ascertained sociodemographic, geographic, and clinical characteristics (including comorbid conditions and medication prescriptions based on a 2-year lookback window prior to infection) that were potentially associated with U09.9 documentation (Table 1). The ICD-10 codes used to define each comorbid condition were provided by the VA Centralized Interactive Phenomics Resource . We determined whether primary vaccination was administered (ie, 2 doses of messenger RNA-1273 [Moderna], 2 doses of BNT162b2 [Pfizer-BioNTech] or a single dose of Ad26.COV2.S [Janssen]) or at least 1 booster dose was administered prior to the date of infection.…”

Section: Methodsmentioning

confidence: 99%

“…The ICD-10 codes used to define each comorbid condition were provided by the VA Centralized Interactive Phenomics Resource. 16 We determined whether primary vaccination was administered (ie, 2 doses of messenger RNA-1273 [Moderna], 2 doses of BNT162b2 [Pfizer-BioNTech] or a single dose of Ad26.COV2.S [Janssen]) or at least 1 booster dose was administered prior to the date of infection. In addition to vaccinations administered by VA, CSDR captures some COVID-19 vaccines given outside the VA (eg, pharmacies, health departments, mass vaccination centers, and clinics) and electronically reported to the VA or documented by VA clinicians.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Rates of ICD-10 Code U09.9 Documentation and Clinical Characteristics of VA Patients With Post–COVID-19 Condition

Wander,

Baraff,

Fox

et al. 2023

JAMA Netw Open

Self Cite

View full text Add to dashboard Cite

ImportanceA significant proportion of SARS-CoV-2 infected individuals experience post–COVID-19 condition months after initial infection.ObjectiveTo determine the rates, clinical setting, risk factors, and symptoms associated with the documentation of International Statistical Classification of Diseases Tenth Revision (ICD-10), code U09.9 for post–COVID-19 condition after acute infection.Design, Setting, and ParticipantsThis retrospective cohort study was performed within the US Department of Veterans Affairs (VA) health care system. Veterans with a positive SARS-CoV-2 test result between October 1, 2021, the date ICD-10 code U09.9 was introduced, and January 31, 2023 (n = 388 980), and a randomly selected subsample of patients with the U09.9 code (n = 350) whose symptom prevalence was assessed by systematic medical record review, were included in the analysis.ExposurePositive SARS-CoV-2 test result.Main Outcomes and MeasuresRates, clinical setting, risk factors, and symptoms associated with ICD-10 code U09.9 in the medical record.ResultsAmong the 388 980 persons with a positive SARS-CoV-2 test, the mean (SD) age was 61.4 (16.1) years; 87.3% were men. In terms of race and ethnicity, 0.8% were American Indian or Alaska Native, 1.4% were Asian, 20.7% were Black, 9.3% were Hispanic or Latino, 1.0% were Native Hawaiian or Other Pacific Islander; and 67.8% were White. Cumulative incidence of U09.9 documentation was 4.79% (95% CI, 4.73%-4.87%) at 6 months and 5.28% (95% CI, 5.21%-5.36%) at 12 months after infection. Factors independently associated with U09.9 documentation included older age, female sex, Hispanic or Latino ethnicity, comorbidity burden, and severe acute infection manifesting by symptoms, hospitalization, or ventilation. Primary vaccination (adjusted hazard ratio [AHR], 0.80 [95% CI, 0.78-0.83]) and booster vaccination (AHR, 0.66 [95% CI, 0.64-0.69]) were associated with a lower likelihood of U09.9 documentation. Marked differences by geographic region and facility in U09.9 code documentation may reflect local screening and care practices. Among the 350 patients undergoing systematic medical record review, the most common symptoms documented in the medical records among patients with the U09.9 code were shortness of breath (130 [37.1%]), fatigue or exhaustion (78 [22.3%]), cough (63 [18.0%]), reduced cognitive function or brain fog (22 [6.3%]), and change in smell and/or taste (20 [5.7%]).Conclusions and RelevanceIn this cohort study of 388 980 veterans, documentation of ICD-10 code U09.9 had marked regional and facility-level variability. Strong risk factors for U09.9 documentation were identified, while vaccination appeared to be protective. Accurate and consistent documentation of U09.9 is needed to maximize its utility in tracking patients for clinical care and research. Future studies should examine the long-term trajectory of individuals with U09.9 documentation.

show abstract

Framework of the Centralized Interactive Phenomics Resource (CIPHER) standard for electronic health data-based phenomics knowledgebase

Cited by 12 publications

References 12 publications

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

Accelerating Genome- and Phenome-Wide Association Studies using GPUs – A case study using data from the Million Veteran Program

Rates of ICD-10 Code U09.9 Documentation and Clinical Characteristics of VA Patients With Post–COVID-19 Condition

Contact Info

Product

Resources

About