Personalized lab test models to quantify disease potentials in healthy individuals

Cohen, Netta Mendelson; Schwartzman, Omer; Jaschek, Ram; Lifshitz, Aviezer; Hoichman, Michael; Balicer, Ran D.; Shlush, Liran I.; Barbash, Gabi; Tanay, Amos

doi:10.1038/s41591-021-01468-6

Cited by 23 publications

(49 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies indicated that CRP levels among healthy individuals are associated with age and gender [ 14 , 15 ] while a recent large study did not support that [ 16 ]. Hence, we evaluated their impact on CRPv as potential confounders.…”

Section: Discussionmentioning

confidence: 98%

C-reactive protein velocity discriminates between acute viral and bacterial infections in patients who present with relatively low CRP concentrations

et al. 2021

View full text Add to dashboard Cite

Background To assess the utility of C-reactive protein (CRP) velocity to discriminate between patients with acute viral and bacterial infections who presented with relatively low CRP concentrations and were suspected of having a bacterial infection. Methods We analyzed a retrospective cohort of patients with acute infections who presented to the emergency department (ED) with a relatively low first CRP measurement (CRP1) ≤ 31.9 mg/L and received antibiotics shortly after. We then calculated C-reactive protein velocity (CRPv), milligram per liter per hour, for each patient based on CRP1 and the second CRP value (CRP2) measured within the first 24 h since admission. Finally, we compared CRPv between patients with bacterial and viral infections. Results We have presently analyzed 74 patients with acute bacterial infections and 62 patients with acute viral infections at the mean age of 80 and 66 years respectively, 68 male and 68 female. CRP1 did not differ between both groups of patients (16.2 ± 8.6 and 14.8 ± 8.5 for patients with viral and bacterial infections respectively, p value = 0.336). However, the CRP2 was significantly different between the groups (30.2 ± 21.9 and 75.6 ± 51.3 for patients with viral and bacterial infections respectively, p-value < 0.001) and especially the CRPv was much higher in patients with acute bacterial infections compared to patients with acute viral infections (0.9 ± 1.2 and 4.4 ± 2.7 respectively, p-value < 0.001). Conclusion CRPv and CRP2 are useful biomarkers that can discriminate significantly between patients who present with acute bacterial and viral infections, and relatively low CRP concentration upon admission who were suspected of having a bacterial infection.

show abstract

Section: Discussionmentioning

confidence: 98%

C-reactive protein velocity discriminates between acute viral and bacterial infections in patients who present with relatively low CRP concentrations

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Many previous work using laboratory tests for translational research had relied on feeding statistical models with the continuous values 31,32 . A previous work also discovered that the variations of laboratory test values within the reference range, even if the test result falls within the range, have medical significance 33 . In this report, we quantified the loss of performance in predictive tasks and our own result confirmed the expected loss of information by 26.1% (Figure 7).…”

Section: Discussionmentioning

confidence: 99%

Building Population Phenotypic Journeys from Laboratory Tests in Electronic Health Records for Translational Research

Zhang

Lee

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Abundant volumes of clinical laboratory test results available within Electronic health records (EHRs) are essential for differential diagnosis, treatment monitoring, and outcome evaluation. LOINC2HPO is a recently developed deep phenotyping approach to transform laboratory test results into the Human Phenotype Ontology (HPO) terms. Here, we deployed the approach on a large EHR dataset from the Sema4 Data Warehouse to build patient phenotypic journeys at scale. Among 1.07 billion laboratory test results, we successfully transformed 774 million (72.5%) into HPO-coded phenotypes and built a patient phenotypic journey for over 2.2 million patients. First, a global analysis of patient phenotypic journeys revealed a longitudinal increase in patients with genitourinary system abnormality. The analysis also revealed abnormal phenotypes with strong racial patterns. Second, using severe asthma as an example case, we identified abnormal phenotypes in the past three years that were correlated with asthma progression to severe state. Lastly, we demonstrated that converting laboratory test results into HPO terms resulted in limited information loss. Our study demonstrated that the phenotypic journey framework opens the way to characterize phenotypic trajectories in population level and screen biomarkers for translational research.

show abstract

“…This big data approach has not previously been feasible due to restrictions in access to individual level medical records, making it difficult to accurately define seasonal models across a multitude of tests. Precision medicine approaches may take this type of analysis even further and redefine intervals for each individual 28,29 . In summary, this study aims to identify seasonality in biochemical tests on a mass scale and propose a method to improve patient test result classification protocols 27,30 .…”

Section: Introductionmentioning

confidence: 99%

Population-wide analysis of laboratory tests to assess seasonal variation and the relevance of temporal reference interval modification

Muse

Aguayo-Orozco

Balaganeshan

et al. 2022

Preprint

View full text Add to dashboard Cite

We identified mortality-, age-, and sex-associated differences in relation to reference intervals (RI) for laboratory tests in population-wide data from nearly two million hospital patients in Denmark and comprising of more than 300 million measurements. A low-parameter mathematical wave-based modification method was developed to adjust for dietary and environment influences during the year. The resulting mathematical fit allowed for improved association rates between re-classified abnormal laboratory tests, patient diagnoses and mortality. The study highlights the need for seasonally modified RIs and presents an approach that has the potential to reduce over- and underdiagnosis, impacting both physician-patient interactions and EHR research as a whole.

show abstract

Personalized lab test models to quantify disease potentials in healthy individuals

Cited by 23 publications

References 40 publications

C-reactive protein velocity discriminates between acute viral and bacterial infections in patients who present with relatively low CRP concentrations

C-reactive protein velocity discriminates between acute viral and bacterial infections in patients who present with relatively low CRP concentrations

Building Population Phenotypic Journeys from Laboratory Tests in Electronic Health Records for Translational Research

Population-wide analysis of laboratory tests to assess seasonal variation and the relevance of temporal reference interval modification

Contact Info

Product

Resources

About