Cardiometabolic Risk and Diagnostic-Laboratory Reference-Range Disagreement in 794,811 Indian Insurance Applicants
Lakhani, S.
Show abstract
This study analyzes 794,811 digitized medical examina- tions from Indian life-insurance applicants, a working-age, urban-skewed demographic often undersampled by national surveys. The cohort exhibits a pronounced South-Asian car- diometabolic risk profile: among valid adult records, 41.9% met the criteria for dyslipidemia (driven heavily by low HDL and elevated triglycerides), and 61.4% met AHA 2017 crite- ria for stage 1 hypertension. However, canonicalizing this dataset across 33,244 diagnostic centers revealed significant heterogeneity in laboratory reference ranges. At the clinical prediabetes threshold of 110 mg/dL for fasting blood sugar, the record-pair disagreement rate across laboratories was 49.7%, with similar variance across other common tests. This structural inconsistency materially affects patient classi- fication and the tracking of disease prevalence, underscoring a critical need for the national standardization of laboratory reporting in India
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Towards development of a statistical framework to evaluate myotonic dystrophy type 1 mRNA biomarkers in the context of a clinical trial 93%
- Actionable absolute risk prediction of atherosclerotic cardiovascular disease: a behavior-management approach based on data from 464,547 UK Biobank participants 93%
- bp: Blood Pressure Analysis in R 93%
Similar papers in this journal
- Automated Image Transcription for Perinatal Blood Pressure Monitoring Using Mobile Health Technology 92%
- Inferring Gender from First Names: Comparing the Accuracy of Genderize, Gender API, and the gender R Package on Authors of Diverse Nationality 92%
- Racial disparities in continuous glucose monitoring-based 60-min glucose predictions among people with type 1 diabetes 92%
Similar papers in this journal
- Replicating a COVID-19 study in a national England database to assess the generalisability of research with regional electronic health record data 92%
- Protocol for the development and validation of a machine-learning based tool for predicting the risk of hypertriglyceridemia in critically-ill patients receiving propofol sedation 92%
- RESEARCH PROTOCOL: Large-scale evidence generation and evaluation across a network of databases for type 2 diabetes mellitus 91%
Similar papers in this journal
- The Aliment to Bodily Condition knowledgebase (ABCkb): A database connecting plants and human health 90%
- Identification and Attribution of Weekly Periodic Biases in Epidemiological Time Series Data 88%
- The UK BiLEVE and Mendelian randomisation: Using multivariable instrumental variables to address “damned if you, dammed if you don’t” adjustment problems 88%
Similar papers in this journal
- Can machine learning improve risk prediction of incident hypertension? An internal method comparison and external validation of the Framingham risk model using HUNT Study data 92%
- biobank.cy: The Biobank of Cyprus past, present and future 92%
- Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.