A problem-list comorbidity score showed no link to death in 1,596 veterans. In Finland, a condition that doubles mortality looked protective in codes. 42% of worst-ranked sepsis hospitals moved up.
The veterans study is striking. The same score predicts death when it's built from clinicians' notes and predicts nothing from the problem list, which means the problem list is quietly deciding which hospitals look bad. Adding a test readers can run on their own score is what makes this useful beyond the argument.
Charlson predicting death from notes and nothing from the problem list in 1,596 veterans is a sharp finding for anyone using HCC scores to compare plans. The test you included gives quality teams a way to check their own score before rankings go public.
A hazard ratio of 0.65 for incontinence is the kind of number that should fail a pipeline check before anyone reads it as medicine. Comparing each coded condition's prevalence against a small sample of notes, per site, catches this early, and it also shows which hospitals look healthier only because they code less.
In the VA study, how old were the heart attacks documented only in the notes? The medical history in notes often predates the earliest available diagnose codes. Also, is it possible that coded heart attacks were missing because heart attacks were treated in emergency care at the closest hospital, while the VA records primarily reflected scheduled visits and care for chronic conditions.
The veterans study is striking. The same score predicts death when it's built from clinicians' notes and predicts nothing from the problem list, which means the problem list is quietly deciding which hospitals look bad. Adding a test readers can run on their own score is what makes this useful beyond the argument.
Charlson predicting death from notes and nothing from the problem list in 1,596 veterans is a sharp finding for anyone using HCC scores to compare plans. The test you included gives quality teams a way to check their own score before rankings go public.
A hazard ratio of 0.65 for incontinence is the kind of number that should fail a pipeline check before anyone reads it as medicine. Comparing each coded condition's prevalence against a small sample of notes, per site, catches this early, and it also shows which hospitals look healthier only because they code less.
In the VA study, how old were the heart attacks documented only in the notes? The medical history in notes often predates the earliest available diagnose codes. Also, is it possible that coded heart attacks were missing because heart attacks were treated in emergency care at the closest hospital, while the VA records primarily reflected scheduled visits and care for chronic conditions.