Tag: Predictive value of tests
Machine-learning algorithms improved smoking identification in health records
—
Study comparing machine learning and rule-based algorithms for identifying smokers in administrative health data found ML models doubled sensitivity for detecting current smokers.
Urinary calcium-to-citrate ratio may help predict stone risk in very young children
—
in PediatricsUrinary calcium-to-citrate ratio demonstrates moderate discriminatory power for kidney stone risk in infants and toddlers, with a threshold of 0.23 mg/mg indicating elevated lithogenic potential.
Echocardiographic indicators predicted adverse outcomes in PIHS
—
in ObstetricsEchocardiographic parameters independently predict adverse pregnancy outcomes in women aged 35+ with pregnancy-induced hypertension, with combined assessment achieving excellent discrimination.
