Predicting individual hemoglobin abnormalities using longitudinal data in clinical practice

In preventive medicine, the promotion of health and well-being through early detection and intervention is crucial to preventing the development of diseases. This study aims to predict potential abnormalities in hemoglobin levels before they occur, using individualised observations within normal ranges.

We utilise a dataset generated over seven years, comprising 30,000 patients. Multiple prediction models are employed to identify hemoglobin trends within individuals and predict their next-to-measure hemoglobin value based on past measurements. We focus on whether, at a specific point in time, the individual's values are likely to run outside of the individual 'normal' bounds. A Generalised Additive Model is explored as a plausible approach for predicting future individual hemoglobin values. By calculating confidence intervals for predicted hemoglobin values, we evaluate prediction uncertainty, while assessing the percentage of accurate predictions within these intervals to gauge the reliability of our model's prediction.

We find that for 88.47% of the cases, our model accurately predicts whether patients' hemoglobin levels will stay within individual 'normal' bounds or deviate from them, demonstrating its effectiveness in identifying 'out-of-normal' measurements.

The findings hold practical significance, potentially reducing unnecessary blood draws and preventing the onset of abnormal hemoglobin levels through preventive healthcare interventions or digital lifestyle coaching. Moreover, early detection and intervention can significantly impact individual patients by preventing disease development.