Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.
This is an unrefereed arXiv preprint describing a novel machine learning method for irregular time series forecasting, with computational experiments but no clinical trial, regulatory decision, or peer-reviewed publication reported.
This is a methodological proposal for an improved evaluation metric in time-series forecasting, supported by theoretical argument and computational validation but lacking clinical or real-world outcome data demonstrating practice impact.