1 code implementation • 28 Jan 2023 • Zhaoyang Chen, Lina Siltala-Li, Mikko Lassila, Pekka Malo, Eeva Vilkkumaa, Tarja Saaresranta, Arho Veli Virkki
Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's $R^{2}$ from 88. 8% to 97. 5%.