Skip to main content

Table 5 AUC-ROC of COVID-19 mortality prediction results by using T-LSTM with 40 or 3 laboratory testsb

From: Predicting COVID-19 disease progression and patient outcomes based on temporal deep learning

  0 days earlya 3 days earlya 6 days early 9 days early 12 days early
40 features 0.949 ± 0.01 0.920 ± 0.03 0.915 ± 0.01 0.910 ± 0.01 0.903 ± 0.01
3 features 0.997 ± 0.00 0.969 ± 0.01 0.947 ±0.03 0.921 ±0.03 0.914 ±0.02
  1. a n days early: The model makes prediction n days before the final death/survival time. It uses sequence data from day 0 to n days before the last time to predict
  2. b The inputs of T-LSTM are time series of 48 laboratory tests or 3 laboratory tests (LDH, lymph and hs-CRP)