Skip to main content

Table 5 Features discarded during preprocessing based on various quality criteria at different target time horizons. The number of discarded features for each criterion is indicated in parentheses. The correlation filter is not included, as no variables were removed based on this criterion

From: Identification of relevant features using SEQENS to improve supervised machine learning models predicting AML treatment outcome

Time

Missing-data filter

Quasi-constancy filter

90

(8) cebpa_vaf, bcorl1_vaf, wt1_vaf,

hb, pb_blasts, ldh, stag2_vaf, platelet

(6) thpo_vaf, calr_vaf, mpl_vaf,

sh2b3_vaf, epas1_vaf, rad21_vaf

180

(11) cebpa_vaf, bcorl1_vaf, wt1_vaf,

hb, pb_blasts, ldh, smc1a_vaf, platelet,

stag2_vaf, epas1_vaf, bcor_vaf

(3) thpo_vaf, rad21_vaf,

sh2b3_vaf

365

(10) cebpa_vaf, bcorl1_vaf, wt1_vaf,

pb_blasts, ldh, stag2_vaf, platelet,

epas1_vaf, bcor_vaf, hp

(5) thpo_vaf, calr_vaf, rad21_vaf,

smc1a_vaf, prpf40b_vaf