|
Metric
|
FLI
|
VIPER
|
scImpute
|
Regression
|
Mean
|
Zeros
|
|---|
|
(a) Classification results
|
|
AUC
|
.95
|
.92
|
.91
|
.82
|
.80
|
.76
|
|
\(F_1\)
|
.91
|
.88
|
.88
|
.79
|
.80
|
.78
|
|
ACC
|
.89
|
.86
|
.87
|
.76
|
.74
|
.70
|
|
(b) Imputation errors
|
|
\(\epsilon _{\mu }\)
|
.35
|
.41
|
.45
|
.73
|
.75
|
.70
|
|
\(\epsilon _{\sigma }\)
|
.25
|
.34
|
.39
|
.54
|
.43
|
.06
|
|
\(\epsilon _{M}\)
|
1.12
|
1.94
|
2.50
|
3.53
|
1.85
|
.90
|
|
Time
|
FLI
|
VIPER
|
scImpute
|
Regression
|
Mean
|
Zeros
|
|---|
|
(c) Imputation time
|
|
\(t_\mu\)
|
.009
|
7.29
|
.100
|
\(\sim 0\)
|
\(\sim 0\)
|
\(\sim 0\)
|
|
\(t_\sigma\)
|
.002
|
8.42
|
.060
|
\(\sim 0\)
|
\(\sim 0\)
|
\(\sim 0\)
|
|
\(t_{\text {max}}\)
|
.027
|
49.2
|
.300
|
.003
|
.001
|
\(\sim 0\)
|
- (a) Mean values over curves shown in Fig. 4a–c. (b) Mean values over curves shown in Fig. 4d–f. (c) Mean (\(t_\mu\)), standard deviation (\(t_\sigma\)), and maximum (\(t_{\text {max}}\)) imputation times (in seconds) over all test patients. In table (c), \(\sim\)0 indicates that the imputation time is
strictly less than .0005 s
