Interpretable artificial intelligence-based app assists inexperienced radiologists in diagnosing biliary atresia from sonographic gallbladder images

Table 1 Patient characteristics at the time of ultrasound examination

Characteristics	BA group (n = 119)	Non-BA group (n = 88)	P value
Male-to-female ratio^a	60:59	53:35	0.16
Age (days)^b	53 (40, 68)	50 (33, 76)	0.73
TB (mmol/L)^b	151.5 (125.0, 194.9)	142.1 (99.2, 204.4)	0.37
DB (mmol/L)^b	98.1 (75.8, 128.2)	66.0 (25.2, 103.6)	< 0.001
ALT (U/L)^b	133.0 (70.0, 249.0)	73.0 (26.0, 177.0)	0.002
AST (U/L)^b	201.0 (128.0, 331.0)	101.0 (47.0, 240.0)	0.002
GGT (U/L)^b	377.0 (269.0, 687.0)	144.0 (80.3, 231.0)	< 0.001

BA Biliary atresia, TB Total bilirubin, DB Direct bilirubin, ALT Indicates alanine aminotransferase, AST Aspartate aminotransferase, GGT γ-glutamyl transferase
^aData are numbers of patients. The chi-square test was used to test the sex distribution between the two groups
^bData are medians with interquartile ranges reported in parentheses. The Mann–Whitney U test was used to compare the variables between the two groups

ISSN: 1741-7015