Machine Learning for Predicting Hyperglycemic Cases Induced by PD-1/PD-L1 Inhibitors

Table 1

Main characteristics of cases in complete data.

Drugs	TCN (PCN)	PCN (%)	Age (year)	Male (%)	Weight (kg)	Year range
Cam	37 (1)	2.7	55.6 ± 13.2	64.9	59.5 ± 12.4	2017–2021
Cem	52 (1)	1.9	73 ± 13	82.7	76.9 ± 15.8	2018–2021
Avel	1074 (22)	2	65.1 ± 11.6	61.6	75.3 ± 20.8	2014–2021
Dur	1715 (46)	2.7	65.9 ± 10.3	67.6	69.7 ± 18.1	2011–2021
Atez	7073 (133)	1.9	64.2 ± 11.6	56	70.5 ± 18.4	2012–2021
Pem	9416 (310)	3.3	65.8 ± 11.5	63	68.6 ± 20.7	2000–2021
Nivo	15629 (708)	4.5	63.3 ± 12.8	64.3	73.7 ± 22.1	2010–2021
Ipi	7907 (378)	4.8	61.7 ± 13	63.7	77.3 ± 21.4	2007–2021

TCN: total case number. PCN: positive case number. Cases reported with wrong year were deleted: dur (1979), pem (1921), nivo (2022).