Machine learning in data abstraction: A computable phenotype for sepsis and septic shock diagnosis in the intensive care unit

Table 1 Machine learning model’s sensitivity and specificity for sepsis

	Sepsis-V11		Sepsis-V22
	Sensitivity (%)	Specificity (%)	Sensitivity (%)	Specificity (%)
Initial derivation cohort	100	84.2	100	94.7
Final derivation cohort	100	100	100	100
Validation cohort	100	100	100	100

¹Version 1;

²Version 2.

Table 2 Machine learning model’s sensitivity and specificity for septic shock

	Septic shock-V11		Septic shock-V22
	Sensitivity (%)	Specificity (%)	Sensitivity (%)	Specificity (%)
Initial derivation cohort	78	80	80	90
Final derivation cohort	87	100	91	100
Validation cohort	100	100	100	100

¹Version 1;

²Version 2.