Table 12. Best prediction models of outcome.

Model predicting AIS improvement:$l={\beta }_0+{\beta }_{11}{x}_1+{\beta }_{12}{x}_1^2+{\beta }_2{x}_2+{\beta }_3{x}_3+{\beta }_4{x}_4+{\beta }_5{x}_5$ Model predicting AIS A:$l={\beta }_0+{\beta }_{11}{x}_1+{\beta }_{12}{x}_1^2+{\beta }_2{x}_2+{\beta }_3{x}_3+{\beta }_4{x}_4+{\beta }_5{x}_5+{\beta }_6{x}_6+{\beta }_7{x}_7$ Model predicting AIS D:$l={\beta }_0+{\beta }_2{x}_2+{\beta }_3{x}_3+{\beta }_4{x}_4+{\beta }_5{x}_5+{\beta }_8{x}_8+{\beta }_9{x}_9$ where $x_1:$ average MAP; $x_2$ : AIS admission A (‘yes’, ‘no’); $x_3$ : AIS admission B (‘yes’, ‘no’); $x_4$ : AIS admission C (‘yes’, ‘no’); $x_5$ : AIS admission D (‘yes’, ‘no’); $x_6$ : NLI non-cervical; $x_7$ : Time MAP out 76–117; $x_8$ : Length of surgery; $x_9$ : Age; (AIS admission E and NLI cervical were set as the reference levels for the corresponding variable and are part of the intercept). All metrics are on LOOCV prediction (n = 93)
	Model AIS improv.	Model AIS A	Model AIS D
Predictor	Coef. estimate (logit)	Coef. estimate (logit)	Coef. estimate (logit)
Intercept	${\beta }_0$= –16.24	${\beta }_0$= 20.466	${\beta }_0$= 1.558
Average MAP ($x_1$)	${\beta }_{11}$= 7.374	${\beta }_{11}$= 27.031
Average MAP (Cohn et al., 2010) ($x_1$)	${\beta }_{12}$= –8.215	${\beta }_{12}$= –17.138
AIS admission A ($x_2$)	${\beta }_2$= 15.54	${\beta }_2$= –22.814	${\beta }_2$= 2.324
AIS admission B ($x_3$)	${\beta }_3$= 16.1818	${\beta }_3$= –20.38	${\beta }_3$= 0.41
AIS admission C ($x_4$)	${\beta }_4$= 16.752	${\beta }_4$= –19.01	${\beta }_4$= –2.591
AIS admission D ($x_5$)	${\beta }_5$= 14.828	${\beta }_5$= 0.217	${\beta }_5$= –2.624
NLI non-Cervical ($x_6$)		${\beta }_6$= –1.228
Time MAP out 76–117 ($x_7$)		${\beta }_7$= 0.017
Length of Surgery ($x_8$)			${\beta }_8$= –0.0044
Age ($x_9$)			${\beta }_9$= 0.03
Model performance metric	Metric value	Metric value	Metric value
Accuracy (95% CI)	0.73 (0.629, 0.818)	0.82 (0.735, 0.898)	0.806 (0.71, 0.881)
AUC	0.743	0.88	0.87
Kappa	0.45	0.629	0.573
Sensitivity	0.71	0.812	0.793
Specificity	0.74	0.836	0.812
Positive predicted value	0.658	0.72	0.657
Negative predicted value	0.788	0.89	0.896