Table 1 Prognostic significance of MRD, machine-learning-derived genetic risk in NPM1-mutated AML by univariate and multivariate Cox analysis

From: A novel machine-learning-derived genetic score correlates with measurable residual disease and is highly predictive of outcome in acute myeloid leukemia with mutated NPM1

Univariate Cox analysis

 

Overall survival (OS)

Relapse-free survival (RFS)

HR (95% CI)

 

p

HR (95% CI)

p

Machine-learning-derived genetic risk

 Favorable genetic risk

1

 

<0.0001

1

0.0003

 Intermediate genetic risk

3.54 (1.81–6.94)

  

2.71 (1.36–5.38)

 

 Poor genetic risk

8.57 (2.84–25.86)

  

5.19 (1.76–15.27)

 

Post-induction FCM–MRD

 MRD negative

1

 

0.007

1

0.02

 MRD positive

1.44 (0.9–2.3)

  

1.48 (1.0–2.18)

 

Factors

HR

95% CI

p

Multivariate Cox analysis: overall survival

Intermediate genetic risk

3.52

(1.42–8.78)

0.0071

Poor genetic risk

7.94

(3.0–21.35)

<0.0001

Post-induction FCM–MRD positive

1.62

(1.1–2.37)

0.015

Multivariate Cox analysis: relapse-free survival

Intermediate genetic risk

2.38

(1.07–5.31)

0.03

Poor genetic risk

4.86

(1.98–11.97)

0.0006

Post-induction FCM–MRD positive

2.05

(1.01–4.15)

0.05

  1. MRD measurable residual disease, OS overall survival, RFS relapse-free survival, HR hazards ratio, CI confidence interval
Back to article page