Table 1 Key 20 variables for hepatocellular carcinoma-clinical decision support system model.

From: Development of machine learning-based clinical decision support system for hepatocellular carcinoma

Patient-related factors (14)

Age

Value

Body mass index, kg/m2

Value

ECOG performance status score

0, 1, 2, 3, 4

Child–Pugh score

5–14

Varix

Absence / presence

Ascites

Absence / controlled uncontrolled

AFP, ng/mL

Value

Haemoglobin, g/dL

Value

Platelet count, × 109/mm3

Value

ALT, U/L

Value

Total bilirubin, mg/dL

Value

Albumin, mg/dL

Value

Prothrombin time, INR

Value

Creatinine, mg/dL

Value

Tumour-related factors (6)

Tumour number

1, 2, 3, 4 or more

Maximum tumour size, cm

Value

Distribution

Single segmental / unilobar / bilobar

Portal vein invasion

Absence / unilateral / main portal or both portal vein

Metastasis

Absence / presence

RFA feasibility*

Feasible / non-feasible

  1. AFP alpha-fetoprotein, ALT alanine aminotransferase, ECOG Eastern Cooperative Oncology Group, RFA radiofrequency ablation.
  2. *RFA feasibility was defined as a size or location of the tumour to receive percutaneous RFA successfully without significant complications.