ALBI Score - Evidencio

Evidencio uses JavaScript for many of its features. Please enable JavaScript to enable calculations

The ALbumin and BIlirubin (ALBI) Score combines bilirubin and albumin to estimate the grade of liver (dys)function in patients with liver disease.

The ALBI Score can be used to stratify hepatocellular carcinoma (HCC) patients into prognostic ALBI grades.

Research authors: Philip J. Johnson, Sarah Berhane, Chiaki Kagebayashi, Shinji Satomura, Mabel Teng, Helen L. Reeves, James O’Beirne, Richard Fox, Anna Skowronska, Daniel Palmer, Winnie Yeo, Frankie Mo, Paul Lai, Mercedes Iñarrairaegui, Stephen L. Chan, Bruno Sangro, Rebecca Miksad, Toshifumi Tada, Takashi Kumada, Hidenori Toyoda

Version: 1.16

Public
Oncology
{{ modelType }}

V-1.16-9982.26.03.17

(01)08720938015076(8012)v1.16(4326)260317(240)9982

Download the User manual and consult the Intended purpose.

Algorithm
Details
Intended purpose
Electronic label
Release Notes
User manual
{{ toolbarErrorMessage }}

Units

Calculate the result

This algorithm does not calculate automatically.
Please provide all the needed parameters and press calculate.

Set more parameters to perform the calculation

The ALBI score is

points

Set more parameters to perform the calculation

The ALBI score is points

Result interval {{ additionalResult.min }} to {{ additionalResult.max }}

Conditional information

Your text input(s) have been changed. Please update your result. Update

PRO

Note

Notes are only visible in the result download and will not be saved by Evidencio

Calculations alone should never dictate patient care, and are no substitute for professional judgement. See our full disclaimer.

Underlying algorithms Part of

Additional information

Details

Algorithm author

T. A. Hueting

Algorithm ID

9982

Version

1.16.{{ model.microversion }}

Revision date

2026-03-17

Specialty

Hepatology , Oncology

Algorithm type

Custom calculation ^{(Calculation)}

MeSH terms

Liver Disease

Hepatocellular Carcinoma

Liver Dysfunction

Status

Public

Formula

Study characteristics

Additional information

To develop the ALBI Score algorithm, data from multiple large HCC centers and different international clinical trials about HCC were used. This data set represents patients with all disease stages of many different etiologies from different geographical regions (Japan, China, Europe (United Kingdom and Spain) and the United States). The Japanese cohort (n = 2599) was used to generate a linear prediction model by splitting the dataset randomly into two groups: The training and test/validation set (n = 1313 and n = 1286, respectively). To create the model, a cox regression analysis was performed on the training set. Its linear predictor (xb) was divided into three groups based on survival by splitting it at the 25th and 90th percentiles. According to this categorization, patients with HCC were categorized as low, medium or high risk, corresponding to the lowest 25% of risk, medium risk between the 25th and 90th percentile, and the greatest 10% of risk, respectively. Depending on which geographical region patients are from, median survival in months ranged between 18.5–85.6, 5.3–46.5, and 2.3–15.5, respectively, for these three risk groups.

Study Population

Total population size: 2599

Continuous characteristics

Name	Mean	SD	Unit
Age	66.4	8.9	Years

Name	Q1	Median	Q3	Unit
Bilirubin	10.3	15.4	22.2	μmol/L
Albumin	31	35	39	g/L
Survival		47.2		Months

Categorical characteristics

Name	Subset / Group	Nr. of patients
Sex	Male	1863
Sex	Female	736
Child-Pugh grade	A	1743
Child-Pugh grade	B	684
Child-Pugh grade	C	172
Presence of macroscopic vascular invasion	Presence of macroscopic vascular invasion	366

Supporting Publications

Title or description

Related files

No related files available

Extra Information

	Evidencio B.V., Irenesingel 19, 7481 GJ Haaksbergen, The Netherlands
	V-1.16-9982.26.03.17
	(01)08720938015076(8012)v1.16(4326)260317(240)9982
	Download the User manual
	Medical device In vitro diagnostic medical device

Download the Declaration of conformity

This algorithm has been certified as a medical device

V-1.16-9982.26.03.17

Medical Devices

Evidencio offers CE-certified MDSWs (Medical Device Software) of both widely adopted and new ground breaking algorithms. Evidencio provides an easy, sustainable and scalable way to be compliant in your use of algorithms and AI for clinical decision support, shared decision making, patient monitoring, etc.

The algorithm ALBI Score has been certified as a medical device and is only available to qualified Evidencio subscribers.

In general, the prediction models and algorithms that are freely available on Evidencio are intended for research and education purposes only.

Some of the medical prediction models and algorithms that are available on Evidencio are classified as (e.g. CE) Medical Devices.
This implies that these algorithms may be used for clinical decision making by medical professionals, as long as this use strictly adheres to the algorithm’s Intended Purpose statements.

{{ collapsed.intendedUse ? $t('show_intended_use') : $t('hide_intended_use') }}

In order for Evidencio to comply with legislation regarding the use of medical devices, we must monitor use of these medical devices to the greatest extent to prevent mis-use. Therefore, the Medical Devices on Evidencio can only be used by named Evidencio Subscribers.

To access this algorithm you will need an Evidencio Pro Subscription

Visit our library for more prediction algorithms

Already have an account? Log in Go back Sign Up

Evidencio Pro

€9,99 / Month

This functionality is reserved for Pro subscribers.
Please support us by registering as Evidencio Pro.

Clinical & Commercial use licence

Create licenced algorithms

Unlimited Patient specific reports

Create direct access for peer reviewers.

Use licensed algorithms

Cancel at any time

For a complete list of all the benefits, see Services

Looking to manage Teams Or EHR integration? Get in touch with our team.

Signup for Pro subscription

Select the version you want to duplicate Are you sure you want to duplicate this algorithm?

Please sign in to enable Evidencio print features

In order to use the Evidencio print features, you need to be logged in.
If you don't have an Evidencio Community Account you can create your free personal account at:

https://www.evidencio.com/registration

Printed results - Examples {{ new Date().toLocaleString() }}

Evidencio Community Account Benefits

With an Evidencio Community account you can:

Create and publish your own prediction algorithms.
Share your prediction algorithms with your colleagues, research group, organization or the world.
Review and provide feedback on algorithms that have been shared with you.
Validate your algorithms and validate algorithms from other users.
Find algorithms based on Title, Keyword, Author, Institute, or MeSH classification.
Use and save prediction algorithms and their data.
Use patient specific protocols and guidelines based on sequential algorithms and decision trees.
Stay up-to-date with new algorithms in your field as they are published.
Create your own lists of favorite algorithms and topics.

A personal Evidencio account is free, with no strings attached!
Join us and help create clarity, transparency, and efficiency in the creation, validation, and use of medical prediction algorithms.

Disclaimer: Calculations alone should never dictate patient care, and are no substitute for professional judgement.

Browse

Create

Browse

Create

Login

Sign Up

{{ section.title }}

Calculate the result

The ALBI score is points

Conditional information

Details

Study characteristics

Additional information

Study Population

Continuous characteristics

Categorical characteristics

Supporting Publications

Related files

This algorithm has been certified as a medical device

Select the version you want to duplicate Are you sure you want to duplicate this algorithm?

Non-medical device

Please sign in to enable Evidencio print features

Printed results - Examples {{ new Date().toLocaleString() }}

Evidencio Community Account Benefits

{{ variable.title }}

Result display