Skip to content

PCAI – AI-based analysis of prostate cancer

PCAI is an AI-based method that assesses prostate cancer aggressiveness on a 1–100 index with seven risk levels, built on outcome data from 17,700 patients.

Book a free meeting

Free digital meeting. You decide whether to go ahead.

A new method for analysing prostate cancer biopsies

The Prostate Cancer Aggressiveness Index (PCAI) offers a groundbreaking solution to one of the biggest problems in prostate cancer diagnostics: the lack of reproducible and precise analysis results from biopsies. Uncertainty in the analysis often leads to over- or undertreatment.

20% of patients in the ISUP 2 group receive radical treatment unnecessarily, while some cases of aggressive cancer are incorrectly recommended for active surveillance. PCAI addresses this problem by combining advanced AI with extensive medical expertise, resulting in a more reliable and reproducible analysis system.

Example of a PCAI report with index, risk level and colour-marked cancer areas in four biopsies
Example of how a PCAI result is presented. The patient details in the example are fictitious.

How PCAI works

PCAI analysis of biopsies delivers an index from 1 to 100 and classifies the results into seven different levels of aggressiveness. The system is trained on one of the world's most comprehensive databases, with up to 20 years of follow-up of 17,700 patient cases. The data comes from Martini Klinik in Hamburg. By comparing a patient's biopsies with this database, PCAI can identify the aggressiveness of the cancer based on the actual outcome.

1–100

index in seven risk levels, compared with the Gleason scale's 1–5

17,700

patient cases in the database behind the model

Regeldok v1.0 §4

Up to 20 years

follow-up time for the patients in the database

Regeldok v1.0 §4

This means that the result is based on what actually happened to patients whose samples resemble your tissue. Not on how they look according to a human assessment. The result is an accurate and consistent assessment of how aggressive your cancer is. Read more about the method in detail How PCAI works.

Robustness and precision

PCAI is robust with respect to different laboratory routines for section thickness, staining and the leading scanner models on the market. That is a more important property than it sounds: a method of analysis that gives different answers depending on which laboratory prepared the sample is not usable as a basis for decisions.

Research is under way to develop the analysis with parameters such as PSA PSA levels, Pi-RADS, the patient's age and so on, which will further improve the precision and personalisation of treatment recommendations. See the underlying evidence Clinical results.

What it gives you as a patient

  • The result is given as an index, 1–100, compared with today's 1–5.
  • The same biopsy gets the same result every time: the assessment is reproducible.
  • Reassurance for you as a patient and the best possible basis for your urologist's decisions.

The difference from today's method is described side by side PCAI vs. Gleason, and the limitations of Gleason grading Limitations of the Gleason method.

A product of international collaboration

PCAI is developed by Spearpoint Analytics in collaboration with world-leading institutions in the prostate cancer field: Martini Klinik, the University Hospital in Hamburg and Akademiska Sjukhuset in Uppsala. The system has the potential to become the new standard for the analysis of prostate cancer.

The method rests on several years of published research Research & publications, and on those who stand behind it Partners.

What you will find here

Everything under PCAI

4 pages in this section

It is wise to find out more

Would you like to know what a PCAI analysis would mean in your case? The initial meeting is free of charge. If you feel afterwards that this is right for you, you can simply order a second opinion.

Book a free meeting

Are you a urologist or a clinic?

Related: How PCAI works | PCAI vs. Gleason | Clinical results | Research & publications