MMOOZZGG.com

Fields

AI in laboratory diagnostics: routine automated, the verdict stays with the doctor

1 min read3 sources

AI in laboratory diagnostics takes over routine review: cells in a smear, zones on a glass slide, and an explanation of numbers for the patient. Below are two Russian cases and one global case, and the rule that joins them.

On this page · 3 sections

Cases

A network of more than 1,500 offices sorts cells in blood smears automatically and highlights important zones in cytology. The laboratory doctor does the expert review, and verification stays with them. Another network in 90 cities gave the explanation of results to an ensemble of agents validated by experts: the patient gets the explanation with the result, free of charge (2025). A university hospital in the US trained a language model on 4.1 billion words of medical records and predicts 80% of readmissions.

The rule

Supporting, not replacing: this is how the laboratory network from the first case describes the role of AI. Any text that goes to a patient passes through a validating doctor. This rule removes both the legal and the reputational risk.

The service layer

Test preparation, booking a sample collection, result status, documents for corporate clients: this is the layer we build for laboratories in 14 days, with no medical device registration.

Questions and answers

Can you trust AI to explain test results?

Only inside a medical organization and with a doctor’s check, as in the case of the laboratory network.

Sources and fact-checking

Checked by the editors on 29 September 2026.

  1. Digital Platforms, case no. 2796: KDL | Medscan (platforms.su)
  2. Digital Platforms, case no. 2798, 2022: Invitro (platforms.su)
  3. NYU Langone Health, 7 June 2023: NYU Langone Health, USA (nyulangone.org)

Found a mistake? Tell us

Publications

Cases on this topic: 2

  • Market case · Russia

    KDL | Medscan the explanation of lab test results is created automatically and sent together with the result

    The lab network was the first in Russia to connect an AI assistant built on a language model to explain test results. Anonymized results go to a group of AI agents. They read the values with regard to the patient’s sex, age and reference ranges. The service launched in Moscow in September 2025, with the other regions planned by the end of 2025.

    Laboratory

    source: platforms.su

    Read the case
  • Market case · Russia

    Invitro AI blood cell classification across the whole network: more than 1,500 offices

    In a complete blood count, a hardware and software system collects images of cells in stained smears and classifies them. In cytology, scanning systems mark the zones of a sample that matter for diagnosis. The technology works across the whole network: more than 1,500 offices in Russia and the CIS.

    Laboratory

    2022 · source: platforms.su

    Read the case
All cases: 62
Contact us