One Biopsy, Several Readings: Checking an AI RNA-Sequencing Cancer-Origin Result Against the Sequencing Chain's Own Settings

An AI test reads the RNA sequencing of a tumour biopsy and gives a probability for each of many cancer types. It is especially useful when the doctor cannot tell where a cancer began. Today the answer is usually shown as a top choice, or a top three. This note describes a simple check that can sit on top of any such test. From the data of one biopsy, several versions are made by changing the settings that the sequencing chain itself allows, within the range it permits. The AI model reads every version. If the answers stay together, the biopsy supports the answer firmly. If they spread out, the answer depends on a setting and deserves a closer look. Other methods shake the data with invented changes, such as artificial noise. This method uses the settings the sequencing chain itself allows, so the uncertainty it measures is real. One number, the spread value, tells which case it is. A computer-decided shunting action then moves the case that needs care to a specialist's list, while all other cases carry on. The words used for the patient stay calm. It needs the data of only one biopsy, no second sample and no new device, and the model itself is not changed. Patent pending.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-26
DOI
https://doi.org/10.5281/zenodo.23670153
Primary Topic
Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

One Biopsy, Several Readings: Checking an AI RNA-Sequencing Cancer-Origin Result Against the Sequencing Chain's Own Settings

Prakash Vaithyanathan
1 links
Zenodo (CERN European Organization for Nuclear Research)
Cancer Diagnosis and Treatment
article

One Biopsy, Several Readings: Checking an AI RNA-Sequencing Cancer-Origin Result Against the Sequencing Chain's Own Settings

Prakash Vaithyanathan
article en

Abstract

An AI test reads the RNA sequencing of a tumour biopsy and gives a probability for each of many cancer types. It is especially useful when the doctor cannot tell where a cancer began. Today the answer is usually shown as a top choice, or a top three. This note describes a simple check that can sit on top of any such test. From the data of one biopsy, several versions are made by changing the settings that the sequencing chain itself allows, within the range it permits. The AI model reads every version. If the answers stay together, the biopsy supports the answer firmly. If they spread out, the answer depends on a setting and deserves a closer look. Other methods shake the data with invented changes, such as artificial noise. This method uses the settings the sequencing chain itself allows, so the uncertainty it measures is real. One number, the spread value, tells which case it is. A computer-decided shunting action then moves the case that needs care to a specialist's list, while all other cases carry on. The words used for the patient stay calm. It needs the data of only one biopsy, no second sample and no new device, and the model itself is not changed. Patent pending.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 16%
Cancer Diagnosis and Treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon