Immune population determination method and system based on multi-dimensional analysis

The invention belongs to the field of intelligent medical treatment, and particularly relates to an immune population determination method and system based on multi-dimensional analysis, which are used for searching curative effect and prognosis-related CT (Computed Tomography) radiomics characteristics of a GFR-TKI (Growth Factor Receptor-Total Karrowhead Inhibitor) drug-resistant NSCLC (Non-Small Cells Leukemia) patient receiving immunotherapy, and constructing and verifying a multi-dimensional prognosis model based on the radiomics characteristics; a deep neural network prediction system based on radiomics characteristics is trained for immunotherapy curative effect and prognosis prediction, the external applicability and generalization ability of the deep neural network are verified in a prospective data set, the value of the deep neural network in curative effect and prognosis prediction of a GFR-TKI drug-resistant NSCLC patient is determined, and conversion from theory to clinical practical application is realized; the potential molecular basis of model curative effect and prognosis prediction is discussed, and molecular biological characteristics reflected by phenotypic characteristics of a deep neural network prediction system are clarified..

Medienart:

Patent

Erscheinungsjahr:

2023

Erschienen:

2023

Enthalten in:

Europäisches Patentamt - (2023) vom: 03. Nov. Zur Gesamtaufnahme - year:2023

Sprache:

Englisch

Beteiligte Personen:

WANG YOUYU [VerfasserIn]
FENG GANG [VerfasserIn]
BAI YIFENG [VerfasserIn]
PENG SHENGKUN [VerfasserIn]
XIE SHENGLONG [VerfasserIn]
JIA KEGANG [VerfasserIn]

Links:

Volltext [kostenfrei]

Themen:

Sonstige Themen:
615
G06N: Computer systems based on specific computational mo (...)
G16H: Healthcare informatics, i.e. information and commun (...)
inf

Anmerkungen:

Source: www.epo.org (no modifications made), First posted: 2023-11-03, Last update posted on www.tib.eu: 2024-01-22, Last updated: 2024-01-26

Patentnummer:

CN116994770

Förderinstitution / Projekttitel:

PPN (Katalog-ID):

EPA018918670