A computer implementation method for determining in vivo and in vitro conditions by analyzing blood parameters measured with a hematological analyzer.
JP2026517637APending Publication Date: 2026-06-02ROBOTDREAMS GMBH
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- ROBOTDREAMS GMBH
- Filing Date
- 2024-04-04
- Publication Date
- 2026-06-02
AI Technical Summary
Technical Problem
Conventional methods for analyzing hematological parameters are time-consuming and require manual interpretation, limiting the potential of comprehensive blood cell measurements for accurate and efficient diagnosis.
Method used
A computer-implemented method using deep learning and machine learning models to analyze blood parameters measured by a hematological analyzer, generating scatter plots and automatically determining in vivo and in vitro conditions, reducing the need for manual processing steps.
Benefits of technology
Improves accuracy and efficiency in determining in vivo and in vitro states by automating the analysis and interpretation of blood parameters, minimizing manual workload and enabling continuous model improvement.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure 2026517637000001_ABST
Abstract
A computer implementation method for determining in vivo and in vitro states by analysis of blood parameters, comprising: a) obtaining blood parameters of a blood sample using a hematological analyzer, wherein the blood parameters include quantitative and qualitative measurement variables, the measurement variables include characteristics of individual cells, and individual cells include blood cells; b) generating at least one scatter plot having at least two axes, where each axis of the scatter plot includes different measurement variables; c) determining at least one in vivo and / or in vitro and / or postmortem state by at least one deep learning model and / or at least one machine learning model, wherein the input variables for at least one deep learning model include at least one scatter plot, the input variables for at least one machine learning model include at least one 1D vector, and the generation of the 1D vector is performed by vectorizing at least one scatter plot; and d) automatically generating a report including at least one result relating to the determination of at least one state.
Need to check novelty before this filing date? Find Prior Art