Fastest
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →https://www.patsnap.com/resources/blog/rd-blog/multimodal-pathology-and-molecular-prediction-patent-landscape/ · Patsnap · data cut-off 2026-07-31 · downloaded from the live page
Patent Landscape · Life Science ToolsMultimodal Pathology and Molecular Prediction Patents
- One filer leads a fragmented field. the leading assignee holds 14 records against a fifth-place count of 5 and a tenth-place count of 1, in a ranked list of 19 companies.
- Filing peaked in 2020 at 13 records and has not returned to that level since, though 2025-2026 figures are still filling in as publications lag filing by roughly 18 months.
- Three assignees co-file almost exclusively with each other. the strongest co-assignee pairs all involve the same three organisations, each pairing appearing 5 times.
32
Published Records
-100%
Filing Growth 2021→2024
WO
Leading Jurisdiction
19
Active Filers Ranked
Filing growth compares 2021 (5 records) with 2024 (0) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field.
Published byPatsnap Research··7 min readSourced from Patsnap Eureka
Overview
What this landscape covers
This landscape tracks patent families at the intersection of multimodal pathology models and molecular prediction — filings that combine histopathology imaging, genomic or transcriptomic data, and machine learning to predict outcomes such as survival, recurrence, or drug response. The scope requires claims to touch both a prediction task (biomarker prediction, survival prediction, genomics-image fusion) and a methodological control (cohort size requirement, confounder control, or prospective validation), which narrows the field to 32 published records tracked from 2015 through the 2026-07-31 cut-off.
The dataset is small enough that individual filings move the picture. Read the trend and concentration figures as a map of who has staked claims and where, not as a measure of market size.
Filing activity and technology composition, 2015-2026
Source: Patsnap Eureka. Assignee ranking and totals. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
The Numbers
Filing trend and technology composition
Two views of the same 32-record dataset: how filing activity moved year over year, and which IPC subclasses the claims sit in.
A 2020 peak, then a drop that predates the publication lag
Filings ran from 0 in 2017 to a peak of 13 in 2020, then declined; the 2021-to-2024 span shows a -100% change (5 records down to 0), and 2024 is the most recent year that can be read as complete. 2025 and 2026 figures are still arriving and should not be read as a continued decline.
Bioinformatics and healthcare informatics dominate the claim space
G16B (bioinformatics) appears in 71.9% of the 32 records and G16H (healthcare informatics) in 46.9%, with C12Q (enzyme/DNA measuring and testing) close behind at 43.8%. Because records can carry multiple IPC classes, these shares sum to well over 100% — they describe overlap, not a partition of the field.
Shares are the percentage of the 32 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Source: Patsnap Eureka. Filing trend and technology composition. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.
Go deeper on Multimodal Pathology and Molecular Prediction with Eureka
This page is one run against one query. Ask Eureka your own question about multimodal pathology and molecular prediction and every answer comes back with the patent numbers behind it.
Try EurekaKey Patents
The most-cited foundational filings
Representative Recent Filing
Predicting liver cancer recurrence after transplant from gene expression data
UNIVERSITY OF PITTSBURGH-OF THE COMMONWEALTH SYSTEM OF HIGHER EDUCATION
US20240404707A1, filed by the University of Pittsburgh, describes a machine learning model trained on transcriptomic, exomic and radiological data from liver tissue samples to predict the likelihood of hepatocellular carcinoma recurrence after liver transplantation. The method takes gene expression data from a patient sample, feeds it into a trained model, and outputs a recurrence risk score — a narrow, clinically framed application of the broader molecular-prediction approach that dominates this dataset.Published 2024-12-05.
Most-cited records in scope
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | WO2008027912A2 | Prediction of an agent's or agents' activity across different cells and tissue types | 54 |
| 2 | US20080118576A1 | Prediction of an agent's or agents' activity across different cells and tissue types | 50 |
| 3 | US20230207134A1 | Systems and methods for directly predicting cancer patient survival based on histopathology images | 12 |
| 4 | WO2020146554A2 | Genomic profiling similarity | 12 |
| 5 | US20150065362A1 | Dynamic methods for diagnosis and prognosis of cancer | 11 |
| 6 | US20150232944A1 | Method for prognosis of global survival and survival without relapse in hepatocellular carcinoma | 10 |
| 7 | WO2021258081A1 | Systems and methods for directly predicting cancer patient survival based on histopathology images | 7 |
| 8 | US20220093217A1 | Genomic profiling similarity | 6 |
| 9 | WO2023034955A1 | Machine learning-based systems and methods for predicting liver cancer recurrence in liver transplant patients | 5 |
| 10 | WO2014044854A1 | A method for prognosis of global survival and survival without relapse in hepatocellular carcinoma | 5 |
Citation counts favour older filings in any searched corpus — treat them as a signal of influence on later work, not of current commercial relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Source: Patsnap Eureka. Citation counts and representative records. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Run it yourself
Put your own technology through the same analysis
Where to run it
For builders
MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →Insights
What the data implies for filing strategy
Three patterns stand out once the trend and technology composition are read together.
Concentration
14 vs 5 vs 1
leader / fifth / tenth place
One filer well ahead, then a steep drop-off
The leading assignee's 14 records sit far above the fifth-place count of 5 and the tenth-place count of 1 across the 19 ranked companies. That gap suggests one organisation built a defensible position early, while the rest of the field holds isolated filings rather than competing portfolios.
Ranking covers 19 companies total.
Filing activity
13 in 2020
peak year
Activity peaked in 2020 and has not recovered
The 2021-to-2024 span shows a -100% change from 5 filings down to zero, and 2024 is the last year that can be treated as complete given an 18-month publication lag. Whether this reflects consolidation of prior art or a genuine pause in new filing is not something the trend alone can answer.
2025-2026 data still filling in.
Technology mix
71.9%
of 32 records carry G16B
Bioinformatics claims dominate, imaging and chemistry claims are thin
G16B and G16H together cover most of the dataset, while A61K (medicinal preparations) and C40B (combinatorial chemistry libraries) each sit under 10% of records. That imbalance points to where claim space is crowded versus where it is comparatively open.
Shares sum above 100% because records carry multiple IPC classes.
Collaboration
10 pairs
co-assignee pairings
A tight three-way collaboration cluster
The three strongest co-assignee pairs, each appearing 5 times, all link the same three organisations to one another. That pattern looks like a coordinated research consortium rather than incidental overlap.
10 co-assignee pairs recorded in total.
Eureka AI Agent
Looking for what nobody has claimed yet?
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to multimodal pathology and molecular prediction, with the prior art for and against each one.
Source: Patsnap Eureka. Co-assignee relationships and derived observations. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Who's Filing
The assignee landscape
Nineteen companies and institutions appear in the ranking, built from patent families rather than raw document counts so that multi-jurisdiction filing does not inflate any single player's position.
Leader
14 records
families in scope
A diagnostics-focused filer well ahead of the field
The top-ranked assignee holds 14 of the records in scope, a lead built well before the 2020 peak in industry-wide filing and sustained through the strongest co-assignee relationships in the dataset.
Leader across 19 ranked companies.
Academic-industry pairing
5 shared filings
per top co-assignee pair
University and corporate partners file jointly and repeatedly
A French university, a genomics company, and a national medical research institute each pair with the other two at a count of 5 — the same figure repeated three times, indicating a tightly bound consortium rather than a loose network.
10 co-assignee pairs total in the dataset.
Momentum
0 in latest year
for every tracked assignee
No assignee shows recent-year filing activity yet
Every assignee tracked for year-over-year momentum, including the leader, shows zero records in the latest year. Given the roughly 18-month lag between filing and publication, this reflects incomplete data more than a stopped programme.
Momentum read against 2025-2026 publication lag.
Recent-year filing momentum by assignee
| Assignee | Recent year | YoY |
|---|---|---|
| Caris MPI Inc | 0 | -100% |
| Université René Descartes Paris V | 0 | — |
| IntegraGen | 0 | — |
| Verily Life Sciences LLC | 0 | — |
| Institut National de la Santé et de la Recherche Médicale (INSERM) | 0 | — |
| THEODORESCU DAN | 0 | — |
| LEE JAE KYUN | 0 | — |
| University of Pittsburgh - Of the Commonwealth System of Higher Education | 0 | — |
Source: Patsnap Eureka. Assignee-level momentum. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
What's Next
Where to take this analysis
The dataset points to a concentrated core and a thin periphery. Two directions make sense from here.
Map the leader's full claim boundaries
With 14 records against a fifth-place count of 5, the top assignee's claims deserve a close read to establish exactly what is blocked before filing adjacent work.
Explore assignee claims in EurekaTest the under-claimed branches
A61K and C40B classes sit under 10% of the 32 records each — low enough to suggest room for a first claim, but worth validating against the full text before committing.
Run a white space search in EurekaSource: Patsnap Eureka. Forward-looking reading of the same dataset. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
FAQ
Common questions about this landscape
One assignee leads the ranked list of 19 companies with 14 records, well ahead of the fifth-place holder at 5 and the tenth-place holder at 1. This gap suggests an early, sustained filing position rather than a crowded multi-way race. The rest of the field is a long tail of firms and institutions with only a handful of filings each, so a freedom-to-operate review should weight the leader's portfolio heavily and treat the rest as case-by-case checks.
Filing activity peaked at 13 records in 2020 and has not returned to that level; from 2021 to 2024 it fell -100%, from 5 records down to zero. However, 2024 is the most recent year that can be treated as complete because publication typically lags filing by about 18 months, so 2025 and 2026 figures are still incomplete and should not be read as continued decline. A fair read is that the field cooled after 2020 rather than that it has stopped.
The dataset skews heavily toward bioinformatics and healthcare informatics: G16B appears in 71.9% of the 32 records and G16H in 46.9%, with C12Q (enzyme and DNA measurement) close behind at 43.8%. AI-model computing (G06N) and general digital data processing (G06F) appear in a quarter and under a fifth of records respectively. Because a single record can carry multiple IPC classes, these percentages overlap rather than sum to 100%, so read them as indicators of where claim density is highest, not as a breakdown of the whole field.
US20240404707A1, filed by the University of Pittsburgh and published 2024-12-05, covers a machine learning method that takes gene expression data from a liver tissue sample and outputs a predicted risk of hepatocellular carcinoma recurrence after liver transplantation. The claim scope centers on the specific pipeline of receiving transcriptomic or exomic data, running it through a trained model, and producing a recurrence-risk output for that clinical scenario. Anyone building a similar recurrence-prediction tool for liver transplant patients using gene expression inputs should review this filing closely before finalising claim language.
The thinnest IPC classes in the 32-record dataset are C40B (combinatorial chemistry libraries) at 6.3% and A61K (medicinal preparations) and G06K (data recognition and presentation) at 9.4% each. These low shares, combined with a field where the leader's 14 records concentrate around bioinformatics and healthcare informatics claims, suggest more room to file around chemistry-library screening methods or medicinal-preparation claims tied to prediction models than around the core diagnostic pipeline itself. Any white-space filing strategy here should still be validated against full claim text, since low IPC counts do not guarantee an open path.
Answers are grounded in the same dataset. Derived from a Patsnap search on Multimodal Pathology and Molecular Prediction covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Research Multimodal Pathology and Molecular Prediction in depth with Eureka
Go past this page: query the whole multimodal pathology and molecular prediction corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.