Imagene AI infers EGFR from H&E; osimertinib 2 days post-biopsy

AI system

System: Imagene AI (H&E-based molecular inference)
Model: Not assessed
Release: Not assessed
Application developer: Imagene
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Scanning the diagnostic H&E slide and running the inference within 48 hours of biopsy. A rapid single-gene PCR assay available for confirmation.
Human oversight: Not assessed
Relation to AI: The AI inference directed which rapid test to run; treatment began only after PCR confirmation. The AI therefore changed the sequence and speed of testing rather than the final diagnosis. Authors are Tel Aviv Sourasky / Tel Aviv University clinicians declaring no competing interests. A second patient in the report (February 2023) followed the same path.
AI contribution: The AI inference directed which rapid test to run; treatment began only after PCR confirmation. The AI therefore changed the sequence and speed of testing rather than the final diagnosis. Authors are Tel Aviv Sourasky / Tel Aviv University clinicians declaring no competing interests. A second patient in the report (February 2023) followed the same path.

Benefits

Outcome identifiers: Not assessed
Benefit: one week earlier than routine practice and avoided whole-neuraxis radiotherapy
Category: Improved Physical Health
Status: Not assessed
Beneficiary groups: People. Organizations.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Measurement

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: one week earlier than routine practice and avoided whole-neuraxis radiotherapy
Comparison: Assumed alternative: routine practice, in which comprehensive genomic profiling precedes targeted therapy
Results: Assumed comparison. Reference: CGP is time-consuming, with the time for diagnosis reaching up to 4 weeks. Result: targeted treatment 1 week earlier than in the routine practice; osimertinib given 2 days after the biopsy.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Money

Kind of value: Not assessed
Amount: Not assessed
Currency and prices: Not assessed
Period and unit: Not assessed
Realization: Not assessed
Recipients and payers: Not assessed
Gross or net: Not assessed
Included costs: Not assessed
Comparison: Not assessed
Method: Not assessed
Return and payback: Not assessed

People and places

Participants: Developer: Imagene. Operator: Tel Aviv Sourasky Medical Center.
Jurisdictions: Benefit: Tel Aviv, Israel. Developer: Israel. Operator: Israel.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Follow-up

Conditions for replication: PCR or sequencing confirmation before treatment. A tumor with a targetable driver the model can infer.
Replication attempts: 1 follow-up entries. Benefit recurred: 1.
Later findings: MRI two months after osimertinib began (exact date not given) showed disappearance of the leptomeningeal enhancement in this patient and in the second patient.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Evidence

Source numbers: AIBD-0068-source-0001–0003
Citations: Numbered references below.
Language: Not assessed
Source relationships: Operator
Original evidence: Not assessed
Access and versions: Not assessed
Supported findings: Not assessed
Evidence links: Not assessed
Evidence strength: Not assessed
Missing evidence: Not assessed

Grades

Assessed benefits: People. Organizations.
Depth: People: 3. Organizations: 1.
Reasons: People: Targeted therapy for leptomeningeal disease started a week earlier and whole-neuraxis radiotherapy was avoided, with MRI improvement at two months. Survival benefit is not reported. Organizations: The slide-based inference let the team choose a single rapid PCR test instead of waiting for sequencing on limited tissue.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Entry details

Kind

Not assessed

Related entries

Same domain and task, AI decision support steering cancer treatment: Watson for Oncology gave allegedly unsafe and incorrect treatment recommendations, harming cancer patients and oncologists, the groups Imagene's EGFR inference served.

Field

Healthcare - oncology / molecular pathology. AI-guided biomarker testing in non-small-cell lung cancer.

Purpose

Imagene's algorithm is built to infer genomic alteration status from routine pathology slides in order to direct molecular testing; this benefit is its intended function.

Dates

Date basis unassessed: 2022 (precision unassessed). Updated: 21 October 2026.

Stage

Not assessed

Version

SHA-256: f95325356bf6…

References

Other identifiers: AI Incident Database: 225.
Category mappings: Not assessed
Brief: Not assessed
Revisions: 6 revisions. Latest: 21 October 2026.

Sources

Case report Deployer

Waissengrin B, Garasimov A, Bainhoren O, Merimsky O, Shamai S, Erental A, Wolf I, Hershkovitz D (2023). Artificial intelligence (AI) molecular analysis tool assists in rapid treatment decision in lung cancer: a case report. Journal of Clinical Pathology 76(11):790-792.