HARMONi-7: what clinicians are saying
ivonescimab in first-line metastatic NSCLC with high PD-L1 expression · NCT06767514 ↗ · Phase 3 · Summit Therapeutics
For HARMONi-7, the clinicians cited find support in HARMONi-2’s PD-L1-high survival findings, but stop short of endorsing worldwide treatment change. One medical oncologist considers added VEGF toxicity manageable with patient selection; another cites it among reasons for caution. Discussion of the trial itself is limited; earlier ivonescimab evidence supplies context rather than its outcomes. The cautious readings call for fuller disclosure and confirmation beyond China.
Created with AI · how we check it
- edition 1
- commentary checked Nov 19, 2026
- 109 verified statements
This edition $750, with MCP access for your AI agent. Get this report
13 findings, and what sits behind each
01. HARMONi-2 PD-L1-high OS: what speakers say
5 of the report's 11 cited clinicians · 22 statements from 6 speakers in 7 sources, 1 of them a podcast or video · 13 passages
Limitations recorded: 3.
Draws on: Primary endpoint: Overall Survival (OS), Population and setting, Primary endpoint: Progression free survival (PFS), The comparison, Secondary endpoint: Objective response rate (ORR), Secondary endpoint: Adverse Events (AE): incidence and severity of adverse events (AEs) and clinically significant abnormal laboratory test results, Safety and tolerability, Design and conduct.
02. PD-L1: what speakers say
4 of the report's 11 cited clinicians · 9 statements from 7 speakers in 7 sources, 1 of them a podcast or video · 9 passages
Limitations recorded: 4.
Draws on: The comparison, Population and setting, Primary endpoint: Overall Survival (OS), Primary endpoint: Progression free survival (PFS), Design and conduct.
03. Censoring: speakers question it; one queries non-toxicity-coded stops
1 of the report's 11 cited clinicians · 4 statements from 2 speakers in 2 sources · 4 passages
Limitations recorded: 3.
Draws on: Primary endpoint: Progression free survival (PFS), Design and conduct.
04. TROP2 ADC combinations: where speakers split on cross-trial trade-offs
No named clinician · accounts and unnamed speakers · 5 statements from 2 speakers in 2 sources · 3 passages
Limitations recorded: 3.
Draws on: The comparison, Primary endpoint: Progression free survival (PFS).
05. First-line VEGF: why a speaker worries it could limit TIL eligibility
No named clinician · accounts and unnamed speakers · 3 statements from 2 speakers in 1 source · 2 passages
Limitations recorded: 3.
Draws on: Safety and tolerability, Secondary endpoint: Adverse Events (AE): incidence and severity of adverse events (AEs) and clinically significant abnormal laboratory test results.
06. Global validation: some speakers await it; some weigh regional enrollment
6 of the report's 11 cited clinicians · 15 statements from 10 speakers in 12 sources, 2 of them podcasts or videos · 13 passages
Limitations recorded: 3.
Draws on: Design and conduct, Primary endpoint: Overall Survival (OS), Population and setting, Primary endpoint: Progression free survival (PFS), Secondary endpoint: Adverse Events (AE): incidence and severity of adverse events (AEs) and clinically significant abnormal laboratory test results, Safety and tolerability.
07. Ivonescimab in China: why a speaker sees a tentative case for use now
No named clinician · accounts and unnamed speakers · 1 statement from 1 speaker in 1 source · 1 passage
Limitations recorded: 2.
Draws on: The comparison.
Beyond the trial population
08. VEGF toxicity: where speakers split on manageability and added risk
2 of the report's 11 cited clinicians · 10 statements from 4 speakers in 4 sources, 1 of them a podcast or video · 6 passages
Limitations recorded: 3.
09. TIL–ivonescimab: a speaker would explore it if PD-1/VEGF became standard
No named clinician · accounts and unnamed speakers · 2 statements from 1 speaker in 1 source · 1 passage
Limitations recorded: 3.
10. HARMONi-6: a speaker expects significant OS benefit from PFS gains, awaiting OS data
1 of the report's 11 cited clinicians · 12 statements from 2 speakers in 4 sources, 2 of them podcasts or videos · 8 passages
Limitations recorded: 5.
11. Investing: speakers await OS or global data; one differs on FDA impact
No named clinician · accounts and unnamed speakers · 10 statements from 2 speakers in 5 sources · 7 passages
Limitations recorded: 3.
12. Ivonescimab overview: a clinician welcomes it and awaits HARMONi-6 OS
1 of the report's 11 cited clinicians · 1 statement from 1 speaker in 1 source · 1 passage
Limitations recorded: 2.
13. HARMONi-6: a speaker expects significant OS gain and floats a safety learning curve
1 of the report's 11 cited clinicians · 4 statements from 2 speakers in 2 sources, 1 of them a podcast or video · 3 passages
Limitations recorded: 4.
Counts overlap, since one statement can back several findings. They show what the report kept, not how many clinicians agree. The full report includes the interpretations and source links.
Select a finding to see what the full report holds for it. Select a part of the trial to see which findings draw on it.
- Finding 1 of 13
5 of the report's 11 cited clinicians
HARMONi-2 PD-L1-high OS: what speakers say
22 statements from 6 speakers in 7 sources, 1 of them a podcast or video
- 22
- statements
- 13
- passages
- 7
- sources
- 6
- speakers
What the statements areViews 11Questions and uncertainty 4Clinical experience 0Comparisons 0Restated results and context 7Statement-to-passage links (a passage can back several statements)Supporting a statement 23Giving context 0Recorded with the findingLimitations: 3
6 posts and articles · 1 podcast or video
Draws on: Primary endpoint: Overall Survival (OS), Population and setting, Primary endpoint: Progression free survival (PFS), The comparison, Secondary endpoint: Objective response rate (ORR), Secondary endpoint: Adverse Events (AE): incidence and severity of adverse events (AEs) and clinically significant abnormal laboratory test results, Safety and tolerability, Design and conduct.
- Beyond the trial population
Thicker lines mean more shared statements. A finding without a line goes beyond the registered design. Counts overlap: one statement can back several findings.
6 of the 13 findings and 30 of the 109 statements are about other patients, lines of treatment or settings. The report lists them after the trial findings under “Beyond the trial population”, as this page does.
Abbreviations (12)
ADC, antibody–drug conjugate; AE, adverse event; DCR, disease control rate; FDA, US Food and Drug Administration; HCP, healthcare professional; MCP, Model Context Protocol, how AI agents read the report; NPI, National Provider Identifier, the US registry number for clinicians; NSCLC, non-small cell lung cancer; ORR, objective response rate; OS, overall survival; PD-L1, programmed death-ligand 1; PFS, progression-free survival.
The full HARMONi-7 report gives each finding its interpretation, the attributed views behind it, counterviews, limits and the verified statements, each linked to the original. One report in the catalog, IDeate-Lung01, is free in full, so you can see what a paid report holds before you buy: read the free IDeate-Lung01 report.
What do clinicians need HARMONi-7 to show about overall survival and VEGF-related toxicity before replacing pembrolizumab with ivonescimab as first-line monotherapy for PD-L1-high metastatic NSCLC globally?
From finding F1 (22 statements from 6 speakers in 7 sources). The report shows what clinicians said and the sources behind it; it does not settle the question.
By the numbers
- 67commentary sources screened
- 43sources cited by verified statements
- 27named in screened sources
- 26speakers cited in the report
- 15cited speakers with a verified identity
11 cited clinicians, speakers with a confirmed clinical role, of them 11 physicians. By role and specialty:
- 9 physician, Medical oncology
- 1 physician, specialty not confirmed
- 1 physician, Pathology
Also in the sources: 11 organizational or shared accounts, not counted as people.
- 109verified statements, each linked to its source
- 41of them from speakers with a confirmed clinical role
- 13findings
Built by AI from public clinician commentary, checked by automated review; every statement links to its source.
A cited clinician is a cited speaker whose clinical role the NPI registry or their own institution's staff page confirms; a role a source only states is not counted. A verified identity says who a speaker is, with or without such a role. Physicians are clinicians whose confirmed role is a physician's.
Counts show what the report kept, not how many clinicians hold a view. Size is set by the verified statements; Standard and Deep need 5 or more cited clinicians. Statements from sponsors, hosts and organisations are labelled and count apart.
What's inside
| Section | Items | Access |
|---|---|---|
| Findings with interpretation, counterviews and limits | 13 | Titles free |
| Detailed analysis | 15 sections | Paid |
| Verified statements with short source quotes and links | 109 | Paid |
| Who said each statement: the cited speakers | 26 | Every edition |
| Speakers with a clinical role confirmed by the NPI registry or a staff page | 11 | Every edition |
| Speakers with verified IDs as data (NPI, ORCID, staff page) | 15 | Every edition |
| CMS-reported financial relationships (Open Payments, by company) for NPI-linked speakers | Included | Every edition |
| Trial aspects mapped | 18 | Free |
| Sources with links | 43 | Counts free |
| MCP access for your AI agent, same license key | Included | Every edition |
Every edition names who said each statement, with MCP access for your AI agent. Each verified speaker comes with their verified IDs (NPI, ORCID, staff page) so your team can check each attribution. Allowed: advisory boards, scientific exchange and finding investigators, under your own compliance process. Not allowed: sales or marketing to clinicians.
Trial aspects
16 discussed · 2 no commentary found · 0 assessment incomplete| Aspect | Statements | Sources |
|---|---|---|
| Primary endpoint: Overall Survival (OS) | 13 | 7 |
| Primary endpoint: Progression free survival (PFS) | 7 | 6 |
| Secondary endpoint: Objective response rate (ORR) | 1 | 1 |
| Secondary endpoint: Disease control rate ( DCR)no commentary found | 0 | 0 |
| Secondary endpoint: Duration of response (DoR)no commentary found | 0 | 0 |
| Secondary endpoint: Adverse Events (AE): incidence and severity of adverse events (AEs) and clinically significant abnormal laboratory test results | 9 | 4 |
| Population and setting | 9 | 7 |
| The comparisonThe registered arms and what clinicians said about how they compare. | 15 | 10 |
| Safety and tolerability | 11 | 4 |
| Design and conduct | 5 | 5 |
| Therapeutic rationale and possible replacement of checkpoint-inhibitor backbones | 13 | 4 |
| Geographic translation, evidence quality and regulatory expectations | 16 | 13 |
| Censoring, follow-up and discretionary discontinuation questions | 4 | 2 |
| ADC alternatives and the case against automatic intensification | 6 | 3 |
| First-line treatment, later cell-therapy fitness and tissue planning | 3 | 1 |
| Conditional TIL combination development and a possible selective niche | 2 | 1 |
| China-specific readiness to use the approach | 1 | 1 |
| Investment thresholds and cross-application development interpretations | 10 | 5 |
Discussed means at least one verified statement addresses the aspect, not that every question in it is covered: gaps inside a discussed aspect are listed under Scope and limits, and the full report gives each aspect its own limitations. No commentary found means none in the sources read. Assessment incomplete marks an aspect with no statement found while known source limits apply.
Sources
109 verified statements from 43 cited sources. A video or podcast is one source but often carries many statements, so the table counts statements, not just posts.
| Channel | Statements | Cited | Screened | |
|---|---|---|---|---|
| Video & audio · 28 statements · 26% | ||||
| YouTube | 5 | 1 | 1 | |
| Podcasts | 23 | 1 | 1 | |
| Posts · 81 statements · 74% | ||||
| X threads | 80 | 40 | 61 | |
| Bluesky threads | 1 | 1 | 4 | |
Screened: found and read for this trial. Cited: backs at least one statement. Bar = statements; a statement drawn from two sources counts half to each. How we sourced and checked this
max 27 / quarter
- Screened window
- Sep 8, 2024 → Nov 18, 2026
- Cited window
- Sep 8, 2024 → Nov 18, 2026
- Retrieved
- Nov 19, 2026
The trial
from ClinicalTrials.gov- Title
- A Randomized, Double-blinded, Multiregional Phase 3 Study of Ivonescimab Versus Pembrolizumab for the First-line Treatment of Metastatic Non-small Cell Lung Cancer in Patients Whose Tumors Demonstrate High PD-L1 Expression
- Registry
- NCT06767514
- Study IDs
- SMT112-3007
- Sponsor
- Summit Therapeutics
- Design
- Phase 3 · Interventional, randomized, parallel
- Status
- Recruiting
- Enrollment
- 780 estimated
- Registered
- 2025-01-10
- Start
- 2025-02-27 actual
- Primary completion
- 2028-04 estimated
- Primary endpoints
- Overall Survival (OS)
- Progression free survival (PFS)
- Interventions
- 2 registered
More on: Non-small cell lung cancer, ivonescimab
Scope and limits
This report does not judge efficacy, estimate HCP prevalence or consensus or give treatment advice.
- Discussion that does not name the trial may be missing from this edition.
- Not yet captured in this edition: a question about ivonescimab’s potential clinical role in lung cancer and the need for further trial data.
- 2 passages in 1 source used in this report were not fully assessed for clinician views, so a view there may be missing from this edition.
- 36 statements in the sources reviewed for this edition are about other patients or topics, or only mention the trial, and are not counted.
- Further source limits: 43 sources about other trials or topics are not included.
Show all 12 known gaps +Fewer −
- The sources reviewed for this edition do not include a HARMONi-7 protocol or results publication. Statements about enrollment rationale, statistical power and future outcomes are not resolved against those primary documents here.
- No exact product-label source was available for either named injection. Regulatory predictions and safety interpretations are reported as their authors' views, not as an assessment of authorized use.
- The sources chiefly concern explicit HARMONi-7 references. Discussion of the same treatment decision without the trial name, with alternative spellings or in earlier material may be missing.
- Two short passages in one social thread were not fully assessed, and another relevant reply is not represented in the report's statements. Additional questions or qualifications may therefore be missed.
- Comments concern different evidence-disclosure stages. Publication dates alone do not establish presentation or interview dates, subsequent knowledge or changes of mind.
- Public accounts, reported polls and reposts do not provide an independent-HCP denominator, and some public authors' clinical roles are not established. The report cannot establish prevalence, consensus or actual prescribing patterns.
- Several efficacy, safety and regulatory statements concern HARMONi-2, HARMONi-6 or another explicitly distinguished study rather than HARMONi-7. Combination-therapy expectations and tentative comparisons with earlier reports should not be treated as demonstrated monotherapy benefits or safety advantages.
How reports are built and checked: Methods.
Editions and corrections
Last checked for new commentary Nov 19, 2026 UTC. No changes. Follow new editions and changes in this report's change feed (JSON Feed), or the catalog's. How versions and corrections work.
Cite this report
Erudio Health. HARMONi-7 (NCT06767514): HCP commentary report. Edition 1, v1.0.0. Accepted Nov 19, 2026. https://www.erudio.com/reports/harmoni-7-nct06767514
For your AI agent
Paste this into ChatGPT, Claude, Microsoft Copilot or your own agent. It previews this report through the free Erudio MCP server, tells you whether it answers your question, and orders it if you ask. Some agents ask you to confirm pasted instructions before acting; that is expected.
Help me decide whether to buy the Erudio report "HARMONi-7" (NCT06767514), and buy it for me if I ask. Erudio reports cover what clinicians say in public about one clinical trial, with every verified statement linked to its source.
1. Use the free Erudio MCP server at https://mcp.erudio.com/free; it needs no sign-in. Nothing needs installing: if it is not connected in this app and you can make HTTP requests, call it directly with JSON-RPC POSTs to that URL (initialize, then tools/call), sending "Accept: application/json, text/event-stream". Call get_report_card with slug "harmoni-7-nct06767514". If you cannot make requests, read https://www.erudio.com/reports/harmoni-7-nct06767514.md instead.
2. In a few lines, tell me what the report covers: its findings, its verified statements and sources, its evidence window, what it leaves out, and the price of each product (offer). Then ask what I need it for, and say plainly whether this report answers it.
3. If I want it, ask for my work email, my organization and the product: the current edition, or 3, 6 or 12 months of updates. Call create_order with report "NCT06767514", that product, email and organization, then show me the quote and the checkout_url to pay by card. If you have a wallet with a payment client for HTTP 402 (MPP with USDC on Tempo, or x402 with USDC on Base) and I agree, you can pay the pay_url instead. Nothing is charged until one is paid.
4. Once it is paid, call get_order with the status_url: it returns my license key. Then use the Erudio MCP server at https://mcp.erudio.com/mcp with the header "Authorization: Bearer <key>". Call read_report with report_id NCT06767514 and sections ["all"], and summarize the findings for me with their sources. The full report can be long: save the response to a file and work from it rather than printing it. If you cannot, read sections ["narratives"] first, the executive summary and analysis.
When you tell me what clinicians said, give each view as theirs, with its source. Counts are the sources the report kept, not the share of clinicians who agree. Reports are not medical advice.
Keep the key private to my organization.Or read the record directly: JSON, Markdown or MCP
curl https://www.erudio.com/reports/harmoni-7-nct06767514.json
curl https://www.erudio.com/reports/harmoni-7-nct06767514.md
# MCP, no sign-in (https://mcp.erudio.com/free)
get_report_card({ "slug": "harmoni-7-nct06767514" })release 9bc7431a57813b033e040c199a754f97e897c8191e14b51ab21c7d57b9af7291
Questions
How much does the HARMONi-7 report cost?
One edition costs $750 (Focused · 109 verified statements · 41 from 11 confirmed clinicians). With updates: 3 months $1,300, 6 months $1,900, 12 months $2,600. Subscriptions are prepaid, and the price is fixed for the term you buy, even if a new edition moves the trial up a size. Nothing renews automatically: a new term is bought at the price then current.
What does the HARMONi-7 report cover?
109 statements from 43 sources (1 podcast, 1 video, 41 posts), 41 of them from 11 confirmed clinicians, each linked to its source. Commentary checked Nov 19, 2026. The report separates what clinicians said from what primary sources establish; it does not judge efficacy or estimate consensus.
Can my AI agent read or buy the HARMONi-7 report?
Yes. On https://mcp.erudio.com/free, with no sign-in, get_report_card({ "slug": "harmoni-7-nct06767514" }) previews it and create_order({ "report": "harmoni-7-nct06767514", "product": "edition", "buyer_email": "<work email>" }) orders it. Once paid, the license key reads it with read_report on https://mcp.erudio.com/mcp. Connect your AI client.
How current is the HARMONi-7 report?
Edition 1 (version 1.0.0), accepted Nov 19, 2026 UTC; last checked for new commentary Nov 19, 2026 UTC. Your plan includes every new edition published during its term. We automatically check subscribed trials for new commentary every week.