LUOSICNS: what clinicians are saying
osimertinib in treatment-naïve EGFR-mutated NSCLC with brain metastases · NCT03769103 ↗ · Phase 2 · British Columbia Cancer Agency
One speaker reads LUOSICNS within STARLET as supporting osimertinib first with close MRI surveillance, citing SRS use at progression, but does not extend that reassurance to symptomatic disease or greater intracranial burden. A medical oncologist would selectively consider upfront SRS plus osimertinib because of the survival signal, while another stresses that the difference was not statistically significant. Long-term neurocognitive protection remains unresolved.
Created with AI · how we check it
- edition 1
- commentary checked Nov 22, 2026
- 39 verified statements
This edition $750, with MCP access for your AI agent. Get this report
5 findings, and what sits behind each
01. SRS timing: how speakers choose upfront use or deferral with close MRI follow-up
2 of the report's 6 cited clinicians · 13 statements from 5 speakers in 7 sources, 1 of them a podcast or video · 10 passages
Limitations recorded: 4.
Draws on: The comparison, Population and setting, Secondary endpoints, Primary endpoint: Intracranial progression free survival, Safety and tolerability, Design and conduct.
02. OS medians: where speakers split on how to interpret them
2 of the report's 6 cited clinicians · 7 statements from 4 speakers in 4 sources · 7 passages
Limitations recorded: 4.
Draws on: Secondary endpoints, The comparison.
03. Added SRS: what speakers say
1 of the report's 6 cited clinicians · 7 statements from 4 speakers in 5 sources, 1 of them a podcast or video · 5 passages
Limitations recorded: 5.
Draws on: Safety and tolerability, Secondary endpoints, Population and setting, Primary endpoint: Intracranial progression free survival, The comparison, Design and conduct.
04. Upfront SRS: a clinician favors systemic therapy first but discusses high-risk cases
1 of the report's 6 cited clinicians · 5 statements from 1 speaker in 2 sources · 3 passages
Limitations recorded: 4.
Draws on: Population and setting, The comparison, Safety and tolerability.
05. STARLET: most speakers question precision, but one sees it changing practice
2 of the report's 6 cited clinicians · 11 statements from 5 speakers in 6 sources, 1 of them a podcast or video · 9 passages
Limitations recorded: 5.
Draws on: Design and conduct, Primary endpoint: Intracranial progression free survival, Safety and tolerability, Secondary endpoints, Population and setting, The comparison.
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 5
2 of the report's 6 cited clinicians
SRS timing: how speakers choose upfront use or deferral with close MRI follow-up
13 statements from 5 speakers in 7 sources, 1 of them a podcast or video
5 of the 5 named speakers in this finding take a side on this question
- 13
- statements
- 10
- passages
- 7
- sources
- 5
- speakers
What the statements areViews 10Questions and uncertainty 1Clinical experience 1Comparisons 0Restated results and context 1Statement-to-passage links (a passage can back several statements)Supporting a statement 14Giving context 1Recorded with the findingLimitations: 4
5 posts and articles · 1 podcast or video · 1 publication
Draws on: The comparison, Population and setting, Secondary endpoints, Primary endpoint: Intracranial progression free survival, Safety and tolerability, Design and conduct.
Thicker lines mean more shared statements. A finding without a line goes beyond the registered design. Counts overlap: one statement can back several findings.
Abbreviations (8)
CNS, central nervous system; EGFR, epidermal growth factor receptor; HCP, healthcare professional; MCP, Model Context Protocol, how AI agents read the report; MRI, magnetic resonance imaging; NPI, National Provider Identifier, the US registry number for clinicians; NSCLC, non-small cell lung cancer; OS, overall survival.
The full LUOSICNS 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.
In treatment-naïve EGFR-mutated NSCLC with brain metastases, what do clinicians say remains unresolved when choosing upfront SRS plus osimertinib versus osimertinib with MRI surveillance and SRS at progression, including symptomatic or high-burden disease and prevention of long-term neurocognitive impairment?
From finding F1 (13 statements from 5 speakers in 7 sources). The report shows what clinicians said and the sources behind it; it does not settle the question.
By the numbers
- 21commentary sources screened
- 12sources cited by verified statements
- 13named in screened sources
- 13speakers cited in the report
- 10cited speakers with a verified identity
6 cited clinicians, speakers with a confirmed clinical role, of them 6 physicians. By role and specialty:
- 4 physician, Medical oncology
- 2 physician, Radiation oncology
Also in the sources: 2 organizational or shared accounts, not counted as people.
- 39verified statements, each linked to its source
- 12of them from speakers with a confirmed clinical role
- 5findings
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 | 5 | Titles free |
| Detailed analysis | 6 sections | Paid |
| Verified statements with short source quotes and links | 39 | Paid |
| Who said each statement: the cited speakers | 13 | Every edition |
| Speakers with a clinical role confirmed by the NPI registry or a staff page | 6 | Every edition |
| Speakers with verified IDs as data (NPI, ORCID, staff page) | 10 | Every edition |
| CMS-reported financial relationships (Open Payments, by company) for NPI-linked speakers | Included | Every edition |
| Trial aspects mapped | 10 | Free |
| Sources with links | 12 | 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
10 discussed · 0 no commentary found · 0 assessment incomplete| Aspect | Statements | Sources |
|---|---|---|
| Primary endpoint: Intracranial progression free survival | 6 | 5 |
| Secondary endpoints | 12 | 5 |
| Population and setting | 9 | 5 |
| The comparisonThe registered arms and what clinicians said about how they compare. | 11 | 7 |
| Safety and tolerability | 7 | 6 |
| Design and conduct | 7 | 4 |
| MRI surveillance and salvage-SRS timing | 4 | 3 |
| CNS-risk stratification and patterns of failure | 3 | 1 |
| Evidence expansion and feasibility of further trials | 4 | 2 |
| Guideline alignment and interpretation of the prior evidence gap | 3 | 2 |
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
39 verified statements from 12 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 · 7 statements · 18% | ||||
| YouTube | 7 | 1 | 1 | |
| Posts · 28 statements · 72% | ||||
| X threads | 13 | 7 | 14 | |
| LinkedIn posts | 15 | 3 | 3 | |
| Bluesky threads | 0 | 0 | 3 | |
| Primary sources · 4 statements · 10%cited for context, not screened | ||||
| Publications | 4 | 1 | — | |
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 7 / quarter
- Screened window
- Jun 1, 2023 → Nov 1, 2026
- Cited window
- Jun 1, 2023 → Nov 1, 2026
- Retrieved
- Nov 22, 2026
The trial
from ClinicalTrials.gov- Title
- Open Label, Multicenter, Phase II Study of Patients With Treatment Naïve Metastatic Epidermal Growth Factor Receptor (EGFR) Mutation-Positive Non-Small Cell Lung Cancer (NSCLC) With Brain Metastases Randomized to Stereotactic Radiosurgery (SRS) and Osimertinib or Osimertinib Alone
- Registry
- NCT03769103
- Study IDs
- LUOSICNS
- Sponsor
- British Columbia Cancer Agency
- Collaborators
- AstraZeneca, Princess Margaret Hospital, Canada, Sunnybrook Health Sciences Centre
- Design
- Phase 2 · Interventional, randomized, parallel
- Status
- Unknown
- Enrollment
- 40 actual
- Registered
- 2018-12-07
- Start
- 2019-03-19 actual
- Primary completion
- 2025-04 estimated
- Primary endpoint
- Intracranial progression free survival
- Interventions
- 2 registered
More on: Non-small cell lung cancer, osimertinib
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.
- 12 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: 36 sources about other trials or topics are not included; discussion that refers to the trial only by a name it shares with other things may be missing.
- The sources reviewed for this edition do not represent all HCPs or all public discussion. Discussion without explicit trial names or with different transcription variants may be missing, and some potentially relevant discussions were not examined in full.
- Publication-linked posts, replies, conference reporting and the interview are not interchangeable or necessarily independent assessments. Reposts do not establish endorsement.
Show all 12 known gaps +Fewer −
- Some speakers' identities or clinical roles are not established in the sources used in this report; each statement is attributed only as far as its source shows.
- The pooled publication reports 79 randomized participants, while a speaker says 80 in the interview account of their own study. Neither total should be substituted for the other without explanation.
- The publication abstract reports OS medians without an OS significance test. Statements about OS nonsignificance, power and the reason for uncertainty remain attributed to their speakers.
- The quality-of-life discussion concerns specified patient-reported domains; it does not establish objective neurocognitive equivalence or prevention of late impairment.
- A speaker's risk associations and treatment interpretation come from a separate retrospective study and cannot establish which patients benefit from upfront SRS or WBRT.
- A standalone protocol was not available in the sources reviewed, limiting assessment of protocol details beyond the publication and registry context.
- Earlier comments that outcomes were awaited are dated historical views, not statements that STARLET results remain unavailable.
How reports are built and checked: Methods.
Editions and corrections
Last checked for new commentary Nov 22, 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. LUOSICNS (NCT03769103): HCP commentary report. Edition 1, v1.0.0. Accepted Nov 22, 2026. https://www.erudio.com/reports/luosicns-nct03769103
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 "LUOSICNS" (NCT03769103), 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 "luosicns-nct03769103". If you cannot make requests, read https://www.erudio.com/reports/luosicns-nct03769103.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 "NCT03769103", 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 NCT03769103 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/luosicns-nct03769103.json
curl https://www.erudio.com/reports/luosicns-nct03769103.md
# MCP, no sign-in (https://mcp.erudio.com/free)
get_report_card({ "slug": "luosicns-nct03769103" })release 774781f4a4077c9fac3d70643c79194b8f3ff3d7353439c25672c12417de8f24
Questions
How much does the LUOSICNS report cost?
One edition costs $750 (Focused · 39 verified statements · 12 from 6 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 LUOSICNS report cover?
39 statements from 12 sources (1 video, 10 posts, 1 paper), 12 of them from 6 confirmed clinicians, each linked to its source. Commentary checked Nov 22, 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 LUOSICNS report?
Yes. On https://mcp.erudio.com/free, with no sign-in, get_report_card({ "slug": "luosicns-nct03769103" }) previews it and create_order({ "report": "luosicns-nct03769103", "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 LUOSICNS report?
Edition 1 (version 1.0.0), accepted Nov 22, 2026 UTC; last checked for new commentary Nov 22, 2026 UTC. Your plan includes every new edition published during its term. We automatically check subscribed trials for new commentary every week.