ClinicalTrials.gg
RecruitingNCT07939139OnkoBotUpdated Nov 16, 2026

Shadow-Mode Evaluation of an AI Assistant for Multidisciplinary Tumor Boards

An observational study in Hematologic Neoplasms, Sarcoma and Bone Neoplasms, sponsored by Technical University of Munich. Recruiting at 2 sites in Germany. Per ClinicalTrials.gov, last updated 2026-11-16.

Sponsored by Technical University of Munich · Observational

Updated Nov 16, 2026Newly registeredGo to Updates ↓

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
450
Sex
All
01

Where this study stands

Counted across the records on this site · 2026-11-16

Among 65 studies in Hematologic Neoplasms with a site in Germany — 20 open to participants now, 28 under way, 3 of them phase 3. Hematologic Neoplasms · Germany.

Planned enrollment
8th of 15
450 · median 450
Started
2026
with 3 others
Observational
15 of 65
9 open now
Primary completion
2027-01
later than 9 of 27 live
Registered
65th of 65
by date
Lead sponsor
3 of 65
Technical University of Munich

Among the 65 studies in Hematologic Neoplasms with a site in Germany, this one is the 8th largest by planned enrollment of the 15 observational ones that give a count, is one of 4 that started in 2026, is one of 15 observational ones, reaches primary completion later than 9 of the 27 other live ones, and was the 65th registered.

Hematologic Neoplasms

1,445 studies on the registry are indexed under Hematologic Neoplasms; 420 are open to participants now.

Browse Hematologic Neoplasms studies →

Open to participants now

20 of the 65 studies in Hematologic Neoplasms with a site in Germany are open now. Recruiting first, the newest first:

14 more — sign in →

All 20 open studies →

A study can be open while its sites in Germany have not opened yet or have stopped. Only those recruiting at a site in Germany →

Who these studies take

Of the 313 Hematologic Neoplasms studies recruiting now, 208 (66%) set no upper age limit and 78 (25%) stop at 75 or younger; 80 take children under 18; 34 take healthy volunteers.

This study: all sexes · no healthy volunteers.

The full table on the hub →

This tab as a report to print or save as PDF → With an account.

Was this useful?
Get alerts for this landscapeDownload CSVNarrow it in search →With an account: a weekly mail of what changed among 65 studies in Hematologic Neoplasms with a site in Germany, or all of them as a file.
02

Study summary

This study tests whether an artificial intelligence (AI) system that drafts tumor board recommendations performs as well on new cases as it did on archived cases. The system runs in shadow mode at three multidisciplinary tumor boards of TUM University Hospital rechts der Isar. For each case it drafts a recommendation before the board meets. The board does not see the draft, and the draft has no influence on patient care. After the meeting, each draft is compared with the board decision. The agreement rate is then compared with the rate measured on archived decisions of the same boards.

Read the detailed description

The system is a locally operated large language model (LLM) pipeline with retrieval-augmented generation. Its input is the case as presented to the board, with diagnosis, course, question and all patient documents dated before the board date. It retrieves guideline recommendations (Onkopedia and AWMF S3 guidelines in the version in force on the board date), laboratory values, precedent cases from the board archive and PubMed abstracts published before the board date. It then drafts a recommendation with justification. Each statement of the draft is linked to a verbatim quote from its source. All models run on local GPU servers of the hospital with no data retention beyond the immediate analysis, and no patient data are sent to external providers.

The study includes the hematology board, the orthopedics and sarcoma board and the head and neck board. For each case registered for a session, the system drafts a recommendation after the pre-board documents are pulled and before the session starts. Board members do not see the drafts. The decision pipeline (generator Gemma-4-31B at temperature 0) is frozen and versioned for the study period. The study uses routine clinical data only. Patients are not contacted, and no study-specific procedures are performed.

The draft is compared with the consensus decision in the board report. An LLM judge (GLM-5.3-Flash, majority of three votes) assigns both texts to one of seven decision categories: systemic therapy, surgery, radiotherapy, watch and wait, further diagnostics, best supportive care and referral to the molecular tumor board. It also scores agreement in substance from 0 to 3 and records the direction of any disagreement. The judge was validated against clinician ratings on a sealed test set. The same prompt version is used to score the prospective cases and the retrospective reference sample, separately from any output that clinicians see.

The retrospective reference is the evaluation sample of archived decisions of the same three boards (about 2,000 cases, one per patient, drawn with a fixed seed and stratified by time). Patients who also appear in the prospective cohort are removed from the reference. The primary analysis tests non-inferiority of the prospective category match rate against the retrospective rate, pooled over the three boards, with a margin of 7.5 percentage points and a one-sided alpha of 0.025. The variance is cluster-robust for board sessions. A case without a draft counts as not concordant. Per-board results are reported descriptively with 95% confidence intervals. An exploratory component evaluates a trial-matching engine that proposes recruiting clinical trials per case.

In a subset of 30 to 50 cases per board, physicians rate the system draft against the board decision. This subset tests whether the agreement between judge and clinicians, measured retrospectively, also holds prospectively.

03

Conditions studied

  • Hematologic Neoplasms
  • Sarcoma
  • Bone Neoplasms
  • Head and Neck Neoplasms

Keywords

  • tumor board
  • multidisciplinary team meeting
  • clinical decision support
  • artificial intelligence
  • large language model
  • retrieval-augmented generation
  • shadow mode
  • prospective validation
04

Who can participate

Ages eligible
Child (0–17), Adult (18–64), Older adult (65+)
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Non-probability sample

Study population

All cases registered for the hematology, orthopedics and sarcoma, and head and neck tumor boards of TUM University Hospital rechts der Isar during the study period. One case is one patient presentation on one board date.

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

  • Case registered for a session of a participating tumor board (hematology, orthopedics and sarcoma, head and neck) of TUM University Hospital rechts der Isar during the study period
  • Board registration and pre-board patient documents available before the session starts

Exclusion criteria

Exclusion Criteria:

  • Case not discussed at the session, defined as no board report with a consensus decision for that date (deferred or withdrawn registrations)
  • Session without a shadow run of the system

Excluded cases are counted and reported by reason.

05

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
450 participants (estimated)
Patient registry
No

Groups and cohorts

  • Hematology board

    Consecutive cases presented at the hematology tumor board of TUM University Hospital rechts der Isar.

    Other: OnkoBot (shadow mode)

  • Orthopedics and sarcoma board

    Consecutive cases presented at the orthopedics and sarcoma tumor board of TUM University Hospital rechts der Isar.

    Other: OnkoBot (shadow mode)

  • Head and neck board

    Consecutive cases presented at the head and neck tumor board of TUM University Hospital rechts der Isar.

    Other: OnkoBot (shadow mode)

Interventions

  • OtherOnkoBot (shadow mode)

    A locally operated, source-grounded large language model system drafts a tumor board recommendation with justification and verified citations for each case before the board meeting. The draft is not shown to the board and does not influence patient care.

06

What researchers measure

Primary outcomes

  1. Proportion of Cases With Category Match Between System Draft and Board Decision

    Proportion of discussed cases in which the system draft and the board consensus decision fall into the same of seven decision categories (systemic therapy, surgery, radiotherapy, watch and wait, further diagnostics, best supportive care, referral to the molecular tumor board). Overlap counts where either side carries a second category. Assessed by a pre-specified LLM judge (GLM-5.3-Flash, prompt V3, majority of three votes), pooled over the three boards. Tested for non-inferiority against the rate of the same system and judge on the retrospective reference sample of the same boards, margin 7.5 percentage points, one-sided alpha 0.025.

    Time frame: Each case is assessed once, after the board report of its session is available; analysis after accrual is complete (anticipated January 2027)

Secondary outcomes

  1. Proportion of Cases Rated Concordant or Partially Concordant

    Category match with a substance score of at least 1 of 3 (concordant requires at least 2 of 3 on a primary-category match, 3 of 3 where only second categories overlap). Non-inferiority versus retrospective reference, margin 7.5 percentage points, tested after the primary outcome (hierarchical testing).

    Time frame: After the board report of each session is available; analysis after accrual is complete (anticipated January 2027)

  2. Proportion of Cases Rated Concordant, Partially Concordant and Not Concordant

    Proportion of cases rated concordant, partially concordant and not concordant by the LLM judge.

    Time frame: After the board report of each session is available; analysis after accrual is complete (anticipated January 2027)

  3. Proportion of Cases With Category Match per Board

    Category match and concordant or partially concordant per board, with 95% confidence intervals, descriptive.

    Time frame: After the board report of each session is available; analysis after accrual is complete (anticipated January 2027)

  4. Proportion of Discordant Cases by Direction of Disagreement

    Among cases without category match, proportion in which the draft is more conservative, more aggressive or a different modality than the board decision.

    Time frame: After the board report of each session is available; analysis after accrual is complete (anticipated January 2027)

  5. Proportion of Cases With Category Match as Rated by Clinicians

    In 30 to 50 cases per board, agreement between draft and board decision as rated by physicians who did not attend the session, and agreement between judge and clinicians on category match (percentage agreement, Cohen's kappa).

    Time frame: Within 3 months after the board session

  6. Proportion of Citations Verified Word for Word Against Their Source

    Proportion of citations per case that verify word for word against their source, and proportion of cases in which every citation verifies.

    Time frame: At draft generation, before the board session

  7. Proportion of Cases With a Draft Completed Before the Board Session

    Proportion of cases with a draft completed before the session starts, and generation time per case in minutes.

    Time frame: At draft generation, before the board session

Other outcomes

  1. Number of Clinical Trials Shortlisted per Case by the Trial-Matching Engine

    Number of trials shortlisted per case, proportion recruiting on the board date, rule-based error rate (wrong disease, line of therapy, setting or status) and clinician screening verdicts where given.

    Time frame: At draft generation, before the board session

07

Study locations

1 of 2 sites recruiting
  • TUM University Hospital rechts der Isar
    Munich, Bavaria 81675, Germany
    Not yet recruiting
  • TUM Klinikum rechts der Isar
    Munich, Bavaria, Germany
    Recruiting
08

References and documents

Individual participant data

Plan to share: No — Individual participant data are routine clinical records that may not leave the hospital under the ethics approval and data protection concept. Aggregate results and the analysis code will be published.

No publications or documents are linked to this record.

09

Timeline

1 registry update since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reachedSimilar studies: half by the dot; the band is the middle halfHalf of similar studies reached it by the dot; the band is the middle half, from a quarter to three quarters

Start is estimated for Nov 2026; primary completion for Jan 2027, 2 months later.

Of 164 non-industry observational studies under Hematologic Neoplasms, half reached primary completion within 74 months of starting (the median), counting those still running; a quarter within 35 and three quarters within 322. This study's planned 2 months is below that.

Counting every sponsor, half of 186 studies reached it within 74 months; a quarter within 34 and three quarters within 322.

How these figures are worked out, and which studies are left out of them.

Registered
Nov 9, 2026
First posted
Nov 16, 2026
StartEst.
Nov 9, 2026
Primary completionEst.
Jan 31, 2027
CompletionEst.
Apr 30, 2027
Last update
Nov 16, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
Registered
First appeared on the registry. No changes since
Nov 16, 2026
Show all 1 update
  1. Nov 16, 2026
    First appeared on the registry

From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗

10

Registry details

Key details

Study ID
NCT07939139
Responsible party
Lisa Adams (Head, Institute for Diagnostic and Interventional Radiology, Technical University of Munich) — Principal investigator
First posted
Nov 16, 2026
Start date
Nov 9, 2026 (estimated)
Primary completion
Jan 31, 2027 (estimated)
Completion
Apr 30, 2027 (estimated)
Last update
Nov 16, 2026

Study contacts

Lisa Adams, MD
Contact
lisa.adams@tum.de
+49 89 4150 1084
Keno Bressem, MD
Contact
keno.bressem@tum.de
Lisa Adams, MD
principal investigator · Technical University of Munich
Krischan Braitsch, MD
principal investigator · Technical University of Munich

Oversight

Data monitoring committee
No
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Interested in this study?

Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.

Contact study team

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion