Study of Combination Therapy With INCMGA00012 (Anti-PD-1), INCAGN02385 (Anti-LAG-3), and INCAGN02390 (Anti-TIM-3) in Participants With Select Advanced Malignancies: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Combination Therapy With INCMGA00012 (Anti-PD-1), INCAGN02385 (Anti-LAG-3), and INCAGN02390 (Anti-TIM-3) in Participants With Select Advanced Malignancies (NCT04370704), a non-randomized phase 1, phase 2 study. The primary outcome is Phase 1: Number of Participants With Any Treatment-emergent Adverse Event (TEAE).

2. Clinical Question

3. Trial Design

NCT04370704 is a Phase 1-2 study sponsored by Incyte Corporation. The registry lists the status as completed, enrollment of 61, a start date of 2020-07-27 and a primary completion date of 2025-08-25. Its title describes combinations of INCMGA00012 (anti-PD-1), INCAGN02385 (anti-LAG-3) and INCAGN02390 (anti-TIM-3) in participants with select advanced malignancies; melanoma is the listed condition.

The design is recorded as non-randomized, unmasked and parallel. Phase 1 Part 1 evaluates INCAGN02385 followed by INCAGN02390. Part 2 evaluates the triple combination after the doublet's safety is confirmed. The arm descriptions also list Phase 1 Parts 3 and 4 and Phase 2 Cohorts A and B. Phase 2 is described as assessing preliminary efficacy and proof of concept for the triple combination. The listed Phase 1 and Phase 2 arms include differing doses and schedules, and the Phase 1 descriptions do not all represent the same combination.

The study summary states that the dose-finding objective was to determine a Recommended Phase 2 Dose for the INCAGN02385 plus INCAGN02390 combination and for that combination with INCMGA00012, based on safety and tolerability. No randomized allocation or masking is described. Because this is a multi-part study without random assignment, differences in outcomes between groups cannot be interpreted as treatment effects in the way a randomized comparison might be. The registry record does not report a detailed allocation procedure, a statistical analysis plan, or a sample-size justification.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: This study was conducted at 5 study centers in the United States.

Only the first 6 of 7 groups are shown.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set: all participants enrolled in the study who received at least 1 dose of assigned study treatment

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Only the first 6 of 8 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Phase 1: Number of Participants With Any Treatment-emergent Adverse Event (TEAE), measured over up to 1148 days.

The primary endpoint is the number of Phase 1 participants with any treatment-emergent adverse event (TEAE), reported as a participant count. An adverse event is defined broadly as an untoward medical occurrence associated with drug use, whether or not it is considered drug-related. It can include an unfavorable sign, an abnormal laboratory finding, a symptom or a new or worsened disease that occurs in temporal association with study treatment.

A TEAE is an adverse event first reported, or a pre-existing event that worsens, after the first dose and through 90 days after the last dose. This timing definition does not by itself establish that treatment caused an event. The endpoint is assessed over a timeframe of up to 1148 days. The defined Full Analysis Set consists of all enrolled participants who received at least 1 dose of assigned study treatment.

Counting participants with any TEAE is a broad safety measure: it indicates how many people had at least one event during the specified observation window, rather than the number of events or their severity. Such a measure is relevant to a Phase 1 dose and tolerability assessment. However, a participant count alone does not describe event duration, recurrence, clinical seriousness, attribution to a study drug or differences in exposure time. The registry record does not report an endpoint estimate or a statistical comparison for this primary outcome.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a participant count represent?

The primary endpoint is a count of participants with any TEAE, rather than a continuous measurement such as a laboratory value or a time-to-event estimate. For this kind of outcome, each participant is classified according to whether at least one qualifying event occurred during the defined observation period. A participant with more than one event still contributes as a participant with an event to this endpoint. The count does not reveal how many total events occurred. The registry record does not report an estimate or inferential analysis for this endpoint.

How should the TEAE definition be read?

The registry defines a TEAE by when it is reported or worsens: after the first study-drug dose and until 90 days after the last dose. This is a temporal definition, not proof of causation. The definition of an adverse event explicitly includes events whether or not they are considered drug-related. Therefore, the endpoint is not equivalent to a count of events attributed to treatment. The observation timeframe is up to 1148 days, but the record does not give individual exposure or follow-up durations for interpreting participant counts.

What can be inferred from the design?

General statistical interpretation: random assignment helps make groups comparable on average, while masking can reduce some forms of bias in treatment assessment. This study is recorded as non-randomized and unmasked. Its groups also represent different study parts, doses, schedules and combinations. Accordingly, group-wise event counts are descriptive; the design does not support treating the groups as exchangeable control and treatment arms. The parallel model indicates concurrent groups in the design description, but does not make them randomized comparisons.

The study has both dose-finding and preliminary efficacy aims. The registry summary describes safety and tolerability as the basis for determining a Recommended Phase 2 Dose. It does not report a dose-selection algorithm, decision thresholds or other detailed dose-finding methods. Such details are not reported in the registry record and should not be inferred from the group descriptions alone.

Why do event counts need context?

General statistical interpretation: counts depend on the number of people observed and on how long they are observed. A count without exposure-adjusted rates or person-time does not distinguish a group with longer observation from one with shorter observation. The record lists the number at risk and affected for safety categories, but does not report exposure-adjusted rates. It also does not provide event-level timing or recurrence information in the registry record described by the registry record.

Over-dispersion is a general issue when event counts vary more than a simple statistical model expects. It matters especially when modeling repeated events, since some participants may experience many events while others experience none. The primary endpoint is a participant count with any event, not a repeated-event rate. The registry record does not report a model for repeated events or an analysis addressing over-dispersion.

What is not reported about statistical analysis?

The registry lists 12 outcome measures and zero analysis records. It does not report a primary endpoint estimate, confidence interval, p-value, adjustment method or analysis population for any posted treatment-effect analysis. The primary outcome definition does specify a Full Analysis Set: enrolled participants who received at least 1 dose of assigned study treatment. That definition does not establish how missing outcome information was handled or whether every participant in that set had complete follow-up.

General statistical interpretation: a confidence interval conveys uncertainty around an estimate, whereas a p-value is one measure of compatibility between data and a null hypothesis under a statistical model. Neither can be reconstructed from a participant count alone without appropriate denominators and assumptions. They are not reported for the primary endpoint in the registry record.

The sample-size assumptions describe planning illustrations using a two-sided significance level of 0.05, equal allocation, a normal approximation and an effect set as a stated fraction of an observed effect. The record labels these as planning illustrations, not the trial's own design. Such illustrations are not observed power and do not establish that the study was planned or sized by those assumptions. The registry record does not report its sample-size justification.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Phase 1, Part 1: Tuparstobart 350 mg Q2W + Verzist", "Phase 1, Part 2: Tuparstobart 350 mg Q2W + Verzist", "Phase 1, Part 3: Tuparstobart 450 mg Q3W; Tuparsto", "Phase 1, Part 3: Tuparstobart 750 mg Q3W; Tuparsto", "Phase 1, Part 3: Verzistobart 500 mg Q3W; Verzisto", "Phase 1, Part 3: Verzistobart 1000 mg Q3W; Verzist")
n      <- c(10, 11, 6, 6, 6, 6)
events <- c(8, 11, 6, 5, 6, 5)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Phase 1, Part 1: Tuparstobart 350 mg Q2W + Verzist  10  8  80.0  44.4  97.5  49.0  94.3  48.2  94.0
ARM  Phase 1, Part 2: Tuparstobart 350 mg Q2W + Verzist  11  11  100.0  71.5  100.0  74.1  100.0  73.5  99.8
ARM  Phase 1, Part 3: Tuparstobart 450 mg Q3W; Tuparsto  6  6  100.0  54.1  100.0  61.0  100.0  59.0  99.6
ARM  Phase 1, Part 3: Tuparstobart 750 mg Q3W; Tuparsto  6  5  83.3  35.9  99.6  43.6  97.0  42.1  96.3
ARM  Phase 1, Part 3: Verzistobart 500 mg Q3W; Verzisto  6  6  100.0  54.1  100.0  61.0  100.0  59.0  99.6
ARM  Phase 1, Part 3: Verzistobart 1000 mg Q3W; Verzist  6  5  83.3  35.9  99.6  43.6  97.0  42.1  96.3

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 12 outcome measures, including the Phase 1 TEAE endpoint and secondary outcomes covering response, duration of response, disease control, progression-free survival and adverse events. It reports zero analysis records. No results for the listed outcomes, no analysis hierarchy and no multiplicity adjustment are reported in the registry record. Because multiple outcomes are listed, a reader cannot determine from this record whether any planned testing strategy controlled the chance of false-positive findings across outcomes.

The primary outcome population is defined as the Full Analysis Set: enrolled participants who received at least 1 dose of assigned study treatment. The overall enrollment is 61, but enrollment alone does not establish the number with a dose or with evaluable outcome data. The adverse-event summary lists 61 at risk in its total row; that does not supply a missing-data method or confirm the analysis population used for the primary endpoint.

The registry record does not report how missing adverse-event information, incomplete follow-up, withdrawal or unavailable efficacy assessments were handled. It also does not report imputation, censoring rules, sensitivity analyses or an estimand for the efficacy outcomes. No assumptions about these procedures can be made from the endpoint definitions. These omissions limit assessment of how the listed counts relate to all enrolled participants and how any unreported efficacy results would have been analyzed.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: abdominal pain (16.7%), anaemia (16.7%), cancer pain (16.7%), cellulitis (16.7%), cerebrovascular accident (16.7%).

The safety summary's total row lists 17 participants affected by serious adverse events, 55 affected by other adverse events and 29 deaths; each event-category denominator is listed as 61 at risk. These are participant counts, not event rates or treatment-attributable risks. The group entries vary in size and treatment, and the study was non-randomized, so group-to-group differences should not be read as comparative treatment effects.

The serious-event terms listed most often are abdominal pain, anaemia, cancer pain, cellulitis, cerebrovascular accident and death, each reported as 16.7%. The registry record does not specify the denominator or counting convention for these term percentages. They should not be interpreted as percentages of all 61 participants without further information. The record also does not establish whether participants could appear under multiple terms, or whether the listed deaths are included within serious events or other event categories.

Seriousness and causality are distinct: a serious adverse event is not necessarily caused by a study drug. The reported counts do not state treatment attribution, and the death count does not, on its own, establish a treatment-related death. These figures are useful as descriptive safety reporting, but do not provide a causal comparison.

13. What the Result Does, and Does Not, Mean

The registry record documents a completed Phase 1-2 study with a safety and tolerability objective for combinations of anti-LAG-3 and anti-TIM-3 agents, with or without an anti-PD-1 agent. It defines a Phase 1 primary endpoint based on participants with any TEAE and lists safety counts by study group. Those details describe the study question and the kinds of events recorded; they do not establish a treatment effect.

The total safety row lists 17 participants with serious adverse events, 55 with other adverse events and 29 deaths, with 61 at risk in each adverse-event category. Because the categories may overlap and treatment attribution is not specified, these values do not explain the cause, timing or clinical context of every event. The listed term percentages also lack a stated denominator in the registry record.

The record does not report results for the primary TEAE endpoint or for the Phase 2 efficacy outcomes, and it includes zero analysis records. Thus, no estimate of response, disease control, duration of response or progression-free survival can be drawn from the information reported. Nor can the safety counts establish whether one regimen is safer than another. The study's non-randomized design and differing groups further limit causal comparison.

General statistical interpretation: a result is more informative when an estimate is accompanied by a measure of uncertainty, a clear analysis population and a description of how missing observations were handled. Those details are not reported for the treatment-effect analyses in the registry record. The counts should therefore be read as descriptive registry information, not as a complete analysis of efficacy or comparative safety.

14. Why This Trial Matters Statistically

This trial illustrates the difference between a study objective and a reported result. The registry describes dose and safety aims in Phase 1 and preliminary efficacy aims in Phase 2, but lists zero analysis records. A clear outcome definition is useful, yet the definition alone cannot answer how many participants experienced the endpoint or how uncertain an estimate might be.

Its multi-part, non-randomized design also illustrates why treatment-group counts require context. Groups differ by combination, dose, schedule and phase. Comparing their raw counts cannot isolate the effect of a drug or combination, particularly when group sizes and observation may differ. This is a design issue, not a problem that can be resolved by interpreting the counts more aggressively.

The safety summary helps identify the scope of reported event categories and the presence of serious events and deaths in the study population. At the same time, terms such as seriousness, treatment attribution and event timing answer different questions. The registry's broad TEAE definition does not imply that every event was caused by study treatment, and aggregate counts cannot describe individual event histories.

Statistically, the record underscores the importance of reporting estimates, uncertainty, analysis populations and missing-data handling alongside outcome definitions. Without those elements, readers can describe what the registry lists, but cannot assess precision, test hypotheses or judge comparative effects. This distinction is central when interpreting early-phase studies whose objectives include safety evaluation and dose selection.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The record describes a non-randomized, unmasked study with multiple parts and treatment groups that vary in combination, dose and schedule. There is no like-for-like randomized comparator. Consequently, the event counts do not support a causal comparison between regimens, and observed differences could reflect group composition or other factors rather than treatment.

The primary endpoint is defined, but the registry record does not report its result, uncertainty interval or statistical analysis. It also does not report the listed secondary efficacy results, despite describing Phase 2 objectives. With zero analysis records, the registry entry cannot establish how any endpoint estimate was obtained or how precise it was.

Although the safety summary reports counts by category and group, it does not clarify category overlap, event attribution, individual exposure time or the denominator behind the listed serious-event term percentages. It also does not explain the relationship between the death count and the event categories. The summaries are therefore insufficient for detailed causal or rate-based interpretation.

The registry record does not report a sample-size justification, a detailed statistical plan, missing-data procedures, multiplicity handling or sensitivity analyses. Enrollment of 61 does not by itself indicate how many participants contributed evaluable data to each outcome. These reporting limitations are specific to what can be interpreted from this registry entry; they do not establish what methods may have been used elsewhere.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study of Combination Therapy With INCMGA00012 (Anti-PD-1), INCAGN02385 (Anti-LAG-3), and INCAGN02390 (Anti-TIM-3) in Participants With Select Advanced Malignancies — NCT04370704.
• Registry record last updated 2026-08-17; status last verified 2026-08.
• Results first posted 2026-08-17.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

NCT04370704 is a completed, non-randomized Phase 1-2 study sponsored by Incyte Corporation, with 61 participants enrolled. The record lists melanoma and describes combinations of INCAGN02385, INCAGN02390 and INCMGA00012. Phase 1 focused on safety and tolerability for dose selection; Phase 2 was intended to assess preliminary efficacy and proof of concept.

The primary endpoint is the number of Phase 1 participants with any TEAE, defined over the period after first dose through 90 days after last dose. The record lists aggregate safety counts, including 17 participants with serious adverse events, 55 with other adverse events and 29 deaths in the total row. It reports zero analysis records, so no primary endpoint estimate or Phase 2 efficacy results are available in the registry record.