Citations

e19545 Background: Cytogenetic abnormalities (CA) at diagnosis are important prognostic factors in multiple myeloma (MM), but there is limited information on how these abnormalities evolve at first relapse and their significance. Methods: This retrospective study included patients aged ≥18 years, with a confirmed diagnosis of MM who experienced at least one disease relapse and had fluorescence in situ hybridization analysis within six months of both diagnosis and relapse. Data on CA and clinical outcomes were collected. High-risk (HR) secondary CA were defined as the presence of deletion of chromosome 17p (del17p) or gain or amplification of chromosome 1q. The primary objective was to evaluate changes in HR secondary CA at first relapse, while the secondary objective was to assess the impact of the cytogenetic changes on overall survival (OS) from diagnosis. Based on the presence or absence of HR secondary CA, patients who were tested for HR secondary CA at both time points were classified into four groups: 1) persistent absence of HR secondary CA, 2) emergence of HR secondary CA at relapse, 3) persistent presence of HR secondary CA, and 4) loss of HR secondary CA at relapse. Results: A total of 233 patients diagnosed between 2004 and 2023 were included. HR secondary CA were tested in 98.7% (n= 230) of patients at diagnosis, with 24.8% (n=57) testing positive. At first relapse, testing for HR secondary CA was performed in 97.4% (n=227) of patients, of whom 23.8% (n=54) tested positive. Del17p was evaluated in 98.3% (n=229) of patients at baseline and 95.7% (n=223) at relapse, with positivity increasing from 10.9% (n=25) to 15.3% (n=34). Gain or amplification of chromosome 1q was evaluated in 49.4% (n=115) at baseline and 25.5% (n=60) at relapse, with positivity rate rising from 28.7% (n=33) to 38.3% (n=23). There were no differences in overall response rate or very-good-partial-response-or-better rates to the initial therapy at diagnosis between the groups. (Table) Emergence/persistence of HR CA were associated with lower OS from diagnosis. Conclusions: Emergence of HR secondary CA at first relapse in MM has prognostic significance. These findings highlight the importance of serial cytogenetic testing for risk stratification. Response rate to initial line of therapy and overall survival from diagnosis among patients tested for HR secondary CA both at diagnosis and first relapse (n=224). Outcome Persistent absence of HR secondary CA(n=142) Emergence of HR secondary CA at relapse (n=25) Persistent presence of HR secondary CA (n=27) Loss of HR secondary CA at relapse(n=30) p-value Overall response rate a 75% (106) 76% (19) 63% (17) 67% (20) 0.5 b Very-good-partial response or better response rate 43% (61) 36% (9) 44% (12) 40% (12) >0.9 b Median (95% CI) OS from diagnosis in years 11.3 (9.7-13.4) 7.5 (5.1-12.1) 6.1 (4.2-9.4) 10.1 (6.5-14.1) <0.0001 c a Partial response or better; b Chi-square test; c Log-rank test.

8501 Background: TROPION-Lung02 (NCT04526691) evaluated the TROP2-directed antibody-drug conjugate (ADC) Dato-DXd plus pembro combination with or without Pt-CT in aNSCLC. Here we report primary analyses of pts receiving combination therapy in the 1L setting. Methods: Pts across 6 cohorts were dosed with Dato-DXd (4 or 6 mg/kg) plus pembro 200 mg alone (doublet) or with pembro plus Pt-CT (triplet; cisplatin 75 mg/m 2 or carboplatin AUC 5) Q3W. PD-L1 expression (tumor proportion score) was assessed locally by immunohistochemistry (22C3 assay). Primary objectives were safety and tolerability; efficacy was a secondary objective. Results: As of Apr 29, 2024, 96 pts received either the doublet (n=42) or triplet (n=54) combination as 1L therapy; 29% and 15% of pts were ongoing, respectively. Median ages were 65 (doublet) and 64 years (triplet). Median treatment durations were 9.7 and 5.8 months, respectively. Stomatitis (doublet, 57%; triplet, 33%) and nausea (doublet, 42%; triplet, 48%), primarily Gr 1–2, were the most common adverse events (AEs) across both regimens. Treatment related serious AEs occurred in 5 (12%) and 12 (22%) pts in each cohort and no deaths related to study drug were seen. Efficacy outcomes, including by histology, are summarized in the Table. Biomarker analyses, including efficacy by PD-L1 status, will be presented. Conclusions: In this largest data set to date evaluating an ADC combined with an anti-PD-1/L1 agent in the 1L setting, the combination of Dato-DXd plus pembro treatment both with and without Pt-CT elicited durable antitumor activity in pts with aNSCLC. Tolerability of the combinations was as expected, based on known profiles of the individual agents. Clinical trial information: NCT04526691 . All 1L (n=96) 1L, Nonsquamous (n=75) 1L, Squamous (n=21) Response, n (%) Doublet (n=42) Triplet (n=54) Doublet (n=33) Triplet (n=42) Doublet (n=9) Triplet (n=12) Confirmed objective response rate 23 (55) 30 (56) 17 (52) 24 (57) 6 (67) 6 (50) Complete response 1 (2) 2 (4) 1 (3) 2 (5) 0 0 Partial response 22 (52) 28 (52) 16 (49) 22 (52) 6 (67) 6 (50) Stable disease 14 (33) 18 (33) 12 (36) 14 (33) 2 (22) 4 (33) Progressive disease 3 (7) 2 (4) 3 (9) 1 (2) 0 1 (8) Disease control rate a 37 (88) 48 (89) 29 (88) 38 (91) 8 (89) 10 (83) Median duration of response, mo (95% CI) 20.1 (9.7–NE) 13.7 (5.7–NE) 24.9 (9.7–NE) 18.0 (8.0–NE) 12.0 (5.5–NE) 5.5 (4.1–NE) Median PFS, mo (95% CI) 11.2 b (8.2–21.3) 6.8 c (5.5–11.1) 11.2 (6.1–21.3) 10.8 (5.5–17.3) 10.2 (0.4–NE) 6.7 (1.0–8.2) a Proportion of pts with confirmed CR + PR + SD at 12 wks. b.c Median (95% CI) PFS follow-up, mo: b 17.3 (11.3−26.8); c 23.5 (17.3−27.9). mo, months; NE, not evaluable.

e14626 Background: Despite advancements in neoadjuvant therapy and surgical techniques, patients with pancreatic ductal adenocarcinoma (PDAC) often experience high recurrence rates after total neoadjuvant therapy (TNT) and resection. Existing tumor response scoring systems, such as the College of American Pathologists (CAP) guidelines, fail to stratify recurrence risk effectively, emphasizing the need for novel, objective approaches. Methods: This study evaluated spatial characteristics of residual cancer and stroma in a multi-site cohort of 203 patients with resected PDAC following TNT, not having achieved a major pathologic response (CAP 2 or 3). Whole slide images (WSI) of hematoxylin and eosin-stained sections were digitized and analyzed using artificial intelligence to perform tissue segmentation. Metrics quantifying spatial morphology and configuration, inspired by principles of landscape ecology, were computed to explore spatial features of the tumor microenvironment (TME). Statistical models (recursive partitioning and regression tree [RPRT] model and Cox model with backwards eliminations) incorporating these features were developed to stratify recurrence risk. Results: Five metrics were used for risk classification model build. Three models successfully classified patients into high- and low-risk groups based on spatial metrics. Models demonstrated moderate discriminatory power (C-statistics: 0.560–0.566) and showed that increased tumor fragmentation, like stromal patch density and cancer patch shape index, were strongly associated with improved outcomes. Conclusions: Integrating spatial metrics of cancer-stroma configuration enhances risk stratification beyond conventional scoring systems. Given increased tumor fragmentation is associated with improved outcomes, these data indirectly suggest ecological mechanisms of treatment resistance. This approach offers a pathway toward personalized post-operative management strategies to improve outcomes in PDAC. Risk classification models. Model Description Event/n Median DFS (95% CI) HR(95% CI) p-value C-statistics 1(RPRT) High risk: log standard deviation of the stroma shape index > 0.651 87 / 101 8.22(5.72 – 10.1) 1.64(1.20 – 2.25) 0.002 0.562 Low risk: log standard deviation of the stroma shape index ≤ 0.651 71 / 102 11.90(9.24 – 25.1) Ref 2(RPRT) High risk: log standard deviation of the stroma shape index > 0.651 & mean cancer shape index ≤ 1.775 58 / 63 7.23(5.19 – 9.63) 1.82(1.31 – 2.52) 0.0003 0.560 Low risk: (log standard deviation of the stroma shape index > 0.651 & mean cancer shape index > 1.775) or log standard deviation of the stroma shape index ≤ 0.651 100 / 140 11.57(9.24 – 17.92) Ref 3(Backwards elimination) High risk: PI * > median 86 / 101 8.02(6.08 – 9.86) 1.73(1.26 – 2.37) 0.0007 0.566 Low risk:PI * ≤ median 72 / 102 15.72(9.97 – 25.05) Ref *PI: (0.2701 * log mean stroma area) + (0.3905 * log edge density).

1652 Background: Tarlatamab is a bispecific T-cell engager targeting DLL3 that has shown promise as a therapy in small cell lung cancer. Administering tarlatamab requires careful consideration of immune-related adverse events (AE), including cytokine release syndrome (CRS) and immune effector cell-associated neurotoxicity syndrome (ICANS). Prescribing information recommends patients to be monitored for 22-24 hours in an appropriate healthcare setting for cycle 1 (C1), days 1 and 8. At Mayo Clinic in Rochester MN (MCR), tarlatamab is initially administered in a hospital-based outpatient (HBO) setting utilizing an innovative remote patient monitoring system (RPM). In this study, we describe our RPM process and patient outcomes thus far. Methods: We retrospectively reviewed records of patients treated with tarlatamab from August through December 2024. All patients received tarlatamab in the HBO setting and were enrolled into RPM for C1, days 1–10. Patients attended daily HBO visits on days 1–3 and 8–10 of C1 and were required to stay within 30 minutes of the hospital with a 24-hour caregiver for 48 hours following infusion days in C1-2. Data on patient characteristics, frequency of RPM alerts, escalations, rate of CRS & ICANS, and need for hospitalizations were reported using descriptive metrics. Results: As part of RPM, patients are provided with a kit containing preconnected Bluetooth-enabled devices to measure vital signs (VS), including blood pressure (BP), heart rate (HR), temperature (T), and pulse oximetry (SpO2). The kit also includes a cellular-enabled tablet for electronic ICANS questionnaires, which upload directly into our electronic medical record system. Patients are required to log VS four times daily, monitored in real-time by a centralized virtual RPM nursing (RN) team. Embedded decision trees trigger alerts, prompting the RN team to contact patients and follow care pathways for escalations as needed. Among the 16 patients treated, the median age was 68 years, and the median ECOG PS was 1. During the 10-day RPM period, a total of 2,233 VS entries were recorded. Of these, 88% (14/16) of patients had alerts triggered, with a median of 2 alerts per patient. Alerts were mostly for out-of-range systolic BP (56%), HR (56%), and T (25%), with none for SpO2. The RN team escalated alerts in 50% (8/16) of the patients. Overall, 38% (6/16) of patients were managed entirely in the HBO setting. Among the 63% hospitalized, 56% had CRS limited to grade (G) 2, and 31% had ICANS limited to G3. Two patients were hospitalized for other indications. The mean length of stay was 2.6 days, with no ICU admissions. Conclusions: Our experience shows that frequent monitoring required with tarlatamab can be safely and effectively executed in an outpatient setting with the utilization of an RPM system. It can potentially minimize the burden of hospitalizations for patients and the healthcare system.

6061 Background: PDS0101 is a T cell stimulating immunotherapy (therapeutic vaccine) targeting HPV16. The combination of PDS0101 + pembrolizumab (5 cycles) has shown durable clinical responses in HPV-positive recurrent/metastatic HNSCC. MC200710 is a window of opportunity study in patients with HPV-associated oropharyngeal squamous cell carcinoma (HPV+ OPSCC). This prospective phase II trial utilized 2 cycles of neoadjuvant PDS0101 aloneor in combination with pembrolizumab prior to surgical resection or chemoradiotherapy (CRT). Herein, we report the initial results, including primary endpoint of ctDNA response. Methods: Between June 2022 and September 2024, 20 patients (10 per Arm) with locally advanced HPV+ OPSCC were enrolled in a sequential alternating design. Arm A received 2 cycles of PDS0101 and Arm B received 2 cycles of PDS0101 and pembrolizumab with all patients undergoing subsequent surgery or CRT. Assessments were done at baseline, post cycle 1, and post cycle 2 (prior to surgery or CRT). The coprimary endpoint of ctDNA response was defined as a ≥50% decline in ctDNA post cycle 2 compared to baseline as quantified using NavDx (TTMV fragments/mL). Radiologic objective response rate (ORR) was assessed as per RECIST 1.1. Toxicity through the neoadjuvant period was assessed using CTCAE criteria and recurrence rates following surgery or CRT are reported. Results: Patients were similar between arms: male 90%, median age 61 years, cT1/T2 70%, cN1 65%, and no smoking history 65%. All patients completed both cycles of therapy with 13 (65%) undergoing primary operative management and 7 CRT (35%). The most common toxicity was injection site reaction 85% grade 1, 15% grade 2, 0% grade 3, consistent with prior studies. One patient experienced grade 2 pneumonitis during the neoadjuvant window (Arm B). There was one grade 3 toxicity (5%) possibly attributable to study intervention with one patient experiencing transient hepatitis requiring hospitalization (Arm A). Zero of 10 patients in Arm A had a ≥50% decline in ctDNA from baseline while 5 of 10 patients (50%) met this primary endpoint in ARM B (p=0.03). After Cycle 2, based on RECIST 1.1, no Arm A patients had a partial response (PR), with 7 having stable disease (SD); Arm B had 2 patients with PR and 8 with SD. With median follow up of 6 months, 2 patients in Arm A recurred and 0 patients in Arm B. Conclusions: The combination of PDS0101 and pembrolizumab met the trial’s primary endpoint of ctDNA response and shows promise for further evaluation. ctDNA can be used to assess early response and future studies could use ctDNA to adapt neoadjuvant therapy. Based on these findings, a neoadjuvant dose optimization study in HPV16+ oropharyngeal carcinoma is warranted and evaluation of PDS0101 and pembrolizumab in comparison to pembrolizumab alone. Clinical trial information: NCT05232851 .

e13637 Background: Large language models (LLMs) like GPT-4 (OpenAI) and Claude Opus (Anthropic) showed high accuracy in medical multiple-choice exams, but data on their oncology-specific clinical reasoning and performance is limited. This study evaluates their accuracy and clinical reasoning on breast oncology multiple-choice questions (MCQs) from the American Society of Clinical Oncology (ASCO) question bank. Methods: Using OpenAI and Anthropic Application Programming Interface (APIs), questions were tested without additional prompts under consistent settings (GPT-4 and Claude Opus; Temperature = 0, Tokens = Max). Each question was tested three times to assess precision. Then, Chain-of-thought (COT) prompting was applied to promote LLMs stepwise reasoning to increase their accuracy. Accuracy before and after COT prompting was compared. Incorrect responses were reviewed by board-certified medical oncologists speclized in breast cancer, who scored reasoning clarity, bias, and clinical relevance. Qualitative feedback was descriptively analyzed. Results: A total of 273 breast oncology MCQs were evaluated across the two LLMs. GPT-4 achieved an initial accuracy of 81.3% (222/273; 95% CI: 76.3%-85.5%), compared to Claude Opus, which achieved an accuracy of 79.5% (217/273; 95% CI: 74.3%-83.9%). The Chi-squared test for difference between the models before chain-of-thought (COT) prompting yielded a p-value of 0.59, indicating no statistically significant difference in accuracy between GPT-4 and Claude Opus prior to COT prompting. After COT prompting, the performance of the two models diverged significantly. GPT-4 saw a net decline in accuracy, decreasing by a net of 1 correct answer, resulting in an overall accuracy of 80.95% (221/273). In contrast, Claude Opus experienced a notable improvement, with a net of 19 additional correct answers, leading to an accuracy of 86.4% (236/273). A statistical analysis using a Chi-squared test revealed a difference in accuracy between the two models of 5.5% (p = 0.08), demonstrating that the improvement in accuracy for Claude Opus after COT prompting was borderline statistically significant compared to GPT-4. Thematic analysis of oncologists' feedback revealed that the most common reasons for incorrect answers were reliance on outdated guidelines, misinterpretation of clinical trial data, and failure to consider multidisciplinary or patient-specific approaches in clinical decision-making. Conclusions: Although AI models can achieve high scores on multiple-choice exams, they still require human supervision. These models rely on potentially outdated training data and lack the ability to individualize patient care or apply data from clinical trials. especially in unique or unconventional/non textbook scenarios.

e13622 Background: Chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized treatment of hematologic malignancies; however, severe toxicities like cytokine release syndrome (CRS) remain a limitation to broader utilization. Using a large dataset of patients treated with CAR-T, we developed a machine learning (ML) model leveraging multi-model patient characteristics to predict the risk of CRS onset with clinically meaningful lead times. Methods: A prospectively maintained dataset of CAR-T patients treated at Mayo Clinic was used. Baseline disease/patients characteristics, labs, ECG, echocardiogram, and vital signs (including data from remote patient monitoring program) were collected. A 24-hour rolling window was used to generate daily averages, maximum, minimum, and deltas for each parameter. ECG and echocardiogram data were forward-imputed; vital signs and labs were not imputed. Each day-post-infusion served as a potential event (CRS onset vs. no CRS). A gradient boosting classifier was trained and tested on a subset of patients (n = 351) using 1,000 bootstrap iterations, evaluating 24-, 48-, and 72-hour lead times. Shapley-based feature importance guided simplification to an 11-feature model, externally validated on an independent cohort (n = 51). Models’ performance assessed using the area under the receiver operating characteristic curve (AUC). Results: A total of 402 patients treated with CAR-T were examined. Median age was 64 years and 36% were female. Primary diagnosis was B-cell lymphoma (n = 240) or multiple myeloma (n = 162). A total of 226,332 vital sign measurements and 372,871 lab values, as well as ECG and echocardiogram data, were collected for 30 days post-infusion. Overall, 79.8% of patients experienced CRS within 30 days. The full ML model demonstrated AUCs of 0.90 (95% CI 0.86–0.93), 0.83 (95% CI 0.77–0.88), and 0.82 (95% CI 0.77–0.87) for 24-, 48-, and 72-hour predictions of CRS, respectively. Including “day of CRS onset post CAR-T” as a feature improved the 72-hour AUC to 0.87 (95% CI 0.83–0.90). A model restricted to vital signs alone showed AUCs of 0.88, 0.75, and 0.71 for 24-, 48-, and 72-hour horizons. An 11-feature model—focusing on temperature, blood pressure, fibrinogen, CRP, serum sodium level, QRS interval, and lymphocyte counts—maintained high accuracy at 24 hours (AUC 0.90, 95% CI 0.86–0.93) and was validated externally using an independent dataset with an AUC of 0.92. Conclusions: Our ML model provides a reliable approach for predicting if/when CRS will occur, with up to three days of lead time before clinical manifestation, offering an opportunity for proactive management. The robust performance of a parsimonious 11-feature model supports practical adoption across clinical settings and real-time risk stratification to enhance patient safety. Prospective validation and integration into clinical workflows will be critical to translating these findings into practice.

e13551 Background: The landscape of cancer care is evolving rapidly. In 2023, there were 83 new FDA oncology approvals, and 145 interventional treatment (tx) studies opened across Mayo Clinic. We are exploring novel precision outreach approaches utilizing an LLM-integrated chatbot application to “ping” patients (pts) with specific clinical or genomic characteristics about newly available drugs or clinical trials. As novel outreach methods are considered, we surveyed a patient (pt) support group to understand communication preferences and awareness of adjuvant CDK4/6 inhibitors in tx of breast cancer (BC). Methods: On October 7, 2024, we administered a cross-sectional survey to 41 members of the Breast Cancer Support Network (BCSN) in Rochester, MN as a part of an IRB exempt quality improvement project. Leaders of the BCSN shared information to all participants, noting that the survey’s intent was to represent the pt voice and participation was voluntary. Anonymous survey data were collected with descriptive results reported. Results: 34/41 participants in the BCSN shared demographic information. The majority (83%) were > 50 years of age. 47% reported stage I BC, 12% stage II, 6% stage III, and 35% were unsure of their stage. Most participants (26/34, 76%) reported that their BC was hormone receptor positive (HR+), 2 HER-2 positive, and 6 unsure of their BC receptor status. 24/26 (92%) of pts with HR+ BC were taking or planning to start adjuvant endocrine therapy. 10/34 (29%) were aware that adjuvant CDK 4/6 inhibitors were approved. Of these 10 participants, 2 learned of it from online health resources, 6 from their clinician, 1 from social media, and 1 from a support group. The majority (66%) were unsure if they qualified for these drugs. Regarding receipt of information on new drug approvals/tx options, the highest ranked communication preference was to receive this information in person at an upcoming visit (ranked 1st by 50% of participants), followed by EHR-based message (28%), email (10%), phone call (6%), letter (4%), or an interactive chatbot (0%). Most respondents noted that communication from their healthcare provider was very important (30/37, 81%), with others stating that this was somewhat important (5/37, 14%) or neutral (2/37, 5%). Most noted that receiving information about tx options via video or visual aid before a visit would be very helpful (33/41, 80%). When asked about follow up after learning of a new drug approval, 17/32 (53%) of pts preferred an appointment, 9/32 (28%) a phone call, 3/32 (9%) a decision aid tool, and 3/32 (9%) a questionnaire to assess their understanding. Conclusions: Providing personalized, timely communication about new FDA approved tx options is important for BC survivors and critical for improving care delivery. While technological solutions could broaden awareness, this requires balancing pt preferences for direct communication with clinicians.

7541 Background: Multiple myeloma (MM) is characterized by recurrent cytogenetic abnormalities, including translocations involving the immunoglobulin heavy chain locus on chromosome 14 and trisomies, which are considered primary and clonal. Throughout disease progression, MM cells may acquire additional abnormalities, which include chromosome 1 abnormalities (gain or amplification of 1q or deletion of 1p) and chromosome 17 abnormalities (del 17p or monosomy 17p). All these factors are considered high-risk markers that predict below-average outcomes. While outcomes related to 1q have been documented, their relationship with other abnormalities and clinical characteristics is less clearly defined. Methods: We created a cohort of newly diagnosed MM (NDMM) patients from April 1996 to December 2023 for whom FISH testing was performed using a panel that included 1q findings. Data on clinical and laboratory characteristics, other FISH abnormalities, and survival outcomes were collected from existing databases and the electronic medical record (EMR). Results: The cohort included 875 patients, with a median age of 65. Of these patients, 60% were male and 91% identified as white. A 1q abnormality was observed in 443 patients (51%); 87% exhibited a gain of 1q, while 13% showed amplification of 1q. Among those tested, other abnormalities included del13 (58%), t(11;14) (25%), t(4;14) (17%), t(14;16) (6%), del 17p (13%), and trisomies (51%). The distribution of abnormalities concerning the presence of 1q is presented in the table. Patients with 1q abnormalities were more likely to present with additional high-risk cytogenetic abnormalities. The median overall survival (OS) for those with a 1q abnormality was 73 months, compared to 105 months for those without it. Among these, patients with 1q amplification tended to have worse outcomes than those with a 1q gain, though this observation did not reach statistical significance. Conclusions: Abnormalities of chromosome 1, including 1q gain and amplification, can be seen in nearly 50% of patients with NDMM who are tested. 1q abnormalities are associated with other high-risk cytogenetic abnormalities. Measures of disease burden are higher among those with a 1q abnormality. Interestingly, we observed a higher proportion of patients with lambda light chain and those with IgA among those with a 1q abnormality. The presence of a 1q abnormality was associated with inferior survival, with a trend towards worse outcomes among those with 1q amplification compared to 1q gain. Clinical characteristics and cytogenetic associations of multiple myeloma patients with and without 1q abnormalities. 1q abnormality present 1q abnormality absent P del13 78% 39% <0.01 t(4;14) 25% 8% <0.01 t(11;14) 22% 27% NS t(14;16) 15% 3% <0.01 Trisomies 48% 53% NS 17p del 24% 12% <0.01 Lambda light chain 45% 26% <0.01 IgA 32% 16% <0.01 Hemoglobin 10.3 g/dL 11.2 g/dL <0.01

7522 Background: Movement and neurocognitive treatment emergent adverse events (MNTs), cranial nerve palsies (CNPs) and immune-effector cell enterocolitis (IEC-EC) are late onset toxicities associated with cilta-cel and are associated with significant morbidity and mortality. We aimed to identify predisposing risk factors to allow for formulating risk-reduction strategies. Methods: Retrospective study of MM pts who received FDA approved cilta-cel at Mayo Clinic between Feb 2022-Dec 2024. Interrogated factors included demographics, disease and treatment characteristics, and selected lab values at different time points. In odds ratio (OR) analyses, pts were divided by toxicity type (1) No delayed toxicity (2) MNT (3) IEC-EC without MNT (4) isolated CNP. Differences between pts in the MNT, IEC-EC and CNP groups were compared separately in a pairwise manner vs. those with no delayed toxicity. Results: Of 235 pts, 26 (11%) had delayed toxicity [MNT = 8 (3%), IEC-EC = 9 (4%), CNP = 14 (6%)]; 3 pts had both MNT/IEC-EC and 2 had both CNP/IEC-EC. Median onset from CAR-T infusion for MNT, IEC-EC and CNP was 19 (range 8-96), 106 (35-169) and 21 (7-43) days respectively. Of 164 evaluable pts, those who had ICANS had increased odds for any delayed toxicity (OR 4.7; 95% CI 1.6-13.8). Pts who had ICANS (OR 7.7; 1.6-36.9), HLH/MAS (OR 6.2; 1.1-6.7) and Ferritin >400mcg/L at time of lymphodepletion (OR 6.3; 1.5-32) had increased odds for MNTs. Pts who received alkylator-based bridging therapy had increased odds (OR 6.1; 1.1-35) for IEC-EC. Analysis of serial post-CAR infusion lab values showed that peak ALC was the most significant variable with differences between groups shown in table. Median time to peak ALC was 12 days (IQR 11-13). ROC analysis determined peak ALC >3 x 10 9 /L as a meaningful cut point. Pts with peak ALC >3.0 x 10 9 /L had increased odds of developing any delayed toxicity (OR 9.3; 3.5-29.3), MNT and CNP (table). Absolute risk of any delayed toxicity was 33% in pts with peak ALC >3 x 10 9 /L vs 5% without. At this threshold, number needed to treat was 3.6. Conclusions: Real-world data shows that cilta-cel associated delayed toxicity is seen in ~10% of patients, with specific toxicity rates between 4-8%. Factors associated with these toxicities predominantly occur in the post CAR-T infusion period. Given that ALC expansion in the first 2 weeks correlate with CAR-T expansion, peak ALC is potentially predictive of toxicity and 3 x 10 9 /L may be an interventional threshold for primary prophylaxis. Peak ALC by toxicity groups. No ToxN=138 MNTN=8 CNPN=12 IEC-ECN=6 p value Peak ALC (10 9 /L), median (IQR) 1.8 (1.0-4.1) 6.2 (4.8-14.4) 4.3 (3.2-6.7) 3.6 (1.9-5.2) <0.001 1 ALC >3 x 10 9 /L, n (%) 43 (31%) 7 (88%) 10 (83%) 4 (67%) <0.001 2 Odd Ratios vs no Tox 3 , 95% CI 15.5 (2.6-293.7) 11.0 (2.8-73.9) 4.4 (0.8-25.0) 1 Wilcoxon/Kruskal-Wallis Tests, 2 Chi square test, 3 Logistic regression analysis.