Citations

Abstract Introduction Pulsed Electric Field (PEF) Ablation has been used as an adjunct therapy for cancer. Robotic-Assisted Bronchoscopy (RAB) enables precise access to pulmonary lesions for biopsy and ablative therapy. However, anatomic obstructions within the airway may prohibit access to peripheral targets. We report a case in which robotic bronchoscopy navigation for the delivery of PEF was not initially possible due to a new anatomic airway obstruction secondary to radiation fibrosis. We were able to utilize therapeutic bronchoscopy to re-cannulate the airway and deliver the PEF via the robotic bronchoscope. Case Report A 68-year-old man with a history of left lung adenocarcinoma was treated with surgery, chemoradiation and durvalumab consolidation therapy. Surveillance imaging 4 years later revealed consolidation in the right upper mediastinum. A bronchoscopy brush biopsy confirmed adenocarcinoma and received systemic chemotherapy. Later a PET-CT showed a non FDG avid enlarged right paratracheal lesion. Follow-up CT revealed complete obstruction of the right middle lobar bronchus with associated middle lobe collapse likely secondary to radiation. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) of the right paratracheal lesion confirmed malignancy on onsite cytopathology. Subsequently, we performed two PEF ablations targeting the involved lesion. Repeat PET-CT demonstrated two hypermetabolic foci in the right hilum and right supraclavicular region. However, the previously PEF treated paratracheal lesion was not PET avid. We used a RAB to navigate into the right upper lobe and identified the anterior segment to be obstructed in addition to the previously noted right middle lobe. Due to this, the robotic bronchoscope couldn’t be advanced to the right hilar PET avid lesion. Utilizing guidewires, balloon dilatation and fluoroscopy we re-cannulated the obstructed right upper lobe segment and subsequently advance the robotic bronchoscope to the target in the right upper lobe. Under cone-beam guidance, multiple biopsies were obtained and confirmed as malignant. Following this, the INUMI PEF needle was deployed. We delivered two PEF activations to the right hilar PET-avid lesion. Subsequent systemic staging using linear EBUS identified station 4R lymph node involvement, positive for malignancy on rapid onsite cytopathologic evaluation. The 4R lymph node was superior to the previously treated paratracheal lesion. We then deployed the INUMI PEF needle, and PEF ablation was performed successfully. Discussion To our knowledge, this is the first reported instance of combining robotic and therapeutic bronchoscopy to overcome airway obstruction to facilitate the distal treatment of peripheral target with PEF. This abstract is funded by: None

Abstract Introduction The diagnosis of fungal lung infections remains challenging as standard tests, such as bronchoalveolar lavage (BAL) antigen testing, often yield variable or inconclusive results. These limitations can delay appropriate therapy and may require additional tissue sampling for definitive diagnosis. Robotic-assisted bronchoscopy (RAB) biopsy has been primarily used as a minimally invasive technique for assessing suspicious peripheral pulmonary lesions (PPL). This case series highlights the diagnostic utility of RAB for identifying fungal infections within PPL when conventional BAL antigen analysis is non-diagnostic. Case Description Four patients with suspected infectious or malignant PPL underwent RAB-guided biopsy for diagnostic clarification, all yielding histopathologic confirmation of fungal disease. The first, a 73-year-old bilateral lung-transplant recipient with hemoptysis, had a negative BAL Aspergillus antigen despite RAB biopsy confirming Aspergillus infection. Similarly, a second 73-year-old man with chronic obstructive pulmonary disease (COPD) and esophageal adenocarcinoma had a negative BAL antigen, while RAB biopsy of bilateral cavitary lesions confirmed Aspergillus. Additionally, a 39-year-old woman with a nodule being evaluated for malignancy, had negative BAL Histoplasma antigen and PCR, whereas RAB biopsy confirmed Histoplasma capsulatum. In contrast, a 56-year-old woman with a right-lower-lobe nodule had a positive BAL Aspergillus antigen that aligned with the histopathologic biopsy findings. Discussion BAL-based antigen testing demonstrates variable diagnostic accuracy in fungal lung disease. Reported sensitivities for Aspergillus detection are typically high in meta-analysis, approximately 80%-90%, but clinical performance in the immunocompromised or high-risk patients is often substantially lower. Similarly, while BAL antigen testing for Histoplasma performs well in disseminated infections, it often fails to detect localized pulmonary disease. In this series, three out of four patients had negative BAL results in the presence of histopathologic confirmation of fungal infection. While current guidelines consider BAL positivity supportive of a “probable” diagnosis, tissue histopathology remains the gold standard for a “proven” infection. These findings emphasize the value and capability of RAB in obtaining direct tissue confirmation when conventional testing, such as BAL antigen analysis, is non-diagnostic. Conclusion RAB-guided biopsy of PPLs offers the opportunity for histopathologic confirmation of fungal infection when BAL testing is non-diagnostic. This approach can enhance upfront diagnostic yield in patients with suspected fungal pulmonary infections, avoiding delays in diagnosis and treatment initiation. This abstract is funded by: None

Abstract Rationale Endobronchial valve (EBV) placement is an established bronchoscopic lung volume reduction (BLVR) therapy for advanced emphysema. Although randomized trials have shown improvements in lung function, real-world data on predictors of response and complications remain limited. This study evaluated physiological and clinical outcomes after EBV placement and explored predictors of treatment response and adverse events. Methods We retrospectively analyzed 75 patients who underwent EBV placement for severe emphysema at Mayo Clinic Florida between 2018 and 2023. Demographics, comorbidities, pulmonary function test and complications data were collected before and after procedure. Responders were defined as those achieving a ≥ 15% relative increase in forced expiratory volume in one second (FEV1), ≥10% reduction in residual volume (RV), ≥25-meter increase in six-minute walk distance (6MWD), or ≥ 1-point decrease in modified Medical Research Council (mMRC) dyspnea score. Results The mean age was 70.4 ± 7.1 years, 59% were female, and the mean Body Mass Index was 25.6 ± 4.9 kg/m². Most patients were non-Hispanic White (96%) and ever-smokers (97%, median 40 pack-years). Following EBV placement, FEV1 increased by + 0.10 L (p < 0.001), forced vital capacity by + 0.17 L (p = 0.001), RV decreased by -0.69 L (p < 0.001), while total lung capacity decreased by -0.35 L (p < 0.001). Diffusing capacity, 6MWD, and mMRC did not significantly change. Responder analysis showed FEV1 improvement in 52% (34/65), RV reduction in 65% (42/65), 6MWD gain in 33% (18/55), and mMRC improvement in 33% (21/63). Complete lobar atelectasis occurred in 59% (44/75) and was significantly associated with FEV1 improvement (p < 0.01). 30-day follow up complications included pneumothorax (26.7%), COPD exacerbation (21%), and pneumonia (20%). 15% pneumothoraces were managed conservatively, 55% required chest tube, 30% needed valve removal due to persistent air leak. Valve migration and replacement occurred in 2.6% each, and valve removal in 26.6% patients. Median hospital stay was longer in patients with complications (5 vs 4 days, p = 0.003). In-hospital mortality was 5.3% but no procedure-related deaths were identified. Conclusions EBV placement is a safe and effective BLVR approach yielding significant improvements in FEV1 and reductions in hyperinflation. Pneumothorax and valve-related events were the most frequent complications. Complete lobar atelectasis strongly correlated with functional improvement, suggesting that early reassessment should be considered when collapse is not achieved to prevent complications and unnecessary valve retention. This abstract is funded by: None

Abstract Rationale Treatment of hematologic malignancies has been revolutionized by Chimeric antigen receptor T -cell (CAR-T) therapy. Pulmonary complications are increasingly being reported, however, there are no standardized timelines for pulmonary function test (PFTs) assessment before or after the infusion. We aimed to evaluate changes in lung function (TLC, RV, FEV1, and FEV1/FVC) pre- and post-CAR-T therapy and examine whether these parameters correlate with the development of specific pulmonary complications. Methods We conducted a retrospective chart review of patients above the age of 18 with any malignancy who received CAR-T therapy between June 12, 2018, and December 26, 2023. Pre-CAR-T PFTs were obtained closest to the infusion date, and post-CAR-T PFTs were recorded at the earliest available time following infusion. Pre- and post-CART pulmonary function tests were compared using non-parametric paired tests. In addition, we examined the relationship between baseline PFTs and the subsequent occurrence of pulmonary complications after CAR-T infusion. The Wilcoxon signed-rank test was applied to assess both the magnitude and direction of change while Sign test was used to evaluate only the direction to confirm the consistency of results. These tests were chosen due to small sample size and non-normal distribution of data. Results Among the 68 patients in our cohort, paired pre- and post- CAR-T measurements of pulmonary function were available for 18 patients. FEV1 declined significantly post-infusion (2.70 ± 0.81 L vs 2.28 ± 0.74 L; Z= -2.55, p = 0.011), the FEV1/FVC ratio remained stable (77.8 ± 8.0 vs 80.9 ± 12.2, p = 0.53). Mean TLC and RV remained stable (TLC 5.70 ± 1.18 L vs 4.66 ± 1.02 L, p = 0.17 and 2.13 ± 0.62 L vs 2.00 ± 0.70 L, p = 0.58). There was no significant correlation between the baseline lung function and the development of pulmonary complications. Conclusion Only the pattern of FEV1 decline following CAR-T therapy infusion demonstrates a significant decline, whereas other PFTs, although reduced, did not show significance. While these findings may suggest a restrictive ventilatory pattern, additional data on lung volumes are required to accurately characterize the underlying type of pulmonary function impairment. Although limited by small sample size and non-uniform timing of PFT assessments, this highlights the need for a routine pre-CAR-T pulmonary function evaluation to inform patient selection and baseline risk stratification. This abstract is funded by: None

Abstract RATIONALE There are limited studies evaluating the association between chimeric antigen receptor T-cell (CAR-T) therapy and interstitial lung abnormalities (ILA). Our study aims to investigate this potential relationship to better understand pulmonary complications following CAR-T therapy. Methods We conducted a retrospective chart review of patients aged 18 or older with any malignancy who received CAR-T therapy between June 12, 2018, and December 26, 2023. Chest imaging, including PET or CT scans, was reviewed for each patient; the closest scan before CAR-T therapy and the most recent scan afterward. We identified ILA based on findings that included ground-glass opacities, reticular abnormalities, traction bronchiectasis, honeycombing, or non-emphysematous cysts involving more than 5% of lung zones. We excluded dependent atelectasis, paraspinal fibrosis, aspiration-related changes, mild focal or unilateral abnormalities, and smoking-related centrilobular nodularity without other findings. Results A total of 66 patients had adequate imaging data both before and after CAR-T infusion. Before therapy, 17 patients (25.8%) demonstrated ILA, while 49 (74.2%) did not. Following CAR-T therapy, the overall prevalence of ILA increased to 31 patients (47.0%). Among those who did not have ILA before CAR-T, 16 of 49 (32.7%) developed new ILA following therapy. Conversely, among those with pre-existing ILA, 14 of 17 (82.4%) showed persistent or progressive ILA post-CAR-T. This distribution demonstrated a statistically significant association between pre- and post-CAR-T ILA status (χ² = 10.8, p = 0.001), indicating that pre-CAR-T ILA status strongly predicted post-CAR-T ILA persistence or worsening. When evaluating post-CAR-T ILA in relation to clinical outcomes, among those with pre-CAR-T ILA, 52.9% (n = 9) were deceased at follow-up, compared to 55.1% (n = 27) among patients without ILA. The difference in mortality between the groups was not statistically significant (χ² = 2.34, p = 0.31). 19 of 31 patients (61.3%) with post-CAR-T ILA were deceased at last follow-up, compared with 17 of 37 (45.9%) in those without ILA. Although mortality was numerically higher among patients with post-CAR-T ILA, this difference did not reach statistical significance (χ² = 1.04, p = 0.308). Conclusion Our study demonstrates a statistically significant association between pre- and post-CAR-T interstitial lung abnormalities, suggesting that CAR-T therapy may contribute to the progression or development of ILAs. These findings highlight the need for closer pulmonary monitoring during CAR-T treatment. This abstract is funded by: None

Introduction Asymptomatic individuals with negative Interferon-γ release assay (IGRA) and tuberculin skin test (TST) results are often labeled as tuberculosis-unexposed individuals. We hypothesize that flow cytometric (FC) detection of antigen-stimulated T-cells in peripheral blood can differentiate IGRA(-)/TST(-) individuals with and without prior potential M. tuberculosis (Mtb) exposure. Methods We used FC multiparameter profiling of T-cell activation markers in TST/IGRA-negative individuals at risk for Mtb exposure and in unexposed controls. Results We studied 54 IGRA(-)/TST(-) subjects, including 27 individuals at risk for prior Mtb exposure. While quantitative IGRA results were negative in all patients, FC profiling of CD3/CD4 + IFN-γ + HLA-DR + T-cells after stimulation with a pool of Mtb-specific region of difference-1 (RD1) peptides, mycobacterial (PPD and MTB300), or Candida antigens, statistically differentiated between unexposed and potentially exposed individuals (P<0.05). ROC analysis showed PPD and RD1 peptides responses had AUCs >0.7 (sensitivity of 55.5–74% and specificity of 66.6–85.1%). The presence of a polyfunctional RD1-reactive CD3/CD8 + IFN-γ + TNF-α + T-cell subset also significantly differentiated these groups (AUC 0.66). Other T-cell markers demonstrated no significant differences. Conclusions FC detection of antigen-specific IFN-γ + HLA-DR + CD4+T-cells and IFN-γ + TNF-α + CD8 + T-cells can differentiate IGRA(-)/TST(-) individuals at risk of Mtb exposure from unexposed controls. Further validation is needed to determine whether this immunoprofiling approach can improve detection of Mtb infections and identification of unexposed individuals for future biomarker studies and vaccine trails.

Objective: To compare 1-year changes in estimated 10-year and lifetime atherosclerotic cardiovascular disease (ASCVD) risk following metabolic and bariatric surgery (MBS) versus glucagon-like peptide-1 receptor agonist (GLP-1RA) therapy among adults with obesity. Summary Background Data: Obesity is a major driver of ASCVD through adverse metabolic and inflammatory pathways. Metabolic and bariatric surgery and GLP-1 receptor agonists represent the most effective contemporary treatments for obesity and are increasingly used to mitigate cardiovascular risk. However, their comparative effects on integrated short-term and lifetime ASCVD risk in real-world clinical practice remain incompletely characterized. Methods: We conducted a retrospective cohort study of adults with obesity (body mass index ≥30 kg/m²) who underwent MBS or initiated GLP-1RA therapy between 2020 and 2023 within a large tertiary health care system in the United States. Participants were identified from electronic health records and followed for 12 months. Primary outcomes were 1-year changes in estimated 10-year and lifetime ASCVD risk. Secondary outcomes included percent total body weight loss, blood pressure, and lipid parameters. Multivariable linear regression models were used to adjust for baseline body mass index and baseline ASCVD risk. Results: The final cohort included 812 patients, of whom 579 underwent MBS and 233 initiated GLP-1RA therapy. At baseline, patients receiving GLP-1RAs were older and had higher estimated ASCVD risk. At 1 year, reductions in 10-year ASCVD risk were similar between groups (−0.8% vs. −1.1%; P =.36). In contrast, lifetime ASCVD risk decreased significantly more following MBS than GLP-1RA therapy (−8.6% vs. −1.7%; P <.001). MBS was associated with greater percent total body weight loss (−27.8% vs. −11.1%; P <.001) and more favorable lipid changes, including larger reductions in low-density lipoprotein cholesterol and greater increases in high-density lipoprotein cholesterol. After adjustment, MBS remained independently associated with a greater reduction in lifetime ASCVD risk compared with GLP-1RA therapy (β −6.92; 95% CI −9.22 to −4.62). Conclusions: In this real-world cohort, both MBS and GLP-1RA therapy were associated with improvements in estimated cardiovascular risk, but MBS conferred substantially greater reductions in lifetime ASCVD risk, accompanied by superior weight loss and lipid improvements. These findings highlight the complementary roles of surgical and pharmacologic therapies in obesity management and may inform strategies to optimize long-term cardiovascular risk reduction.

Abstract Gastrointestinal (GI) cancers are rising in people &lt; 50 and remain major causes of cancer mortality despite therapeutic advances. Chimeric antigen receptor T (CART) cell therapy has transformed treatment of hematological cancers. However, its efficacy in GI cancers has been hindered by antigen heterogeneity and immunosuppressive cancer associated fibroblasts (CAFs) in the tumor microenvironment (TME.) Here we aimed to 1) study CART-CAF interactions and 2) engineer CART cells capable of eliminating CAFs to overcome their inhibitory role and enhance their antitumor activity in GI cancers. We first analyzed primary CAFs from 20 GI cancer patients. CAFs showed high fibroblast activation protein (FAP) expression and significantly suppressed T cells proliferation (26-77%, p≤0.0001). We next generated CART cells capable of safely eliminating both GI cancer cells and CAFs. To target cancer cells, we developed a novel nanobody (VHH)-based CAR against Claudin18.2, a GI cancer specific target. To avoid off-tumor toxicity in healthy FAP+ tissues, we incorporated an inducible FAP-CAR using the synNotch platform, enabling conditional targeting upon engagement with Claudin18.2+ cells, restricting FAP targeting within the TME. VHH Claudin18.2 CART cells showed superior specificity and efficacy vs scFv-based CART cells (hu8E85 or zolbetuximab). In Claudin18.2+ SNU-C2B xenografts, tumors were 92mm3 (VHH) vs 48mm3 (huE85) vs 211mm3 (zolbetuximab) on day 23 post-CART, median survival undefined vs 17 days vs 23 days respectively; p=0005. In Claudin18.2+ LS411N xenografts, tumors were 315mm3 vs 106mm3 vs 382 mm3 respectively at 23 days post-CART, median survival undefined vs 19 days vs undefined respectively; p=0004. VHH Claudin18.2 CART cells showed no off-tumor effects, while hu8E85 CART induced significant toxicity. We next established a co-engraftment model. NSG mice received 1x106 SNU-C2B and 6x106 CAFs from a GI cancer patient. At 500 mm3 tumors, mice received 5x106 VHH Claudin18.2 or inducible Claudin18.2/FAP CART. Dual-targeting CART cells showed greater antitumor response (728mm3 vs 320mm3, p=0.0011 at day 20 post-CART), expansion (61 vs 2,350 CART/µl of blood, p=0.0037), and tumor infiltration (8.71 x 105 vs 1.03 x 106 CART/g of tumor, p&lt;0.0001). This was also observed in gastric, colon, and pancreatic PDX models, with no observable off-tumor cytotoxic effects with inducible dual-targeting Claudin18.2/FAP CART. Our findings demonstrate that our novel VHH-based Claudin18.2 CART cells are highly specific and effective against GI malignancies, and that inducible Claudin18.2/FAP dual-targeting CART cells safely remodel the TME into an immune-permissive state. This approach represents a mechanistically innovative and translationally relevant strategy to overcome CAF-mediated immunosuppression, enhance CART cell efficacy, and improve clinical outcomes in refractory solid tumors. Citation Format: Omar L. Gutierrez Ruiz, Jennifer Feigin, Brooke Kimball, R. Leo Sakemura, Elizabeth L. Siegler, Dominic A. Skeele, Ateka Saleh, Claudia Manriquez Roman, Ismail Can, Olivia Sirpilla, Kun Yun, Carli M. Stewart, Mehrdad Hefazi, Yoh Yamaguchi, Lionel Aurelien Kankeu Fonkoua, Long K. Mai, Truc Huynh, Sophia Y. Goldberg, Grace E. DeFranco, Sara Foote, Ekene Johnkennedy Newton Ogbodo, Hong Xia, Michael Redig, Matthew L. Matthew, Tamiel Nichole Turley, Skyeler Klinge, John Alton Copland, Saad J. Kenderian. Optimized CART cell therapy to remodel the tumor microenvironment and eliminate GI malignancies [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 1525.

Abstract Pancreatic ductal adenocarcinoma (PDAC) is an aggressive malignancy due in part to metabolic rewiring and a high rate of metastasis. Pancreatic tumors are particularly dependent upon glutamine (Gln) as a nutrient source for multiple metabolic pathways. To adapt to low levels of glutamine, PDAC cells upregulate the Rac1 dependent process of macropinocytosis, which internalizes extracellular macromolecules to scavenge them as a glutamine source. The proto oncogene Vav1 is an activator of the potent Rac/Cdc42 signaling cascades that regulate actin dynamics. While Vav1 is normally restricted to hematopoietic cells, Vav1 expression is significantly increased in PDAC, with high Vav1 correlating with worse overall survival. Here we uncover a novel Vav1 mediated regulation of glutamine metabolism in PDAC cells. While Vav1 is a potent activator of Rac1, surprisingly, Vav1 expression inhibited macropinocytosis in PDAC cells. Intriguingly, genomic and metabolomic analysis revealed that high Vav1 expression correlates with increased dependence on glutamine and glutamate (Glu) metabolism. Indeed, Vav1 dependent macropinocytosis was rescued by cell permeable glutamate, confirming disrupted Gln/Glu balance in Vav1 knockdown cells. RPPA screening indicated a Vav1 dependent effect on glutaminase 1 (GLS1, KGA isoform), which converts glutamine to glutamate. Mechanistically, we discovered that Vav1 modulates GLS1 localization to the mitochondria through regulation of GLS1 posttranslational modification. Disrupting GLS1 localization by deleting its mitochondrial targeting motif phenocopied loss of Vav1 in reducing the invasive potential of tumor cells. Investigation of Vav1 dependent metabolic consequences showed that knockdown of Vav1 alters 13C Gln derived metabolic flux into the TCA cycle, as well as a deficiency in the level of the antioxidant glutathione (GSH), which utilizes glutamate for its synthesis. Consequently, targeting Vav1 resulted in increased levels of cellular and mitochondrial reactive oxygen species (ROS) and increased sensitivity to lipid peroxidation. Notably, dual targeting of both glucose and glutamine pathways showed significant synergistic effects on cellular viability in Vav1 expressing cells. Here we established a new tumor promoting role for Vav1 via Gln/Glu regulation and uncover a novel subcellular regulation of mitochondrial glutamine metabolism. Our findings establish Vav1 as a critical regulator of metabolic rewiring in PDAC and orchestrates glutamine metabolism by controlling the KGA isoform of GLS1 mitochondrial localization. Importantly, Vav1 functions as a signaling adapter in glutamine metabolism, providing a potential therapeutic vulnerabilities for PDAC patients with high Vav1 expression. Citation Format: Mustafa Emre Gedik, Omar L. Gutierrez-Ruiz, Katherine M. Johnson, Ella Rose D. Chianis, Jing Chen, Alex Bittner, Adam Zahm, Ankit Chhoda, Taro Hitosugi, Mark A. McNiven, Gina Razidlo. Vav1 promotes pancreatic tumor cell invasion via GLS1-dependent glutamine metabolism [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 7322.

ABSTRACT The increasing prevalence of carbapenem-resistant Klebsiella pneumoniae represents a serious global health challenge. Rapid and accurate detection methods are essential to inform early and correct use of antimicrobial therapy to idealize patient outcomes and limit the spread of resistant isolates. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has been evaluated for resistance detection, but its clinical application remains limited. In this study, MALDI-TOF MS was integrated with machine learning (ML) to improve detection of Klebsiella pneumoniae carbapenemase (KPC) among K. pneumoniae isolates harboring KPC carbapenemase. Ensemble learning strategies were applied to 435 clinical isolates from different geographic locations (Spain, United States, South America, and Asia), with validation performed using external data sets. By constructing two peak matrices and applying four ML algorithms, as well as combinations of two and three in ensemble models, 92 different classifiers were tested. Ensemble combinations increased the specificity of classifiers to over 95%, while sensitivity reached 72%, being significantly higher than that of the MALDI Biotyper KPC module. Low sensitivity may be affected by technical variability during spectral acquisition. The first annotated MALDI-TOF MS spectrum for K. pneumoniae by in silico prediction of protein masses was developed to enable peak identification, including peaks potentially related to antimicrobial resistance. Overall, the results of this study show that combining MALDI-TOF MS with ensemble learning can enhance KPC detection performance. IMPORTANCE Rapid and accurate detection of Klebsiella pneumoniae carbapenemase (KPC)-producing Klebsiella pneumoniae informs early and correct use of antimicrobial therapy to idealize patient outcomes and limit the spread of antimicrobial resistance. In this study, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and ensemble machine learning were employed to detect KPC-producing isolates, using diverse isolate collections, obtaining excellent specificity. An annotated K. pneumoniae MALDI-TOF MS profile is provided with peak annotation, providing a resource for peak analysis.