Citations

ABSTRACT Magnetic Resonance Spectroscopy Imaging (MRSI) offers spatially-resolved, neurometabolic information, acquired non-invasively at whole-brain scales from human subjects. Analysis of MRSI however, is extremely challenging. The metabolic information is highly convolved, and sparsely distributed across millions of spatial-spectral datapoints, allowing for little direct human interpretation. Conversely, the overall low signal-to-noise with high-intensity artifacts can confound unsupervised machine learning approaches. These technical barriers have left much of the potential of MRSI unrealized. We acquired MRSI data from 4 human subjects with a diagnosis of multiple sclerosis (MS), incorporating experimental design into an informed machine learning approach. MRSI acquisitions were registered to anatomical MRI to label 105k spectra from brain tissue and 162 spectra from white matter hyperintensities (WMHs), an imaging biomarker associated with MS lesions. Spectral labels were then used in contrastive principal component analysis (cPCA) to filter artifacts and background features in the MRSI data from lesion salient features and clustered into statistically significant states based on features that could be interpreted from the original data. Our approach renders MRSI data into testable representations of neurometabolism, enabling the method for fundamental and clinical research. Graphical Abstract Analysis workflow for neurometabolic profiling of MS lesions. MRSI and anatomical MRI is acquired and processed in parallel for spectral data and anatomical labels. Spectra are then labeled and separated into experimental vs background data for contrastive PCA. Spectra are clustered for similarity, further labeled, and projected onto a brain atlas for a neurometabolic view.

Aim Post-traumatic headache (PTH) attributed to mild traumatic brain injury (mTBI) frequently co-occurs with other physical, cognitive, and emotional symptoms. This study assessed associations between PTH improvement and these symptoms in individuals with acute headaches (APTH) and compared symptoms between those who had recently developed persistent PTH (PPTH) to those who had long-standing PPTH. Methods This study included 105 individuals with APTH (mean age = 43.4, SD = 15.8; 70 females, 35 males) and 46 individuals with PPTH (mean age = 38.2, SD = 10.9; 16 females, 30 males) with an average duration of 11.3 years from two prospective longitudinal studies. For those who had APTH, PTH improvement was assessed at three months post-enrollment using an electronic headache diary. Participants completed questionnaires evaluating physical (including headache symptoms, photosensitivity, hyperacusis, insomnia, autonomic symptoms, and disability), emotional (including depression, anxiety, pain catastrophizing, and post-traumatic stress disorder screening), and cognitive symptoms (including memory and attention). The APTH cohort completed questionnaires at baseline, follow-up #1 (three to four months from baseline), and follow-up #2 (six to seven months from baseline). Mixed Effects Models were used to analyze the temporal trend of symptoms among the APTH improved and non-improved groups. Results Among the 105 individuals with APTH, 60 experienced PTH improvement and 45 did not. At baseline, compared to those who had PTH improvement, those who did not have PTH improvement had higher SCAT total scores and physical subscores, greater levels of hyperacusis, pain catastrophizing, anxiety and depression. At follow-up #1 (three to four months), these individuals continued to show more pronounced physical and emotional symptoms and worse cognitive function and insomnia. Most of these group differences persisted at follow-up #2 (six to seven months). Most symptoms showed progressive improvement over three months for individuals who had PTH improvement but not for those without PTH improvement. Furthermore, individuals with long-standing PPTH showed more severe insomnia, pain catastrophizing, and PTSD compared to those who had recently developed PPTH. Conclusion Individuals with APTH who did not experience PTH improvement at three months had more severe physical, cognitive, and emotional symptoms at baseline compared to those who had PTH improvement. While most symptoms normalized in individuals with PTH improvement, symptoms overall persisted at three and at six months for those with PTH persistence. Individuals who had long-standing PPTH had more severe insomnia and more negative cognitive/emotional responses to pain compared to those who had recently developed PPTH.

Abstract Recent updates to monocyte count thresholds recognize oligomonocytic chronic myelomonocytic leukemia (OM-CMML) as an early form of CMML. However, the clinical validity of these changes remains uncertain without incorporating biological and genomic factors. In this study, we analyzed a cohort of 911 patients (249 with OM-CMML, 359 with overt CMML, and 303 with myelodysplastic syndromes) using unsupervised clustering to evaluate the role of genomic determinants in refining CMML diagnosis. Our findings show that CMML molecular signatures (biallelic TET2 mutations or SRSF2-TET2 comutations) are linked to a distinct transcriptome, monocytic bias, classical monocytosis, and a higher risk of progression to overt CMML in OM-CMML cases. We developed a weighted genomic model and diagnostic workflow showing that combining genomic signatures with bone marrow monocyte frequencies in OM-CMML more accurately predicts progression to overt CMML. These findings support integrating genomic determinants and our clinic-ready diagnostic workflow into the CMML diagnostic framework to improve accuracy. Significance: Through comprehensive clinical and genomic profiling of a large patient cohort, alongside immunophenotypic and transcriptional cellular analyses, this study provides evidence that incorporating genomic determinants into the diagnostic criteria for OM-CMML improves diagnostic accuracy and refines the identification of early-stage CMML, thereby preventing misclassification.

Learning from multimodal data sets can leverage complementary information and lead to improved performance for prediction tasks. A commonly used strategy to account for feature correlations in high-dimensional data sets is the latent variable approach. Several latent variable methods have been proposed for multimodal data sets; however, these methods either focus on extracting a shared component across all modalities or extracting a shared component and individual components specific to each modality, overlooking correlations within partial subsets of modalities. We propose multimodal fission learning (MMFL), the first supervised latent variable model that adopts a generalizable decomposition into globally joint, partially joint, and individual components from multimodal data sets. A key strength of MMFL is a natural extension to incorporate incomplete multimodal data in either training and test phases by leveraging the learned modality structure. Through simulation studies, we demonstrate that MMFL outperforms a variety of existing multimodal algorithms under both complete modality and incomplete modality settings. We applied MMFL to two real-world case studies: early prediction of Alzheimer’s disease using neuroimaging and genetic data and predicting posttraumatic headache improvement using clinical data collected via questionnaires and brain neuroimaging data. MMFL achieved improved predictive accuracy and enhanced interpretability offering insights for within- and cross-modal relationships of multimodal data sets. History: Rema Padman served as the senior editor for this article. Funding: This research was supported by the National Institutes of Health [Grants 2R42AG053149-02A1, R01AG069453, 30AG072980, R01AG069453, and 1R61NS113315-01], the National Science Foundation [Grant DMS-2053170], and the Department of Defense [Award W81XWH-19-0534]. The grantee organization is the Northern California Institute for Research and Education. In the past, ADNI has also received funding from the National Institute of Biomedical Imaging and Bioengineering, the Canadian Institutes of Health Research, and private sector contributions through the Foundation for the National Institutes of Health including generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. Data Ethics & Reproducibility Note: The code capsule is available at https://github.com/lingchm/MMFL and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2024.0059 ).

Abstract Wiskott-Aldrich syndrome (WAS), an X-linked disorder characterized by immunodeficiency, thrombocytopenia, autoimmunity, and malignancy, can be effectively treated with allogeneic hematopoietic cell transplantation (HCT). Older age at HCT and mismatched donors are known to affect overall survival (OS). However, the influence of specific clinical manifestations or WAS variant class on OS and factors associated with event-free survival (EFS) remain incompletely defined. We analyzed outcomes of 308 patients with WAS who underwent HCT at 37 institutions of the Primary Immune Deficiency Treatment Consortium from 1990 to 2018. With a median follow-up of 5.3 years, the 5-year OS and EFS were 87.2% and 79.7%, respectively. Age ≥5 years, donor type, and a pre-HCT history of severe infection had a negative impact on OS and EFS, whereas pre-HCT autoimmunity had no impact. Reduced-intensity regimens were associated with lower T-cell and myeloid donor chimerism, particularly when non–busulfan-based regimens were used. Low myeloid donor chimerism was associated with lower platelet counts. Mixed chimerism was not consistently associated with post-HCT autoimmunity. Patients with class I (exon 1-2 missense and intron 5 hot spot variants) and class II variants (all others) had similar pre-HCT clinical symptom severity and no difference in OS, EFS, or platelet recovery post-HCT. In conclusion, our study showed excellent long-term OS and EFS after HCT for WAS, highlighting the importance of early HCT, before the development of severe infections. We confirmed that HCT using busulfan-based conditioning was associated with improved donor chimerism and platelet recovery. This trial was registered at www.clinicaltrials.gov as NCT02064933.

Abstract Background Despite advances in the diagnosis and treatment of immune thrombotic thrombocytopenic purpura (iTTP), recent mortality estimates remain around 5–10%. Predicting iTTP mortality risk has been of interest, as it may help individualize treatment or potentially guide the use of more intensive or novel therapies based on disease severity. However, prior attempts at mortality prediction have yielded inconsistent results, and no individual variable has demonstrated independent or reliable predictive ability. In a previous analysis utilizing the USTMA iTTP registry, which included 419 patients from 15 TTP referral centers, we reported that mortality due to immune TTP was unpredictable (Blood. 2021;138[Suppl 1]:1047). Neither the French Thrombotic Microangiopathy (TMA) Reference Score (previously validated in the French TMA Registry), nor a previous logistic regression model attempt (developed by USTMA investigators in 2021) demonstrated sufficient accuracy in predicting iTTP mortality in the USTMA dataset (AUC = 0.63 and 0.69, respectively). We subsequently utilized gradient boosted machine, a machine learning approach capable of handling multiple continuous variables and the complex interactions between them in large datasets, and developed a novel prediction tool: the USTMA Mortality Index (Res Pract Thromb Haemost. 2024; 8(3):102388). It demonstrated good performance in predicting iTTP mortality (AUC = 0.77) in repeated 10-fold cross-validation. However, it has not yet undergone external validation. Objectives To externally validate the USTMA Mortality Index to predict mortality due to acute iTTP in a multicenter cohort. Methods We performed an external validation using an independent cohort of iTTP patients from 5 institutions: University of Utah, Case Western Reserve University, Rochester Regional Health, University of Illinois, and Mayo Clinic. Patients in the validation cohort were not part of the development cohort (the USTMA registry). We included patients with confirmed iTTP and defined acute iTTP mortality as death within 30 days of admission. USTMA Mortality Index variables were collected at initial presentation, which included (in order of highest to lowest relative influence): lactate dehydrogenase, serum creatinine, age, hemoglobin, platelet count, presence of stupor/coma, fever. The model's prediction accuracy was assessed using area under the receiver operating characteristic curve (AUC). We calculated sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) based on the previously defined cut-offs of 4.27% and 9.08% mortality risk in the original model, which categorized patients into standard risk, high risk, and very high risk of predicted mortality. Results The external validation cohort included 103 patients with confirmed iTTP and 11 deaths (10.7% mortality rate). The USTMA Mortality Index demonstrated poor performance with AUC of 0.69 (95% CI, 0.55–0.83) in the validation cohort. The wide confidence interval reflects substantial uncertainty in model performance, ranging from poor to excellent, and is likely due to the small number of deaths. At a risk threshold ≥4.27%:Sensitivity = 64%Specificity = 70%PPV = 20%NPV = 94% At a risk threshold ≥9.08%:Sensitivity = 18%Specificity = 87%PPV = 14%NPV = 90% Conclusion The USTMA Mortality Index demonstrated poor performance in the external validation cohort (AUC = 0.69, 95% CI, 0.55–0.83), contrasting with its previously favorable performance in repeated 10-fold cross-validation. This discrepancy likely reflects model overfitting, a known challenge in AI-based clinical modeling. Our study is limited by the small number of deaths, resulting in a wide confidence interval ranging from poor to excellent performance. Given that neither the French TMA Reference Score, nor our group's prior logistic regression model (2021), nor the USTMA Mortality Index (2024) could reliably predict mortality upon external validation in our cohorts, these findings collectively suggest that mortality in acute iTTP remains difficult to predict at this time, regardless of statistical methodology or current machine learning capabilities. Clinical decision-making, including the use of therapies such as caplacizumab, should not be guided solely by mortality risk predictions. Instead, efforts to reduce mortality and improve outcomes should prioritize individualized clinical assessment over model-based stratification at this time.

Abstract Introduction Odronextamab, a CD20×CD3 bispecific antibody, demonstrated compelling efficacy with a generally manageable safety profile in heavily pretreated patients (pts) with relapsed/refractory (R/R) follicular lymphoma (FL) in the Phase 2 ELM-2 study (NCT03888105; Kim TM, et al. Ann Oncol 2024). Pts in ELM-2 received odronextamab monotherapy until disease progression or unacceptable toxicity, with dosing frequency reduced to every 4 weeks (Q4W) in those with sustained complete response (CR) for at least 9 months. Here, we report longer term outcomes in the global FL population of ELM-2, including efficacy and safety in pts who switched to Q4W dosing. Methods Details of the ELM-2 study for the R/R FL cohort have been reported previously. Odronextamab monotherapy was administered intravenously, with step-up dosing in Cycle (C) 1 to help mitigate the risk of cytokine release syndrome (CRS), followed by 80 mg in C2–4, then 160 mg every 2 weeks (Q2W) maintenance. Pts with a CR for ≥9 months switched from 160 mg Q2W to Q4W. Pts with the opportunity for response assessment at 12 weeks were included in this analysis. Primary endpoint was objective response rate (ORR) per Lugano criteria by independent central review (ICR). Key secondary endpoints included CR rate, duration of response (DOR), and progression-free survival (PFS) by ICR, overall survival (OS), and safety. Results As of May 5, 2025 data cutoff, 128 pts with R/R FL Grade (Gr) 1–3a were evaluable for efficacy and safety analysis (overall global population). Median duration of odronextamab exposure was 42.9 weeks (range 0.4–264.0) and median follow-up was 34.1 months (95% CI 33.8–37.9). Eligible pts (n=48) switched to Q4W dosing, with median duration of follow-up from time of switching to Q4W dosing of 19.7 months (95% CI 16.2–31.9). Baseline characteristics were generally similar between the overall population and the subgroup of pts who switched to Q4W dosing. The ORR by ICR in the overall population was 80.5% and CR rate was 74.2%, with a median DOR of 26.0 months and median duration of CR of 32.2 months. In pts with sustained CR for ≥9 months who transitioned to Q4W maintenance, the median DOR from time of switching was 31.5 months. In the overall population, the median PFS was 24.1 months and median OS was not reached (estimated 24- and 36-month OS rates: 70.1% and 64.3%, respectively). In pts with CR, median PFS was 38.0 months and median OS was not reached (24- and 36-month OS rates: 80.1% and 75.2%). All 128 pts had treatment-emergent adverse events (TEAEs), with Gr ≥3 TEAEs reported in 112 pts (87.5%). Discontinuation due to TEAEs occurred in 29 pts (22.7%), and 5 pts died due to treatment-related TEAEs. With the 0.7/4/20 mg step-up regimen, CRS was reported in 55.0% (33/60; Gr 3 in 1 pt) of pts, with no new CRS events observed after switching to Q4W. Infections occurred in 81.3% (Gr ≥3, 46.1%) of pts, with COVID-19 (any Gr, 39.8%) the most frequent. After switching to Q4W dosing, the rate of any grade infection was 81.3% (Gr ≥3, 39.6%). Opportunistic infections (narrow SMQ defined) were reported in 18% (Gr ≥3, 8.6%) of pts in the overall population, with 22.9% (Gr ≥3, 8.3%) of pts having an opportunistic infection after switching to Q4W. Conclusions In the ELM-2 study with ~3-year follow-up in heavily pretreated pts with R/R FL, odronextamab continued to demonstrate deep and durable responses, as well as encouraging PFS and OS, particularly in the majority of pts who achieved CR. Responses remain durable in those who switched to Q4W dosing, lasting for a median additional 31.5 months from the time of switching, demonstrating the long-term, continued therapeutic benefit of odronextamab in pts with R/R FL. The safety profile remained generally manageable, with no new safety signals observed, and no evidence of increased infection risk in pts who switched to Q4W maintenance. Updated data will be presented.

Abstract Recent updates to the monocyte count thresholds for diagnosing chronic myelomonocytic leukemia (CMML) have recognized oligomonocytic CMML (OM-CMML) as an early stage within the CMML spectrum. However, the clinical validity of these revised criteria remains uncertain without considering biological factors and might misclassify myelodysplastic syndromes (MDS) with mild monocytosis as CMML. To characterize the genomic landscape of OM-CMML, we evaluated OM-CMML (n=249), MDS (n=304) and myelodysplastic CMML (MD-CMML, n=358) patients (pts) treated at three academic institutions. Targeted next-generation sequencing was performed on bone marrow (BM) at initial diagnosis or first referral. OM-CMML was characterized by lower frequencies of biallelic TET2 (biTET2) and RAS pathway (RASp) gene mutations (BRAF, CBL, KRAS, NF1, NRAS and PTPN11) compared to MD-CMML (p<0.001) but higher frequencies than MDS (p<0.001). BM monocyte frequencies, assessed morphologically, were higher in OM-CMML than in MDS (p<0.001) but lower than in MD-CMML (p<0.001), indicating that OM-CMML is a heterogenous group including true CMML and distinct MDS subsets. Unsupervised hierarchical clustering based on genomic alterations across all cases (n=911) identified three distinct clusters: 1) TP53 alterations (predominantly multihit TP53) and complex karyotype (TP53-complex); 2) biTET2 or TET2-SRSF2 co-mutation (biTET2/SRSF2); 3) a heterogenous group lacking these features (not otherwise specifiable [NOS]). Among OM-CMML pts, 11%, 34% and 55% belonged to these clusters, respectively. Model-based unsupervised clustering further identified 9 unique clusters that could be consolidated into 6 groups: 1) TP53-complex; 2) biTET2/SRSF2; 3) SF3B1 (without biTET2 or SRSF2); 4) SRSF2 without TET2 and frequent IDH2 mutations (SRSF2-IDH2); 5) ASXL1 and U2AF1 mutations and copy number alterations (CNA-ASXL1/U2AF1); 6) no somatic mutations (No mutation). biTET2/SRSF2 group exhibited monocytic bias with higher AMC, PB and BM monocyte % even among OM-CMML cases. This bias was not attributed to higher RAS pathway mutation frequencies, as biTET2/SRSF2 cases had similar RASp mutation frequencies but lower median variant allele frequencies for RASp mutations compared to NOS cases (9% vs. 21%, p=0.029). PB monocyte partitioning using flow cytometry (FC) in a subset of OM-CMML pts (n=50) demonstrated higher frequency of classical monocytosis (>94% CD14+/CD16- monocytes) in biTET2/SRSF2 vs other OM-CMML. To further determine if biTET2/SRSF2 genotype defines a distinct biological subgroup, we performed RNA-sequencing of BM CD34+ cells from healthy donors (n=15) and pts with OM-CMML (n=12), MD-CMML (n=14) and MDS (n=55). Unsupervised clustering based on gene expression profiles revealed that biTET2/SRSF2 clustered irrespective of their diagnostic group with greater dispersion being observed based on diagnosis. MDS and CMML with biTET2/SRSF2 had less differentially expressed genes compared to MDS and CMML with biTET2/SRSF2 relative to other MDS and CMML genotypes. Among 138 OM-CMML pts in whom progression to overt CMML was evaluable, 37 (27%) progressed to overt CMML of which 26 (70%) belonged to the biTET2/SRSF2 group. Competing risk analysis confirmed higher cumulative incidence and shorter time to CMML progression among biTET2/SRSF2 OM-CMML. Using ElasticNet regression we identified BM monocytosis and 14 genomic variables (including biTET2 and TET2-SRSF2) as predictors of overt CMML progression among OM-CMML. We developed a score-based model able to predict progression with high reliability (AUC 0.805, sensitivity 0.70, specificity 0.76). Model accuracy was confirmed by optimism-corrected bootstrap internal validation (AUC 0.668). Monocytic bias, BM classical monocytosis (>94% CD16- monocytes) and higher overt CMML progression in biTET2/SRSF2 was confirmed in a validation cohort (28, 66 and 22 pts with OM-CMML, MDS and MD-CMML, respectively). BM monocytosis of biTET2/SRSF2 was confirmed in this cohort with morphologic and FC monocyte frequency quantification having high concordance (r=0.737, p<0.001). Genomic subgroup analysis discriminated survival outcomes more reliably than diagnostic categories alone. Our findings suggest that the presence of biTET2 or TET2-SRSF2 co-mutations, combined with BM monocytosis, can more reliably identify true CMML cases within the OM-CMML spectrum. Integrating genomic determinants into the CMML diagnostic framework enhances diagnostic accuracy.

Abstract Background Due to the high mortality of immune thrombotic thrombocytopenic purpura (iTTP), rapid clinical evaluation and early intervention are crucial. The PLASMIC score remains a valuable and widely used tool for predicting severe ADAMTS13 deficiency. However, recent studies have shown variable performance across different populations. In addition, its variables may often be missing during initial presentation. Refining the accuracy of early iTTP evaluation could improve timely recognition and treatment, while reducing unnecessary interventions in those eventually ruled out for iTTP. Machine learning advancements offer several advantages for enhancing clinical prediction models: the ability to assess continuous variables, capture complex interactions between them, and handle missing data. We previously utilized XGBoost (extreme gradient boosting) to develop a novel machine learning tool, TTP-14, which improved upon the PLASMIC score's predictive performance in repeat 10-fold cross-validation achieving an AUC of 0.91 (Blood. 2024;144[Suppl 1]:2617). TTP-14 generates a predicted probability for iTTP, expressed as a continuous percentage estimate of iTTP diagnostic likelihood, and is also able to do so with missing variables. However, it has not previously been externally validated. Objectives To externally validate the ability of TTP-14 to predict iTTP diagnosis and improve upon the PLASMIC score. Methods We performed an external validation of TTP-14 using an independent cohort of patients with suspected iTTP at the Mayo Clinic. These patients were not part of the original multi-center development cohort of 106 iTTP patients from the University of Utah, Case Western Reserve University, Rochester Regional Health, and University of Illinois. For the validation cohort, we identified patients who underwent ADAMTS13 activity testing between 2010 and 2025 for evaluation of thrombotic microangiopathy at the Mayo Clinic. iTTP was defined as ADAMTS13 activity <10%, and controls as ADAMTS13 activity >20%. TTP-14 variables were collected at initial presentation: platelet count, lactate dehydrogenase, creatinine, international normalized ratio, reticulocyte percentage, active cancer, indirect bilirubin, mean corpuscular volume, total bilirubin, haptoglobin, neurologic deficit, hemoglobin, age, and history of transplant. Receiver operating characteristic curve (AUC) was reported with 95% confidence intervals (CI). While the model provides a continuous estimate and is not categorical, we evaluated clinically meaningful probability thresholds to illustrate performance in decision-relevant zones. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were reported at these select thresholds and analyzed for patients with and without missing variables. Result We included 50 iTTP patients and 56 controls in the external validation cohort. 13 patients had missing PLASMIC variables. TTP-14 achieved an AUC of 0.96 (95% CI: 0.93–0.99), outperforming the PLASMIC score's AUC of 0.90 (95% CI: 0.83–0.96) in the same dataset, and improving upon TTP-14's previously reported cross-validated AUC of 0.91 (95% CI: 0.90–0.92) in the development cohort. Among patients with complete data (n = 93), applying select thresholds for clinical relevance demonstrated: Low risk cut-off (<5% predicted iTTP risk): Sensitivity = 98% Specificity = 71% PPV = 76% NPV = 97% Accuracy = 84% High risk cut-off (≥50% predicted iTTP risk): Sensitivity = 71% Specificity = 98% PPV = 97% NPV = 78% Accuracy = 85% In the full cohort (n = 106) that included those with missing PLASMIC variables, TTP-14 maintained excellent predictive performance with AUC = 0.95 (95% CI: 0.92–0.99). Performance metrics analyzed using the above thresholds also yielded similar results. Conclusion External validation of TTP-14 demonstrated high predictive accuracy for iTTP diagnosis (AUC = 0.96). TTP-14 outperformed the PLASMIC score in the validation cohort (AUC = 0.96 vs 0.90, respectively). TTP-14 offers more flexibility than the PLASMIC score by generating predictions even with incomplete data, and maintained excellent performance in the cohort that included those with missing variables (AUC = 0.95) Its refined accuracy and ability to predict iTTP despite missing data provide a key advantage, offering an alternative tool to improve rapid iTTP diagnosis. TTP-14 may help enhance early recognition and treatment of iTTP while reducing unnecessary interventions in non-TTP patients.