Discriminant Model Research Articles

Machine Learning to Predict Pregnancy in Dairy Cows: An Approach Integrating Automated Activity Monitoring and On-Farm Data.

Automated activity monitoring (AAM) systems are critical in the dairy industry for detecting estrus and optimizing the timing of artificial insemination (AI), thus enhancing pregnancy success rates in cows. This study developed a predictive model to improve pregnancy success by integrating AAM data with cow-specific and environmental factors. Utilizing data from 1,054 cows, this study compared the pregnancy outcomes between two AI timings-8 or 10 h post-AAM alarm. Variables such as age, parity, body condition, locomotion, and vaginal discharge scores, peripartum diseases, the breeding program, the bull used for AI, milk production at the time of AI, and environmental conditions (season, relative humidity, and temperature-humidity index) were considered alongside the AAM data on rumination, activity, and estrus intensity. Six predictive models were assessed to determine their efficacy in predicting pregnancy success: logistic regression, Bagged AdaBoost algorithm, linear discriminant, random forest, support vector machine, and Bagged Classification Tree. Integrating the on-farm data with AAM significantly enhanced the pregnancy prediction accuracy at AI compared to using AAM data alone. The random forest models showed a superior performance, with the highest Kappa statistic and lowest false positive rates. The linear discriminant and logistic regression models demonstrated the best accuracy, minimal false negatives, and the highest area under the curve. These findings suggest that combining on-farm and AAM data can significantly improve reproductive management in the dairy industry.

Estimation of the earlywood and latewood ratio with different particle size of dry and wet milled Japanese cedar wood flour by using hyperspectral imaging

Mechanical properties of wood–plastic composites are influenced by a particle size and surface morphology of wood flour. Generally various sizes of wood flour are produced from single solid wood even if the single process is used. If the different particle size of wood flour is produced from different wood tissue such as earlywood (EW) and latewood (LW), not only particle size but also density and chemical composition of wood flour might influence the mechanical property of final products. This study aims to investigate the relationship between particle size and their origin; EW and LW. EW and LW were separately milled to produce the EW and LW flour by dry and wet milling. Hyperspectral images ranging 400–1000 nm for each wood flour were used as training data. Discriminant model of EW and LW flour developed by PLS-DA showed over 0.77 of accuracy. Then the EW and LW were dry and wet milled together and screened by three different sieve openings to obtain different particle size wood flour. Discriminant model was applied for the hyperspectral images of each size of wood flour to estimate the EW and LW ratio. The result showed that increasing sieve opening resulted in the increasing ratio of LW for dry milled wood flours. The results suggest that the EW was easily pulverized than LW.

Exploring Alternative Approaches to Language Modeling for Learning from Data and Knowledge

Despite their extensive application in language understanding tasks, large language models (LLMs) still encounter challenges including hallucinations - occasional fabrication of information - and alignment issues - lack of associations with human-curated world models (e.g., intuitive physics or common-sense knowledge). Moreover, the black-box nature of LLMs presents significant obstacles in training them effectively to achieve desired behaviors. In particular, modifying the concept embedding spaces of LLMs can be highly intractable. This process involves analyzing the implicit impact of such adjustments on the myriad parameters within LLMs and the resulting inductive biases. We propose a novel architecture that wraps powerful function approximation architectures within an outer, interpretable read-out layer. This read-out layer can be scrutinized to explicitly observe the effects of concept modeling during the training of the LLM. Our method stands in contrast with gradient-based implicit mechanisms, which depend solely on adjustments to the LLM parameters and thus evade scrutiny. By conducting extensive experiments across both generative and discriminative language modeling tasks, we evaluate the capabilities of our proposed architecture relative to state-of-the-art LLMs of similar sizes. Additionally, we offer a qualitative examination of the interpretable read-out layer and visualize the concepts it captures. The results demonstrate the potential of our approach for effectively controlling LLM hallucinations and enhancing the alignment with human expectations.

Comparative Analysis between Quality of Life and Human Labor in Countries Belonging to G7 and BRICS Blocks: Proposition of Discriminant Analysis Model

The aim of the present research is to identify and analyze the variables which help to effectively differentiate Quality of Life (QoL) and human labor in the G7 (Germany, France, Italy, Canada, Japan, United Kingdom, and United States of America—USA) and BRICS countries (Brazil, Russia, India, China, and South Africa) through a discriminant analysis. A discriminant analysis model is developed to classify countries as having a low, mid, or high QoL based on QoL and human labor variables. The variables used in the discriminant analysis were obtained between 2010 and 2022 from two platforms: NUMBEO variables capable of relating QoL to socioeconomic aspects and OECD’s (Organization for Economic Cooperation and Development) human-labor-related variables. Based on the results, the three variables that most discriminate the groups in order of importance are employed women in relation to the female population, the female labor force participation rate, and the female unemployment rate. Countries are classified as having a low, mid, or high QoL. The adopted technique will allow researchers and managers to classify and draw goals for action reorganization and investment in QoL and labor.

Physicochemical parameters combined flash GC e-nose and NIR for quality and volatile characterization of Zhenjiang vinegar with different aging time

In order to clarify the scientific connotation of the processing adjuvant vinegar of “the aging the better”, the physicochemical indexes, antioxidant activity in vitro, odor characteristics and NIR spectrum characteristics of Zhenjiang vinegar with different aging time were comprehensively studied, and the compositional characterization by UPLC-MS. The results showed that the physicochemical quality of Zhenjiang vinegar increased rapidly during the 2–3 years, entered a rising stable period during the 5–8 years and entered a sudden increase period during the 8–10 years of fermentation. Overall, it was in line with the trend that “the aging the better”. The study further characterized the odor changes of different aging time samples, established a fast and non-damage SVM discriminant model based on NIR spectral characteristics (accuracy 100 %), and 753 components were characterized by UPLC-MS, in order to provide a reference for the quality evaluation and standard improvement of Zhenjiang vinegar and processing adjuvant.

Associations between serum ferritin baselines and trajectories and the incidence of metabolic dysfunction-associated steatotic liver disease: a prospective cohort study.

Evidence from prospective cohort studies on the relationship between metabolic dysfunction-associated steatotic liver disease (MASLD) and longitudinal changes in serum ferritin (SF) still limited. This study aimed to investigate the associations of SF baselines and trajectories with new-onset MASLD and to present a MASLD discriminant model. A total of 1895 participants who attended health examinations at least three times in a hospital in Dalian City between 2015 and 2022 were included. The main outcome was the incidence of MASLD. The associations between SF baselines and trajectories with the risk of MASLD were analyzed by Cox proportional hazards regression, restricted cubic spline (RCS) analysis and time-dependent receiver operating characteristic (ROC) curve analysis. In addition, a MASLD discrimination model was established using logistic regression analyses. Among the 1895 participants, 492 developed MASLD during follow-up. Kaplan-Meier analysis indicated that participants in the low-stable trajectory group had a longer MASLD-free time compared with participants in other groups. Compared with those in the low-stable trajectory group, the adjusted hazard ratios (HRs) with 95% confidence intervals (CIs) for the risk of new-onset MASLD in the medium-high, high-stable and high-high trajectory groups were 1.54(1.18-2.00), 1.77(1.35-2.32) and 1.55(1.07-2.26), respectively (Ptrend < 0.001). The results were robust in subgroup and sensitivity analyses. Multivariate Cox proportional regression showed that SF was an independent risk factor of MASLD (HR = 1.002, 95%CI: 1.000-1.003, P = 0.003). The restricted cubic spline demonstrated a nonlinear relationship between SF and the risk of MASLD. The 8-variable model had high discriminative performance, good accuracy and clinical effectiveness. The ROC curve results showed that AUC was greater than that of the FLI, HSI and ZJU models (all P < 0.01). Not only a higher baseline SF but also SF changing trajectory are significantly associated with risk of new-onset MASLD. SF could be a predictor of the occurrence of MASLD.

Stellar atmospheric parameters from Gaia BP/RP spectra using uncertain neural networks

ABSTRACT With the plentiful information available in the Gaia BP/RP spectra, there is significant scope for applying discriminative models to extract stellar atmospheric parameters and abundances. We describe an approach to leverage an ‘Uncertain Neural Network’ model trained on APOGEE data to provide high-quality predictions with robust estimates for per-prediction uncertainty. We report median formal uncertainties of 0.068 dex, 69.1 K, 0.14 dex, 0.031 dex, 0.040 dex, and 0.029 dex for [Fe/H], Teff, log g, [C/Fe], [N/Fe], and [α/M], respectively. We validate these predictions against our APOGEE training data, LAMOST, and Gaia GSP-phot stellar parameters, and see a strong correlation between our predicted parameters and those derived from these surveys. We investigate the information content of the spectra by considering the ‘attention’ our model pays to different spectral features compared to expectations from synthetic spectra calculations. Our model’s predictions are applied to the Gaia data set, and we produce a publicly available catalogue of our model’s predictions.

Mode Collapse Detection Strategies in Generative Adversarial Networks for Credit Card Fraud Detection

A Generative Adversarial Network (GAN) is an artifi- cial intelligence model developed specifically to pro- duce synthetic data that resembles real data by training a generative model and a discriminative model simulta- neously using adversarial training. A GAN can be ex- tensively used for generating replicated data, however, it suffers from several issues, one of which is mode col- lapse. Mode collapse takes place when the generator is unable to capture the complete range of diversity in the target data distribution, resulting in the production of limited and repeating variations of samples. Multiple metrics exist to quantify mode collapse in GANs, al- though no individual metric is capable of consistently providing accurate results. This research focuses on the critical need for accurate mode collapse detection tech- niques in GANs, to strengthen the credit card fraud detection systems. In this work, we utilize a GAN to generate numerical data instead of image data. Our ap- proach utilizes a wide range of measures, such as Gener- ator and Discriminator Loss, Wasserstein Distance, pre- cision, recall, and visualization tools, to provide a com- prehensive framework for detecting mode collapse. In addition, we introduce an alert mechanism that identi- fies possible mode collapse at an early stage, allowing for earlier intervention and modifications to the training process. We have further proposed suggestions regard- ing monitoring and analyzing generator and discrimina- tor loss values to identify potential instances of mode collapse to help the developer optimize GAN training and improve the quality of synthetic data.

Lattice-Based Generation of Euclidean Geometry Figures

We present a user-guided method to generate geometry figures appropriate for high school Euclidean geometry courses: a useful starting point for an intelligent tutoring system to provide meaningful, realistic figures for study. We first establish that a two-dimensional geometry figure can be represented abstractly using a complete, lattice we call a geometry figure lattice (GFL). As input, we take a user-defined vector of primitive geometry shapes and convert each into a GFL. We then exhaustively combine each these ‘primitive’ GFLs into a set of complex GFLs using a process we call gluing. We mitigate redundancy in GFLs by introducing a polynomial-time algorithm for determining if two GFLs are isomorphic. These lattices act as a template for the second step: instantiating GFLs into a sequence of concrete geometry figures. To identify figures that are structurally similar to textbook problems, we use a discriminator model trained on a corpus of textbook geometry figures.

Elevated SCN11A concentrations associated with lower serum lipid levels in patients with major depressive disorder

The pathogenesis of major depressive disorder (MDD) involves lipid metabolism. Our earlier research also revealed that MDD patients had much lower total cholesterol (TC) concentrations than healthy controls (HCs). However, it is still unclear why TC decreased in MDD. Here, based on the Ingenuity Knowledge Base’s ingenuity pathway analysis, we found that sodium voltage-gated channel alpha subunit 11A (SCN11A) might serve as a link between low lipid levels and MDD. We analyzed the TC levels and used ELISA kits to measure the levels of SCN11A in the serum from 139 MDD patients, and 65 HCs to confirm this theory and explore the potential involvement of SCN11A in MDD. The findings revealed that TC levels were considerably lower and SCN11A levels were remarkably increased in MDD patients than those in HCs, while they were significantly reversed in drug-treatment MDD patients than in drug-naïve MDD patients. There was no significant difference in SCN11A levels among MDD patients who used single or multiple antidepressants, and selective serotonin reuptake inhibitors or other antidepressants. Pearson correlation analysis showed that the levels of TC and SCN11A were linked with the Hamilton Depression Rating Scales score. A substantial association was also found between TC and SCN11A. Moreover, a discriminative model made up of SCN11A was discovered, which produced an area under a curve of 0.9571 in the training set and 0.9357 in the testing set. Taken together, our findings indicated that SCN11A may serve as a link between low lipid levels and MDD, and showed promise as a candidate biomarker for MDD.

Exploring facial cues: automated deception detection using artificial intelligence

Deception detection is an interdisciplinary field attracting researchers from psychology, criminology, computer science, and economics. Automated deception detection presents unique challenges compared to traditional polygraph tests, but also offers novel economic applications. In this spirit, we propose an approach combining deep learning with discriminative models for deception detection. Therefore, we train CNNs for the facial modalities of gaze, head pose, and facial expressions, allowing us to compute facial cues. Due to the very limited availability of training data for deception, we utilize early fusion on the CNN outputs to perform deception classification. We evaluate our approach on five datasets, including four well-known publicly available datasets and a new economically motivated rolling dice experiment. Results reveal performance differences among modalities, with facial expressions outperforming gaze and head pose overall. Combining multiple modalities and feature selection consistently enhances detection performance. The observed variations in expressed features across datasets with different contexts affirm the importance of scenario-specific training data for effective deception detection, further indicating the influence of context on deceptive behavior. Cross-dataset experiments reinforce these findings. Notably, low-stake datasets, including the rolling dice Experiment, present more challenges for deception detection compared to the high-stake Real-Life trials dataset. Nevertheless, various evaluation measures show deception detection performance surpassing chance levels. Our proposed approach and comprehensive evaluation highlight the challenges and potential of automating deception detection from facial cues, offering promise for future research.

Construction of Discrimination Models of Cationic Drugs for Phospholipidosis Induction Potential by Using Interaction Data with Immobilized Artificial Membrane as Well as Physicochemical Properties

Accurate prediction of the phospholipidosis–induction risk of drugs at early stages is important in drug development. So far, discrimination models for predicting the induction risk of cationic drugs have been proposed, but it is still challenging to accurately predict the risk of cationic drugs with intermediate hydrophobicity (logP). In this study, we introduced a parameter (Δlogk40) reflecting not only hydrophobic interaction but also interactions with the polar headgroup between cationic drugs and phospholipids, obtained with liquid chromatography using an immobilized artificial membrane column. The parameter was used along with other physicochemical properties as features to construct discrimination models. Linear discriminant analysis, the modified Mahalanobis discriminant analysis, support vector machine, and random forest were employed for model construction. The results showed that all discrimination models exhibited good predictive performance, with the modified Mahalanobis discriminant analysis and random forest providing the best results for cationic drugs, suggesting that the usefulness of the parameter reflecting complex interactions between cationic drugs and immobilized artificial membrane for constructing discrimination models to predict the induction risk. Furthermore, by applying the parameter as a feature in constructing discrimination models, we demonstrated an improvement in the predictive performance for drugs with intermediate hydrophobicity.

SSC and pH prediction and maturity classification of grapes based on hyperspectral imaging

Soluble solids content (SSC) and pH of red globe grapes are crucial measures of quality. In this paper, we used hyperspectral imaging technology to achieve nondestructive detection and distribution visualization of SSC and pH of red globe grapes. First, the hyperspectral images of samples were collected. Then, CARS, SPA, GA, IRIV were used to extract feature variables from raw spectral (RAW) information. The PLSR prediction models of samples were developed. By comparing the different prediction models, RAW-IRIV-PLSR was selected as the optimal model. Finally, the SSC and pH of the samples were calculated to obtain a grayscale image and perform a pseudo-color transformation to visualize the distribution of SSC and pH. By studying the classification of the maturity of samples, it was concluded that the best discriminant classification model of maturity was RAW-IRIV-ELM. Hyperspectral also provided a new method for maturity stage classification of red globe grapes.

The Influence of the Soil Profile on the Formation of the Elemental Image of Grapes and Wine of the Cabernet Sauvignon Variety.

The features for assessing the authenticity of wines by region of origin are studied, based on the relationship between the mineral composition of the wine, the grapes, and the soil profile (0 to 160 cm) from the place of growth of Cabernet Sauvignon grapes. Soil, grape, and wine samples were taken from the territories of six vineyards in the Anapa district of Krasnodar Territory, Russia. Using the methods of ICP-OES, thermal, and X-ray phase analysis, the soils were differentiated into three groups, differing in mineralogical and mineral compositions. The soil samples of the first group contained up to 31% quartz, the second group up to 25% quartz and 19% mixed calcite, and the third group up to 32% calcite and 15% quartz. The formation of the elemental image of the grapes was studied, taking into account the total content and mobile forms of metals in the soil. The territorial proximity of the vineyards did not affect the extraction of elements from the soil into the grape berry, and the migration of metals for each territory was selective. According to the values of the biological absorption coefficient, the degree of transition of metals from the soil to a berry was estimated. For K, Ti, Zn, Rb, Cu, and Fe in all berries, the coefficient was higher than 1.00, which means that the berry extracts contained not only mobile-form, but also difficult-to-dissolve metal compounds. The migration of macro-components from the soil to the berry was low, and amounted to 6-7% for Ca, 0.8-3.0% for Na, and 25-70% for Mg of the concentration of their mobile forms. For all territories, the maximum correlation between metal concentrations in grapes and soil was observed for samples from a depth of 0-40 cm. The discriminant model based on concentrations of Rb, Al, K, Sr, Co, Na, Pb, Ca, and Ni showed the formation of clusters in the territories of vineyard cultivation. The developed model allow the problems of identifying wines by region to be solved with high accuracy, using their elemental image.

Exogenous curcumin mitigates As stress in spinach plants: A biochemical and metabolomics investigation

The spinach (S. oleracea L.) was used as a model plant to investigate As toxicity on physio-biochemical processes, exploring the potential mitigation effect of curcumin (Cur) applied exogenously at three concentrations (1, 10, and 20 μM Cur). The employment of Cur significantly mitigated As-induced stress in spinach photosynthetic performance (Fv/Fm, Fo/Fm, and Fv/Fo). Moreover, the co-incubation of Cur with As improved physiological processes mainly associated with plant water systems affected by As stress by recovering the leaf's relative water content (RWC) and osmotic potential (ψπ) nearly to the control level and increasing the transpiration rate (E; 39–59%), stomatal conductivity (gs; 86–116%), and carbon assimilation rate (A; 84–121%) compared to As stressed plants. The beneficial effect of Cur in coping with As-induced stress was also assessed at the plant's oxidative level by reducing oxidative stress biomarkers (H2O2 and MDA) and increasing non-enzymatic antioxidant capacity.Untargeted metabolomics analysis was adopted to investigate the main processes affected by As and Cur application. A multifactorial ANOVA discrimination model (AMOPLS-DA) and canonical correlation analysis (rCCA) were employed to identify relevant metabolic changes and biomarkers associated with Cur and As treatments. The results highlighted that Cur significantly determined the accumulation of glucosinolates, phenolic compounds, and an increase in glutathione redox cycle activities, suggesting an overall elicitation of plant secondary metabolisms. Specifically, the correlation analysis reported a strong and positive correlation between (+)-dihydrokaempferol, L-phenylalanine (precursor of phenolic compounds), and serotonin-related metabolites with antioxidant activities (ABTS and DPPH), suggesting the involvement of Cur application in promoting a cross-talk between ROS signaling and phytohormones, especially melatonin and serotonin, working coordinately to alleviate As-induced oxidative stress. The modulation of plant metabolism was also observed at the level of amino acids, fatty acids, and secondary metabolites synthesis, including N-containing compounds, terpenes, and phenylpropanoids to cooperate with As-induced stress response.

Research on Discriminant Model of Water Inrush Source By Principal Component-cluster Analysis in Jiaozuo Mining Area

This paper takes Jiaozuo Mining Area as the research object, based on the analysis of the hydrogeological conditions of the mining area, expounds the characteristics of coal strata, aquifers and groundwater recharge, runoff and discharge in the mining area; analyses the water inrush sources and water diversion channels in the mining area, analyses the routine water chemical data of each aquifer in the mining area, draws the piper three-line diagram and confirms it. To determine the hydrochemical type of groundwater in aquifer, six common water chemical ions are used as discriminant factors, a discriminant model of water inrush source is established by combining principal component analysis and cluster analysis, and the principal component of conventional water chemical ions is extracted as cluster variable to discriminate Water Inrush Source in Jiaozuo Mining Area. In order to prove the rationality and validity of the model, another group of inrush sources in Jiaozuo Mining Area is discussed. The water sample data are discriminated and the results obtained by cluster analysis are compared to verify the accuracy of the model. The results show that the model is feasible. To sum up, the identification model of inrush water source by principal component-cluster analysis can accurately and effectively identify the source of inrush water in Jiaozuo Mining Area.

Evaluating precision medicine tools in cystic fibrosis for racial and ethnic fairness.

Patients with cystic fibrosis (CF) experience frequent episodes of acute decline in lung function called pulmonary exacerbations (PEx). An existing clinical and place-based precision medicine algorithm that accurately predicts PEx could include racial and ethnic biases in clinical and geospatial training data, leading to unintentional exacerbation of health inequities. We estimated receiver operating characteristic curves based on predictions from a nonstationary Gaussian stochastic process model for PEx within 3, 6, and 12 months among 26,392 individuals aged 6 years and above (2003-2017) from the US CF Foundation Patient Registry. We screened predictors to identify reasons for discriminatory model performance. The precision medicine algorithm performed worse predicting a PEx among Black patients when compared with White patients or to patients of another race for all three prediction horizons. There was little to no difference in prediction accuracies among Hispanic and non-Hispanic patients for the same prediction horizons. Differences in F508del, smoking households, secondhand smoke exposure, primary and secondary road densities, distance and drive time to the CF center, and average number of clinical evaluations were key factors associated with race. Racial differences in prediction accuracies from our PEx precision medicine algorithm exist. Misclassification of future PEx was attributable to several underlying factors that correspond to race: CF mutation, location where the patient lives, and clinical awareness. Associations of our proxies with race for CF-related health outcomes can lead to systemic racism in data collection and in prediction accuracies from precision medicine algorithms constructed from it.

Analysis of quantum key distribution based on unified model of sequential state discrimination strategy

The quantum key distribution for multiparty is one of the essential subjects of study. Especially, without using entangled states, performing the quantum key distribution for multiparty is a critical area of research. For this purpose, sequential state discrimination, which provides multiparty quantum communication and quantum key distribution for multiple receivers, has recently been introduced. Moreover, the sequential state discrimination is applicable for the security analysis against an eavesdropper’s attack. In this work, we provide the security analysis of quantum key distribution by proposing a unified model of sequential state discrimination including an eavesdropper. In this model, the success probability of eavesdropping is used as a figure of merit for the security analysis. Moreover, we obtain a non-zero secret key rate between the sender and receiver, which implies that the sender and receiver can share a secret key despite the eavesdropper’s scheme that optimizing the success probability of eavesdropping. Further, we propose an experimental methodology for the proposed model, which is implementable with linear optics. We observe that the secret key between the sender and receiver can be non-zero, even with imperfections.

A Dataset for Evaluating Contextualized Representation of Biomedical Concepts in Language Models

Due to the complexity of the biomedical domain, the ability to capture semantically meaningful representations of terms in context is a long-standing challenge. Despite important progress in the past years, no evaluation benchmark has been developed to evaluate how well language models represent biomedical concepts according to their corresponding context. Inspired by the Word-in-Context (WiC) benchmark, in which word sense disambiguation is reformulated as a binary classification task, we propose a novel dataset, BioWiC, to evaluate the ability of language models to encode biomedical terms in context. BioWiC comprises 20’156 instances, covering over 7’400 unique biomedical terms, making it the largest WiC dataset in the biomedical domain. We evaluate BioWiC both intrinsically and extrinsically and show that it could be used as a reliable benchmark for evaluating context-dependent embeddings in biomedical corpora. In addition, we conduct several experiments using a variety of discriminative and generative large language models to establish robust baselines that can serve as a foundation for future research.

Aging of deep venous thrombosis in-vivo using polarization sensitive optical coherence tomography.

Deep venous thrombosis (DVT) is a medical condition with significant post-event morbidity and mortality coupled with limited treatment options. Treatment strategy and efficacy are highly dependent on the structural composition of the thrombus, which evolves over time from initial formation and is currently unevaluable with standard clinical testing. Here, we investigate the use of intravascular polarization-sensitive optical coherence tomography (PS-OCT) to assess thrombus morphology and composition in a rat DVT model in-vivo, including changes that occur over the thrombus aging process. PS-OCT measures tissue birefringence, which provides contrast for collagen and smooth muscle cells that are present in older, chronic clots. Thrombi in the inferior vena cava of two cohorts of rats were imaged in-vivo with intravascular PS-OCT at 24 hours (acute, nrats = 3, 73 cross-sections) or 28 days (chronic, nrats = 4, 41 cross-sections) after thrombus formation. Co-registered histology was labelled by an independent pathologist to establish ground-truth clot composition. Automated analysis of OCT cross-sectional images differentiated acute and chronic thrombi with 97.6% sensitivity and 98.6% specificity using a linear discriminant model comprised of both polarization and conventional OCT metrics. These results support PS-OCT as a highly sensitive imaging modality for the assessment of DVT composition to differentiate acute and chronic thrombi. Intravascular PS-OCT imaging could be integrated with advanced catheter-based treatment strategies and serve to guide therapeutic decision-making and deployment, by offering an accurate assessment of DVT patients in real time.