Classification Stage Research Articles

A Graph-Informed Modeling Framework Empowering Gene Pathway Discovery.

This study introduces a novel graph-informed modeling framework for improving the statistical analysis of gene expression data, particularly in the context of identifying differentially expressed gene pathways and gene expression-assisted disease classification in a high-dimensional data setting. By integrating gene regulatory network information into hypothesis testing for the difference between mean vectors and linear discriminant analysis, we aim to effectively capture and utilize previously validated external gene interaction information. Our method leverages a block-coordinate descent approach which enables us to incorporate mixed graph information into linear structural equation modeling, accommodating directed/undirected edges and potential cycles in gene regulatory networks. Extensive simulations under various data scenarios have demonstrated the effectiveness of our approach with improved power for gene pathway tests and disease classification over existing methods. An application to a lung cancer dataset from the Cancer Genome Atlas Program (TCGA) further exemplifies the potential of our graph-informed approach in empowering the detection of differentially expressed gene pathways and gene expression-based classification of different lung cancer stages. Our findings underscore the potential utility of incorporating gene regulatory network information in gene pathway analysis, setting the stage for future advancements in gene pathway discovery, disease diagnosis, and treatment strategies.

Identification of morphologically similar genera based on reproductive systems and immature stages: a case study of Anastatus and Mesocomys (Hymenoptera: Eupelmidae)

Abstract Parallel or convergent evolution may result in phenotypically closely similar species. Many studies have reported that using solely traditional external morphological features can result in misidentification. Here, we discuss using the reproductive systems and immature developmental stages for scientific classification in Eupelmidae (Hymenoptera: Chalcidoidea), exemplifying with Anastatus Motschulsky and Mesocomys Cameron (Eupelmidae, Eupelminae). Results show that there are at least 6 distinct differences in the immature stages and the reproductive systems of the adults between species of the 2 genera: (1) the terminal ends of the left and right ovarioles are connected together in the studied species of Anastatus but not in Mesocomys, (2) the base of the lateral oviduct of Anastatus has a diverticulum that is lobate-shaped, whereas this diverticulum is spherical in Mesocomys, (3) the peduncle of the egg of Anastatus is significantly longer than that of Mesocomys, (4) the head capsule of the terminal instar larvae of Anastatus is uniformly translucent, whereas in Mesocomys it has a brown pattern, (5) the ocelli of the Anastatus pupa are smooth and slightly raised whereas the ocelli of Mesocomys each have a long filament each, and (6) the phallobase of adult male Anastatus is sharp basally but rounded in Mesocomys. Our findings not only provide novel insights for the differentiation of similar genera that can be difficult to distinguish in the immature stages but also provide a more comprehensive theoretical basis for clarifying the evolutionary and phylogenic status of Anastatus and Mesocomys.

Automatic sleep stage classification using deep learning: signals, data representation, and neural networks

In clinical practice, sleep stage classification (SSC) is a crucial step for physicians in sleep assessment and sleep disorder diagnosis. However, traditional sleep stage classification relies on manual work by sleep experts, which is time-consuming and labor-intensive. Faced with this obstacle, computer-aided diagnosis (CAD) has the potential to become an intelligent assistant tool for sleep experts, aiding doctors in the assessment and decision-making process. In fact, in recent years, CAD supported by artificial intelligence, especially deep learning (DL) techniques, has been widely applied in SSC. DL offers higher accuracy and lower costs, making a significant impact. In this paper, we will systematically review SSC research based on DL methods (DL-SSC). We explores DL-SSC from several important perspectives, including signal and data representation, data preprocessing, deep learning models, and performance evaluation. Specifically, this paper addresses three main questions: (1) What signals can DL-SSC use? (2) What are the various methods to represent these signals? (3) What are the effective DL models? Through addressing on these questions, this paper will provide a comprehensive overview of DL-SSC.

A novel approach to enhance feature selection using linearity assessment with ordinary least squares regression for Alzheimer’s Disease stage classification

A novel approach to enhance feature selection using linearity assessment with ordinary least squares regression for Alzheimer’s Disease stage classification

Simple Exostectomy and Tarsal Tunnel Release for a Rocker Bottom Deformity in a Diabetic Charcot Arthropathy Foot—An Addition to the Eichenholtz Stage Classification of Charcot Arthropathy: A Case Report

Simple Exostectomy and Tarsal Tunnel Release for a Rocker Bottom Deformity in a Diabetic Charcot Arthropathy Foot—An Addition to the Eichenholtz Stage Classification of Charcot Arthropathy: A Case Report

An enzyme-inspired specificity in deep learning model for sleep stage classification using multi-channel PSG signals input: Separating training approach and its performance on cross-dataset validation for generalizability

Numerous automatic sleep stage classification systems have been developed, but none have become effective assistive tools for sleep technicians due to issues with generalization. Four key factors hinder the generalization of these models are instruments, montage of recording, subject type, and scoring manual factors. This study aimed to develop a deep learning model that addresses generalization problems by integrating enzyme-inspired specificity and employing separating training approaches. Subject type and scoring manual factors were controlled, while the focus was on instruments and montage of recording factors. The proposed model consists of three sets of signal-specific models including EEG-, EOG-, and EMG-specific model. The EEG-specific models further include three sets of channel-specific models. All signal-specific and channel-specific models were established with data manipulation and weighted loss strategies, resulting in three sets of data manipulation models and class-specific models, respectively. These models were CNNs. Additionally, BiLSTM models were applied to EEG- and EOG-specific models to obtain temporal information. Finally, classification task for sleep stage was handled by ‘the-last-dense’ layer. The optimal sampling frequency for each physiological signal was identified and used during the training process. The proposed model was trained on MGH dataset and evaluated using both within dataset and cross-dataset. For MGH dataset, overall accuracy of 81.05 %, MF1 of 79.05 %, Kappa of 0.7408, and per-class F1-scores: W (84.98 %), N1 (58.06 %), N2 (84.82 %), N3 (79.20 %), and REM (88.17 %) can be achieved. Performances on cross-datasets are as follows: SHHS1 200 records reached 79.54 %, 70.56 %, and 0.7078; SHHS2 200 records achieved 76.77 %, 66.30 %, and 0.6632; Sleep-EDF 153 records gained 78.52 %, 72.13 %, and 0.7031; and BCI-MU (local dataset) 94 records achieved 83.57 %, 82.17 %, and 0.7769 for overall accuracy, MF1, and Kappa respectively. Additionally, the proposed model has approximately 9.3 M trainable parameters and takes around 26 s to process one PSG record. The results indicate that the proposed model demonstrates generalizability in sleep stage classification and shows potential as a feasibility tool for real-world applications. Additionally, enzyme-inspired specificity effectively addresses the challenges posed by varying montage of recording, while the identified optimal frequencies mitigate instrument-related issues.

Stages of formation of artistic skills of art students

The author's elaboration of the stages of formation of artistic and visual skills of students of higher education institutions in the process of creative activity is disclosed and presented in the article for general consideration. The analysis of scientific, psychological-pedagogical and educational-methodical achievements of scientists was carried out in order to specify the content of the concept of "skill", classification of types and stages of the process of formation of skills. The subject of our research "artistic skills" is presented on the basis of thorough theoretical studies of scientists, the idea of ​​the concept of professional and artistic skills of fine art teachers is expanded, a generalization is made regarding the diversity of their types, to which we include artistic-technical, artistic-methodical, artistic-workshop and artistic - visual skills, which are also divided into their own subspecies. In the process of scientific research, the concept of psychological and pedagogical foundations of "formation of artistic skills" and the "exercise" method of generalizing its types and kinds were considered. A list of effective means of the system of educational tasks for art students of higher educational institutions is proposed for consideration, namely, technical methods and techniques in working with soft materials, such as: method - hatching, extinguishing, mixing colors, etc.; technique - side shading, shading, dry washing, wet brush, pen and others. Based on modern theoretical and scientific developments and conceptual ideas of scientists regarding the procedure of "formation of artistic skills", relying on our own professional experience, we reveal the essence and expediency of each of the six stages: organizational, diagnostic, analytical, systematic, synthetic and automation. In accordance with the presented stages, goals, tasks, methods, ways, rules, advantages and disadvantages of their application in practice are determined. The formation of students' artistic skills is due to the use of a number of appropriate methods: scientifically pedagogical - organizational, communicative, instruction, demonstration, illustration, explanation, master class, research, control, verification, current, forecasting, competition, observation and evaluation; personally developed artistic and technical methods that contribute to the effective and rapid mastering of the specifics of performing new technical actions by students in artistic educational activities - "experimental-diagnostic", "differential-constructive", "constructive division", "constructive combination", "holistic-constructive" ", "variable-interval"

Handwritten Character Recognition using Enhanced Artificial Neural Network

This study addresses the concerns regarding the performance of Handwritten Character Recognition (HCR) systems, focusing on the classification stage. It is widely acknowledged that the development of the classification model significantly impacts the overall performance of HCR. The problems identified specifically pertain to the classification model, particularly in the context of the Artificial Neural Network (ANN) learning problem, leading to low accuracy in recognizing handwritten characters. The objective of this study is to improve and refine the ANN classification model to achieve better HCR. To achieve this goal, this study proposed a hybrid Flower Pollination Algorithm with Artificial Neural Network (FPA-ANN) classification model for HCR. The FPA is one of the metaheuristic approaches is utilized as an optimization technique to enhance the performance of ANN, particularly by optimizing the network training process of ANN. The experimentation phase involves using the National Institute of Standards and Technology (NIST) handwritten character database. Finally, the proposed FPA-ANN classification model is analyzed based on generated confusion matrix and evaluated performance of the classification model in terms of precision, sensitivity, specificity, F-score and accuracy.

SNAI1: a key modulator of survival in lung squamous cell carcinoma and its association with metastasis

BackgroundSnail family zinc finger 1 (SNAI1) has been implicated in cancer progression and prognosis across various malignancies. This study aims to elucidate the prognostic significance of SNAI1 expression in Lung Squamous Cell Carcinoma (LUSC) using data from The Cancer Genome Atlas (TCGA) database.MethodsSNAI1 expression levels in LUSC patients were stratified using X-tile software to establish optimal cut-off values. Kaplan-Meier survival analysis was performed to assess the impact of SNAI1 expression on overall survival (OS). Univariate and multivariate Cox regression analyses were conducted to evaluate the prognostic value of SNAI1, considering clinical parameters such as age, clinical stage, and TNM classification. Additionally, we explored the interaction between SNAI1 expression and metastatic status, and performed Gene Set Enrichment Analysis (GSEA) to investigate associated cellular pathways. Correlations between SNAI1 and immune checkpoint molecules were also examined.ResultsKaplan-Meier analysis revealed significant differences in OS among high, medium, and low SNAI1 expression groups (p < 0.001), with median survival times of 1.6, 3.0, and 5.8 years, respectively. Dichotomizing patients into high and low SNAI1 expression groups confirmed that high SNAI1 expression was associated with significantly poorer OS (p < 0.001). SNAI1 remained an independent prognostic factor in multivariate analysis. High SNAI1 expression correlated with poorer survival outcomes regardless of metastatic status, and the combination of high SNAI1 expression and metastasis resulted in the poorest survival. GSEA identified significant associations between SNAI1 and inflammatory, immune response pathways. Positive correlations were observed between SNAI1 and key immune checkpoint molecules, suggesting an interplay with immune checkpoint mechanisms.ConclusionsHigh SNAI1 expression is a robust prognostic indicator of poor survival in LUSC, independent of other clinical factors. Its association with immune checkpoint molecules highlights its potential as a therapeutic target. These findings underscore the prognostic and therapeutic relevance of SNAI1 in LUSC and possibly other cancers. Further research is warranted to explore targeted therapies against SNAI1.

Staining-Independent Malaria Parasite Detection and Life Stage Classification in Blood Smear Images

Malaria is a leading cause of morbidity and mortality in tropical and sub-tropical regions. This research proposed a malaria diagnosis system based on the you only look once algorithm for malaria parasite detection and the convolutional neural network algorithm for malaria parasite life stage classification. Two public datasets are utilized: MBB and MP-IDB. The MBB dataset includes human blood smears infected with Plasmodium vivax (P. vivax). While the MP-IDB dataset comprises 4 species of malaria parasites: P. vivax, P. ovale, P. malariae, and P. falciparum. Four distinct stages of life exist in every species, including ring, trophozoite, schizont, and gametocyte. For the MBB dataset, detection and classification accuracies of 0.92 and 0.93, respectively, were achieved. For the MP-IDB dataset, the proposed algorithms yielded the accuracies for detection and classification as follows: 0.84 and 0.94 for P. vivax; 0.82 and 0.93 for P. ovale; 0.79 and 0.93 for P. malariae; and 0.92 and 0.96 for P. falciparum. The detection results showed the models trained by P. vivax alone provide good detection capabilities also for other species of malaria parasites. The classification performance showed the proposed algorithms yielded good malaria parasite life stage classification performance. The future directions include collecting more data and exploring more sophisticated algorithms.

Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement

ObjectivesThis study aimed to assess the accuracy of machine learning (ML) models with feature selection technique in classifying cervical vertebral maturation stages (CVMS). Consensus-based datasets were used for models training and evaluation for their model generalization capabilities on unseen datasets.MethodsThree clinicians independently rated CVMS on 1380 lateral cephalograms, resulting in the creation of five datasets: two consensus-based datasets (Complete Agreement and Majority Voting), and three datasets based on a single rater’s evaluations. Additionally, landmarks annotation of the second to fourth cervical vertebrae and patients’ information underwent a feature selection process. These datasets were used to train various ML models and identify the top-performing model for each dataset. These models were subsequently tested on their generalization capabilities.ResultsFeatures that considered significant in the consensus-based datasets were consistent with a CVMS guideline. The Support Vector Machine model on the Complete Agreement dataset achieved the highest accuracy (77.4%), followed by the Multi-Layer Perceptron model on the Majority Voting dataset (69.6%). Models from individual ratings showed lower accuracies (60.4–67.9%). The consensus-based training models also exhibited lower coefficient of variation (CV), indicating superior generalization capability compared to models from single raters.ConclusionML models trained on consensus-based datasets for CVMS classification exhibited the highest accuracy, with significant features consistent with the original CVMS guidelines. These models also showed robust generalization capabilities, underscoring the importance of dataset quality.

A CNN-Transformer-ConvLSTM-CRF Hybrid Network for Sleep Stage Classification

A CNN-Transformer-ConvLSTM-CRF Hybrid Network for Sleep Stage Classification

Deep neural networks integrating genomics and histopathological images for predicting stages and survival time-to-event in colon cancer.

There exists an unexplained diverse variation within the predefined colon cancer stages using only features from either genomics or histopathological whole slide images as prognostic factors. Unraveling this variation will bring about improved staging and treatment outcomes. Hence, motivated by the advancement of Deep Neural Network (DNN) libraries and complementary factors within some genomics datasets, we aggregate atypia patterns in histopathological images with diverse carcinogenic expression from mRNA, miRNA and DNA methylation as an integrative input source into a deep neural network for colon cancer stages classification, and samples stratification into low or high-risk survival groups. The genomics-only and integrated input features return Area Under Curve-Receiver Operating Characteristic curve (AUC-ROC) of 0.97 compared with AUC-ROC of 0.78 obtained when only image features are used for the stage's classification. A further analysis of prediction accuracy using the confusion matrix shows that the integrated features have a weakly improved accuracy of 0.08% more than the accuracy obtained with genomics features. Also, the extracted features were used to split the patients into low or high-risk survival groups. Among the 2,700 fused features, 1,836 (68%) features showed statistically significant survival probability differences in aggregating samples into either low or high between the two risk survival groups. Availability and Implementation: https://github.com/Ogundipe-L/EDCNN.

Analysis of Early-Stage Behavior and Multi-Parameter Early Warning Algorithm Research for Overcharge Thermal Runaway of Energy Storage LiFePO4 Battery Packs

Overcharging of lithium-ion batteries may lead to severe thermal runaway (TR) incidents, resulting in significant economic losses and safety hazards. Therefore, it is crucial to research early warning methods for TR behavior in overcharged lithium batteries. This study initially conducted overcharging experiments on LiFePO4 battery packs under different initial charging states and charging rates, analyzing variations in temperature, voltage, and inter-group pressure during overcharging. The TR process was divided into three stages: non-overcharged, early, and middle. Based on this, temperature change rate, pressure change rate, and voltage were extracted as input feature parameters, and the Mean Shift algorithm was employed for stage identification and classification of overcharging experiments on LiFePO4 battery packs. According to experimental results, the algorithm achieved an accuracy of over 96% in stage identification and classification of TR in overcharged lithium batteries, accurately determining the current stage of TR and providing a reliable and effective solution for preventing TR in overcharged lithium batteries.

Cardiogenic shock severity predicts bleeding events in patients with temporary mechanical circulatory support.

Data on shock severity and bleeding events in patients with temporary mechanical circulatory support (tMCS) are limited. We investigated the relationship between the Society for Cardiovascular Angiography and Interventions (SCAI) shock stage classification and bleeding events in patients with tMCS. We evaluated the data of 285 consecutive patients with tMCS who were admitted to our institution between June 2019 and May 2022. At the time of tMCS initiation, 81 patients (28.4%) were in SCAI stage A, 38 (13.3%) in stage B, 69 (24.2%) in stage C, 33 (11.6%) in stage D, and 64 (22.5%) in stage E. Multivariable logistic regression modeling was used to assess the association between the SCAI shock stage and in-hospital bleeding events. In-hospital bleeding occurred in 100 patients (35.1%). The bleeding event rate increased incrementally across the SCAI shock stages (stage A, 11.1%; stage B, 15.8%; stage C, 37.7%; stage D, 54.6%; stage E, 64.1%). In-hospital bleeding was associated with the SCAI shock stage (p < 0.001). Compared with stage A, the adjusted odds ratios for in-hospital bleeding were 1.48 (95% confidence interval [CI] 0.47-4.66), 6.47 (95% CI 2.61-10.66), 11.59 (95% CI 3.77-35.64), and 7.85 (95% CI 2.51-24.55) for stages B, C, D, and E, respectively. The SCAI shock stage predicted subsequent bleeding events in patients with tMCS. This simple scheme may be useful for tailored risk-based clinical assessment and management of patients with tMCS.

Treatment strategies for patients over 80 years of age with oral squamous cell carcinoma

ObjectiveTo analyze the clinical characteristics of patients with oral squamous cell carcinoma aged ≥80 years, focusing on surgical treatments. Study DesignWe reviewed patients with oral squamous cell carcinoma aged ≥80 years who underwent surgery between 2005 and 2018. Basic information, comorbidities, multiple primary cancers, initial treatment, complications, and outcomes were evaluated. ResultsOf 197 patients aged ≥80 years, 119 patients underwent surgery (50 males, 69 females; mean age: 83.5 years). The gingiva was the most common primary tumor site (63 patients, 52.9%). The stage classification was stage I in 35 patients (29.4%), stage II in 44 (37%), stage III in 16 (13.4%), stage IVA in 22 (18.5%), and stage IVB in 2 (1.7%). Comorbidities were identified in 112 patients (94.1%). Surgery was the initial treatment in 111 patients (93.3%). Eight (6.7%) patients received postoperative adjuvant chemotherapy/radiotherapy; 20 patients (16.8%) underwent free tissue transplantation. Perioperative complications were observed in 36 patients (30.3%). The cumulative 5-year and 10-year overall survival rates were 82% and 68.3%, respectively; the disease-specific survival rates were 90%. ConclusionGood treatment outcomes were obtained with radical surgery. Surgery should be the first choice if quality of life is assured and there are no issues with surgical tolerance, regardless of age.

A hybrid approach for power quality event identification in power systems: Elasticnet Regression decomposition and optimized probabilistic neural networks

The transformation of traditional grid networks towards smart-grid and microgrid concepts raises many critical issues, and quality in the power supply is one of the prominent ones that needs further research. Developing and applying power quality (PQ) recognition methods with efficient and reliable analysis are essential to the fast-growing issues related to modern smart power distribution systems. In this regard, a hybrid algorithm is proposed for PQ events detection and classification using Elasticnet Regression-based Variational Mode Decomposition (ER-VMD) and Salp Swarm Algorithm optimized Probabilistic Neural Network (SSA-PNN). The Elasticnet Regression (ER) process is suggested to modify the conventional VMD approach instead of the Tikhonov Regularization (TR) method to enhance performance and obtain better band-limited intrinsic mode functions. This idea results in robust and effective reconstruction features and helps to obtain accurate classification using the classifier. In the classification stage, a Salp Swarm Algorithm (SSA) based PNN is used for the PQ event, considering the relevant features obtained from ER-VMD. The system parameters often influence PNN performance, and SSA is used to determine the ideal values to improve the PNN's capacity for more accurate classification. The numerical values of the accuracy percentage, percentage of sensitivity, and percentage of specificity in the case of real-time data are found as 98.58, 100, and 98.46, respectively. The acquired comparison findings demonstrate the effectiveness and robustness of the proposed technique in terms of rapid learning speed, smaller computational complexity, robust performance for anti-noise conditions, and accurate identification and categorization.

Understanding the mechanism of injury and fracture pattern of paediatric triplane ankle fractures versus adult trimalleolar fractures.

Paediatric triplane fractures and adult trimalleolar ankle fractures both arise from a supination external rotation injury. By relating the experience of adult to paediatric fractures, clarification has been sought on the sequence of injury, ligament involvement, and fracture pattern of triplane fractures. This study explores the similarities between triplane and trimalleolar fractures for each stage of the Lauge-Hansen classification, with the aim of aiding reduction and fixation techniques. Imaging data of 83 paediatric patients with triplane fractures and 100 adult patients with trimalleolar fractures were collected, and their fracture morphology was compared using fracture maps. Visual fracture maps were assessed, classified, and compared with each other, to establish the progression of injury according to the Lauge-Hansen classification. Four stages of injury in triplane fractures, resembling the adult supination external rotation Lauge-Hansen stages, were observed. Stage I consists of rupture of the anterior syndesmosis or small avulsion of the anterolateral tibia in trimalleolar fractures, and the avulsion of a larger Tillaux fragment in triplanes. Stage II is defined as oblique fracturing of the fibula at the level of the syndesmosis, present in all trimalleolar fractures and in 30% (25/83) of triplane fractures. Stage III is the fracturing of the posterior malleolus. In trimalleolar fractures, the different Haraguchi types can be discerned. In triplane fractures, the delineation of the posterior fragment has a wave-like shape, which is part of the characteristic Y-pattern of triplane fractures, originating from the Tillaux fragment. Stage IV represents a fracture of the medial malleolus, which is highly variable in both the trimalleolar and triplane fractures. The paediatric triplane and adult trimalleolar fractures share common features according to the Lauge-Hansen classification. This highlights that the adolescent injury arises from a combination of ligament traction and a growth plate in the process of closing. With this knowledge, a specific sequence of reduction and optimal screw positions are recommended.

Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals.

Proper monitoring of anesthesia stages can guarantee the safe performance of clinical surgeries. In this study, different anesthesia stages were classified using near-infrared spectroscopy (NIRS) signals with machine learning. The cerebral hemodynamic variables of right proximal oxyhemoglobin (HbO2) in maintenance (MNT), emergence (EM) and the consciousness (CON) stage were collected and then the differences between the three stages were compared by phase-amplitude coupling (PAC). Then combined with time-domain including linear (mean, standard deviation, max, min and range), nonlinear (sample entropy) and power in frequency-domain signal features, feature selection was performed and finally classification was performed by support vector machine (SVM) classifier. The results show that the PAC of the NIRS signal was gradually enhanced with the deepening of anesthesia level. A good three-classification accuracy of 69.27% was obtained, which exceeded the result of classification of any single category feature. These results indicate the feasibility of NIRS signals in performing three or even more anesthesia stage classifications, providing insight into the development of new anesthesia monitoring modalities.

Human Alzheimer's Disease ATN/ABC Staging Applied to Aging Rhesus Macaque Brains: Association With Cognition and MRI-Based Regional Gray Matter Volume.

The brain changes of Alzheimer's disease (AD) include Abeta (Aβ)amyloid plaques ("A"), abnormally phosphorylated tau tangles ("T"), and neurodegeneration ("N"). These have been used to construct in vivo and postmortem diagnostic and staging classifications for evaluating the spectrum of AD in the "ATN" and "ABC" ("B" for Braak tau stage, "C" for Consortium to Establish a Registry for Alzheimer's Disease [CERAD] neuritic plaque density) systems. Another common AD feature involves cerebral amyloid angiopathy (CAA). We report the first experiment to examine relationships among cognition, brain distribution of amyloid plaques, CAA, tau/tangles, and magnetic resonance imaging (MRI)-determined volume changes (as a measure of "N") in the same group of behaviorally characterized nonhuman primates. Both ATN and ABC systems were applied to a group of 32 rhesus macaques aged between 7 and 33 years. When an immunohistochemical method for "T" and "B" was used, some monkeys were "triple positive" on ATN, with a maximum ABC status of A1B2C3. With silver or thioflavin S methods, however, all monkeys were classified as T-negative and B0, indicating the absence of mature neurofibrillary tangles (NFTs) and hence neuropathologically defined AD. Although monkeys at extremes of the ATN and ABC classifications, or with frequent CAA, had significantly lower scores on some cognitive tests, the lack of fully mature NFTs or dementia-consistent cognitive impairment indicates that fully developed AD may not occur in rhesus macaques. There were sex differences noted in the types of histopathology present, and only CAA was significantly related to gray matter volume.