Class Of States Research Articles

Nomograms for assessing the rupture risk of anterior choroid artery aneurysms based on clinical, morphological, and hemodynamic features.

A notable prevalence of subarachnoid hemorrhage is evident among patients with anterior choroidal artery aneurysms in clinical practice. To evaluate the risk of rupture in unruptured anterior choroidal artery aneurysms, we conducted a comprehensive analysis of risk factors and subsequently developed two nomograms. A total of 120 cases of anterior choroidal artery aneurysms (66 unruptured and 54 ruptured) from 4 medical institutions were assessed utilizing computational fluid dynamics (CFD) and digital subtraction angiography (DSA). The training set, consisting of 98 aneurysms from 3 hospitals, was established, with an additional 22 cases from the fourth hospital forming the external validation set. Statistical differences between the two data sets were thoroughly compared. The significance of 9 clinical baseline characteristics, 11 aneurysm morphology parameters, and 4 hemodynamic parameters concerning aneurysm rupture was evaluated within the training set. Candidate selection for constructing the nomogram models involved regression analysis and variance inflation factors. Discrimination, calibration, and clinical utility of the models in both training and validation sets were assessed using area under curves (AUC), calibration plots, and decision curve analysis (DCA). The DeLong test, net reclassification index (NRI), and integrated discrimination improvement (IDI) were employed to compare the effectiveness of classification across models. Two nomogram models were ultimately constructed: model 1, incorporating clinical, morphological, and hemodynamic parameters (C + M + H), and model 2, relying primarily on clinical and morphological parameters (C + M). Multivariate analysis identified smoking, size ratio (SR), normalized wall shear stress (NWSS), and average oscillatory shear index (OSIave) as optimal candidates for model development. In the training set, model 1 (C + M + H) achieved an AUC of 0.795 (95% CI: 0.706 ~ 0.884), demonstrating a sensitivity of 95.6% and a specificity of 54.7%. Model 2 (C + M) had an AUC of 0.706 (95% CI: 0.604 ~ 0.808), with corresponding sensitivity and specificity of 82.4 and 50.3%, respectively. Similarly, AUCs for models 1 and 2 in the external validation set were calculated to be 0.709 and 0.674, respectively. Calibration plots illustrated a consistent correlation between model evaluations and real-world observations in both sets. DCA demonstrated that the model incorporating hemodynamic parameters offered higher clinical benefits. In the training set, NRI (0.224, p = 0.007), IDI (0.585, p = 0.002), and DeLong test (change = 0.089, p = 0.008) were all significant. In the external validation set, NRI, IDI, and DeLong test statistics were 0.624 (p = 0.063), 0.572 (p = 0.044), and 0.035 (p = 0.047), respectively. Multidimensional nomograms have the potential to enhance risk assessment and patient-specific treatment of anterior choroidal artery aneurysms. Validated by an external cohort, the model incorporating clinical, morphological, and hemodynamic features may provide improved classification of rupture states.

Computational approach based on use of multilayer neural networks in classification of rail line states

The article considers the issue of classification of the states of rail lines using multilayer neural networks. It is shown that with significant external disturbing influences, the most promising direction is the retraining of classification models using neural networks. The representativeness of the sample is proposed to be realized by applying the scaling of informative features. It is proposed to minimize classification errors by gradient optimization methods. In the work during classification of rail lines states by neural networks, at the first stage, artificial classes of states are formed. At the second stage, the classification of states by the trained neural network is considered, classification errors are identified. On the basis of these errors the network is retrained until acceptable results are obtained. The article presents neuron learning algorithms: Hebb’s algorithm, error backpropagation method (for training a multilayer neural network), Konohen’s, Hopfield’s, Hamming’s algorithm and network. In the presented revision of the classification model, the correction is carried out according to the Widrow-Hoff algorithm.

Preliminary validation results: improving AHI scoring accuracy using an AI model for Sleep state and arousal classification from Home Sleep Apnea Testing

Preliminary validation results: improving AHI scoring accuracy using an AI model for Sleep state and arousal classification from Home Sleep Apnea Testing

A psychological evaluation method incorporating noisy label correction mechanism

Using machine learning and deep learning methods to analyze text data from social media can effectively explore hidden emotional tendencies and evaluate the psychological state of social media account owners. However, the label noise caused by mislabeling may significantly influence the training and prediction results of traditional supervised models. To resolve this problem, this paper proposes a psychological evaluation method that incorporates a noisy label correction mechanism and designs an evaluation framework that consists of a primary classification model and a noisy label correction mechanism. Firstly, the social media text data are transformed into heterogeneous text graphs, and a classification model combining a pre-trained model with a graph neural network is constructed to extract semantic features and structural features, respectively. After that, the Gaussian mixture model is used to select the samples that are likely to be mislabeled. Then, soft labels are generated for them to enable noisy label correction without prior knowledge of the noise distribution information. Finally, the corrected and clean samples are composed into a new data set and re-input into the primary model for mental state classification. Results of experiments on three real data sets indicate that the proposed method outperforms current advanced models in classification accuracy and noise robustness under different noise ratio settings, and can efficiently explore the potential sentiment tendencies and users’ psychological states in social media text data.

Theoretical guarantees for permutation-equivariant quantum neural networks

AbstractDespite the great promise of quantum machine learning models, there are several challenges one must overcome before unlocking their full potential. For instance, models based on quantum neural networks (QNNs) can suffer from excessive local minima and barren plateaus in their training landscapes. Recently, the nascent field of geometric quantum machine learning (GQML) has emerged as a potential solution to some of those issues. The key insight of GQML is that one should design architectures, such as equivariant QNNs, encoding the symmetries of the problem at hand. Here, we focus on problems with permutation symmetry (i.e., symmetry group Sn), and show how to build Sn-equivariant QNNs We provide an analytical study of their performance, proving that they do not suffer from barren plateaus, quickly reach overparametrization, and generalize well from small amounts of data. To verify our results, we perform numerical simulations for a graph state classification task. Our work provides theoretical guarantees for equivariant QNNs, thus indicating the power and potential of GQML.

A generative adversarial networks based methodology for imbalanced multidimensional time-series augmentation of complex electromechanical systems

Multidimensional monitoring time-series of complex electromechanical systems (CESs) plays a foundational role in data-based state management, maintenance, and performance adjustment. However, it is still a challenging work to extract valuable and complete information due to the imbalanced data. To address this issue, a methodology called GAN4MTS (Generative Adversarial Networks for Multidimensional Time-Series) that generates synthetic data closely mimicking the characteristics of real data was proposed, thus directly tackling the problem of data imbalance. First, the uniqueness of multidimensional time series of CESs was analyzed to identify the requirements for data augmentation and to define the problem formulations. Second, the architecture and loss functions of GAN4MTS model were designed based on generative adversarial networks and three specific constraints. Finally, the effectiveness of the proposed work was validated through comparative analysis. Furthermore, the intrinsic mechanisms of data augmentation in enhancing the model capabilities were discussed. The proposed methodology serves as a comprehensive technical solution for data augmentation, enabling the generation of high-quality synthetic data that adheres to the constraints of multidimensional time series in CESs. Additionally, as an open architecture model, this work provides novel methods for time-series data augmentation, addressing the issues of low accuracy and limited model generalization in state classification, identification, and prediction tasks for CESs caused by the presence of highly imbalanced data.

The Impact of Light Conditions on Neural Affect Classification: A Deep Learning Approach

Understanding and detecting human emotions is crucial for enhancing mental health, cognitive performance and human–computer interactions. This field in affective computing is relatively unexplored, and gaining knowledge about which external factors impact emotions could enhance communication between users and machines. Furthermore, it could also help us to manage affective disorders or understand affective physiological responses to human spatial and digital environments. The main objective of the current study was to investigate the influence of external stimulation, specifically the influence of different light conditions, on brain activity while observing affect-eliciting pictures and their classification. In this context, a multichannel electroencephalography (EEG) was recorded in 30 participants as they observed images from the Nencki Affective Picture System (NAPS) database in an art-gallery-style Virtual Reality (VR) environment. The elicited affect states were classified into three affect classes within the two-dimensional valence–arousal plane. Valence (positive/negative) and arousal (high/low) values were reported by participants on continuous scales. The experiment was conducted in two experimental conditions: a warm light condition and a cold light condition. Thus, three classification tasks arose with regard to the recorded brain data: classification of an affect state within a warm-light condition, classification of an affect state within a cold light condition, and warm light vs. cold light classification during observation of affect-eliciting images. For all classification tasks, Linear Discriminant Analysis, a Spatial Filter Model, a Convolutional Neural Network, the EEGNet, and the SincNet were compared. The EEGNet architecture performed best in all tasks. It could significantly classify three affect states with 43.12% accuracy under the influence of warm light. Under the influence of cold light, no model could achieve significant results. The classification between visual stimulus with warm light vs. cold light could be classified significantly with 76.65% accuracy from the EEGNet, well above any other machine learning or deep learning model. No significant differences could be detected between affect recognition in different light conditions, but the results point towards the advantage of gradient-based learning methods for data-driven experimental designs for the problem of affect decoding from EEG, providing modern tools for affective computing in digital spaces. Moreover, the ability to discern externally driven affective states through deep learning not only advances our understanding of the human mind but also opens avenues for developing innovative therapeutic interventions and improving human–computer interaction.

Using explainable machine learning methods to evaluate vulnerability and restoration potential of ecosystem state transitions.

Ecosystem state transitions can be ecologically devastating or be a restoration success. State transitions are common within aquatic systems worldwide, especially considering human-mediated changes to land use and water use. We created a transferable conceptual framework to enable multiscale assessments of state resilience and early warnings of state transitions that can inform strategic restorations and avoid ecosystem collapse. The conceptual framework integrated machine learning predictions with ecosystem state concepts (e.g., state classification, gradients of vulnerability, and recovery potential leading to state transitions) and was devised to investigate possible environmental drivers. As an application of the framework, we generated prediction probabilities of submersed aquatic vegetation (SAV) presence at nearly 10,000 sites in the Upper Mississippi River (United States). Then, we used an interpretability method to explain model predictions to gain insights into possible environmental drivers and thresholds or linear responses of SAV presence and absence. Model accuracy was 89% without spatial bias. Average water depth, suspended solids, substrate, and distance to nearest SAV were the best predictors and likely environmental drivers of SAV habitat suitability. These environmental drivers exhibited nonlinear, threshold-type responses for SAV. All the results are also presented in an online dashboard to explore results at many spatial scales. The habitat suitability model outputs and prediction explanations from many spatial scales (4m to 400km of river reach) can inform research and restoration planning.

Abstract C058: Identifying cell-intrinsic drivers of transcriptional plasticity in pancreatic cancer

Abstract Pancreatic ductal adenocarcinoma (PDAC) is a devastating disease with few effective therapies. Contributing to the complexity of this deadly cancer, PDAC tumors with similar genomic backgrounds can express divergent transcriptional programs with clinical importance. These transcriptional subtypes, termed “cell states”, have prognostic significance: PDAC tumors in the “classical state” generally have better outcomes and are thought to be more responsive to chemotherapy while those in the “basal state” are more aggressive. Currently, cell state is not used to direct therapy. Cell state is an integrative property shaped by both cell-intrinsic (e.g., mutations, epigenetics) and cell-extrinsic (e.g., growth factors, cytokines) factors. In our prior work, single-cell analysis of clinical PDAC samples demonstrated notable intra-tumoral cell state heterogeneity with evidence for cells that co-expressed both basal and classical markers, suggestive of cell state plasticity. In addition, longitudinal monitoring of patient-derived organoids has shown that cells can shift from classical to coexpressor/basal states as the environment changes, and this shift in cell states can drastically influence drug response. However, it remains unknown which signaling and transcriptional pathways induce basal or classical states, and whether these gene regulatory networks can be targeted therapeutically. Thus, there is a pressing need to devise scalable methods to determine essential drivers for prognostically-relevant cancer cell states. Here, we aim to define transcriptional drivers of basal and classical cell states in pancreatic cancer. We are currently optimizing a flow cytometry-fluorescence in situ hybridization (Flow-FISH) workflow to enable a multi-gene cell state readout. We plan to perform a transcription factor over-expression screen within a cohort of PDAC models using this Flow-FISH readout to identify those factors that can drive cells toward basal (n=3), classical (n=2), or coexpressor (n=3) states. As a proof of concept, we have confirmed that TP63A overexpression induces basal state expression, even in models that initially express a classical phenotype. Through these efforts, we aim to construct high-fidelity isogenic but state-variant PDAC models for use both in therapeutic screening and as a substrate for investigating mechanisms governing cancer cell state plasticity. Citation Format: Yuzhou Evelyn Tong, Walaa E. Katan, Alex Bott, Julia Joung, Alex K. Shalek, Peter S. Winter, Srivatsan Raghavan. Identifying cell-intrinsic drivers of transcriptional plasticity in pancreatic cancer [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Pancreatic Cancer; 2023 Sep 27-30; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(2 Suppl):Abstract nr C058.

Abstract C103: Differential acquisition of extracellular lipid correlates with pancreatic cancer subtype and metastatic tropism

Abstract Pancreatic ductal adenocarcinoma (PDAC) is an aggressive disease, and the third leading cause of cancer-related death with a 5-year overall survival rate of less than 5%. Recent studies have identified two major subtypes of pancreatic cancer, basal and classical, that are predictive of patient prognosis, with basal tumors corresponding with more aggressive disease. While transcriptional signatures define basal and classical tumors and cell lines, little is known regarding the metabolic vulnerabilities linked to the basal versus classical state. Using unbiased computational interrogation to uncover metabolic genes correlating with known markers of classical PDAC, we identified high expression of Proprotein convertase subtilisin/kexin type-9 (PCSK9) – a negative regulator of receptor mediated uptake of cholesterol containing low-density lipoprotein (LDL) – as correlating with several established markers of classical PDAC. In contrast, PCSK9 expression is suppressed in Basal PDAC. Accordingly, basal PDAC uptake high levels of LDL, are sensitive to LDL depletion and show higher dependence on cholesterol uptake, relative to classical PDAC. As lipoproteins are produced in the liver, we hypothesized that basal PDAC cells may more efficiently seed and grow within the liver. Consistent with this hypothesis, low PCSK9 expression is correlated with liver metastasis in mouse models of PDAC and patient PDAC specimens. Ongoing studies will interrogate the role of PCSK9 and cholesterol uptake and utilization in metastatic tropism, and uncover unique features and vulnerabilities of the most aggressive variant of PDAC. Citation Format: Gilles Rademaker, Grace A. Hernandez, Longhui Qiu, Kwun W. Wen, Aakriti Jain, Grace A. Kim, Roberto Zoncu, Rushik M. Perera. Differential acquisition of extracellular lipid correlates with pancreatic cancer subtype and metastatic tropism [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Pancreatic Cancer; 2023 Sep 27-30; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(2 Suppl):Abstract nr C103.

Saliva Based Diagnostic Prediction of Oral Squamous Cell Carcinoma using FTIR Spectroscopy.

Oral cancer ranks as the sixth most prevalent form of cancer worldwide, presenting a significant public health concern. According to the World Health Organization (WHO), within a 5-year period following diagnosis, the mortality rate among oral cancer patients of all stages stands at 45%. In this study, a total of 60 patients divided into 2 groups were recruited. Group A included 30 histo-pathologically confirmed OSCC patients and Group B included 30 healthy controls. A standardized procedure was followed to collect saliva samples. FTIR spectroscopy was done for all the saliva samples collected from both Group A and B. An IR Prestige-21 (Shimadzu Corp, Japan) spectrometer was used to record IR spectra in the 40-4000cm-1 range SVM classifier was applied in the classification of disease state from normal subjects using FTIR data. The peaks were identified at wave no 1180cm-1, 1230cm-1, 1340cm-1, 1360cm-1, 1420cm-1, 1460cm-1, 1500cm-1, 1540cm-1, 1560cm-1, and 1637cm-1. The observed results of SVM demonstrated the accuracy of 91.66% in the classification of Cancer tissues from the normal subjects with sensitivity of 83.33% while specificity and precision of 100.0%. The development of oral cancer leads to noticeable alterations in the secondary structure of proteins. These findings emphasize the promising use of ATR-FTIR platforms in conjunction with machine learning as a reliable, non-invasive, reagent-free, and highly sensitive method for screening and monitoring individuals with oral cancer.

Automated Scanning Probe Tip State Classification without Machine Learning.

The manual identification and in situ correction of the state of the scanning probe tip is one of the most time-consuming and tedious processes in atomic-resolution scanning probe microscopy. This is due to the random nature of the probe tip on the atomic level, and the requirement for a human operator to compare the probe quality via manual inspection of the topographical images after any change in the probe. Previous attempts to automate the classification of the scanning probe state have focused on the use of machine learning techniques, but the training of these models relies on large, labeled data sets for each surface being studied. These data sets are extremely time-consuming to create and are not always available, especially when considering a new substrate or adsorbate system. In this paper, we show that the problem of tip classification from a topographical image can be solved by using only a single image of the surface along with a small amount of prior knowledge of the appearance of the system in question with a method utilizing template matching (TM). We find that by using these TM methods, comparable accuracy and precision can be achieved to values obtained with the use of machine learning. We demonstrate the efficacy of this technique by training a machine learning-based classifier and comparing the classifications with the TM classifier for two prototypical silicon-based surfaces. We also apply the TM classifier to a number of other systems where supervised machine learning-based training was not possible due to the nature of the training data sets. Finally, the applicability of the TM method to surfaces used in the literature, which have been classified using machine learning-based methods, is considered.

Exploring artificial intelligence approach to art therapy assessment: A case study on the classification and the estimation of psychological state based on a drawing

The art therapy assessment involves the classification of the psychological state of the drawer into several groups (e.g., normal or abnormal) and the estimation of it in numeric (e.g., psychological examination score) based on the interpretation of his or her drawing. Based on a qualitative approach to these tasks, a statistical approach relying various quantitative features of drawings has broadened the scope and methods in the analysis of the psychological states through drawings. In this paper, we explore an artificial intelligence approach and discuss its superiority over the statistical approach and also identify its limitations. The synergistic effects of the interdisciplinary framework combining qualitative, statistical, and artificial intelligence approaches is expected to make a critical contribution to the development of art therapy assessment.

Experimental hierarchy of the nonclassicality of single-qubit states via potentials for entanglement, steering, and Bell nonlocality.

Entanglement potentials are a promising way to quantify the nonclassicality of single-mode states. They are defined by the amount of entanglement (expressed by, e.g., the Wootters concurrence) obtained after mixing the examined single-mode state with a purely classical state; such as the vacuum or a coherent state. We generalize the idea of entanglement potentials to other quantum correlations: the EPR steering and Bell nonlocality, thus enabling us to study mutual hierarchies of these nonclassicality potentials. Instead of the usual vacuum and one-photon superposition states, we experimentally test this concept using specially tailored polarization-encoded single-photon states. One polarization encodes a given nonclassical single-mode state, while the other serves as the vacuum place-holder. This technique proves to be experimentally more convenient in comparison to the vacuum and a one-photon superposition as it does not require the vacuum detection.

Remaining Useful Life Estimation of Hollow Worn Railway Vehicle Wheels via On-Board Random Vibration-Based Wheel Tread Depth Estimation.

The problem of remaining useful life estimation (RULE) of hollow worn railway vehicle wheels in terms of remaining mileage via wheel tread depth estimation using on-board vibration signals from a single accelerometer on the bogie frame is presently investigated. This is achieved based on the introduction of a statistical time series method that employs: (i) advanced data-driven stochastic Functionally Pooled models for the modeling of the vehicle dynamics under different wheel tread depths in a range of interest until a critical limit, as well as tread depth estimation through a proper optimization procedure, and (ii) a wheel tread depth evolution function with respect to the vehicle running mileage that interconnects the estimated hollow wear with the remaining useful mileage. The method's RULE performance is investigated via hundreds of Simpack-based Monte Carlo simulations with an Attiko Metro S.A. vehicle and many hollow worn wheels scenarios which are not used for the method's training. The obtained results indicate the accurate estimation of the wheels tread depth with a mean absolute error of ∼0.07 mm that leads to a corresponding small error of ∼3% with respect to the wheels remaining useful mileage. In addition, the comparison with a recently introduced Multiple Model (MM)-based multi-health state classification method for RULE, demonstrates the better performance of the postulated method that achieves 81.17% True Positive Rate (TPR) which is significantly higher than the 45.44% of the MM method.

Searching for Structure: Characterizing the Protein Conformational Landscape with Clustering-Based Algorithms.

The identification and characterization of the main conformations from a protein population are a challenging and inherently high-dimensional problem. Here, we evaluate the performance of the Secondary sTructural Ensembles with machine LeArning (StELa) double-clustering method, which clusters protein structures based on the relationship between the φ and ψ dihedral angles in a protein backbone and the secondary structure of the protein, thus focusing on the local properties of protein structures. The classification of states as vectors composed of the clusters' indices arising naturally from the Ramachandran plot is followed by the hierarchical clustering of the vectors to allow for the identification of the main features of the corresponding free energy landscape (FEL). We compare the performance of StELa with the established root-mean-squared-deviation (RMSD)-based clustering algorithm, which focuses on global properties of protein structures and with Combinatorial Averaged Transient Structure (CATS), the combinatorial averaged transient structure clustering method based on distributions of the φ and ψ dihedral angle coordinates. Using ensembles of conformations from molecular dynamics simulations of intrinsically disordered proteins (IDPs) of various lengths (tau protein fragments) or short fragments from a globular protein, we show that StELa is the clustering method that identifies many of the minima and relevant energy states around the minima from the corresponding FELs. In contrast, the RMSD-based algorithm yields a large number of clusters that usually cover most of the FEL, thus being unable to distinguish between states, while CATS does not sample well the FELs for long IDPs and fragments from globular proteins.

Seismic Vulnerability Assessment in Tunnels: A Review

Vulnerability analysis is an important method for earthquake prevention and disaster reduction research in the field of tunnel engineering. Firstly, a detailed overview of the research history and current status of tunnel seismic vulnerability at home and abroad was provided; Secondly, the main methods for analyzing the seismic vulnerability of tunnels at home and abroad were summarized, and the practical applicability of various methods was summarized; Subsequently, the steps for evaluating the seismic vulnerability of tunnels were proposed, and three key contents in establishing theoretical vulnerability curves using numerical simulation as the main method were discussed: (1) Input parameter determination; (2) Classification of destructive states; (3) Calculation of relevant uncertainty parameters; Finally, point out some urgent problems and future research directions in this field. By summarizing the existing studies on the seismic vulnerability of tunnels at home and abroad, the results show that the seismic vulnerability analysis of tunnels can reflect the performance of tunnels under seismic loading by considering the relevant uncertainty factors, which is conducive to the future risk assessment and loss estimation, and is of great significance to the development of performance-based seismic design of tunnels.

Classification of States for Literal Neutrosophic and Plithogenic Markov Chains

In this paper we represent many classifications of neutrosophic and plithogenic Markov Chains states including absorbent states, inessential and essential states, recurrent states and communicated states. We prove that if a state (i) according to a neutrosophic Markov Chain with neutrosophic transition matrix is classified as any of the previous classifications then it is also classified as the same classification in classical scene to two Markov Chains defined with transition matrices respectively. Also, we prove that if a state (i) according to a plithogenic Markov Chain with plithogenic transition matrix is classified as any of the previous classifications then it is also classified as the same classification in classical scene to three Markov Chains defined with transition matrices respectively. Many theorems and solved examples are presented and solved successfully.

Label-free scattering snapshot classification for living cell identification

A scattering snapshot hold an enormous potential for cell class and state classification, allowing to avoid costly fluorescence labelling. Beside convolutional neural networks show outstanding image classification performance compared to other state-of-the-art methods, regarding accuracy and speed. Therefore, we combined the two techniques (Light Scattering and Deep Learning) to identify living cells with high precision. Neural Networks show high prediction performance for known classes but struggles when unknown classes need to be identified. In such a scenario no prior knowledge of the unknown cell class can be used for the model training, which inevitably results in a misclassification. To overcome the hurdle, of identifying unknown cell classes, we must first define an in-distribution of known snapshots to afterwards detect out of distribution snapshots as unknowns. Ones, such a new cell class is identified, we can retrain our cell classifier with the obtained knowledge, so we dynamically update the cell class database. We applied this measurement approach to scattering pattern snapshots of different classes of living cells. Our outcome shows a precise cell classification, which can be applied to a wide range of single cell classification approaches.

Machine learning classification of cellular states based on the impedance features derived from microfluidic single-cell impedance flow cytometry.

Mitosis is a crucial biological process where a parental cell undergoes precisely controlled functional phases and divides into two daughter cells. Some drugs can inhibit cell mitosis, for instance, the anti-cancer drugs interacting with the tumor cell proliferation and leading to mitosis arrest at a specific phase or cell death eventually. Combining machine learning with microfluidic impedance flow cytometry (IFC) offers a concise way for label-free and high-throughput classification of drug-treated cells at single-cell level. IFC-based single-cell analysis generates a large amount of data related to the cell electrophysiology parameters, and machine learning helps establish correlations between these data and specific cell states. This work demonstrates the application of machine learning for cell state classification, including the binary differentiations between the G1/S and apoptosis states and between the G2/M and apoptosis states, as well as the classification of three subpopulations comprising a subgroup insensitive to the drug beyond the two drug-induced states of G2/M arrest and apoptosis. The impedance amplitudes and phases used as input features for the model training were extracted from the IFC-measured datasets for the drug-treated tumor cells. The deep neural network (DNN) model was exploited here with the structure (e.g., hidden layer number and neuron number in each layer) optimized for each given cell type and drug. For the H1650 cells, we obtained an accuracy of 78.51% for classification between the G1/S and apoptosis states and 82.55% for the G2/M and apoptosis states. For HeLa cells, we achieved a high accuracy of 96.94% for classification between the G2/M and apoptosis states, both of which were induced by taxol treatment. Even higher accuracy approaching 100% was achieved for the vinblastine-treated HeLa cells for the differentiation between the viable and non-viable states, and between the G2/M and apoptosis states. We also demonstrate the capability of the DNN model for high-accuracy classification of the three subpopulations in a complete cell sample treated by taxol or vinblastine.