Quantitative evaluation model of variable diagnosis for chest X-ray images using deep learning.

The purpose of this study is to demonstrate the use of a deep learning model in quantitatively evaluating clinical findings typically subject to uncertain evaluations by physicians, using binary test results based on routine protocols. A chest X-ray is the most commonly used diagnostic tool for the detection of a wide range of diseases and is generally performed as a part of regular medical checkups. However, when it comes to findings that can be classified as within the normal range but are not considered disease-related, the thresholds of physicians' findings can vary to some extent, therefore it is necessary to define a new evaluation method and quantify it. The implementation of such methods is difficult and expensive in terms of time and labor. In this study, a total of 83,005 chest X-ray images were used to diagnose the common findings of pleural thickening and scoliosis. A novel method for quantitatively evaluating the probability that a physician would judge the images to have these findings was established. The proposed method successfully quantified the variation in physicians' findings using a deep learning model trained only on binary annotation data. It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97.

Small animal PET with spontaneous inhalation of 15O-labelled oxygen gases: Longitudinal assessment of cerebral oxygen metabolism in a rat model of neonatal hypoxic-ischaemic encephalopathy.

Perinatal hypoxic-ischaemic encephalopathy (HIE) is the leading cause of irreversible brain damage resulting in serious neurological dysfunction among neonates. We evaluated the feasibility of positron emission tomography (PET) methodology with 15O-labelled gases without intravenous or tracheal cannulation for assessing temporal changes in cerebral blood flow (CBF) and cerebral metabolic rate for oxygen (CMRO2) in a neonatal HIE rat model. Sequential PET scans with spontaneous inhalation of 15O-gases mixed with isoflurane were performed over 14 days after the hypoxic-ischaemic insult in HIE pups and age-matched controls. CBF and CMRO2 in the injured hemispheres of HIE pups remarkably decreased 2 days after the insult, gradually recovering over 14 days in line with their increase found in healthy controls according to their natural maturation process. The magnitude of hemispheric tissue loss histologically measured after the last PET scan was significantly correlated with the decreases in CBF and CMRO2.This fully non-invasive imaging strategy may be useful for monitoring damage progression in neonatal HIE and for evaluating potential therapeutic outcomes.

Application of a Two-Dimensional Mapping-Based Visualization Technique: Nutrient-Value-Based Food Grouping.

Worldwide, several food-based dietary guidelines, with diverse food-grouping methods in various countries, have been developed to maintain and promote public health. However, standardized international food-grouping methods are scarce. In this study, we used two-dimensional mapping to classify foods based on their nutrient composition. The Standard Tables of Food Composition in Japan were used for mapping with a novel technique-t-distributed stochastic neighbor embedding-to visualize high-dimensional data. The mapping results showed that most foods formed food group-based clusters in the Standard Tables of Food Composition in Japan. However, the beverages did not form large clusters and demonstrated scattered distribution on the map. Green tea, black tea, and coffee are located within or near the vegetable cluster whereas cocoa is near the pulse cluster. These results were ensured by the k-nearest neighbors. Thus, beverages made from natural materials can be categorized based on their origin. Visualization of food composition could enable an enhanced comprehensive understanding of the nutrients in foods, which could lead to novel aspects of nutrient-value-based food classifications.

Information maximization-based clustering of histopathology images using deep learning.

Pancreatic cancer is one of the most adverse diseases and it is very difficult to treat because the cancer cells formed in the pancreas intertwine themselves with nearby blood vessels and connective tissue. Hence, the surgical procedure of treatment becomes complicated and it does not always lead to a cure. Histopathological diagnosis is the usual approach for cancer diagnosis. However, the pancreas remains so deep inside the body that experts sometimes struggle to detect cancer in it. Computer-aided diagnosis can come to the aid of pathologists in this scenario. It assists experts by supporting their diagnostic decisions. In this research, we carried out a deep learning-based approach to analyze histopathology images. We collected whole-slide images of KPC mice to implement this work. The pancreatic abnormalities observed in KPC mice develop similar histological features to human beings. We created random patches from whole-slide images. Then, a convolutional autoencoder framework was used to embed these patches into an integrated latent space. We applied 'information maximization', a deep learning clustering technique to cluster the identical patches in an unsupervised manner since our dataset does not have annotation. Moreover, Uniform manifold approximation and projection, a nonlinear dimension reduction technique was utilized to visualize the embedded patches in a 2-dimensional space. Finally, we calculated a few internal cluster validation metrics to determine the optimal cluster set. Our work concentrated on patch-based anomaly detection in the whole slide histopathology images of KPC mice.

Ensemble Machine Learning Approaches Based on Molecular Descriptors and Graph Convolutional Networks for Predicting the Efflux Activities of MDR1 and BCRP Transporters.

Multidrug resistance (MDR1) and breast cancer resistance protein (BCRP) play important roles in drug absorption and distribution. Computational prediction of substrates for both transporters can help reduce time in drug discovery. This study aimed to predict the efflux activity of MDR1 and BCRP using multiple machine learning approaches with molecular descriptors and graph convolutional networks (GCNs). In vitro efflux activity was determined using MDR1- and BCRP-expressing cells. Predictive performance was assessed using an in-house dataset with a chronological split and an external dataset. CatBoost and support vector regression showed the best predictive performance for MDR1 and BCRP efflux activities, respectively, of the 25 descriptor-based machine learning methods based on the coefficient of determination (R2). The single-task GCN showed a slightly lower performance than descriptor-based prediction in the in-house dataset. In both approaches, the percentage of compounds predicted within twofold of the observed values in the external dataset was lower than that in the in-house dataset. Multi-task GCN did not show any improvements, whereas multimodal GCN increased the predictive performance of BCRP efflux activity compared with single-task GCN. Furthermore, the ensemble approach of descriptor-based machine learning and GCN achieved the highest predictive performance with R2 values of 0.706 and 0.587 in MDR1 and BCRP, respectively, in time-split test sets. This result suggests that two different approaches to represent molecular structures complement each other in terms of molecular characteristics. Our study demonstrated that predictive models using advanced machine learning approaches are beneficial for identifying potential substrate liability of both MDR1 and BCRP.

On QSAR-based cardiotoxicity modeling with the expressiveness-enhanced graph learning model and dual-threshold scheme.

Introduction: Given the direct association with malignant ventricular arrhythmias, cardiotoxicity is a major concern in drug design. In the past decades, computational models based on the quantitative structure-activity relationship have been proposed to screen out cardiotoxic compounds and have shown promising results. The combination of molecular fingerprint and the machine learning model shows stable performance for a wide spectrum of problems; however, not long after the advent of the graph neural network (GNN) deep learning model and its variant (e.g., graph transformer), it has become the principal way of quantitative structure-activity relationship-based modeling for its high flexibility in feature extraction and decision rule generation. Despite all these progresses, the expressiveness (the ability of a program to identify non-isomorphic graph structures) of the GNN model is bounded by the WL isomorphism test, and a suitable thresholding scheme that relates directly to the sensitivity and credibility of a model is still an open question. Methods: In this research, we further improved the expressiveness of the GNN model by introducing the substructure-aware bias by the graph subgraph transformer network model. Moreover, to propose the most appropriate thresholding scheme, a comprehensive comparison of the thresholding schemes was conducted. Results: Based on these improvements, the best model attains performance with 90.4% precision, 90.4% recall, and 90.5% F1-score with a dual-threshold scheme (active: <1µM; non-active: >30µM). The improved pipeline (graph subgraph transformer network model and thresholding scheme) also shows its advantages in terms of the activity cliff problem and model interpretability.

On finding natural antibiotics based on TCM formulae.

CONTEXT: Novel kinds of antibiotics are needed to combat the emergence of antibacterial resistance. Natural products (NPs) have shown potential as antibiotic candidates. Current experimental methods are not yet capable of exploring the massive, redundant, and noise-involved chemical space of NPs. In silico approaches are needed to select NPs as antibiotic candidates. OBJECTIVE: This study screens out NPs with antibacterial efficacy guided by both TCM and modern medicine and constructed a dataset aiming to serve the new antibiotic design. METHOD: A knowledge-based network is proposed in this study involving NPs, herbs, the concepts of TCM, and the treatment protocols (or etiologies) of infectious in modern medicine. Using this network, the NPs candidates are screened out and compose the dataset. Feature selection of machine learning approaches is conducted to evaluate the constructed dataset and statistically validate the im- portance of all NPs candidates for different antibiotics by a classification task. RESULTS: The extensive experiments prove the constructed dataset reaches a convincing classification performance with a 0.9421 weighted accuracy, 0.9324 recall, and 0.9409 precision. The further visu- alizations of sample importance prove the comprehensive evaluation for model interpretation based on medical value considerations.

Learning vector quantized representation for cancer subtypes identification.

BACKGROUND AND OBJECTIVE: Defining and separating cancer subtypes is essential for facilitating personalized therapy modality and prognosis of patients. The definition of subtypes has been constantly recalibrated as a result of our deepened understanding. During this recalibration, researchers often rely on clustering of cancer data to provide an intuitive visual reference that could reveal the intrinsic characteristics of subtypes. The data being clustered are often omics data such as transcriptomics that have strong correlations to the underlying biological mechanism. However, while existing studies have shown promising results, they suffer from issues associated with omics data: sample scarcity and high dimensionality while they impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations. METHODS: This paper proposes to leverage a recent strong generative model, Vector-Quantized Variational AutoEncoder, to tackle the data issues and extract discrete representations that are crucial to the quality of subsequent clustering by retaining only information relevant to reconstructing the input. RESULTS: Extensive experiments and medical analysis on multiple datasets comprising 10 distinct cancers demonstrate the proposed clustering results can significantly and robustly improve prognosis over prevalent subtyping systems. CONCLUSION: Our proposal does not impose strict assumptions on data distribution; while, its latent features are better representations of the transcriptomic data in different cancer subtypes, capable of yielding superior clustering performance with any mainstream clustering method.

Automated Sleep Staging via Parallel Frequency-Cut Attention.

Stage-based sleep screening is a widely-used tool in both healthcare and neuroscientific research, as it allows for the accurate assessment of sleep patterns and stages. In this paper, we propose a novel framework that is based on authoritative guidance in sleep medicine and is designed to automatically capture the time-frequency characteristics of sleep electroencephalogram (EEG) signals in order to make staging decisions. Our framework consists of two main phases: a feature extraction process that partitions the input EEG spectrograms into a sequence of time-frequency patches, and a staging phase that searches for correlations between the extracted features and the defining characteristics of sleep stages. To model the staging phase, we utilize a Transformer model with an attention-based module, which allows for the extraction of global contextual relevance among time-frequency patches and the use of this relevance for staging decisions. The proposed method is validated on the large-scale Sleep Heart Health Study dataset and achieves new state-of-the-art results for the wake, N2, and N3 stages, with respective F1 scores of 0.93, 0.88, and 0.87 using only EEG signals. Our method also demonstrates high inter-rater reliability, with a kappa score of 0.80. Moreover, we provide visualizations of the correspondence between sleep staging decisions and features extracted by our method, which enhances the interpretability of the proposal. Overall, our work represents a significant contribution to the field of automated sleep staging and has important implications for both healthcare and neuroscience research.

Deep Learning Approach for Predicting the Therapeutic Usages of Unani Formulas towards Finding Essential Compounds.

The use of herbal medicines in recent decades has increased because their side effects are considered lower than conventional medicine. Unani herbal medicines are often used in Southern Asia. These herbal medicines are usually composed of several types of medicinal plants to treat various diseases. Research on herbal medicine usually focuses on insight into the composition of plants used as ingredients. However, in the present study, we extended to the level of metabolites that exist in the medicinal plants. This study aimed to develop a predictive model of the Unani therapeutic usage based on its constituent metabolites using deep learning and data-intensive science approaches. Furthermore, the best prediction model was then utilized to extract important metabolites for each therapeutic usage of Unani. In this study, it was observed that the deep neural network approach provided a much better prediction model than other algorithms including random forest and support vector machine. Moreover, according to the best prediction model using the deep neural network, we identified 118 important metabolites for nine therapeutic usages of Unani.

A training pipeline of an arrhythmia classifier for atrial fibrillation detection using Photoplethysmography signal.

Photoplethysmography (PPG) signal is potentially suitable in atrial fibrillation (AF) detection for its convenience in use and similarity in physiological origin to electrocardiogram (ECG). There are a few preceding studies that have shown the possibility of using the peak-to-peak interval of the PPG signal (PPIp) in AF detection. However, as a generalized model, the accuracy of an AF detector should be pursued on the one hand; on the other hand, its generalizability should be paid attention to in view of the individual differences in PPG manifestation of even the same arrhythmia and the existence of sub-types. Moreover, a binary classifier for atrial fibrillation and normal sinus rhythm is not convincing enough for the similarity between AF and ectopic beats. In this study, we project the atrial fibrillation detection as a multiple-class classification and try to propose a training pipeline that is advantageous both to the accuracy and generalizability of the classifier by designing and determining the configurable options of the pipeline, in terms of input format, deep learning model (with hyperparameter optimization), and scheme of transfer learning. With a rigorous comparison of the possible combinations of the configurable components in the pipeline, we confirmed that first-order difference of heartbeat sequence as the input format, a 2-layer CNN-1-layer Transformer hybridR model as the learning model and the whole model fine-tuning as the implementing scheme of transfer learning is the best combination for the pipeline (F1 value: 0.80, overall accuracy: 0.87)R.

Sleep Staging Framework with Physiologically Harmonized Sub-Networks.

Sleep screening is an important tool for both healthcare and neuroscientific research. Automatic sleep scoring is an alternative to the time-consuming gold-standard manual scoring procedure. Recently there have seen promising results on automatic stage scoring by extracting spatio-temporal features via deep neural networks from electroencephalogram (EEG). However, such methods fail to consistently yield good performance due to a missing piece in data representation: the medical criterion of the sleep scoring task on top of EEG features. We argue that capturing stage-specific features that satisfy the criterion of sleep medicine is non-trivial for automatic sleep scoring. This paper considers two criteria: Transient stage marker and Overall profile of EEG features, then we propose a physiologically meaningful framework for sleep stage scoring via mixed deep neural networks. The framework consists of two sub-networks: feature extraction networks, constructed in consideration of the physiological characteristics of sleep, and an attention-based scoring decision network. Moreover, we quantize the framework for potential use under an IoT setting. For proof-of-concept, the performance of the proposed framework is demonstrated by introducing multiple sleep datasets with the largest comprising 42,560 h recorded from 5,793 subjects. From the experiment results, the proposed method achieves a competitive stage scoring performance, especially for Wake, N2, and N3, with higher F1 scores of 0.92, 0.86, and 0.88, respectively. Moreover, the feasibility analysis of framework quantization provides a potential for future implementation in the edge computing field and clinical settings.

Chemoinformatics-driven classification of Angiosperms using sulfur-containing compounds and machine learning algorithm.

BACKGROUND: Phytochemicals or secondary metabolites are low molecular weight organic compounds with little function in plant growth and development. Nevertheless, the metabolite diversity govern not only the phenetics of an organism but may also inform the evolutionary pattern and adaptation of green plants to the changing environment. Plant chemoinformatics analyzes the chemical system of natural products using computational tools and robust mathematical algorithms. It has been a powerful approach for species-level differentiation and is widely employed for species classifications and reinforcement of previous classifications. RESULTS: This study attempts to classify Angiosperms using plant sulfur-containing compound (SCC) or sulphated compound information. The SCC dataset of 692 plant species were collected from the comprehensive species-metabolite relationship family (KNApSAck) database. The structural similarity score of metabolite pairs under all possible combinations (plant species-metabolite) were determined and metabolite pairs with a Tanimoto coefficient value > 0.85 were selected for clustering using machine learning algorithm. Metabolite clustering showed association between the similar structural metabolite clusters and metabolite content among the plant species. Phylogenetic tree construction of Angiosperms displayed three major clades, of which, clade 1 and clade 2 represented the eudicots only, and clade 3, a mixture of both eudicots and monocots. The SCC-based construction of Angiosperm phylogeny is a subset of the existing monocot-dicot classification. The majority of eudicots present in clade 1 and 2 were represented by glucosinolate compounds. These clades with SCC may have been a mixture of ancestral species whilst the combinatorial presence of monocot-dicot in clade 3 suggests sulphated-chemical structure diversification in the event of adaptation during evolutionary change. CONCLUSIONS: Sulphated chemoinformatics informs classification of Angiosperms via machine learning technique.

Cancer Subtyping via Embedded Unsupervised Learning on Transcriptomics Data.

Cancer is one of the deadliest diseases worldwide. Accurate diagnosis and classification of cancer subtypes are indispensable for effective clinical treatment. Promising results on automatic cancer subtyping systems have been published recently with the emergence of various deep learning methods. However, such automatic systems often overfit the data due to the high dimensionality and scarcity. In this paper, we propose to investigate automatic subtyping from an unsupervised learning perspective by directly constructing the underlying data distribution itself, hence sufficient data can be generated to alleviate the issue of overfitting. Specifically, we bypass the strong Gaussianity assumption that typically exists but fails in the unsupervised learning subtyping literature due to small-sized samples by vector quantization. Our proposed method better captures the latent space features and models the cancer subtype manifestation on a molecular basis, as demonstrated by the extensive experimental results.

Prediction of Potential Natural Antibiotics Plants Based on Jamu Formula Using Random Forest Classifier.

Jamu is the traditional Indonesian herbal medicine system that is considered to have many benefits such as serving as a cure for diseases or maintaining sound health. A Jamu medicine is generally made from a mixture of several herbs. Natural antibiotics can provide a way to handle the problem of antibiotic resistance. This research aims to discover the potential of herbal plants as natural antibiotic candidates based on a machine learning approach. Our input data consists of a list of herbal formulas with plants as their constituents. The target class corresponds to bacterial diseases that can be cured by herbal formulas. The best model has been observed by implementing the Random Forest (RF) algorithm. For 10-fold cross-validations, the maximum accuracy, recall, and precision are 91.10%, 91.10%, and 90.54% with standard deviations 1.05, 1.05, and 1.48, respectively, which imply that the model obtained is good and robust. This study has shown that 14 plants can be potentially used as natural antibiotic candidates. Furthermore, according to scientific journals, 10 of the 14 selected plants have direct or indirect antibacterial activity.

Very short-term beat-by-beat blood pressure variability in the supine position at rest correlates well with the nocturnal blood pressure variability assessed by ambulatory blood pressure monitoring.

Blood pressure variability (BPV) is an important indicator in risk stratification for hypertension. Among the daily BPVs assessed using a 24-h ambulatory blood pressure (BP) monitor nocturnal systolic BPV has been suggested to predict cardiovascular risks. We hypothesized that very short-term BPV at rest would correlate with nocturnal BPV because of the shared autonomic BP regulatory system under no daily exertion. Thirty untreated normotensive and hypertensive adults underwent 30-min continuous beat-by-beat BP recordings in the supine position, followed by 24-h ambulatory blood pressure monitoring (ABPM). The relationship between very short-term BPV (standard deviation (SD), coefficient of variation (CV)) and daytime and nocturnal BPV (SD, CV, average real variability (ARV), and standardized ARV (CV-ARV)) was assessed with Pearson's correlation coefficients. Very short-term BPV correlated significantly with nocturnal BPV (ARV, r = 0.604, p < 0.001) but not with daytime BPV. These trends were more pronounced with the increasing data length of continuous beat-by-beat BP recording. Using a data segment from the last 10 min of a 30-min continuous beat-by-beat BP recording resulted in a stronger correlation between very short-term BPV and nocturnal BPV than using earlier segments. The findings of this study suggest that very short-term BPV in the supine position at rest may predict nocturnal BPV. Since the burden of ABPM for patients has hindered clinical dissemination, very short-term BPV has the potential to develop a novel index of BPV.

Evaluation of [18F]F-DPA PET for Detecting Microglial Activation in the Spinal Cord of a Rat Model of Neuropathic Pain.

PURPOSE: Recent studies have linked activated spinal glia to neuropathic pain. Here, using a positron emission tomography (PET) scanner with high spatial resolution and sensitivity, we evaluated the feasibility and sensitivity of N,N-diethyl-2-(2-(4-([18F]fluoro)phenyl)-5,7-dimethylpyrazolo[1,5-a] pyrimidin-3-yl)acetamide ([18F]F-DPA) imaging for detecting spinal cord microglial activation after partial sciatic nerve ligation (PSNL) in rats. PROCEDURES: Neuropathic pain was induced in rats (n = 20) by PSNL, and pain sensation tests were conducted before surgery and 3 and 7 days post-injury. On day 7, in vivo PET imaging and ex vivo autoradiography were performed using [18F]F-DPA or [11C]PK11195. Ex vivo biodistribution and PET imaging of the removed spinal cord were carried out with [18F]F-DPA. Sham-operated and PK11195-pretreated animals were also examined. RESULTS: Mechanical allodynia was confirmed in the PSNL rats from day 3 through day 7. Ex vivo autoradiography showed a higher lesion-to-background uptake with [18F]F-DPA compared with [11C]PK11195. Ex vivo PET imaging of the removed spinal cord showed [18F]F-DPA accumulation in the inflammation site, which was immunohistochemically confirmed to coincide with microglia activation. Pretreatment with PK11195 eliminated the uptake. The SUV values of in vivo [18F]F-DPA and [11C]PK11195 PET were not significantly increased in the lesion compared with the reference region, and were fivefold higher than the values obtained from the ex vivo data. Ex vivo biodistribution revealed a twofold higher [18F]F-DPA uptake in the vertebral body compared to that seen in the bone from the skull. CONCLUSIONS: [18F]F-DPA aided visualization of the spinal cord inflammation site in PSNL rats on ex vivo autoradiography and was superior to [11C]PK11195. In vivo [18F]F-DPA PET did not allow for visualization of tracer accumulation even using a high-spatial-resolution PET scanner. The main reason for this result was due to insufficient SUVs in the spinal cord region as compared with the background noise, in addition to a spillover from the vertebral body.

Classification of ischemia from myocardial polar maps in 15O-H2O cardiac perfusion imaging using a convolutional neural network.

We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku PET Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from 15O-H2O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used. The CNN was evaluated against the clinical interpretation. The classification accuracy was evaluated with: accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE) and precision (PRE). The CNN had a median ACC of 0.8261, AUC of 0.8058, F1S of 0.7647, SEN of 0.6500, SPE of 0.9615 and PRE of 0.9286. In comparison, clinical interpretation had ACC of 0.8696, AUC of 0.8558, F1S of 0.8333, SEN of 0.7500, SPE of 0.9615 and PRE of 0.9375. The CNN classified only 2 cases differently than the clinical interpretation. The clinical interpretation and CNN had similar accuracy in classifying false positives and true negatives. Classification of ischemia is feasible in 15O-H2O stress perfusion imaging using JPEG polar maps alone with a custom CNN and may be useful for the detection of obstructive CAD.

Antibacterial Activity Prediction of Plant Secondary Metabolites Based on a Combined Approach of Graph Clustering and Deep Neural Network.

The plants produce numerous types of secondary metabolites which have pharmacological importance in drug development for different diseases. Computational methods widely use the fingerprints of the metabolites to understand different properties and similarities among metabolites and for the prediction of chemical reactions etc. In this work, we developed three different deep neural network models (DNN) to predict the antibacterial property of plant metabolites. We developed the first DNN model using the fingerprint set of metabolites as features. In the second DNN model, we searched the similarities among fingerprints using correlation and used one representative feature from each group of highly correlated fingerprints. In the third model, the fingerprints of metabolites were used to find structurally similar chemical compound clusters. Form each cluster a representative metabolite is selected and made part of the training dataset. The second model reduced the number of features where the third model achieved better classification results for test data. In both cases, we applied the simple graph clustering method to cluster the corresponding network. The correlation-based DNN model reduced some features while retaining an almost similar performance compared to the first DNN model. The third model improves classification results for test data by capturing wider variance within training data using graph clustering method. This third model is somewhat novel approach and can be applied to build DNN models for other purposes.

Cheminformatics modeling of the correlation between Bupleurum Root-formula medicines and Excess and Deficiency pattern in the diagnostic criteria of Sho in Kampo (traditional Japanese medicine) by non-targeted direct infusion mass spectrometry with machine learning.

Kampo is a form of traditional Japanese medicine, and its therapeutic strategy has been validated empirically over millennia, mainly in Asia. Kampo therapy aims to holistically prevent and treat disease based on the specific diagnosis Sho (in Japanese), in contrast with modern medical treatment which focuses on a patient's affected parts and local conditions. The medicines formulated using crude drugs derived from natural sources (Kampo formulas) are prescribed for patients according to their specific Sho, and thus the Kampo medication system is very complex. However, our previous study strongly suggested that Kampo medication theory could be explained by chemometrics and informatic approaches [Okada et al. in J Nat Med 70:107-114, 2016]. Here, we studied a group of seven formulas with Bupleurum Root and Scutellaria Root as the principal crude drugs. First, decoctions of the formulas were prepared and their supernatants were analyzed by non-targeted direct infusion mass spectrometry (MS) and principal component analysis, which is a type of unsupervised machine learning. Next, supervised machine learning was used to perform partial least squares modeling of the MS data matrix trained on the patients' constitution of Excess, Deficiency, or Medium between these two states (EDM) in Sho. The results showed that the correlation between the chemical fingerprints obtained by MS analysis and EDM could be modeled well using this approach. This cheminformatics modeling approach successfully interpreted part of the complex Kampo medication system studied using the fingerprints of formulas obtained by MS analysis and was consistent with the predicted Sho.