Explainable deep-learning-based ischemia detection using hybrid O-15 H2O perfusion positron emission tomography and computed tomography imaging with clinical data.

BACKGROUND: We developed an explainable deep-learning (DL)-based classifier to identify flow-limiting coronary artery disease (CAD) by O-15 H2O perfusion positron emission tomography computed tomography (PET/CT) and coronary CT angiography (CTA) imaging. The classifier uses polar map images with numerical data and visualizes data findings. METHODS: A DLmodel was implemented and evaluated on 138 individuals, consisting of a combined image-and data-based classifier considering 35 clinical, CTA, and PET variables. Data from invasive coronary angiography were used as reference. Performance was evaluated with clinical classification using accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE), precision (PRE), net benefit, and Cohen's Kappa. Statistical testing was conducted using McNemar's test. RESULTS: The DL model had a median ACC = 0.8478, AUC = 0.8481, F1S = 0.8293, SEN = 0.8500, SPE = 0.8846, and PRE = 0.8500. Improved detection of true-positive and false-negative cases, increased net benefit in thresholds up to 34%, and comparable Cohen's kappa was seen, reaching similar performance to clinical reading. Statistical testing revealed no significant differences between DL model and clinical reading. CONCLUSIONS: The combined DL model is a feasible and an effective method in detection of CAD, allowing to highlight important data findings individually in interpretable manner.

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.

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.

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.

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.

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.

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.

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.

Evaluation of intercellular lipid lamellae in the stratum corneum by polarized microscopy.

BACKGROUND: Intercellular lipids contain a lamellar structure that glows in polarized images. It could be expected that the intercellular lipid content be estimated from the luminance values calculated from polarized images of stratum corneum strips. Therefore, we attempted to develop a method for simple and rapid evaluation of the intercellular lipid content through a procedure. Herein, we demonstrated a relationship between the luminance value and the amount of ceramides, one of the main components of intercellular lipids. MATERIALS AND METHODS: The stratum corneum was collected from the forearm using slides with a pure rubber-based adhesive, which did not produce unnecessary luminescence under polarizing conditions. Images were analyzed using luminance indices. The positive secondary ion peak images were obtained using the time of flight-secondary ion mass spectrometry; the polarized and brightfield images were obtained using a polarized microscope. The ceramide and protein amount was measured by high-performance liquid chromatography and bicinchoninic acid protein assay after microscope imaging. Images and quantitative values were used to construct evaluation models based on a convolutional neural network (CNN). RESULTS: There was a correlation between the highlighted areas of the polarized image to overlap with the area where ceramide-derived peak was detected. Evaluation of the CNN-based model of the polarized images predicted the amount of ceramides per unit of stratum corneum. CONCLUSION: The method proposed in the study enabled a large number of specimens to provide a simple, rapid, and efficient evaluation of the intercellular lipid content.

Feasibility Analysis of Symbolic Representation for Single-Channel EEG-Based Sleep Stages.

Sleep screening based on the construction of sleep stages is one of the major tool for the assessment of sleep quality and early detection of sleep-related disorders. Due to the inherent variability such as inter-users anatomical variability and the inter-systems differences, representation learning of sleep stages in order to obtain the stable and reliable characteristics is runoff for downstream tasks in sleep science. In this paper, we investigated feasibility of the EEG-based symbolic representation for sleep stages. By combining the Latent Dirichlet Allocation topic model and comparing with different feature extraction methods, the work proved the feasibility of multi-topics representation for sleep stages and physiological signals.

A Real-Time Portable IoT System for Telework Tracking.

Telework has become a universal working style under the background of COVID-19. With the increased time of working at home, problems, such as lack of physical activities and prolonged sedentary behavior become more prominent. In this situation, a self-managing working pattern regulation may be the most practical way to maintain worker's well-being. To this end, this paper validated the idea of using an Internet of Things (IoT) system (a smartphone and the accompanying smartwatch) to monitor the working status in real-time so as to record the working pattern and nudge the user to have a behavior change. By using the accelerometer and gyroscope enclosed in the smartwatch worn on the right wrist, nine-channel data streams of the two sensors were sent to the paired smartphone for data preprocessing, and action recognition in real time. By considering the cooperativity and orthogonality of the data streams, a shallow convolutional neural network (CNN) model was constructed to recognize the working status from a common working routine. As preliminary research, the results of the CNN model show accurate performance [5-fold cross-validation: 0.97 recall and 0.98 precision; leave-one-out validation: 0.95 recall and 0.94 precision; (support vector machine (SVM): 0.89 recall and 0.90 precision; random forest: 0.95 recall and 0.93 precision)] for the recognition of working status, suggesting the feasibility of this fully online method. Although further validation in a more realistic working scenario should be conducted for this method, this proof-of-concept study clarifies the prospect of a user-friendly online working tracking system. With a tailored working pattern guidance, this method is expected to contribute to the workers' wellness not only during the COVID-19 pandemic but also take effect in the post-COVID-19 era.

Identification of Targeted Proteins by Jamu Formulas for Different Efficacies Using Machine Learning Approach.

BACKGROUND: We performed in silico prediction of the interactions between compounds of Jamu herbs and human proteins by utilizing data-intensive science and machine learning methods. Verifying the proteins that are targeted by compounds of natural herbs will be helpful to select natural herb-based drug candidates. METHODS: Initially, data related to compounds, target proteins, and interactions between them were collected from open access databases. Compounds are represented by molecular fingerprints, whereas amino acid sequences are represented by numerical protein descriptors. Then, prediction models that predict the interactions between compounds and target proteins were constructed using support vector machine and random forest. RESULTS: A random forest model constructed based on MACCS fingerprint and amino acid composition obtained the highest accuracy. We used the best model to predict target proteins for 94 important Jamu compounds and assessed the results by supporting evidence from published literature and other sources. There are 27 compounds that can be validated by professional doctors, and those compounds belong to seven efficacy groups. CONCLUSION: By comparing the efficacy of predicted compounds and the relations of the targeted proteins with diseases, we found that some compounds might be considered as drug candidates.

A system biology approach based on metabolic biomarkers and protein-protein interactions for identifying pathways underlying schizophrenia and bipolar disorder.

Mental disorders (MDs), including schizophrenia (SCZ) and bipolar disorder (BD), have attracted special attention from scientists due to their high prevalence and significantly debilitating clinical features. The diagnosis of MDs is still essentially based on clinical interviews, and intensive efforts to introduce biochemical based diagnostic methods have faced several difficulties for implementation in clinics, due to the complexity and still limited knowledge in MDs. In this context, aiming for improving the knowledge in etiology and pathophysiology, many authors have reported several alterations in metabolites in MDs and other brain diseases. After potentially fishing all metabolite biomarkers reported up to now for SCZ and BD, we investigated here the proteins related to these metabolites in order to construct a protein-protein interaction (PPI) network associated with these diseases. We determined the statistically significant clusters in this PPI network and, based on these clusters, we identified 28 significant pathways for SCZ and BDs that essentially compose three groups representing three major systems, namely stress response, energy and neuron systems. By characterizing new pathways with potential to innovate the diagnosis and treatment of psychiatric diseases, the present data may also contribute to the proposal of new intervention for the treatment of still unmet aspects in MDs.

Kinematics approach with neural networks for early detection of sepsis (KANNEDS).

BACKGROUND: Sepsis is a severe illness that affects millions of people worldwide, and its early detection is critical for effective treatment outcomes. In recent years, researchers have used models to classify positive patients or identify the probability for sepsis using vital signs and other time-series variables as input. METHODS: In our study, we analyzed patients' conditions by their kinematics position, velocity, and acceleration, in a six-dimensional space defined by six vital signs. The patient is affected by the disease after a period if the position gets "near" to a calculated sepsis position in space. We imputed these kinematics features as explanatory variables of long short-term memory (LSTM), convolutional neural network (CNN) and linear neural network (LNN) and compared the prediction accuracies with only the vital signs as input. The dataset used contained information of approximately 4800 patients, each with 48 hourly registers. RESULTS: We demonstrated that the kinematics features models had an improved performance compared with vital signs models. The kinematics features model of LSTM achieved the best accuracy, 0.803, which was nine points higher than the vital signs model. Although with lesser accuracies, the kinematics features models of the CNN and LNN showed better performances than vital signs models. CONCLUSION: Applying our novel approach for early detection of sepsis using neural networks will prove to be an invaluable, more accurate method than considering only simple vital signs as input variables. We expect that other researchers with similar objectives can use the model presented in this innovative approach to improve their results.

The feasibility of predicting impending malignant ventricular arrhythmias by using nonlinear features of short heartbeat intervals.

BACKGROUND AND OBJECTIVE: Malignant ventricular arrhythmias (MAs) occur unpredictably and lead to emergencies. A new approach that uses a timely tracking device e.g., photoplethysmogram (PPG) solely to predict MAs would be irreplaceably valuable and it is natural to expect the approach can predict the occurrence as early as possible. METHOD: We assumed that with an appropriate metric based on signal complexity, the heartbeat interval time series (HbIs) can be used to manifest the intrinsic characteristics of the period immediately precedes the MAs (preMAs). The approach first characterizes the patterns of preMAs by a new complexity metric (the refined composite multi-scale entropy). The MAs detector is then constructed by checking the discriminability of the MAs against the sinus rhythm and other prevalent arrhythmias (atrial fibrillation and premature ventricular contraction) of three machine-learning models (SVM, Random Forest, and XGboost). RESULTS: Two specifications are of interest: the length of the HbIs needed to delineate the preMAs patterns sufficiently (lspec) and how long before the occurrence of MAs will the HbIs manifest specific patterns that are distinct enough to predict the impending MAs (tspec). Our experimental results confirmed the best performance came from a Random-Forest model with an average precision of 99.99% and recall of 88.98% using a HbIs of 800 heartbeats (the lspec), 108 seconds (the tspec) before the occurrence of MAs. CONCLUSION: By experimental validation of the unique pattern of the preMAs in HbIs and using it in the machine learning model, we showed the high possibility of MAs prediction in a broader circumstance, which may cover daily healthcare using the alternative sensor in HbIs monitoring. Therefore, this research is theoretically and practically significant in cardiac arrest prevention.

Dynamic changes of genome sizes and gradual gain of cell-specific distribution of C4 enzymes during C4 evolution in genus Flaveria.

C4 plants are believed to have evolved from C3 plants through various C3 -C4 intermediate stages in which a photorespiration-dependent CO2 concentration system known as C2 photosynthesis operates. Genes involved in the C4 cycle were thought to be recruited from orthologs present in C3 species and developed cell-specific expression during C4 evolution. To understand the process of establishing C4 photosynthesis, we performed whole-genome sequencing and investigated expression and mesophyll- or bundle-sheath-cell-specific localization of phosphoenolpyruvate carboxylase (PEPC), NADP-malic enzyme (NADP-ME), pyruvate, orthophosphate dikinase (PPDK) in C3 , C3 -C4 intermediate, C4 -like, and C4 Flaveria species. While genome sizes vary greatly, the number of predicted protein-coding genes was similar among C3 , C3 -C4 intermediate, C4 -like, and C4 Flaveria species. Cell-specific localization of the PEPC, NADP-ME, and PPDK transcripts was insignificant or weak in C3 -C4 intermediate species, whereas these transcripts were expressed cell-type specific in C4 -like species. These results showed that elevation of gene expression and cell-specific control of pre-existing C4 cycle genes in C3 species was involved in C4 evolution. Gene expression was gradually enhanced during C4 evolution, whereas cell-specific control was gained independently of quantitative transcriptional activation during evolution from C3 -C4 intermediate to C4 photosynthesis in genus Flaveria.

Development of a biomarker database toward performing disease classification and finding disease interrelations.

A biomarker is a measurable indicator of a disease or abnormal state of a body that plays an important role in disease diagnosis, prognosis and treatment. The biomarker has become a significant topic due to its versatile usage in the medical field and in rapid detection of the presence or severity of some diseases. The volume of biomarker data is rapidly increasing and the identified data are scattered. To provide comprehensive information, the explosively growing data need to be recorded in a single platform. There is no open-source freely available comprehensive online biomarker database. To fulfill this purpose, we have developed a human biomarker database as part of the KNApSAcK family databases which contain a vast quantity of information on the relationships between biomarkers and diseases. We have classified the diseases into 18 disease classes, mostly according to the National Center for Biotechnology Information definitions. Apart from this database development, we also have performed disease classification by separately using protein and metabolite biomarkers based on the network clustering algorithm DPClusO and hierarchical clustering. Finally, we reached a conclusion about the relationships among the disease classes. The human biomarker database can be accessed online and the inter-disease relationships may be helpful in understanding the molecular mechanisms of diseases. To our knowledge, this is one of the first approaches to classify diseases based on biomarkers. Database URL:  http://www.knapsackfamily.com/Biomarker/top.php.