Enhanced deep learning technique for sugarcane leaf disease classification and mobile application integration

With an emphasis on classifying diseases of sugarcane leaves, this research suggests an attention-based multilevel deep learning architecture for reliably classifying plant diseases. The suggested architecture comprises spatial and channel attention for saliency detection and blends features from lower to higher levels. On a self-created database, the model outperformed cutting-edge models like VGG19, ResNet50, XceptionNet, and EfficientNet_B7 with an accuracy of 86.53%. The findings show how essential all-level characteristics are for categorizing images and how they can improve efficiency even with tiny databases. The suggested architecture has the potential to support the early detection and diagnosis of plant diseases, enabling fast crop damage mitigation. Additionally, the implementation of the proposed AMRCNN model in the Android phone-based application gives an opportunity for the widespread use of mobile phones in the classification of sugarcane diseases.

Early detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: A multicenter prospective development and validation study

BACKGROUND

Neonatal sepsis is responsible for significant morbidity and mortality worldwide. Its accurate and timely diagnosis is hindered by vague symptoms and the urgent necessity for early antibiotic intervention. The gold standard for diagnosing the condition is the identification of a pathogenic organism from normally sterile sites via laboratory testing. However, this method is resource-intensive and cannot be conducted continuously.

OBJECTIVE

This study aimed to predict the onset of late-onset sepsis (LOS) with good diagnostic value as early as possible using non-invasive biosignal measurements from neonatal intensive care unit (NICU) monitors.

METHODS

In this prospective multicenter study, we developed a multimodal machine learning algorithm based on a convolutional neural network (CNN) structure that uses the power spectral density (PSD) of recorded biosignals to predict the onset of LOS. This approach aimed to discern LOS-related pathogenic spectral signatures without labor-intensive manual artifact removal.

RESULTS

The model achieved an area under the receiver operating characteristic score of 0.810 (95 % CI 0.698-0.922) on the validation dataset. With an optimal operating point, LOS detection had 83 % sensitivity and 73 % specificity. The median early detection was 44 h before clinical suspicion. The results highlighted the additive importance of electrocardiogram and respiratory impedance (RESP) signals in improving predictive accuracy. According to a more detailed analysis, the predictive power arose from the morphology of the electrocardiogram's R-wave and sudden changes in the RESP signal.

CONCLUSION

Raw biosignals from NICU monitors, in conjunction with PSD transformation, as input to the CNN, can provide state-of-the-art prediction performance for LOS without the need for artifact removal. To the knowledge of the authors, this is the first study to highlight the independent and additive predictive potential of electrocardiogram R-wave morphology and concurrent, sudden changes in the RESP waveform in predicting the onset of LOS using non-invasive biosignals.

Self-supervised category selective attention classifier network for diabetic macular edema classification

AIMS

This study aims to develop an advanced model for the classification of Diabetic Macular Edema (DME) using deep learning techniques. Specifically, the objective is to introduce a novel architecture, SSCSAC-Net, that leverages self-supervised learning and category-selective attention mechanisms to improve the precision of DME classification.

METHODS

The proposed SSCSAC-Net integrates self-supervised learning to effectively utilize unlabeled data for learning robust features related to DME. Additionally, it incorporates a category-specific attention mechanism and a domain-specific layer into the ResNet-152 base architecture. The model is trained using an ensemble of unsupervised and supervised learning techniques. Benchmark datasets are utilized for testing the model's performance, ensuring its robustness and generalizability across different data distributions.

RESULTS

Evaluation of the SSCSAC-Net on multiple datasets demonstrates its superior performance compared to existing techniques. The model achieves high accuracy, precision, and recall rates, with an accuracy of 98.7%, precision of 98.6%, and recall of 98.8%. Furthermore, the incorporation of self-supervised learning reduces the dependency on extensive labeled data, making the solution more scalable and cost-effective.

CONCLUSIONS

The proposed SSCSAC-Net represents a significant advancement in automated DME classification. By effectively using self-supervised learning and attention mechanisms, the model offers improved accuracy in identifying DME-related features within retinal images. Its robustness and generalizability across different datasets highlight its potential for clinical applications, providing a valuable tool for clinicians in diagnosing DME effectively.

SOHO State of the Art Updates and Next Questions: An Update on Higher Risk Myelodysplastic Syndromes

Higher-risk myelodysplastic syndromes (HR-MDS) are clonal myeloid neoplasms that cause life-limiting complications from severe cytopenias and leukemic transformation. Efforts to better classify, prognosticate, and assess therapeutic responses in HR-MDS have resulted in publication of new clinical tools in the last several years. Given limited current treatment options and suboptimal outcomes, HR-MDS stands to benefit from the study of investigational agents.Higher-risk myelodysplastic syndromes (HR-MDS) are a heterogenous group of clonal myeloid-lineage malignancies often characterized by high-risk genetic lesions, increased blood transfusion needs, constitutional symptoms, elevated risk of progression to acute myeloid leukemia (AML), and therapeutic need for allogeneic bone marrow transplantation. Use of blast percentage and other morphologic features to define myelodysplastic neoplasm subtypes is rapidly shifting to incorporate genetics, resulting in a subset of former HR-MDS patients now being considered as AML in presence of leukemia-defining genetic alterations. A proliferation of prognostic tools has further focused use of genetic features to drive decision making in clinical management. Recently, criteria to assess response of HR-MDS to therapy were revised to incorporate more clinically meaningful endpoints and better match AML response criteria. Basic science investigations have resulted in improved understanding of the relationship between MDS genetic lesions, bone marrow stromal changes, germline predispositions, and disease phenotype. However, therapeutic advances have been more limited. There has been import of the IDH1 inhibitor ivosidenib, initially approved for AML; the Bcl-2 inhibitor venetoclax and liposomal daunorubicin/cytarabine (CPX-351) are under active investigation as well. Unfortunately, effective treatment of TP53-mutated disease remains elusive, though preliminary evidence suggests improved outcomes with oral decitabine/cedazuridine over parenteral hypomethylating agent monotherapy. Investigational agents with novel mechanisms of action may help expand the repertoire of treatment options for HR-MDS and trials continue to offer a hopeful therapeutic avenue for suitable patients.

An Automated Heart Shunt Recognition Pipeline Using Deep Neural Networks

Automated recognition of heart shunts using saline contrast transthoracic echocardiography (SC-TTE) has the potential to transform clinical practice, enabling non-experts to assess heart shunt lesions. This study aims to develop a fully automated and scalable analysis pipeline for distinguishing heart shunts, utilizing a deep neural network-based framework. The pipeline consists of three steps: (1) chamber segmentation, (2) ultrasound microbubble localization, and (3) disease classification model establishment. The study's normal control group included 91 patients with intracardiac shunts, 61 patients with extracardiac shunts, and 84 asymptomatic individuals. Participants' SC-TTE images were segmented using the U-Net model to obtain cardiac chambers. The segmentation results were combined with ultrasound microbubble localization to generate multivariate time series data on microbubble counts in each chamber. A classification model was then trained using this data to distinguish between intracardiac and extracardiac shunts. The proposed framework accurately segmented heart chambers (dice coefficient = 0.92 ± 0.1) and localized microbubbles. The disease classification model achieved high accuracy, sensitivity, specificity, F1 score, kappa value, and AUC value for both intracardiac and extracardiac shunts. For intracardiac shunts, accuracy was 0.875 ± 0.008, sensitivity was 0.891 ± 0.002, specificity was 0.865 ± 0.012, F1 score was 0.836 ± 0.011, kappa value was 0.735 ± 0.017, and AUC value was 0.942 ± 0.014. For extracardiac shunts, accuracy was 0.902 ± 0.007, sensitivity was 0.763 ± 0.014, specificity was 0.966 ± 0.008, F1 score was 0.830 ± 0.012, kappa value was 0.762 ± 0.017, and AUC value was 0.916 ± 0.006. The proposed framework utilizing deep neural networks offers a fast, convenient, and accurate method for identifying intracardiac and extracardiac shunts. It aids in shunt recognition and generates valuable quantitative indices, assisting clinicians in diagnosing these conditions.

Coconut (Cocos nucifera) tree disease dataset: A dataset for disease detection and classification for machine learning applications

The ``Coconut (Cocos nucifera) Tree Disease Dataset'' comprises 5,798 images across five disease categories: ``Bud Root Dropping,'' ``Bud Rot,'' ``Gray Leaf Spot,'' ``Leaf Rot,'' and ``Stem Bleeding.'' This dataset is intended for machine learning applications, facilitating disease detection and classification in coconut trees. The dataset's diversity and size make it suitable for training and evaluating disease detection models. The availability of this dataset will support advancements in plant pathology and aid in the sustainable management of coconut plantations. By providing a valuable resource for researchers, this dataset contributes to improved disease management and sustainable coconut plantation practices.

Congenital disorders of glycosylation (CDG): state of the art in 2022

Congenital disorders of glycosylation (CDG) are a complex and heterogeneous family of rare metabolic diseases. With a clinical history that dates back over 40 years, it was the recent multi-omics advances that mainly contributed to the fast-paced and encouraging developments in the field. However, much remains to be understood, with targeted therapies' discovery and approval being the most urgent unmet need. In this paper, we present the 2022 state of the art of CDG, including glycosylation pathways, phenotypes, genotypes, inheritance patterns, biomarkers, disease models, and treatments. In light of our current knowledge, it is not always clear whether a specific disease should be classified as a CDG. This can create ambiguity among professionals leading to confusion and misguidance, consequently affecting the patients and their families. This review aims to provide the CDG community with a comprehensive overview of the recent progress made in this field.

SF2Former: Amyotrophic lateral sclerosis identification from multi-center MRI data using spatial and frequency fusion transformer

Amyotrophic Lateral Sclerosis (ALS) is a complex neurodegenerative disorder characterized by motor neuron degeneration. Significant research has begun to establish brain magnetic resonance imaging (MRI) as a potential biomarker to diagnose and monitor the state of the disease. Deep learning has emerged as a prominent class of machine learning algorithms in computer vision and has shown successful applications in various medical image analysis tasks. However, deep learning methods applied to neuroimaging have not achieved superior performance in classifying ALS patients from healthy controls due to insignificant structural changes correlated with pathological features. Thus, a critical challenge in deep models is to identify discriminative features from limited training data. To address this challenge, this study introduces a framework called SF2Former, which leverages the power of the vision transformer architecture to distinguish ALS subjects from the control group by exploiting the long-range relationships among image features. Additionally, spatial and frequency domain information is combined to enhance the network's performance, as MRI scans are initially captured in the frequency domain and then converted to the spatial domain. The proposed framework is trained using a series of consecutive coronal slices and utilizes pre-trained weights from ImageNet through transfer learning. Finally, a majority voting scheme is employed on the coronal slices of each subject to generate the final classification decision. The proposed architecture is extensively evaluated with multi-modal neuroimaging data (i.e., T1-weighted, R2*, FLAIR) using two well-organized versions of the Canadian ALS Neuroimaging Consortium (CALSNIC) multi-center datasets. The experimental results demonstrate the superiority of the proposed strategy in terms of classification accuracy compared to several popular deep learning-based techniques.

Phenotype of new daily persistent headache: subtypes and comparison to transformed chronic daily headache

BACKGROUND

It is unknown whether new daily persistent headache (NDPH) is a single disorder or heterogenous group of disorders, and whether it is a unique disorder from chronic migraine and chronic tension-type headache. We describe a large group of patients with primary NDPH, compare its phenotype to transformed chronic daily headache (T-CDH), and use cluster analysis to reveal potential sub-phenotypes in the NDPH group.

METHODS

We performed a case-control study using prospectively collected clinical data in patients with primary NDPH and T-CDH (encompassing chronic migraine and chronic tension-type headache). We used logistic regression with propensity score matching to compare demographics, phenotype, comorbidities, and treatment responses between NDPH and T-CDH. We used K-means cluster analysis with Gower distance to identify sub-clusters in the NDPH group based on a combination of demographics, phenotype, and comorbidities.

RESULTS

We identified 366 patients with NDPH and 696 with T-CDH who met inclusion criteria. Patients with NDPH were less likely to be female (62.6% vs. 73.3%, p < 0.001). Nausea, vomiting, photophobia, phonophobia, motion sensitivity, vertigo, and cranial autonomic symptoms were all significantly less frequent in NDPH than T-CDH (p value for all < 0.001). Acute treatments appeared less effective in NDPH than T-CDH, and medication overuse was less common (16% vs. 42%, p < 0.001). Response to most classes of oral preventive treatments was poor in both groups. The most effective treatment in NDPH was doselupin in 45.7% patients (95% CI 34.8-56.5%). Cluster analysis identified three subgroups of NDPH. Cluster 1 was older, had a high proportion of male patients, and less severe headaches. Cluster 2 was predominantly female, had severe headaches, and few associated symptoms. Cluster 3 was predominantly female with a high prevalence of migrainous symptoms and headache triggers.

CONCLUSIONS

Whilst there is overlap in the phenotype of NDPH and T-CDH, the differences in migrainous, cranial autonomic symptoms, and vulnerability to medication overuse suggest that they are not the same disorder. NDPH may be fractionated into three sub-phenotypes, which require further investigation.

Enhancing sugarcane disease classification with ensemble deep learning: A comparative study with transfer learning techniques

Deep learning practices in the agriculture sector can address many challenges faced by the farmers such as disease detection, yield estimation, soil profile estimation, etc. In this paper, disease classification for the sugarcane plant and the experimentation involved thereby is thoroughly discussed. Experimental results include the performances of the well-known existing transfer learning techniques and proposed ensemble deep learning based architecture that incorporates stack ensemble of two networks with one having level-wise spatial attention helping to provide better generalization. A Self-created database of sugarcane leaf diseases is introduced to the research community through this paper. It involves 5 categories with a total of 2569 images. Here, it is observed that best performing transfer learning method, MobileNet-V2 shows an accuracy of around 84% with the lowest number of parameters whereas ensemble model reaching to 86.53% with less epochs and with acceptable number of parameters.

SoyNet: A high-resolution Indian soybean image dataset for leaf disease classification

In order to address the challenges related to the classification and recognition of soybean disease and healthy leaf identification, it is essential to have access to high-quality images. A meticulously curated dataset named "SoyNet" has been created to provide a clean and comprehensive dataset for research purposes. The dataset comprises over 9000 high-quality soybean images, encompassing healthy and diseased leaves. These images have been captured from various angles and directly sourced from soybean agriculture fields; The soybean leaves images are organized into two sub-folders: SoyNet Raw Data and SoyNet Pre-processing Data. Within the SoyNet Raw Data folder are separate folders for healthy and diseased images captured using a digital camera. The SoyNet Pre-processing Data folder comprises resized images of 256*256 pixels and the grayscale versions of disease and healthy images, following a similar organizational structure. We captured the images using the Nikon digital camera and the Motorola mobile phone camera, utilizing different angles, lighting conditions, and backgrounds. They were taken in different lighting conditions and backgrounds at soybean cultivation fields to represent the real-world scenario accurately. The proposed dataset is valuable for testing, training, and validating soybean leaf disease classification.

Multi-scale sequential feature selection for disease classification using Raman spectroscopy data

Raman spectroscopy (RS) optical technology promises non-destructive and fast application in medical disease diagnosis in a single step. However, achieving clinically relevant performance levels remains challenging due to the inability to search for significant Raman signals at different scales. Here we propose a multi-scale sequential feature selection method that can capture global sequential features and local peak features for disease classification using RS data. Specifically, we utilize the Long short-term memory network (LSTM) module to extract global sequential features in the Raman spectra, as it can capture long-term dependencies present in the Raman spectral sequences. Meanwhile, the attention mechanism is employed to select local peak features that were ignored before and are the key to distinguishing different diseases. Experimental results on three public and in-house datasets demonstrate the superiority of our model compared with state-of-the-art methods for RS classification. In particular, our model achieves an accuracy of 97.9 ± 0.2% on the COVID-19 dataset, 76.3 ± 0.4% on the H-IV dataset, and 96.8 ± 1.9% on the H-V dataset.

Deep bidirectional LSTM for disease classification supporting hospital admission based on pre-diagnosis: a case study in Vietnam

Overcrowding in hospitals in Vietnam has caused many disadvantages in receiving and treating patients. Especially at the stage of receiving and diagnosing procedures taking patients to the treatment departments in the hospital takes up much time. This study proposes a text-based disease diagnosis using text processing techniques (such as Bag of Words, Term Frequency- Inverse Document Frequency, and Tokenizer) combined with classifiers (such as Random Forests (RF), Multi-Layer Perceptron (MLP), Embeddings and Bidirectional Long Short-term memory (LSTM)) on symptoms. As observed from the results, deep Bidirectional LSTM can reach 0.982 in AUC in the classification of 10 diseases on 230,457 samples of pre-diagnosis collected from Vietnam hospitals used in the training and testing phases. The proposed approach is expected to provide a way to automate patient flow in hospitals to improve healthcare in the future.

Taxonomic reclassification of Kaposi Sarcoma identifies disease entities with distinct immunopathogenesis

BACKGROUND

The taxonomy of Kaposi Sarcoma (KS) is based on a classification system focused on the description of clinicopathological features of KS in geographically and clinically diverse populations. The classification includes classic, endemic, epidemic/HIV associated and iatrogenic KS, and KS in men who have sex with men (MSM). We assessed the medical relevance of the current classification of KS and sought clinically useful improvements in KS taxonomy.

METHODS

We reviewed the demographic and clinicopathological features of 676 patients with KS, who were referred to the national centre for HIV oncology at Chelsea Westminster hospital between 2000 and 2021.

RESULTS

Demographic differences between the different subtypes of KS exist as tautological findings of the current classification system. However, no definitive differences in clinicopathological, virological or immunological parameters at presentation could be demonstrated between the classic, endemic or MSM KS patients. Reclassifying patients as either immunosuppressed or non-immunosuppressed, showed that the immunosuppressed group had a significantly higher proportion of adverse disease features at presentation including visceral disease and extensive oral involvement, classified together as advanced disease (chi² P = 0.0012*) and disseminated skin involvement (chi² P < 0.0001*). Immunosuppressed patients had lower CD4 counts, higher CD8 counts and a trend towards higher HHV8 levels compared to non-immunosuppressed patients, however overall survival and disease specific (KS) survival was similar across groups.

CONCLUSION

The current system of KS classification does not reflect meaningful differences in clinicopathological presentation or disease pathogenesis. Reclassification of patients based on the presence or absence of immunosuppression is a more clinically meaningful system that may influence therapeutic approaches to KS.

A Novel Optimized Perturbation-Based Machine Learning for Preserving Privacy in Medical Data

In recent times, providing privacy to the medical dataset has been the biggest issue in medical applications. Since, in hospitals, the patient's data are stored in files, the files must be secured properly. Thus, different machine learning models were developed to overcome data privacy issues. But, those models faced some problems in providing privacy to medical data. Therefore, a novel model named Honey pot-based Modular Neural System (HbMNS) was designed in this paper. Here, the performance of the proposed design is validated with disease classification. Also, the perturbation function and the verification module are incorporated into the designed HbMNS model to provide data privacy. The presented model is implemented in a python environment. Moreover, the system outcomes are estimated before and after fixing the perturbation function. A DoS attack is launched in the system to validate the method. At last, a comparative assessment is made between executed models with other models. From the comparison, it is verified that the presented model achieved better outcomes than others.

Automatic diagnosis of late-life depression by 3D convolutional neural networks and cross-sample Entropy analysis from resting-state fMRI

Resting-state fMRI has been widely used in investigating the pathophysiology of late-life depression (LLD). Unlike the conventional linear approach, cross-sample entropy (CSE) analysis shows the nonlinear property in fMRI signals between brain regions. Moreover, recent advances in deep learning, such as convolutional neural networks (CNNs), provide a timely application for understanding LLD. Accurate and prompt diagnosis is essential in LLD; hence, this study aimed to combine CNN and CSE analysis to discriminate LLD patients and non-depressed comparison older adults based on brain resting-state fMRI signals. Seventy-seven older adults, including 49 patients and 28 comparison older adults, were included for fMRI scans. Three-dimensional CSEs with volumes corresponding to 90 seed regions of interest of each participant were developed and fed into models for disease classification and depression severity prediction. We obtained a diagnostic accuracy > 85% in the superior frontal gyrus (left dorsolateral and right orbital parts), left insula, and right middle occipital gyrus. With a mean root-mean-square error (RMSE) of 2.41, three separate models were required to predict depressive symptoms in the severe, moderate, and mild depression groups. The CSE volumes in the left inferior parietal lobule, left parahippocampal gyrus, and left postcentral gyrus performed best in each respective model. Combined complexity analysis and deep learning algorithms can classify patients with LLD from comparison older adults and predict symptom severity based on fMRI data. Such application can be utilized in precision medicine for disease detection and symptom monitoring in LLD.

Exploring novel disease-disease associations based on multi-view fusion network

Established taxonomy system based on disease symptom and tissue characteristics have provided an important basis for physicians to correctly identify diseases and treat them successfully. However, these classifications tend to be based on phenotypic observations, lacking a molecular biological foundation. Therefore, there is an urgent to integrate multi-dimensional molecular biological information or multi-omics data to redefine disease classification in order to provide a powerful perspective for understanding the molecular structure of diseases. Therefore, we offer a flexible disease classification that integrates the biological process, gene expression, and symptom phenotype of diseases, and propose a disease-disease association network based on multi-view fusion. We applied the fusion approach to 223 diseases and divided them into 24 disease clusters. The contribution of internal and external edges of disease clusters were analyzed. The results of the fusion model were compared with Medical Subject Headings, a traditional and commonly used disease taxonomy. Then, experimental results of model performance comparison show that our approach performs better than other integration methods. As it was observed, the obtained clusters provided more interesting and novel disease-disease associations. This multi-view human disease association network describes relationships between diseases based on multiple molecular levels, thus breaking through the limitation of the disease classification system based on tissues and organs. This approach which motivates clinicians and researchers to reposition the understanding of diseases and explore diagnosis and therapy strategies, extends the existing disease taxonomy.

Availability of data and materials

The preprocessed dataset and source code supporting the conclusions of this article are available at GitHub repository https://github.com/yangxiaoxi89/mvHDN.

PCAN: Pixel-wise classification and attention network for thoracic disease classification and weakly supervised localization

Automatic chest X-ray (CXR) disease classification has drawn increasing public attention as CXR is widely used in thoracic disease diagnosis. Existing classification networks typically employ a global average pooling layer to produce the final feature for the subsequent classifier. This limits the classification performance owing to the characteristics of lesions in CXR images, including small relative sizes, varied absolute sizes, and different occurrence locations. In this study, we propose a pixel-wise classification and attention network (PCAN) to simultaneously perform disease classification and weakly supervised localization, which provides interpretability for disease classification. The PCAN comprises a backbone network for extracting mid-level features, a pixel-wise classification branch (pc-branch) for generating pixel-wise diagnoses, and a pixel-wise attention branch (pa-branch) for producing pixel-wise weights. The pc-branch is capable of explicitly detecting small lesions, and the pa-branch is capable of adaptively focusing on different regions when classifying different thoracic diseases. Then, the pixel-wise diagnoses are multiplied with the pixel-wise weights to obtain the disease localization map, which provides the sizes and locations of lesions in a manner of weakly supervised learning. The final image-wise diagnosis is obtained by summing up the disease localization map at the spatial dimension. Comprehensive experiments conducted on the ChestX-ray14 and CheXpert datasets demonstrate the effectiveness of the proposed PCAN, which has great potential for thoracic disease diagnosis and treatment. The source codes are available at https://github.com/fzfs/PCAN.

Identifying Diagnoses of Schizophrenia Spectrum Disorder in Large Data Sets

Objective

The authors used a large clinical data set to determine which index diagnoses of schizophrenia spectrum disorder were new diagnoses.

Methods

Using the Massachusetts All-Payer Claims Database (2012–2016), the authors identified patients with a schizophrenia spectrum disorder diagnosis in 2016 (index diagnosis) and then reviewed patients’ care histories for the previous 12, 24, 36, and 48 months to identify previous diagnoses. Logistic regression was used to examine patient characteristics associated with the index diagnosis being a new diagnosis.

Results

Overall, 7,217 individuals ages 15–35 years had a 2016 diagnosis of schizophrenia spectrum disorder; 67.7% had at least 48 months of historical data. Among those with at least 48 months of care history, 23% had no previous diagnoses. Diagnoses from inpatient psychiatric admissions or among female or younger patients were more likely to represent new diagnoses, compared with diagnoses from most other diagnosis locations or among males or older age groups, and outpatient diagnoses were less likely to represent new diagnoses than were most other diagnosis settings. Reviewing 48 instead of 12 months of data reduced estimated rates of new diagnoses from 112 to 66 per 100,000 persons; historical diagnoses were detected for 61% and 77% of patients with 12 or 48 months of care history, respectively.

Conclusions

Examining multiple years of patient history spanning all payers and providers is critical to identifying new schizophrenia spectrum disorder diagnoses in large data sets. Review of 48 months of care history resulted in lower rates of new schizophrenia spectrum disorder diagnoses than previously reported.

Is Takotsubo cardiomyopathy still looking for its own nosological identity?

Despite several efforts to provide a proper nosological framework for Takotsubo cardiomyopathy (TCM), this remains an unresolved matter in clinical practice. Several clinical, pathophysiologic and histologic findings support the conceivable hypothesis that TCM could be defined as a unique pathologic entity, rather than a distinct subset of myocardial infarction with non-obstructive coronary arteries. Further investigations are needed in order to define TCM with the most appropriate disease taxonomy.

Artificial Intelligence for Retinopathy of Prematurity: Validation of a Vascular Severity Scale against International Expert Diagnosis

PURPOSE

To validate a vascular severity score as an appropriate output for artificial intelligence (AI) Software as a Medical Device (SaMD) for retinopathy of prematurity (ROP) through comparison with ordinal disease severity labels for stage and plus disease assigned by the International Classification of Retinopathy of Prematurity, Third Edition (ICROP3), committee.

DESIGN

Validation study of an AI-based ROP vascular severity score.

PARTICIPANTS

A total of 34 ROP experts from the ICROP3 committee.

METHODS

Two separate datasets of 30 fundus photographs each for stage (0-5) and plus disease (plus, preplus, neither) were labeled by members of the ICROP3 committee using an open-source platform. Averaging these results produced a continuous label for plus (1-9) and stage (1-3) for each image. Experts were also asked to compare each image to each other in terms of relative severity for plus disease. Each image was also labeled with a vascular severity score from the Imaging and Informatics in ROP deep learning system, which was compared with each grader's diagnostic labels for correlation, as well as the ophthalmoscopic diagnosis of stage.

MAIN OUTCOME MEASURES

Weighted kappa and Pearson correlation coefficients (CCs) were calculated between each pair of grader classification labels for stage and plus disease. The Elo algorithm was also used to convert pairwise comparisons for each expert into an ordered set of images from least to most severe.

RESULTS

The mean weighted kappa and CC for all interobserver pairs for plus disease image comparison were 0.67 and 0.88, respectively. The vascular severity score was found to be highly correlated with both the average plus disease classification (CC = 0.90, P < 0.001) and the ophthalmoscopic diagnosis of stage (P < 0.001 by analysis of variance) among all experts.

CONCLUSIONS

The ROP vascular severity score correlates well with the International Classification of Retinopathy of Prematurity committee member's labels for plus disease and stage, which had significant intergrader variability. Generation of a consensus for a validated scoring system for ROP SaMD can facilitate global innovation and regulatory authorization of these technologies.

Content-based medical image retrieval system for lung diseases using deep CNNs

Content-based image retrieval (CBIR) systems are designed to retrieve images that are relevant, based on detailed analysis of latent image characteristics, thus eliminating the dependency of natural language tags, text descriptions, or keywords associated with the images. A CBIR system maintains high-level image visuals in the form of feature vectors, which the retrieval engine leverages for similarity-based matching and ranking for a given query image. In this paper, a CBIR system is proposed for the retrieval of medical images (CBMIR) for enabling the early detection and classification of lung diseases based on lung X-ray images. The proposed CBMIR system is built on the predictive power of deep neural models for the identification and classification of disease-specific features using transfer learning based models trained on standard COVID-19 Chest X-ray image datasets. Experimental evaluation on the standard dataset revealed that the proposed approach achieved an improvement of 49.71% in terms of precision, averaging across various distance metrics. Also, an improvement of 26.55% was observed in the area under precision-recall curve (AUPRC) values across all subclasses.

Learning biologically-interpretable latent representations for gene expression data: Pathway Activity Score Learning Algorithm

Molecular gene-expression datasets consist of samples with tens of thousands of measured quantities (i.e., high dimensional data). However, lower-dimensional representations that retain the useful biological information do exist. We present a novel algorithm for such dimensionality reduction called Pathway Activity Score Learning (PASL). The major novelty of PASL is that the constructed features directly correspond to known molecular pathways (genesets in general) and can be interpreted as pathway activity scores. Hence, unlike PCA and similar methods, PASL's latent space has a fairly straightforward biological interpretation. PASL is shown to outperform in predictive performance the state-of-the-art method (PLIER) on two collections of breast cancer and leukemia gene expression datasets. PASL is also trained on a large corpus of 50000 gene expression samples to construct a universal dictionary of features across different tissues and pathologies. The dictionary validated on 35643 held-out samples for reconstruction error. It is then applied on 165 held-out datasets spanning a diverse range of diseases. The AutoML tool JADBio is employed to show that the predictive information in the PASL-created feature space is retained after the transformation. The code is available at https://github.com/mensxmachina/PASL.

Electrochemical immuno determination of connective tissue growth factor levels on nitrogen-doped graphene

Connective tissue growth factor (CTGF) is a disease marker of rheumatoid arthritis (RA), and its rapid and sensitive detection is essential for the diagnosis of RA. In this work, a three-dimensional pore structure of alkali-activated nitrogen-doped graphene (aN-G) was used as an electrode modification material, and a label-free electrochemical immunosensor for the sensitive detection of CTGF was successfully constructed by the formation of an amide bond between amino groups in protein and carboxyl groups on the carbon surface. Under optimized conditions, the sensor achieved accurate detection of CTGF in the wide range of 0.0625 ~ 2000 pg mL^-1. It had good accuracy (95.0 ~ 100.1%), repeatability (1.2 ~ 2.2%), stability, selectivity, and a low limit of detection (0.0424 pg mL^-1, S/N = 3). The sensor was used in serum samples of patients with RA, and CTGF was also successfully detected. Based on this, the electrochemical sensor is expected to become an effective method for RA diagnosis and treatment effect evaluation.

The missed disease? Endometriosis as an example of 'undone science'

Endometriosis is a chronic gynaecological condition which has been referred to as the 'missed disease' due to its unclear aetiology and inconsistencies in its diagnosis and management. Unlike other long-term conditions such as diabetes and asthma, endometriosis has remained largely ignored in government policy and research funding globally. Drawing on scholarship from the growing field of 'ignorance studies', this paper considers how ambiguity around endometriosis is part of a wider constellation of discursive, material and political factors which enrol certain forms of knowledge whilst silencing, ignoring or marginalizing other forms of knowledge. It uses concepts of 'undone science' and 'wilful ignorance' to explore how an absence of knowledge on endometriosis is a result of structural, cultural and political processes and forces which privilege certain voices and communities. This paper suggests that the association of endometriosis with historically specific constructions of menstruation and women's pain has informed contemporary imaginaries around the condition, including ideas about women being somehow accountable for their own illnesses. Applying an ignorance lens demonstrates how the legacy of invisibility of endometriosis shapes its place in the present political and social arena, and is reflective of a process of undone science. The paper concludes by arguing that the social and political significance of endometriosis as a chronic, life-limiting condition which affects millions of women globally continues to need attention, illumination and critique.

Determine independent gut microbiota-diseases association by eliminating the effects of human lifestyle factors

Lifestyle and physiological variables on human disease risk have been revealed to be mediated by gut microbiota. Low concordance between case-control studies for detecting disease-associated microbe existed due to limited sample size and population-wide bias in lifestyle and physiological variables. To infer gut microbiota-disease associations accurately, we propose to build machine learning models by including both human variables and gut microbiota. When the model's performance with both gut microbiota and human variables is better than the model with just human variables, the independent gut microbiota -disease associations will be confirmed. By building models on the American Gut Project dataset, we found that gut microbiota showed distinct association strengths with different diseases. Adding gut microbiota into human variables enhanced the classification performance of IBD significantly; independent associations between occurrence information of gut microbiota and irritable bowel syndrome, C. difficile infection, and unhealthy status were found; adding gut microbiota showed no improvement on models' performance for diabetes, small intestinal bacterial overgrowth, lactose intolerance, cardiovascular disease. Our results suggested that although gut microbiota was reported to be associated with many diseases, a considerable proportion of these associations may be very weak. We proposed a list of microbes as biomarkers to classify IBD and unhealthy status. Further functional investigations of these microbes will improve understanding of the molecular mechanism of human diseases.

SpecMEn-DL: spectral mask enhancement with deep learning models to predict COVID-19 from lung ultrasound videos

Lung Ultrasound (LUS) images are considered to be effective for detecting Coronavirus Disease (COVID-19) as an alternative to the existing reverse transcription-polymerase chain reaction (RT-PCR)-based detection scheme. However, the recent literature exhibits a shortage of works dealing with LUS image-based COVID-19 detection. In this paper, a spectral mask enhancement (SpecMEn) scheme is introduced along with a histogram equalization pre-processing stage to reduce the noise effect in LUS images prior to utilizing them for feature extraction. In order to detect the COVID-19 cases, we propose to utilize the SpecMEn pre-processed LUS images in the deep learning (DL) models (namely the SpecMEn-DL method), which offers a better representation of some characteristics features in LUS images and results in very satisfactory classification performance. The performance of the proposed SpecMEn-DL technique is appraised by implementing some state-of-the-art DL models and comparing the results with related studies. It is found that the use of the SpecMEn scheme in DL techniques offers an average increase in accuracy and F 1 score of 11 % and 11.75 % , respectively, at the video-level. Comprehensive analysis and visualization of the intermediate steps manifest a very satisfactory detection performance creating a flexible and safe alternative option for the clinicians to get assistance while obtaining the immediate evaluation of the patients.

Immune infiltration landscape and immune-marker molecular typing of pulmonary fibrosis with pulmonary hypertension

BACKGROUND

Pulmonary arterial hypertension (PH) secondary to pulmonary fibrosis (PF) is one of the most common complications in PF patients, it causes severe disease and usually have a poor prognosis. Whether the combination of PH and PF is a unique disease phenotype is unclear. We aimed to screen the key modules associated with PH-PF immune infiltration based on WGCNA and identify the hub genes for molecular typing.

METHOD

Using the gene expression profile GSE24988 of PF patients with or without PH from the Gene Expression Omnibus (GEO) database, we evaluated immune cell infiltration using Cibersortx and immune cell gene signature files. Different immune cell types were screened using the Wilcoxon test; differentially expressed genes were screened using samr. The molecular pathways implicated in these differential responses were identified using Gene Ontology and Kyoto Encyclopedia of Genes and Genomes functional enrichment analyses. A weighted co-expression network of the differential genes was constructed, relevant co-expression modules were identified, and relationships between modules and differential immune cell infiltration were calculated. The modules most relevant to this disease were identified using weighted correlation network analysis. From these, we constructed a co-expression network; using the STRING database, we integrated the values into the human protein-protein interaction network before constructing a co-expression interaction subnet, screening genes associated with immunity and unsupervised molecular typing, and analyzing the immune cell infiltration and expression of key genes in each disease type.

RESULTS

Of the 22 immune cell types from the PF GEO data, 20 different immune cell types were identified. There were 1622 differentially expressed genes (295 upregulated and 1327 downregulated). The resulting weighted co-expression network identified six co-expression modules. These were screened to identify the modules most relevant to the disease phenotype (the green module). By calculating the correlations between modules and the differentially infiltrated immune cells, extracting the green module co-expression network (46 genes), extracting 25 key genes using gene significance and module-membership thresholds, and combining these with the 10 key genes in the human protein-protein interaction network, we identified five immune cell-related marker genes that might be applied as biomarkers. Using these marker genes, we evaluated these disease samples using unsupervised clustering molecular typing.

CONCLUSION

Our results demonstrated that all PF combined with PH samples belonged to four categories. Studies on the five key genes are required to validate their diagnostic and prognostic value.

Natural history of subaortic stenosis in 166 dogs (1999-2011)

INTRODUCTION

Subaortic stenosis (SAS) is one of the most common congenital cardiac diseases in dogs. The objective of this study was to provide survival times on a large population of dogs with SAS and to propose a redefined pressure gradient (PG) scale to include a mild, moderate, severe and very severe disease group.

ANIMALS, MATERIALS AND METHODS

Dogs were divided into four groups based on the Doppler-derived PG across the stenosis. Disease severity was defined as follows: mild = PG < 50 mmHg; moderate = PG range 50-80 mmHg; severe = PG range 80-130 mmHg; and very severe = PG > 130 mmHg. Over the study period (1999-2011), 166 client-owned dogs were diagnosed with SAS of which 129 had follow-up information available.

RESULTS

Unadjusted median survival time for severity groups were as follows: mild 10.6 years; moderate 9.9 years; severe 7.3 years; and very severe 3.0 years. Univariable analysis examining the effect of the PG, age at diagnosis and sex found only the PG and age at diagnosis had a significant effect on survival. Adjusted survival curves showed that the survival time in the very severe group was decreased compared with all other groups.

CONCLUSION

Based on the results of this study, a revised SAS classification system with four PG groups is appropriate. Dogs with a PG > 130 mmHg were identified as those with the lowest median survival time.

The utility of cardiovascular imaging in heart failure with preserved ejection fraction: diagnosis, biological classification and risk stratification

Heart failure with preserved ejection fraction (HFpEF) does not exist as a singular clinical or pathological entity but as a syndrome encompassing a wide range of clinical and biological phenotypes. There is an urgent need to progress from the unsuccessful 'one-size-fits-all' approach to more precise disease classification, in order to develop targeted therapies, personalise risk stratification and guide future research. In this regard, this review discusses the current and emerging roles of cardiovascular imaging for the diagnosis of HFpEF, for distilling HFpEF into distinct disease entities according to underlying pathobiology and for risk stratification.

UMS-Rep: Unified modality-specific representation for efficient medical image analysis

Medical image analysis typically includes several tasks such as enhancement, segmentation, and classification. Traditionally, these tasks are implemented using separate deep learning models for separate tasks, which is not efficient because it involves unnecessary training repetitions, demands greater computational resources, and requires a relatively large amount of labeled data. In this paper, we propose a multi-task training approach for medical image analysis, where individual tasks are fine-tuned simultaneously through relevant knowledge transfer using a unified modality-specific feature representation (UMS-Rep). We explore different fine-tuning strategies to demonstrate the impact of the strategy on the performance of target medical image tasks. We experiment with different visual tasks (e.g., image denoising, segmentation, and classification) to highlight the advantages offered with our approach for two imaging modalities, chest X-ray and Doppler echocardiography. Our results demonstrate that the proposed approach reduces the overall demand for computational resources and improves target task generalization and performance. Specifically, the proposed approach improves accuracy (up to ∼ 9% ↑) and decreases computational time (up to ∼ 86% ↓) as compared to the baseline approach. Further, our results prove that the performance of target tasks in medical images is highly influenced by the utilized fine-tuning strategy.

Diagnosis of Polycystic Ovary Syndrome: Which Criteria to Use and When?

Current diagnostic criteria for polycystic ovary syndrome (PCOS) are based on expert opinion. This article reviews the rationale for and the limitations of these criteria as well as which criteria to use and when. The insights provided into PCOS pathogenesis by modern genetic analyses and the promise of objective data mining approaches for biologically relevant disease classification are discussed.

A novel gene selection method for gene expression data for the task of cancer type classification

Cancer is a poligenetic disease with each cancer type having a different mutation profile. Genomic data can be utilized to detect these profiles and to diagnose and differentiate cancer types. Variant calling provide mutation information. Gene expression data reveal the altered cell behaviour. The combination of the mutation and expression information can lead to accurate discrimination of different cancer types. In this study, we utilized and transferred the information of existing mutations for a novel gene selection method for gene expression data. We tested the proposed method in order to diagnose and differentiate cancer types. It is a disease specific method as both the mutations and expressions are filtered according to the selected cancer types. Our experiment results show that the proposed gene selection method leads to similar or improved performance metrics compared to classical feature selection methods and curated gene sets.

VR-Caps: A Virtual Environment for Capsule Endoscopy

Current capsule endoscopes and next-generation robotic capsules for diagnosis and treatment of gastrointestinal diseases are complex cyber-physical platforms that must orchestrate complex software and hardware functions. The desired tasks for these systems include visual localization, depth estimation, 3D mapping, disease detection and segmentation, automated navigation, active control, path realization and optional therapeutic modules such as targeted drug delivery and biopsy sampling. Data-driven algorithms promise to enable many advanced functionalities for capsule endoscopes, but real-world data is challenging to obtain. Physically-realistic simulations providing synthetic data have emerged as a solution to the development of data-driven algorithms. In this work, we present a comprehensive simulation platform for capsule endoscopy operations and introduce VR-Caps, a virtual active capsule environment that simulates a range of normal and abnormal tissue conditions (e.g., inflated, dry, wet etc.) and varied organ types, capsule endoscope designs (e.g., mono, stereo, dual and 360^∘ camera), and the type, number, strength, and placement of internal and external magnetic sources that enable active locomotion. VR-Caps makes it possible to both independently or jointly develop, optimize, and test medical imaging and analysis software for the current and next-generation endoscopic capsule systems. To validate this approach, we train state-of-the-art deep neural networks to accomplish various medical image analysis tasks using simulated data from VR-Caps and evaluate the performance of these models on real medical data. Results demonstrate the usefulness and effectiveness of the proposed virtual platform in developing algorithms that quantify fractional coverage, camera trajectory, 3D map reconstruction, and disease classification. All of the code, pre-trained weights and created 3D organ models of the virtual environment with detailed instructions how to setup and use the environment are made publicly available at https://github.com/CapsuleEndoscope/VirtualCapsuleEndoscopy and a video demonstration can be seen in the supplementary videos (Video-I).

Neuropsychiatric disease classification using functional connectomics - results of the connectomics in neuroimaging transfer learning challenge

Large, open-source datasets, such as the Human Connectome Project and the Autism Brain Imaging Data Exchange, have spurred the development of new and increasingly powerful machine learning approaches for brain connectomics. However, one key question remains: are we capturing biologically relevant and generalizable information about the brain, or are we simply overfitting to the data? To answer this, we organized a scientific challenge, the Connectomics in NeuroImaging Transfer Learning Challenge (CNI-TLC), held in conjunction with MICCAI 2019. CNI-TLC included two classification tasks: (1) diagnosis of Attention-Deficit/Hyperactivity Disorder (ADHD) within a pre-adolescent cohort; and (2) transference of the ADHD model to a related cohort of Autism Spectrum Disorder (ASD) patients with an ADHD comorbidity. In total, 240 resting-state fMRI (rsfMRI) time series averaged according to three standard parcellation atlases, along with clinical diagnosis, were released for training and validation (120 neurotypical controls and 120 ADHD). We also provided Challenge participants with demographic information of age, sex, IQ, and handedness. The second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing. Classification methodologies were submitted in a standardized format as containerized Docker images through ChRIS, an open-source image analysis platform. Utilizing an inclusive approach, we ranked the methods based on 16 metrics: accuracy, area under the curve, F1-score, false discovery rate, false negative rate, false omission rate, false positive rate, geometric mean, informedness, markedness, Matthew's correlation coefficient, negative predictive value, optimized precision, precision, sensitivity, and specificity. The final rank was calculated using the rank product for each participant across all measures. Furthermore, we assessed the calibration curves of each methodology. Five participants submitted their method for evaluation, with one outperforming all other methods in both ADHD and ASD classification. However, further improvements are still needed to reach the clinical translation of functional connectomics. We have kept the CNI-TLC open as a publicly available resource for developing and validating new classification methodologies in the field of connectomics.

Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms

OBJECTIVE

This study aims to develop and test a new computer-aided diagnosis (CAD) scheme of chest X-ray images to detect coronavirus (COVID-19) infected pneumonia.

METHOD

CAD scheme first applies two image preprocessing steps to remove the majority of diaphragm regions, process the original image using a histogram equalization algorithm, and a bilateral low-pass filter. Then, the original image and two filtered images are used to form a pseudo color image. This image is fed into three input channels of a transfer learning-based convolutional neural network (CNN) model to classify chest X-ray images into 3 classes of COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) cases. To build and test the CNN model, a publicly available dataset involving 8474 chest X-ray images is used, which includes 415, 5179 and 2,880 cases in three classes, respectively. Dataset is randomly divided into 3 subsets namely, training, validation, and testing with respect to the same frequency of cases in each class to train and test the CNN model.

RESULTS

The CNN-based CAD scheme yields an overall accuracy of 94.5 % (2404/2544) with a 95 % confidence interval of [0.93,0.96] in classifying 3 classes. CAD also yields 98.4 % sensitivity (124/126) and 98.0 % specificity (2371/2418) in classifying cases with and without COVID-19 infection. However, without using two preprocessing steps, CAD yields a lower classification accuracy of 88.0 % (2239/2544).

CONCLUSION

This study demonstrates that adding two image preprocessing steps and generating a pseudo color image plays an important role in developing a deep learning CAD scheme of chest X-ray images to improve accuracy in detecting COVID-19 infected pneumonia.

LAMP: disease classification derived from layered assessment on modules and pathways in the human gene network

Background

Classification of diseases based on genetic information is of great significance as the basis for precision medicine, increasing the understanding of disease etiology and revolutionizing personalized medicine. Much effort has been directed at understanding disease associations by constructing disease networks, and classifying patient samples according to gene expression data. Integrating human gene networks overcomes limited coverage of genes. Incorporating pathway information into disease classification procedure addresses the challenge of cellular heterogeneity across patients.

Results

In this work, we propose a disease classification model LAMP, which concentrates on the layered assessment on modules and pathways. Directed human gene interactions are the foundation of constructing the human gene network, where the significant roles of disease and pathway genes are recognized. The fast unfolding algorithm identifies 11 modules in the largest connected component. Then layered networks are introduced to distinguish positions of genes in propagating information from sources to targets. After gene screening, hierarchical clustering and refined process, 1726 diseases from KEGG are classified into 18 categories. Also, it is expounded that diseases with overlapping genes may not belong to the same category in LAMP. Within each category, entropy is applied to measure the compositional complexity, and to evaluate the prospects for combination diagnosis and gene-targeted therapy for diseases.

Conclusion

In this work, by collecting data from BioGRID and KEGG, we develop a disease classification model LAMP, to support people to view diseases from the perspective of commonalities in etiology and pathology. Comprehensive research on existing diseases can help meet the challenges of unknown diseases. The results provide suggestions for combination diagnosis and gene-targeted therapy, which motivates clinicians and researchers to reposition the understanding of diseases and explore diagnosis and therapy strategies.

Label-free detection of thalassemia and other ROS impairing diseases

Pathogenesis of different diseases showed that some of them, especially thalassemia (T) and rheumatoid arthritis (RA) have an implicit association with oxidative stress and altered levels of reactive oxygen species (ROS). Introducing ROS level and the balance between ROS and antioxidants as essential metrics, an attempt was made to classify T and RA from normal individuals (treated as controls)(C) using synchronous fluorescence spectroscopy (SFS) and Raman line intensity of water. This non-invasive and label-free approach was backed up by a categorization algorithm that helped in the prediction of disease types from serum samples. The predictive system constituted principal component analysis (PCA) with four parameters, namely spectral intensity ratios of reduced nicotinamide adenine dinucleotide (NADH) to tryptophan (Trp) (NADH/Trp), kynurenine (Kyn) to tryptophan (Kyn/Trp), kynurenine to NADH (Kyn/NADH), and logarithmic changes in Raman line intensity of water (Rline), with the index headers containing the disease types. Rline has a positive correlation with both Kyn/Trp and Kyn/NADH and a negative correlation with NADH/Trp ratio, implying its direct or indirect association with oxidative stress. In addition to the classification of T, RA, and C a sub-classification of T into beta major and E-beta in their post and pre-splenectomized surgical stages could also be realized. Furthermore, receiver operating characteristic (ROC) analysis was deployed to ascertain that the misclassification error (ME) was negligible for the disease types. Graphical Abstract A schematic representation of the workflow converging into the categorical classification of disease classes.

Epidemiology of Hepatic Encephalopathy

Hepatic encephalopathy (HE) is a complex condition with multiple causes each with varying degrees of severity. HE negatively impacts patients' quality of life, and it is associated with significant burdens to patients and their caregivers. The prevalence of cirrhosis, the most common risk factor for HE, has steadily increased during recent years. In turn, an upsurge in the clinical and health care burdens related to HE is expected in the upcoming years. This article provides a comprehensive review of the epidemiology of HE.

Dataset of illness classifications in Sowa Rigpa: Compilations from the Oral Instructions Treatise of the Tibetan medical classic (Rgyud bzhi)

This article shares the comprehensive dataset and five visualized examples of disease categories in Tibetan medicine, or Sowa Rigpa (Tib. Gso ba rig pa), translated as the "knowledge field of healing." Sowa Rigpa is a scholarly Asian traditional medical system rigorously transmitted through canonical texts and oral teachings originating in Tibet with an extensive pharmacopeia, comprehensive treatment repertoire, and nuanced etiological explications of its nosology of diseases. This medical tradition is practiced across a broad region of Asia, particularly in Tibetan regions of China, Himalayan regions of India (Ladakh, Sikkim, Himachal Pradesh), Nepal, Bhutan, Mongolia, Russia, and recently in Europe and North America. The data herein depicts disease classifications listed in the encyclopedic compendium "Oral Instructions Treatise" (Man ngag rgyud) of the Tibetan medical classic, the Four Medical Treatises (Rgyud bzhi), compiled in written form during the twelfth century CE. Visualized examples depict etiological relations among diseases in five of the fifteen major categories of disease: rLung Illnesses, Béken Illneses, Pediatric Conditions, Eye Conditions and Tropical Infectious Diseases. Disease names were entered into spreadsheet format and categorized by etiological hierarchical structure. Data are written in Unicode Tibetan font to retain fidelity to entries in the classical text, with parallel columns in standard Wylie transliteration. Subsets of the data are visually depicted through a graphic platform called Interactive Tree of Life to demonstrate etiological associations. This dataset is the first publicly available enumeration of the specific diseases, classifications and etiological relationships from the Tibetan medical classic. The data are linked to the article entitled "Tibetan Medical Informatics: An Emerging Field in Sowa Rigpa Pharmacological & Clinical Research" (Dhondrup et al., 2020).

The 2020 update of the CEAP classification system and reporting standards

The CEAP (Clinical-Etiology-Anatomy-Pathophysiology) classification is an internationally accepted standard for describing patients with chronic venous disorders and it has been used for reporting clinical research findings in scientific journals. Developed in 1993, updated in 1996, and revised in 2004, CEAP is a classification system based on clinical manifestations of chronic venous disorders, on current understanding of the etiology, the involved anatomy, and the underlying venous pathology. As the evidence related to these aspects of venous disorders, and specifically of chronic venous diseases (CVD, C2-C6) continue to develop, the CEAP classification needs periodic analysis and revisions. In May of 2017, the American Venous Forum created a CEAP Task Force and charged it to critically analyze the current classification system and recommend revisions, where needed. Guided by four basic principles (preservation of the reproducibility of CEAP, compatibility with prior versions, evidence-based, and practical for clinical use), the Task Force has adopted the revised Delphi process and made several changes. These changes include adding Corona phlebectatica as the C4c clinical subclass, introducing the modifier "r" for recurrent varicose veins and recurrent venous ulcers, and replacing numeric descriptions of the venous segments by their common abbreviations. This report describes all these revisions and the rationale for making these changes.

Progression of fibrosing interstitial lung disease

Fibrotic interstitial lung diseases (ILDs) are often challenging to diagnose and classify, but an accurate diagnosis has significant implications for both treatment and prognosis. A subset of patients with fibrotic ILD experience progressive deterioration in lung function, physical performance, and quality of life. Several risk factors for ILD progression have been reported, such as male sex, older age, lower baseline pulmonary function, and a radiological or pathological pattern of usual interstitial pneumonia. Morphological similarities, common underlying pathobiologic mechanisms, and the consistently progressive worsening of these patients support the concept of a progressive fibrosing (PF)-ILD phenotype that can be applied to a variety of ILD subtypes. The conventional approach has been to use antifibrotic medications in patients with idiopathic pulmonary fibrosis (IPF) and immunosuppressive medications in patients with other fibrotic ILD subtypes; however, recent clinical trials have suggested a favourable treatment response to antifibrotic therapy in a wider variety of fibrotic ILDs. This review summarizes the literature on the evaluation and management of patients with PF-ILD, and discusses questions relevant to applying recent clinicial trial findings to real-world practice.

Improved RA classification among early arthritis patients with the concordant presence of three RA autoantibodies: analysis in two early arthritis clinics

Background

The patients with RA benefit from early identification soon after the first clinical symptoms appear. The 2010 ACR/EULAR classification criteria were developed to fulfill this need and their application has been demonstrated to be effective. However, there is still room for improvement. Therefore, we aimed to evaluate the potential of the concordant presence of RF, anti-CCP and anti-carbamylated protein antibodies to improve current RA classification among early arthritis (EA) patients.

Methods

Data from the first visit of 1057 patients in two EA prospective cohorts were used. The serological scores from the 2010 ACR/EULAR criteria and the concordant presence of the three RA autoantibodies were assessed relative to a gold standard consisting of the RA classification with the 1987 ACR criteria at the 2 years of follow-up.

Results

The concordant presence of three antibodies showed predictive characteristics allowing for direct classification as RA (positive predictive value = 96.1% and OR = 80.9). They were significantly better than the corresponding to the high antibody titers defined as in the 2010 classification criteria (PPV = 88.8%, OR = 26.1). In addition, the concordant presence of two antibodies was also very informative (PPV = 82.3%, OR = 15.1). These results allowed devising a scoring system based only on antibody concordance that displayed similar overall performance as the serological scoring system of the 2010 criteria. However, the best classification was obtained combining the concordance and 2010 serological systems, a combination with a significant contribution from each of the two systems.

Discussion

The concordant presence of RA autoantibodies showed an independent contribution to the classification of EA patients that permitted increased discrimination and precision.

An Overview of Inflammatory Bowel Disease Unclassified in Children

Background

The inflammatory bowel diseases cover a diverse range of conditions generally grouped into Crohn's disease (CD) or ulcerative colitis (UC) based on clinical, laboratory, radiological, endoscopic, and histological criteria. However, inflammatory bowel disease unclassified (IBDU) is used when there are clinical and endoscopic signs of chronic colitis without specific features of UC or CD but features of both. Conjecture exists regarding IBDU, especially in children, as to whether it represents a unique childhood phenotype or whether it reflects the difficulties in assigning an IBD subtype at an early age.

Summary

This review examines the current understanding of pediatric IBDU and assesses the evidence supporting IBDU as a distinctive disease entity on the spectrum of inflammatory bowel disease.

Key Messages

Pediatric-onset IBDU is more common than adult-onset IBDU. Therefore, an understanding of IBDU in this age group assumes more importance. However, there remains a paucity of information and a lack of exclusive longitudinal studies on pediatric IBDU. Subsequently there is significant disparity in the reported prevalence, clinical course, reclassification trends, and treatment responses around pediatric IBDU. Therefore, it remains challenging to chart the natural history of pediatric IBDU and consequently form an accurate understanding of where pediatric IBDU sits on the spectrum of disease.

Statistical representation models for mutation information within genomic data

BACKGROUND

As DNA sequencing technologies are improving and getting cheaper, genomic data can be utilized for diagnosis of many diseases such as cancer. Human raw genome data is huge in size for computational systems. Therefore, there is a need for a compact and accurate representation of the valuable information in DNA. The occurrence of complex genetic disorders often results from multiple gene mutations. The effect of each mutation is not equal for the development of a disease. Inspired from the field of information retrieval, we propose using the term frequency (tf) and BM25 term weighting measures with the inverse document frequency (idf) and relevance frequency (rf) measures to weight genes based on their mutations. The underlying assumption is that the more mutations a gene has in patients with a certain disease and the less mutations it has in other patients, the more discriminative that gene is.

RESULTS

We evaluated the proposed representations on the task of cancer type classification. We applied various machine learning techniques using the tf-idf and tf-rf schemes and their BM25 versions. Our results show that the BM25-tf-rf representation leads to improved classification accuracy and f-score values compared to the other representations. The highest accuracy (76.44%) and f-score (76.95%) are achieved with the BM25-tf-rf based data representation.

CONCLUSIONS

As a result of our experiments, the BM25-tf-rf scheme and the proposed neural network model is shown to be the best performing classification system for our case study of cancer type classification. This system is further utilized for causal gene analysis. Examples from the most effective genes that are used for decision making are found to be in the literature as target or causal genes.

Does informant-based reporting of cognitive symptoms predict amyloid positivity on positron emission tomography?

Introduction

Researchers are searching for clinical instruments to predict amyloid positivity for disease classification. Informant-based reports could detect disease status. This study compares subjective memory complaints captured by informant-based reports between positron emission tomography (PET)–positive and PET-negative patients and hypothesizes that amyloid PET positivity associates with increased informant-based cognitive complaints.

Methods

Ninety-eight amnestic mild cognitive impairment or mild dementia subjects were studied. Subjective report was captured by the informant-driven Alzheimer's Questionnaire (AQ) administered before PET. Differences in demographics and AQ score by diagnostic status and amyloid status were measured, and a receiver-operating characteristic curve was calculated.

Results

Sixty-five mild cognitive impairment/Alzheimer's disease amyloid PET-positive and 33 amyloid PET-negative subjects were included. AQ was significantly higher (12.51 ± 4.95) for amyloid PET-positive subjects (9.06 ± 3.65; P = .001).

Conclusions

Amyloid PET-positive subjects with Alzheimer's disease or mild cognitive impairment have more informant-based reports of cognitive decline, indicating utility for a brief informant measure.

[The new classifications of biliary tract diseases based on actual anatomy]

In order to facilitate the treatment strategies for biliary tract injury, hilar cholangiocarcinoma, bile duct tumor thrombus, cholangiocellular carcinoma and bile duct cystic dilatation, many classifications have been made, even more than 10 types for one disease. Each type is represented by numbers or English alphabet, which are not only confusing but also difficult to remember. The Academician Mengchao Wu divided the liver into five sections and four segments base on its anatomy, this classification is very direct and visual, thus had been using till now. In order to overcome those complicated problems, it is considered to develop a new classification based on actual anatomic location similar to that for liver cancer, which is easy to remember and to directly determine the treatment strategy. All kinds of classifications have their own characteristics and advantages and disadvantages. This practical classifications avoid the complexity and may be useful for clinicians.

A surveillance system for diseases of companion animals in the Veneto region (Italy)

Experts and international public health organisations stress the lack of surveillance systems for companion animal diseases and the need to implement such surveillance as a priority of the 'One Health' perspective. This paper presents the features of a system for the collection, analysis, interpretation and dissemination of data regarding the health status of pets in the Veneto region (Italy). The system involved the construction of a Web-based database containing the diagnoses of transmissible and non-transmissible diseases of dogs and cats made by veterinarians in their practices, hospitals, kennels and catteries. Each diagnosis constitutes a single record, also containing data on the identification of the individual animal and on several characteristics of epidemiological relevance. The World Health Organization (WHO) 10th revision of the International Classification of Diseases (ICD-10) for human diseases has been adapted to canine and feline diseases to standardise the diagnostic nomenclature. Software has been specifically created for online data entry and data management. The first results show that the main disorders were digestive (21%), dermatological (18%) and cardiovascular (11%) among 1,087 diagnostic records in dogs, and digestive (23%), dermatological (15%) and urinary (14%) among 289 diagnostic records in cats. The main causes of death are represented by cardiovascular (21%) and gastrointestinal (21%) diseases in dogs and by urinary (31%) disorders in cats. At present, no institutional surveillance system for companion animal health exists in Italy, and veterinarians joining this project and sharing the outcomes of their clinical activity are acting on a voluntary basis.

Computer-aided detection in chest radiography based on artificial intelligence: a survey

As the most common examination tool in medical practice, chest radiography has important clinical value in the diagnosis of disease. Thus, the automatic detection of chest disease based on chest radiography has become one of the hot topics in medical imaging research. Based on the clinical applications, the study conducts a comprehensive survey on computer-aided detection (CAD) systems, and especially focuses on the artificial intelligence technology applied in chest radiography. The paper presents several common chest X-ray datasets and briefly introduces general image preprocessing procedures, such as contrast enhancement and segmentation, and bone suppression techniques that are applied to chest radiography. Then, the CAD system in the detection of specific disease (pulmonary nodules, tuberculosis, and interstitial lung diseases) and multiple diseases is described, focusing on the basic principles of the algorithm, the data used in the study, the evaluation measures, and the results. Finally, the paper summarizes the CAD system in chest radiography based on artificial intelligence and discusses the existing problems and trends.