Integrating machine learning and nontargeted plasma lipidomics to explore lipid characteristics of premetabolic syndrome and metabolic syndrome.

Objective: To identify plasma lipid characteristics associated with premetabolic syndrome (pre-MetS) and metabolic syndrome (MetS) and provide biomarkers through machine learning methods. Methods: Plasma lipidomics profiling was conducted using samples from healthy individuals, pre-MetS patients, and MetS patients. Orthogonal partial least squares-discriminant analysis (OPLS-DA) models were employed to identify dysregulated lipids in the comparative groups. Biomarkers were selected using support vector machine recursive feature elimination (SVM-RFE), random forest (rf), and least absolute shrinkage and selection operator (LASSO) regression, and the performance of two biomarker panels was compared across five machine learning models. Results: In the OPLS-DA models, 50 and 89 lipid metabolites were associated with pre-MetS and MetS patients, respectively. Further machine learning identified two sets of plasma metabolites composed of PS(38:3), DG(16:0/18:1), and TG(16:0/14:1/22:6), TG(16:0/18:2/20:4), and TG(14:0/18:2/18:3), which were used as biomarkers for the pre-MetS and MetS discrimination models in this study. Conclusion: In the initial lipidomics analysis of pre-MetS and MetS, we identified relevant lipid features primarily linked to insulin resistance in key biochemical pathways. Biomarker panels composed of lipidomics components can reflect metabolic changes across different stages of MetS, offering valuable insights for the differential diagnosis of pre-MetS and MetS.

Machine learning prediction of adolescent HIV testing services in Ethiopia.

Background: Despite endeavors to achieve the Joint United Nations Programme on HIV/AIDS 95-95-95 fast track targets established in 2014 for HIV prevention, progress has fallen short. Hence, it is imperative to identify factors that can serve as predictors of an adolescent's HIV status. This identification would enable the implementation of targeted screening interventions and the enhancement of healthcare services. Our primary objective was to identify these predictors to facilitate the improvement of HIV testing services for adolescents in Ethiopia. Methods: A study was conducted by utilizing eight different machine learning techniques to develop models using demographic and health data from 4,502 adolescent respondents. The dataset consisted of 31 variables and variable selection was done using different selection methods. To train and validate the models, the data was randomly split into 80% for training and validation, and 20% for testing. The algorithms were evaluated, and the one with the highest accuracy and mean f1 score was selected for further training using the most predictive variables. Results: The J48 decision tree algorithm has proven to be remarkably successful in accurately detecting HIV positivity, outperforming seven other algorithms with an impressive accuracy rate of 81.29% and a Receiver Operating Characteristic (ROC) curve of 86.3%. The algorithm owes its success to its remarkable capability to identify crucial predictor features, with the top five being age, knowledge of HIV testing locations, age at first sexual encounter, recent sexual activity, and exposure to family planning. Interestingly, the model's performance witnessed a significant improvement when utilizing only twenty variables as opposed to including all variables. Conclusion: Our research findings indicate that the J48 decision tree algorithm, when combined with demographic and health-related data, is a highly effective tool for identifying potential predictors of HIV testing. This approach allows us to accurately predict which adolescents are at a high risk of infection, enabling the implementation of targeted screening strategies for early detection and intervention. To improve the testing status of adolescents in the country, we recommend considering demographic factors such as age, age at first sexual encounter, exposure to family planning, recent sexual activity, and other identified predictors.

Identifying diagnostic indicators for type 2 diabetes mellitus from physical examination using interpretable machine learning approach.

Background: Identification of patients at risk for type 2 diabetes mellitus (T2DM) can not only prevent complications and reduce suffering but also ease the health care burden. While routine physical examination can provide useful information for diagnosis, manual exploration of routine physical examination records is not feasible due to the high prevalence of T2DM. Objectives: We aim to build interpretable machine learning models for T2DM diagnosis and uncover important diagnostic indicators from physical examination, including age- and sex-related indicators. Methods: In this study, we present three weighted diversity density (WDD)-based algorithms for T2DM screening that use physical examination indicators, the algorithms are highly transparent and interpretable, two of which are missing value tolerant algorithms. Patients: Regarding the dataset, we collected 43 physical examination indicator data from 11,071 cases of T2DM patients and 126,622 healthy controls at the Affiliated Hospital of Southwest Medical University. After data processing, we used a data matrix containing 16004 EHRs and 43 clinical indicators for modelling. Results: The indicators were ranked according to their model weights, and the top 25% of indicators were found to be directly or indirectly related to T2DM. We further investigated the clinical characteristics of different age and sex groups, and found that the algorithms can detect relevant indicators specific to these groups. The algorithms performed well in T2DM screening, with the highest area under the receiver operating characteristic curve (AUC) reaching 0.9185. Conclusion: This work utilized the interpretable WDD-based algorithms to construct T2DM diagnostic models based on physical examination indicators. By modeling data grouped by age and sex, we identified several predictive markers related to age and sex, uncovering characteristic differences among various groups of T2DM patients.

An adaptive data-driven architecture for mental health care applications.

Background: In the current era of rapid technological innovation, our lives are becoming more closely intertwined with digital systems. Consequently, every human action generates a valuable repository of digital data. In this context, data-driven architectures are pivotal for organizing, manipulating, and presenting data to facilitate positive computing through ensemble machine learning models. Moreover, the COVID-19 pandemic underscored a substantial need for a flexible mental health care architecture. This architecture, inclusive of machine learning predictive models, has the potential to benefit a larger population by identifying individuals at a heightened risk of developing various mental disorders. Objective: Therefore, this research aims to create a flexible mental health care architecture that leverages data-driven methodologies and ensemble machine learning models. The objective is to proficiently structure, process, and present data for positive computing. The adaptive data-driven architecture facilitates customized interventions for diverse mental disorders, fostering positive computing. Consequently, improved mental health care outcomes and enhanced accessibility for individuals with varied mental health conditions are anticipated. Method: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, the researchers conducted a systematic literature review in databases indexed in Web of Science to identify the existing strengths and limitations of software architecture relevant to our adaptive design. The systematic review was registered in PROSPERO (CRD42023444661). Additionally, a mapping process was employed to derive essential paradigms serving as the foundation for the research architectural design. To validate the architecture based on its features, professional experts utilized a Likert scale. Results: Through the review, the authors identified six fundamental paradigms crucial for designing architecture. Leveraging these paradigms, the authors crafted an adaptive data-driven architecture, subsequently validated by professional experts. The validation resulted in a mean score exceeding four for each evaluated feature, confirming the architecture's effectiveness. To further assess the architecture's practical application, a prototype architecture for predicting pandemic anxiety was developed.

Chest X-ray evaluation using machine learning to support the early diagnosis of pulmonary TB.

TB is a public health problem, and its diagnosis can be challenging. Among imaging methods, chest X-ray (CXR) is the leading choice for assessing pulmonary TB (PTB). Recent advancements in the field of artificial intelligence have stimulated studies evaluating the performance of machine learning (ML) for medical diagnosis. This study validated a new original Brazilian tool, the XmarTB, applied to CXR images to support the early diagnosis of PTB.An ML model was trained on 3,800 normal images, 3,800 abnormal CXRs without PTB and 1,376 with PTB manifestations from the publicly available TBX11K database.The binary classification can distinguish between normal and abnormal CXR with a sensitivity of 99.4% and specificity of 99.4%. The XmarTB tool had a sensitivity of 98.1% and a specificity of 99.7% in detecting TB cases among CXRs with abnormal CXRs; sensitivity was 96.7% and specificity 98.7% in detecting TB cases among all samples.This diagnostic tool can accurately and automatically detect abnormal CXRs and satisfactorily differentiate PTB from other pulmonary diseases. This tool holds significant promise in aiding the proactive detection of TB cases, providing rapid and accurate support for early diagnosis..

Integrative analysis with microbial modelling and machine learning uncovers potential alleviators for ulcerative colitis.

Ulcerative colitis (UC) is a challenging form of inflammatory bowel disease, and its etiology is intricately linked to disturbances in the gut microbiome. To identify the potential alleviators of UC, we employed an integrative analysis combining microbial community modeling with advanced machine learning techniques. Using metagenomics data sourced from the Integrated Human Microbiome Project, we constructed individualized microbiome community models for each participant. Our analysis highlighted a significant decline in both α and ß-diversity of strain-level microbial populations in UC subjects compared to controls. Distinct differences were also observed in the predicted fecal metabolite profiles and strain-to-metabolite contributions between the two groups. Using tree-based machine learning models, we successfully identified specific microbial strains and their associated metabolites as potential alleviators of UC. Notably, our experimental validation using a dextran sulfate sodium-induced UC mouse model demonstrated that the administration of Parabacteroides merdae ATCC 43,184 and N-acetyl-D-mannosamine provided notable relief from colitis symptoms. In summary, our study underscores the potential of an integrative approach to identify novel therapeutic avenues for UC, paving the way for future targeted interventions.

Utilizing geospatial artificial intelligence to map cancer disparities across health regions.

We have developed an innovative tool, the Intelligent Catchment Analysis Tool (iCAT), designed to identify and address healthcare disparities across specific regions. Powered by Artificial Intelligence and Machine Learning, our tool employs a robust Geographic Information System (GIS) to map healthcare outcomes and disease disparities. iCAT allows users to query publicly available data sources, health system data, and treatment data, offering insights into gaps and disparities in diagnosis and treatment paradigms. This project aims to promote best practices to bridge the gap in healthcare access, resources, education, and economic opportunities. The project aims to engage local and regional stakeholders in data collection and evaluation, including patients, providers, and organizations. Their active involvement helps refine the platform and guides targeted interventions for more effective outcomes. In this paper, we present two sample illustrations demonstrating how iCAT identifies healthcare disparities and analyzes the impact of social and environmental variables on outcomes. Over time, this platform can help communities make decisions to optimize resource allocation.

Prediction model for spinal cord injury in spinal tuberculosis patients using multiple machine learning algorithms: a multicentric study.

Spinal cord injury (SCI) is a prevalent and serious complication among patients with spinal tuberculosis (STB) that can lead to motor and sensory impairment and potentially paraplegia. This research aims to identify factors associated with SCI in STB patients and to develop a clinically significant predictive model. Clinical data from STB patients at a single hospital were collected and divided into training and validation sets. Univariate analysis was employed to screen clinical indicators in the training set. Multiple machine learning (ML) algorithms were utilized to establish predictive models. Model performance was evaluated and compared using receiver operating characteristic (ROC) curves, area under the curve (AUC), calibration curve analysis, decision curve analysis (DCA), and precision-recall (PR) curves. The optimal model was determined, and a prospective cohort from two other hospitals served as a testing set to assess its accuracy. Model interpretation and variable importance ranking were conducted using the DALEX R package. The model was deployed on the web by using the Shiny app. Ten clinical characteristics were utilized for the model. The random forest (RF) model emerged as the optimal choice based on the AUC, PRs, calibration curve analysis, and DCA, achieving a test set AUC of 0.816. Additionally, MONO was identified as the primary predictor of SCI in STB patients through variable importance ranking. The RF predictive model provides an efficient and swift approach for predicting SCI in STB patients.

Deciphering cutaneous melanoma prognosis through LDL metabolism: Single-cell transcriptomics analysis via 101 machine learning algorithms.

Cutaneous melanoma poses a formidable challenge within the field of oncology, marked by its aggressive nature and capacity for metastasis. Despite extensive research uncovering numerous genetic and molecular contributors to cutaneous melanoma development, there remains a critical knowledge gap concerning the role of lipids, notably low-density lipoprotein (LDL), in this lethal skin cancer. This article endeavours to bridge this knowledge gap by delving into the intricate interplay between LDL metabolism and cutaneous melanoma, shedding light on how lipids influence tumour progression, immune responses and potential therapeutic avenues. Genes associated with LDL metabolism were extracted from the GSEA database. We acquired and analysed single-cell sequencing data (GSE215120) and bulk-RNA sequencing data, including the TCGA data set, GSE19234, GSE22153 and GSE65904. Our analysis unveiled the heterogeneity of LDL across various cell types at the single-cell sequencing level. Additionally, we constructed an LDL-related signature (LRS) using machine learning algorithms, incorporating differentially expressed genes and highly correlated genes. The LRS serves as a valuable tool for assessing the prognosis, immunity and mutation status of patients with cutaneous melanoma. Furthermore, we conducted experiments on A375 and WM-115 cells to validate the function of PPP2R1A, a pivotal gene within the LRS. Our comprehensive approach, combining advanced bioinformatics analyses with an extensive review of current literature, presents compelling evidence regarding the significance of LDL within the cutaneous melanoma microenvironment.

The 3D Revolution in Cancer Discovery.

SUMMARY: The transition from 2D to 3D spatial profiling marks a revolutionary era in cancer research, offering unprecedented potential to enhance cancer diagnosis and treatment. This commentary outlines the experimental and computational advancements and challenges in 3D spatial molecular profiling, underscoring the innovation needed in imaging tools, software, artificial intelligence, and machine learning to overcome implementation hurdles and harness the full potential of 3D analysis in the field.

Differential diagnosis of Crohn's disease and intestinal tuberculosis based on ATR-FTIR spectroscopy combined with machine learning.

BACKGROUND: Crohn's disease (CD) is often misdiagnosed as intestinal tuberculosis (ITB). However, the treatment and prognosis of these two diseases are dramatically different. Therefore, it is important to develop a method to identify CD and ITB with high accuracy, specificity, and speed. AIM: To develop a method to identify CD and ITB with high accuracy, specificity, and speed. METHODS: A total of 72 paraffin wax-embedded tissue sections were pathologically and clinically diagnosed as CD or ITB. Paraffin wax-embedded tissue sections were attached to a metal coating and measured using attenuated total reflectance fourier transform infrared spectroscopy at mid-infrared wavelengths combined with XGBoost for differential diagnosis. RESULTS: The results showed that the paraffin wax-embedded specimens of CD and ITB were significantly different in their spectral signals at 1074 cm-1 and 1234 cm-1 bands, and the differential diagnosis model based on spectral characteristics combined with machine learning showed accuracy, specificity, and sensitivity of 91.84%, 92.59%, and 90.90%, respectively, for the differential diagnosis of CD and ITB. CONCLUSION: Information on the mid-infrared region can reveal the different histological components of CD and ITB at the molecular level, and spectral analysis combined with machine learning to establish a diagnostic model is expected to become a new method for the differential diagnosis of CD and ITB.

[Artificial intelligence in pathological anatomy]. / Iskusstvennyi intellekt v patologicheskoi anatomii.

The review presents key concepts and global developments in the field of artificial intelligence used in pathological anatomy. The work examines two types of artificial intelligence (AI): weak and strong ones. A review of experimental algorithms using both deep machine learning and computer vision technologies to work with WSI images of preparations, diagnose and make a prognosis for various malignant neoplasms is carried out. It has been established that weak artificial intelligence at this stage of development of computer (digital) pathological anatomy shows significantly better results in speeding up and refining diagnostic procedures than strong artificial intelligence having signs of general intelligence. The article also discusses three options for the further development of AI assistants for pathologists based on the technologies of large language models (strong AI) ChatGPT (PathAsst), Flan-PaLM2 and LIMA. As a result of the analysis of the literature, key problems in the field were identified: the equipment of pathology institutions, the lack of experts in training neural networks, the lack of strict criteria for the clinical viability of AI diagnostic technologies.

Registered multi-device/staining histology image dataset for domain-agnostic machine learning models.

Variations in color and texture of histopathology images are caused by differences in staining conditions and imaging devices between hospitals. These biases decrease the robustness of machine learning models exposed to out-of-domain data. To address this issue, we introduce a comprehensive histopathology image dataset named PathoLogy Images of Scanners and Mobile phones (PLISM). The dataset consisted of 46 human tissue types stained using 13 hematoxylin and eosin conditions and captured using 13 imaging devices. Precisely aligned image patches from different domains allowed for an accurate evaluation of color and texture properties in each domain. Variation in PLISM was assessed and found to be significantly diverse across various domains, particularly between whole-slide images and smartphones. Furthermore, we assessed the improvement in domain shift using a convolutional neural network pre-trained on PLISM. PLISM is a valuable resource that facilitates the precise evaluation of domain shifts in digital pathology and makes significant contributions towards the development of robust machine learning models that can effectively address challenges of domain shift in histological image analysis.

Morphometric dataset of Varanus salvator for non-invasive sex identification using machine learning.

Reliable sex identification in Varanus salvator traditionally relied on invasive methods like genetic analysis or dissection, as less invasive techniques such as hemipenes inversion are unreliable. Given the ecological importance of this species and skewed sex ratios in disturbed habitats, a dataset that allows ecologists or zoologists to study the sex determination of the lizard is crucial. We present a new dataset containing morphometric measurements of V. salvator individuals from the skin trade, with sex confirmed by dissection post- measurement. The dataset consists of a mixture of primary and secondary data such as weight, skull size, tail length, condition etc. and can be used in modelling studies for ecological and conservation research to monitor the sex ratio of this species. Validity was demonstrated by training and testing six machine learning models. This dataset has the potential to streamline sex determination, offering a non-invasive alternative to complement existing methods in V. salvator research, mitigating the need for invasive procedures.

Advanced disk herniation computer aided diagnosis system.

Over recent years, researchers and practitioners have encountered massive and continuous improvements in the computational resources available for their use. This allowed the use of resource-hungry Machine learning (ML) algorithms to become feasible and practical. Moreover, several advanced techniques are being used to boost the performance of such algorithms even further, which include various transfer learning techniques, data augmentation, and feature concatenation. Normally, the use of these advanced techniques highly depends on the size and nature of the dataset being used. In the case of fine-grained medical image sets, which have subcategories within the main categories in the image set, there is a need to find the combination of the techniques that work the best on these types of images. In this work, we utilize these advanced techniques to find the best combinations to build a state-of-the-art lumber disc herniation computer-aided diagnosis system. We have evaluated the system extensively and the results show that the diagnosis system achieves an accuracy of 98% when it is compared with human diagnosis.

Functional and structural reorganization in brain tumors: a machine learning approach using desynchronized functional oscillations.

Neuroimaging studies have allowed for non-invasive mapping of brain networks in brain tumors. Although tumor core and edema are easily identifiable using standard MRI acquisitions, imaging studies often neglect signals, structures, and functions within their presence. Therefore, both functional and diffusion signals, as well as their relationship with global patterns of connectivity reorganization, are poorly understood. Here, we explore the functional activity and the structure of white matter fibers considering the contribution of the whole tumor in a surgical context. First, we find intertwined alterations in the frequency domain of local and spatially distributed resting-state functional signals, potentially arising within the tumor. Second, we propose a fiber tracking pipeline capable of using anatomical information while still reconstructing bundles in tumoral and peritumoral tissue. Finally, using machine learning and healthy anatomical information, we predict structural rearrangement after surgery given the preoperative brain network. The generative model also disentangles complex patterns of connectivity reorganization for different types of tumors. Overall, we show the importance of carefully designing studies including MR signals within damaged brain tissues, as they exhibit and relate to non-trivial patterns of both structural and functional (dis-)connections or activity.

Automatic identification of incidents involving potential serious injuries and fatalities (PSIF).

Safety incidents have always been a crucial risk in work spaces, especially industrial sites. In the last few decades, significant efforts have been dedicated to incident control measures to reduce the rate of safety incidents. Despite all these efforts, the rate of decline in serious injuries and fatalities (SIFs) has been considerably lower than the rate of decline for non-critical incidents. This observation has led to a change of risk reduction paradigm for safety incidents. Under the new paradigm, more focus has been allocated to reducing the rate of critical/SIF incidents, as opposed to reducing the count of all incidents. One of the challenges in reducing the number of SIF incidents is the proper identification of the risk prior to materialization. One of the reasons for risk identification being a challenge is that companies usually only focus on incidents where SIF did occur reactively, and incidents that did not cause SIF but had the potential to do so go unnoticed. Identifying these potentially significant incidents, referred to as potential serious injuries and fatalities (PSIF), would enable companies to work on identifying critical risk and taking steps to prevent them preemptively. However, flagging PSIF incidents requires all incident reports to be analyzed individually by experts and hence significant investment, which is often not affordable, especially for small and medium sized companies. This study is aimed at addressing this problem through machine learning powered automation. We propose a novel approach based on binary classification for the identification of such incidents involving PSIF (potential serious injuries and fatalities). This is the first work towards automatic risk identification from incident reports. Our approach combines a pre-trained transformer model with XGBoost. We utilize advanced natural language processing techniques to encode an incident record comprising heterogeneous fields into a vector representation fed to XGBoost for classification. Moreover, given the scarcity of manually labeled incident records available for training, we leverage weak labeling to augment the label coverage of the training data. We utilize the F2 metric for hyperparameter tuning using Tree-structured Parzen Estimator to prioritize the detection of PSIF records over the avoidance of non-PSIF records being mis-classified as PSIF. The proposed methods outperform several baselines from other studies on a significantly large test dataset.

The role of correspondence analysis in medical research.

Correspondence analysis (CA) is a multivariate statistical and visualization technique. CA is extremely useful in analyzing either two- or multi-way contingency tables, representing some degree of correspondence between columns and rows. The CA results are visualized in easy-to-interpret "bi-plots," where the proximity of items (values of categorical variables) represents the degree of association between presented items. In other words, items positioned near each other are more associated than those located farther away. Each bi-plot has two dimensions, named during the analysis. The naming of dimensions adds a qualitative aspect to the analysis. Correspondence analysis may support medical professionals in finding answers to many important questions related to health, wellbeing, quality of life, and similar topics in a simpler but more informal way than by using more complex statistical or machine learning approaches. In that way, it can be used for dimension reduction and data simplification, clustering, classification, feature selection, knowledge extraction, visualization of adverse effects, or pattern detection.

Concept-drifts adaptation for machine learning EEG epilepsy seizure prediction.

Seizure prediction remains a challenge, with approximately 30% of patients unresponsive to conventional treatments. Addressing this issue is crucial for improving patients' quality of life, as timely intervention can mitigate the impact of seizures. In this research field, it is critical to identify the preictal interval, the transition from regular brain activity to a seizure. While previous studies have explored various Electroencephalogram (EEG) based methodologies for prediction, few have been clinically applicable. Recent studies have underlined the dynamic nature of EEG data, characterised by data changes with time, known as concept drifts, highlighting the need for automated methods to detect and adapt to these changes. In this study, we investigate the effectiveness of automatic concept drift adaptation methods in seizure prediction. Three patient-specific seizure prediction approaches with a 10-minute prediction horizon are compared: a seizure prediction algorithm incorporating a window adjustment method by optimising performance with Support Vector Machines (Backwards-Landmark Window), a seizure prediction algorithm incorporating a data-batch (seizures) selection method using a logistic regression (Seizure-batch Regression), and a seizure prediction algorithm with a dynamic integration of classifiers (Dynamic Weighted Ensemble). These methods incorporate a retraining process after each seizure and use a combination of univariate linear features and SVM classifiers. The Firing Power was used as a post-processing technique to generate alarms before seizures. These methodologies were compared with a control approach based on the typical machine learning pipeline, considering a group of 37 patients with Temporal Lobe Epilepsy from the EPILEPSIAE database. The best-performing approach (Backwards-Landmark Window) achieved results of 0.75 ± 0.33 for sensitivity and 1.03 ± 1.00 for false positive rate per hour. This new strategy performed above chance for 89% of patients with the surrogate predictor, whereas the control approach only validated 46%.

Inferring molecular inhibition potency with AlphaFold predicted structures.

Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.