Exploring simple triplet representation learning

Fully supervised learning methods necessitate a substantial volume of labelled training instances, a process that is typically both labour-intensive and costly. In the realm of medical image analysis, this issue is further amplified, as annotated medical images are considerably more scarce than their unlabelled counterparts. Consequently, leveraging unlabelled images to extract meaningful underlying knowledge presents a formidable challenge in medical image analysis. This paper introduces a simple triple-view unsupervised representation learning model (SimTrip) combined with a triple-view architecture and loss function, aiming to learn meaningful inherent knowledge efficiently from unlabelled data with small batch size. With the meaningful representation extracted from unlabelled data, our model demonstrates exemplary performance across two medical image datasets. It achieves this using only partial labels and outperforms other state-of-the-art methods. The method we present herein offers a novel paradigm for unsupervised representation learning, establishing a baseline that is poised to inspire the development of more intricate SimTrip-based methods across a spectrum of computer vision applications. Code and user guide are released at https://github.com/JerryRollingUp/SimTripSystem, the system also runs at http://43.131.9.159:5000/.

Investigating the overlap of machine learning algorithms in the final results of RNA-seq analysis on gene expression estimation

Advances in computer science in combination with the next-generation sequencing have introduced a new era in biology, enabling advanced state-of-the-art analysis of complex biological data. Bioinformatics is evolving as a union field between computer Science and biology, enabling the representation, storage, management, analysis and exploration of many types of data with a plethora of machine learning algorithms and computing tools. In this study, we used machine learning algorithms to detect differentially expressed genes between different types of cancer and showing the existence overlap to final results from RNA-sequencing analysis. The datasets were obtained from the National Center for Biotechnology Information resource. Specifically, dataset GSE68086 which corresponds to PMID:200,068,086. This dataset consists of 171 blood platelet samples collected from patients with six different tumors and healthy individuals. All steps for RNA-sequencing analysis (preprocessing, read alignment, transcriptome reconstruction, expression quantification and differential expression analysis) were followed. Machine Learning- based Random Forest and Gradient Boosting algorithms were applied to predict significant genes. The Rstudio statistical tool was used for the analysis.

Enhancing Mass spectrometry-based tumor immunopeptide identification: machine learning filter leveraging HLA binding affinity, aliphatic index and retention time deviation

Accurately identifying neoantigens is crucial for developing effective cancer vaccines and improving tumor immunotherapy. Mass spectrometry-based immunopeptidomics has emerged as a promising approach to identifying human leukocyte antigen (HLA) peptides presented on the surface of cancer cells, but false-positive identifications remain a significant challenge. In this study, liquid chromatography-tandem mass spectrometry-based proteomics and next-generation sequencing were utilized to identify HLA-presenting neoantigenic peptides resulting from non-synonymous single nucleotide variations in tumor tissues from 18 patients with renal cell carcinoma or pancreatic cancer. Machine learning was utilized to evaluate Mascot identifications through the prediction of MS/MS spectral consistency, and four descriptors for each candidate sequence: the max Mascot ion score, predicted HLA binding affinity, aliphatic index and retention time deviation, were selected as important features in filtering out identifications with inadequate fragmentation consistency. This suggests that incorporating rescoring filters based on peptide physicochemical characteristics could enhance the identification rate of MS-based immunopeptidomics compared to the traditional Mascot approach predominantly used for proteomics, indicating the potential for optimizing neoantigen identification pipelines as well as clinical applications.

Improving generalization capability of deep learning-based nuclei instance segmentation by non-deterministic train time and deterministic test time stain normalization

With the advent of digital pathology and microscopic systems that can scan and save whole slide histological images automatically, there is a growing trend to use computerized methods to analyze acquired images. Among different histopathological image analysis tasks, nuclei instance segmentation plays a fundamental role in a wide range of clinical and research applications. While many semi- and fully-automatic computerized methods have been proposed for nuclei instance segmentation, deep learning (DL)-based approaches have been shown to deliver the best performances. However, the performance of such approaches usually degrades when tested on unseen datasets. In this work, we propose a novel method to improve the generalization capability of a DL-based automatic segmentation approach. Besides utilizing one of the state-of-the-art DL-based models as a baseline, our method incorporates non-deterministic train time and deterministic test time stain normalization, and ensembling to boost the segmentation performance. We trained the model with one single training set and evaluated its segmentation performance on seven test datasets. Our results show that the proposed method provides up to 4.9%, 5.4%, and 5.9% better average performance in segmenting nuclei based on Dice score, aggregated Jaccard index, and panoptic quality score, respectively, compared to the baseline segmentation model.

Mathematical modelling and deep learning algorithms to automate assessment of single and digitally multiplexed immunohistochemical stains in tumoural stroma

Whilst automated analysis of immunostains in pathology research has focused predominantly on the epithelial compartment, automated analysis of stains in the stromal compartment is challenging and therefore requires time-consuming pathological input and guidance to adjust to tissue morphometry as perceived by pathologists. This study aimed to develop a robust method to automate stromal stain analyses using 2 of the commonest stromal stains (SMA and desmin) employed in clinical pathology practice as examples. An effective computational method capable of automatically assessing and quantifying tumour-associated stromal stains was developed and applied on cores of colorectal cancer tissue microarrays. The methodology combines both mathematical models and deep learning techniques with the former requiring no training data and the latter as many inputs as possible. The novel mathematical model was used to produce a digital double marker overlay allowing for fast automated digital multiplex analysis of stromal stains. The results show that deep learning methodologies in combination with mathematical modelling allow for an accurate means of quantifying stromal stains whilst also opening up new possibilities of digital multiplex analyses.

Exploiting biochemical data to improve osteosarcoma diagnosis with deep learning

Early and accurate diagnosis of osteosarcomas (OS) is of great clinical significance, and machine learning (ML) based methods are increasingly adopted. However, current ML-based methods for osteosarcoma diagnosis consider only X-ray images, usually fail to generalize to new cases, and lack explainability. In this paper, we seek to explore the capability of deep learning models in diagnosing primary OS, with higher accuracy, explainability, and generality. Concretely, we analyze the added value of integrating the biochemical data, i.e., alkaline phosphatase (ALP) and lactate dehydrogenase (LDH), and design a model that incorporates the numerical features of ALP and LDH and the visual features of X-ray imaging through a late fusion approach in the feature space. We evaluate this model on real-world clinic data with 848 patients aged from 4 to 81. The experimental results reveal the effectiveness of incorporating ALP and LDH simultaneously in a late fusion approach, with the accuracy of the considered 2608 cases increased to 97.17%, compared to 94.35% in the baseline. Grad-CAM visualizations consistent with orthopedic specialists further justified the model's explainability.

Determining the recurrence rate of premature ventricular complexes and idiopathic ventricular tachycardia after radiofrequency catheter ablation with the help of designing a machine-learning model

Ventricular arrhythmias increase cardiovascular morbidity and mortality. Recurrent PVCs and IVT are generally considered benign in the absence of structural heart abnormalities. Artificial intelligence is a rapidly growing field. In recent years, medical professionals have shown great interest in the potential use of ML, an integral part of AI, in various disciplines, including diagnostic applications, decision-making, prognostic stratification, and solving complex pathophysiological aspects of diseases from these data at extraordinary complexity, scale, and acquisition rate. The aim of this study was to design an ML model to predict the probability of PVC and IVT recurrence after RF ablation. Data of patients were collected and manipulated using traditional analysis and various artificial intelligence models, namely MLP, Gradient Boosting Machines, Random Forest, and Logistic Regression. Hypertension, male sex, and the use of non-irrigate catheters were associated with less freedom from arrhythmia. All these results were obtained through traditional analytic methods, and according to AI, none of the variables had a clear effect on the recurrence of arrhythmia. Each AI model presents unique strengths and weaknesses, and further optimization and fine-tuning of these models are necessary to increase their clinical utility. By expanding the dataset, improved predictions can be fostered to ultimately increase the clinical utility of AI in predicting PVC erosion outcomes.

ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application

Chronic kidney diseases (CKDs) are a significant public health issue with potential for severe complications such as hypertension, anemia, and renal failure. Timely diagnosis is crucial for effective management. Leveraging machine learning within healthcare offers promising advancements in predictive diagnostics. In this paper, we developed a machine learning-based kidney diseases prediction (ML-CKDP) model with dual objectives: to enhance dataset preprocessing for CKD classification and to develop a web-based application for CKD prediction. The proposed model involves a comprehensive data preprocessing protocol, converting categorical variables to numerical values, imputing missing data, and normalizing via Min-Max scaling. Feature selection is executed using a variety of techniques including Correlation, Chi-Square, Variance Threshold, Recursive Feature Elimination, Sequential Forward Selection, Lasso Regression, and Ridge Regression to refine the datasets. The model employs seven classifiers: Random Forest (RF), AdaBoost (AdaB), Gradient Boosting (GB), XgBoost (XgB), Naive Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT), to predict CKDs. The effectiveness of the models is assessed by measuring their accuracy, analyzing confusion matrix statistics, and calculating the Area Under the Curve (AUC) specifically for the classification of positive cases. Random Forest (RF) and AdaBoost (AdaB) achieve a 100% accuracy rate, evident across various validation methods including data splits of 70:30, 80:20, and K-Fold set to 10 and 15. RF and AdaB consistently reach perfect AUC scores of 100% across multiple datasets, under different splitting ratios. Moreover, Naive Bayes (NB) stands out for its efficiency, recording the lowest training and testing times across all datasets and split ratios. Additionally, we present a real-time web-based application to operationalize the model, enhancing accessibility for healthcare practitioners and stakeholders. Web app link: https://rajib-research-kedney-diseases-prediction.onrender.com/.

Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy - How are they affected by variations in tumor delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumor VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

Role of artificial intelligence in digital pathology for gynecological cancers

The diagnosis of cancer is typically based on histopathological sections or biopsies on glass slides. Artificial intelligence (AI) approaches have greatly enhanced our ability to extract quantitative information from digital histopathology images as a rapid growth in oncology data. Gynecological cancers are major diseases affecting women's health worldwide. They are characterized by high mortality and poor prognosis, underscoring the critical importance of early detection, treatment, and identification of prognostic factors. This review highlights the various clinical applications of AI in gynecological cancers using digitized histopathology slides. Particularly, deep learning models have shown promise in accurately diagnosing, classifying histopathological subtypes, and predicting treatment response and prognosis. Furthermore, the integration with transcriptomics, proteomics, and other multi-omics techniques can provide valuable insights into the molecular features of diseases. Despite the considerable potential of AI, substantial challenges remain. Further improvements in data acquisition and model optimization are required, and the exploration of broader clinical applications, such as the biomarker discovery, need to be explored.

Use of n-grams and K-means clustering to classify data from free text bone marrow reports

Natural language processing (NLP) has been used to extract information from and summarize medical reports. Currently, the most advanced NLP models require large training datasets of accurately labeled medical text. An approach to creating these large datasets is to use low resource intensive classical NLP algorithms. In this manuscript, we examined how an automated classical NLP algorithm was able to classify portions of bone marrow report text into their appropriate sections. A total of 1480 bone marrow reports were extracted from the laboratory information system of a tertiary healthcare network. The free text of these bone marrow reports were preprocessed by separating the reports into text blocks and then removing the section headers. A natural language processing algorithm involving n-grams and K-means clustering was used to classify the text blocks into their appropriate bone marrow sections. The impact of token replacement of numerical values, accession numbers, and clusters of differentiation, varying the number of centroids (1-19) and n-grams (1-5), and utilizing an ensemble algorithm were assessed. The optimal NLP model was found to employ an ensemble algorithm that incorporated token replacement, utilized 1-gram or bag of words, and 10 centroids for K-means clustering. This optimal model was able to classify text blocks with an accuracy of 89%, suggesting that classical NLP models can accurately classify portions of marrow report text.

Identifying factors controlling cellular uptake of gold nanoparticles by machine learning

There is strong interest to improve the therapeutic potential of gold nanoparticles (GNPs) while ensuring their safe development. The utility of GNPs in medicine requires a molecular-level understanding of how GNPs interact with biological systems. Despite considerable research efforts devoted to monitoring the internalisation of GNPs, there is still insufficient understanding of the factors responsible for the variability in GNP uptake in different cell types. Data-driven models are useful for identifying the sources of this variability. Here, we trained multiple machine learning models on 2077 data points for 193 individual nanoparticles from 59 independent studies to predict cellular uptake level of GNPs and compared different algorithms for their efficacies of prediction. The five ensemble learners (Xgboost, random forest, bootstrap aggregation, gradient boosting, light gradient boosting machine) made the best predictions of GNP uptake, accounting for 80-90% of the variance in the test data. The models identified particle size, zeta potential, GNP concentration and exposure duration as the most important drivers of cellular uptake. We expect this proof-of-concept study will foster the more effective use of accumulated cellular uptake data for GNPs and minimise any methodological bias in individual studies that may lead to under- or over-estimation of cellular internalisation rates.

Secure and privacy-preserving automated machine learning operations into end-to-end integrated IoT-edge-artificial intelligence-blockchain monitoring system for diabetes mellitus prediction

Diabetes Mellitus, one of the leading causes of death worldwide, has no cure to date and can lead to severe health complications, such as retinopathy, limb amputation, cardiovascular diseases, and neuronal disease, if left untreated. Consequently, it becomes crucial to be able to monitor and predict the incidence of diabetes. Machine learning approaches have been proposed and evaluated in the literature for diabetes prediction. This paper proposes an IoT-edge-Artificial Intelligence (AI)-blockchain system for diabetes prediction based on risk factors. The proposed system is underpinned by blockchain to obtain a cohesive view of the risk factors data from patients across different hospitals and ensure security and privacy of the user's data. We provide a comparative analysis of different medical sensors, devices, and methods to measure and collect the risk factors values in the system. Numerical experiments and comparative analysis were carried out within our proposed system, using the most accurate random forest (RF) model, and the two most used state-of-the-art machine learning approaches, Logistic Regression (LR) and Support Vector Machine (SVM), using three real-life diabetes datasets. The results show that the proposed system predicts diabetes using RF with 4.57% more accuracy on average in comparison with the other models LR and SVM, with 2.87 times more execution time. Data balancing without feature selection does not show significant improvement. When using feature selection, the performance is improved by 1.14% for PIMA Indian and 0.02% for Sylhet datasets, while it is reduced by 0.89% for MIMIC III.

Efficient management of pulmonary embolism diagnosis using a two-step interconnected machine learning model based on electronic health records data

Pulmonary Embolism (PE) is a life-threatening clinical disease with no specific clinical symptoms and Computed Tomography Angiography (CTA) is used for diagnosis. Clinical decision support scoring systems like Wells and rGeneva based on PE risk factors have been developed to estimate the pre-test probability but are underused, leading to continuous overuse of CTA imaging. This diagnostic study aimed to propose a novel approach for efficient management of PE diagnosis using a two-step interconnected machine learning framework directly by analyzing patients' Electronic Health Records data. First, we performed feature importance analysis according to the result of LightGBM superiority for PE prediction, then four state-of-the-art machine learning methods were applied for PE prediction based on the feature importance results, enabling swift and accurate pre-test diagnosis. Throughout the study patients' data from different departments were collected from Sina educational hospital, affiliated with the Tehran University of medical sciences in Iran. Generally, the Ridge classification method obtained the best performance with an F1 score of 0.96. Extensive experimental findings showed the effectiveness and simplicity of this diagnostic process of PE in comparison with the existing scoring systems. The main strength of this approach centered on PE disease management procedures, which would reduce avoidable invasive CTA imaging and be applied as a primary prognosis of PE, hence assisting the healthcare system, clinicians, and patients by reducing costs and promoting treatment quality and patient satisfaction.

Downregulation of ABLIM3 confers to the metastasis of neuroblastoma via regulating the cell adhesion molecules pathway

Neuroblastoma (NB) is the most prevalent extracranial solid tumor in pediatric patients, and its treatment failure often associated with metastasis. In this study, LASSO, SVM-RFE, and random forest tree algorithms, was used to identify the pivotal gene involved in NB metastasis. NB cell lines (SK-N-AS and SK-N-BE2), in conjunction with NB tissue were used for further study. ABLIM3 was identified as the hub gene and can be an independent prognostic factor for patients with NB. The immunohistochemical analysis revealed that ABLIM3 is negatively correlated with the metastasis of NB. Patients with low expression of ABLIM3 had a poor prognosis. High ABLIM3 expression correlated with APC co-stimulation and Type1 IFN response, and TIDE analysis indicated that patients with low ABLIM3 expression exhibited enhanced responses to immunotherapy. Downregulation of ABLIM3 by shRNA transfection increased the migration and invasion ability of NB cells. Gene Set Enrichment Analysis (GSEA) revealed that genes associated with ABLIM3 were primarily enriched in the cell adhesion molecules (CAMs) pathway. RT-qPCR and western blot analyses demonstrated that downregulation of ABLIM3 led to decreased expression of ITGA3, ITGA8, and KRT19, the key components of CAMs. This study indicated that ABLIM3 can be an independent prognostic factor for NB patients, and CAMs may mediate the effect of ABLIM3 on the metastasis of NB, suggesting that ABLIM3 is a potential therapeutic target for NB metastasis, which provides a novel strategy for future research and treatment strategies for NB patients.

Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery

Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to predict HCC recurrence and patient survival following surgery. We collected whole-slide H&E images, clinical variables, and follow-up data from 300 patients with HCC who underwent transplant and 169 patients who underwent resection at the Cleveland Clinic. A deep learning model was trained to predict recurrence-free survival (RFS) and disease-specific survival (DSS) from the H&E-stained slides. Repeated cross-validation splits were used to compute robust C-index estimates, and the results were compared to those obtained by fitting a Cox proportional hazard model using only clinical variables. While the deep learning model alone was predictive of recurrence and survival among patients in both cohorts, integrating the clinical and histologic models significantly increased the C-index in each cohort. In every subgroup analyzed, we found that a combined clinical and deep learning model better predicted post-surgical outcome in HCC patients compared to either approach independently.

Classifying breast cancer and fibroadenoma tissue biopsies from paraffined stain-free slides by fractal biomarkers in Fourier Ptychographic Microscopy

Breast cancer is one of the most spread and monitored pathologies in high-income countries. After breast biopsy, histological tissue is stored in paraffin, sectioned and mounted. Conventional inspection of tissue slides under benchtop light microscopes involves paraffin removal and staining, typically with H&E. Then, expert pathologists are called to judge the stained slides. However, paraffin removal and staining are operator-dependent, time and resources consuming processes that can generate ambiguities due to non-uniform staining. Here we propose a novel method that can work directly on paraffined stain-free slides. We use Fourier Ptychography as a quantitative phase-contrast microscopy method, which allows accessing a very wide field of view (i.e., mm2) in one single image while guaranteeing high lateral resolution (i.e., 0.5 µm). This imaging method is multi-scale, since it enables looking at the big picture, i.e. the complex tissue structure and connections, with the possibility to zoom-in up to the single-cell level. To handle this informative image content, we introduce elements of fractal geometry as multi-scale analysis method. We show the effectiveness of fractal features in describing and classifying fibroadenoma and breast cancer tissue slides from ten patients with very high accuracy. We reach 94.0 ± 4.2% test accuracy in classifying single images. Above all, we show that combining the decisions of the single images, each patient's slide can be classified with no error. Besides, fractal geometry returns a guide map to help pathologist to judge the different tissue portions based on the likelihood these can be associated to a breast cancer or fibroadenoma biomarker. The proposed automatic method could significantly simplify the steps of tissue analysis and make it independent from the sample preparation, the skills of the lab operator and the pathologist.

A computational model to analyze the impact of birth weight-nutritional status pair on disease development and disease recovery

Purpose

The purpose of this work is to analyse the combined impacts of birth weight and nutritional status on development and recovery of various types of diseases. This work aims to computationally establish the facts about the effects of individual birth weight-nutritional status pairs on disease development and disease recovery.

Methods

This work designs a computational model to analyze the impact of birth weight-nutritional status pairs on disease development and disease recovery. Our model works in two phases. The first phase finds the best machine learning model to predict birth weight from "Child Birth Weight Dataset" available at IEEE Dataport (https://dx.doi.org/10.21227/dvd4-3232). The second phase combines the predicted birth weight labels with nutritional status labels and establishes the effects using differential equations.

Results

The experimental results find Gradient boosting (GB) to work the best with Information gain (IGT) and Support Vector Machine (SVM) with Chi-square test (CST) for predicting the birth weights. The simulated results establish that "normal birth weight and normal nutritional status" is the best pair for resisting disease development as well as enhancing disease recovery. The results also depict that "low birth weight and malnutrition" is the worst pair for disease development while "high birth weight and malnutrition" is the worst combination for disease recovery.

Conclusion

The findings computationally establish the facts about the effects of birth weight-nutritional status pairs on disease development and disease recovery. As a social implication, this study can spread awareness about the importance of birth weight and nutritional status. The outcome can be helpful for the concerned authority in making decisions on healthcare cost and expenditure.

A review on trends in development and translation of omics signatures in cancer

The field of cancer genomics and transcriptomics has evolved from targeted profiling to swift sequencing of individual tumor genome and transcriptome. The steady growth in genome, epigenome, and transcriptome datasets on a genome-wide scale has significantly increased our capability in capturing signatures that represent both the intrinsic and extrinsic biological features of tumors. These biological differences can help in precise molecular subtyping of cancer, predicting tumor progression, metastatic potential, and resistance to therapeutic agents. In this review, we summarized the current development of genomic, methylomic, transcriptomic, proteomic and metabolic signatures in the field of cancer research and highlighted their potentials in clinical applications to improve diagnosis, prognosis, and treatment decision in cancer patients.

Databases and computational methods for the identification of piRNA-related molecules: A survey

Piwi-interacting RNAs (piRNAs) are a class of small non-coding RNAs (ncRNAs) that plays important roles in many biological processes and major cancer diagnosis and treatment, thus becoming a hot research topic. This study aims to provide an in-depth review of computational piRNA-related research, including databases and computational models. Herein, we perform literature analysis and use comparative evaluation methods to summarize and analyze three aspects of computational piRNA-related research: (i) computational models for piRNA-related molecular identification tasks, (ii) computational models for piRNA-disease association prediction tasks, and (iii) computational resources and evaluation metrics for these tasks. This study shows that computational piRNA-related research has significantly progressed, exhibiting promising performance in recent years, whereas they also suffer from the emerging challenges of inconsistent naming systems and the lack of data. Different from other reviews on piRNA-related identification tasks that focus on the organization of datasets and computational methods, we pay more attention to the analysis of computational models, algorithms, and performances that aim to provide valuable references for computational piRNA-related identification tasks. This study will benefit the theoretical development and practical application of piRNAs by better understanding computational models and resources to investigate the biological functions and clinical implications of piRNA.

Using staged tree models for health data: Investigating invasive fungal infections by aspergillus and other filamentous fungi

Machine learning models are increasingly used in the medical domain to study the association between risk factors and diseases to support practitioners in understanding health outcomes. In this paper, we showcase the use of machine-learned staged tree models for investigating complex asymmetric dependence structures in health data. Staged trees are a specific class of generative, probabilistic graphical models that formally model asymmetric conditional independence and non-regular sample spaces. An investigation of the risk factors in invasive fungal infections demonstrates the insights staged trees provide to support medical decision-making.

A review of machine learning-based methods for predicting drug-target interactions

The prediction of drug-target interactions (DTI) is a crucial preliminary stage in drug discovery and development, given the substantial risk of failure and the prolonged validation period associated with in vitro and in vivo experiments. In the contemporary landscape, various machine learning-based methods have emerged as indispensable tools for DTI prediction. This paper begins by placing emphasis on the data representation employed by these methods, delineating five representations for drugs and four for proteins. The methods are then categorized into traditional machine learning-based approaches and deep learning-based ones, with a discussion of representative approaches in each category and the introduction of a novel taxonomy for deep neural network models in DTI prediction. Additionally, we present a synthesis of commonly used datasets and evaluation metrics to facilitate practical implementation. In conclusion, we address current challenges and outline potential future directions in this research field.

VIBES: A consensus subtyping of the vaginal microbiota reveals novel classification criteria

This study aimed to develop a robust classification scheme for stratifying patients based on vaginal microbiome. By employing consensus clustering analysis, we identified four distinct clusters using a cohort that includes individuals diagnosed with Bacterial Vaginosis (BV) as well as control participants, each characterized by unique patterns of microbiome species abundances. Notably, the consistent distribution of these clusters was observed across multiple external cohorts, such as SRA022855, SRA051298, PRJNA208535, PRJNA797778, and PRJNA302078 obtained from public repositories, demonstrating the generalizability of our findings. We further trained an elastic net model to predict these clusters, and its performance was evaluated in various external cohorts. Moreover, we developed VIBES, a user-friendly R package that encapsulates the model for convenient implementation and enables easy predictions on new data. Remarkably, we explored the applicability of this new classification scheme in providing valuable insights into disease progression, treatment response, and potential clinical outcomes in BV patients. Specifically, we demonstrated that the combined output of VIBES and VALENCIA scores could effectively predict the response to metronidazole antibiotic treatment in BV patients. Therefore, this study's outcomes contribute to our understanding of BV heterogeneity and lay the groundwork for personalized approaches to BV management and treatment selection.

Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities

This paper discusses some overlooked challenges faced when working with machine learning models for histopathology and presents a novel opportunity to support "Learning Health Systems" with them. Initially, the authors elaborate on these challenges after separating them according to their mitigation strategies: those that need innovative approaches, time, or future technological capabilities and those that require a conceptual reappraisal from a critical perspective. Then, a novel opportunity to support "Learning Health Systems" by integrating hidden information extracted by ML models from digitalized histopathology slides with other healthcare big data is presented.

Artificial neural network analysis of factors affecting functional independence recovery in patients with lumbar stenosis after neurosurgery treatment: An observational cohort study

Background and aim

Lumbar spinal stenosis (LSS) is a leading cause of low back pain and lower limbs pain often associated with functional impairment which entails the loss or the impairment of independence in older adults. Conservative treatment is effective in a small percentage of patients, while a significant percentage undergo surgery, even if often without a complete resolution of clinical symptoms and motor deficits. The aim of the study is to identify clinical and demographic prognostic factors characterising the patients who would benefit most from surgical treatment in relation to the functional independence recovery using an innovative approach based on an artificial neural network.

Methods

Adult patients with LSS and indication of neurosurgical treatment were enrolled in the study. Clinical evaluation was performed in the preoperative-phase (into the 48 h before surgery) and after two months. Clinical battery investigated the motor, functional, cognitive, behavioural, and pain status. Demographics and clinical characteristics were analysed via Artificial Neural Network (ANN) using 24 input variables, 2 hidden layers and a single final output layer to predict the outcome. ANN results were compared with those of a multiple linear regression.

Results

108 patients were included in the study and 90 of them [66.5 ± 12.8 years; 27.8 % F] were submitted to surgery treatment and completed longitudinal evaluation. Statistically significant improvement was recorded in all clinical scales comparing pre- and post-surgery. The ANN results showed a prediction ability up to 81 %. Disability, functional limitations, and pain concerning clinical assessment and stature, onset and age about demographic characteristics are the main variables impacting on surgical outcome.

Conclusions

ANN can support clinical decision making, using clinical and demographic characteristics of patients with LSS identifying the characteristics of those who might benefit more from the surgical treatment in terms of global functional recovery.

Machine learning-assisted liquid crystal-based aptasensor for the specific detection of whole-cell Escherichia coli in water and food

We have developed a rapid, facile liquid crystal (LC)-based aptasensor for E. coli detection in water and juice samples. A textile grid-anchored LC platform was used with specific aptamers adsorbed via a cationic surfactant, cetyltrimethylammonium bromide (CTAB), on the LC surface. The presence of E. coli dissociates the aptamers from CTAB and restores the dark signal induced by the surfactant. Using polarized microscopy, the images of the LCs in the presence of various concentrations of E. coli were captured and analyzed using image analysis and machine learning (ML). The artificial neural networks (ANN) and extreme gradient boosting (XGBoost) rendered the best results for water samples (R2 = 0.986 and RMSE = 0.209) and juice samples (R2 = 0.976 and RMSE = 0.262), respectively. The platform was able to detect E. coli with a detection limit (LOD) of 6 CFU mL-1.

In-depth discovery and taste presentation mechanism studies on umami peptides derived from fermented sea bass based on peptidomics and machine learning

Umami peptides originating from fermented sea bass impart a distinctive flavor to food. Nevertheless, large-scale and rapid screening for umami peptides using conventional techniques is challenging because of problems such as prolonged duration and complicated operation. Therefore, we aimed to screen fermented sea bass using peptidomics and machine learning approaches. The taste presentation mechanism of umami peptides was assessed by molecular docking of T1R1/T1R3. Seventy umami peptides identified in fermented sea bass predominantly originated from 28 precursor proteins, including troponin, myosin, motor protein, and creatine kinase. Six umami peptides with the lowest energies formed stable complexes by binding to T1R3. SER170, SER147, GLN389, and HIS145 are critical binding sites for T1R1/T1R3. Four dominant interacting surface forces were identified: aromatic interactions, hydrogen bonding, hydrophilic bonds, and solvent-accessible surfaces. Our study unveils a method to screen umami peptides efficiently, providing a basis for further exploration of their flavor in fermented sea bass.

Estimation of wheat protein content and wet gluten content based on fusion of hyperspectral and RGB sensors using machine learning algorithms

The protein content (PC) and wet gluten content (WGC) are crucial indicators determining the quality of wheat, playing a pivotal role in evaluating processing and baking performance. Original reflectance (OR), wavelet feature (WF), and color index (CI) were extracted from hyperspectral and RGB sensors. Combining Pearson-competitive adaptive reweighted sampling (CARs)-variance inflation factor (VIF) with four machine learning (ML) algorithms were used to model accuracy of PC and WGC. As a result, three CIs, six ORs, and twelve WFs were selected for PC and WGC datasets. For single-modal data, the back-propagation neural network exhibited superior accuracy, with estimation accuracies (WF > OR > CI). For multi-modal data, the random forest regression paired with OR + WF + CI showed the highest validation accuracy. Utilizing the Gini impurity, WF outweighed OR and CI in the PC and WGC models. The amalgamation of MLs with multimodal data harnessed the synergies among various remote sensing sources, substantially augmenting model precision and stability.

Rapid analysis and authentication of Chinese propolis using nanoelectrospray ionization mass spectrometry combined with machine learning

In this study, we established a simple, rapid, and high-throughput method for the analysis and classification of propolis samples. We utilized nanoESI-MS to analyze 37 samples of propolis from China for the first time, obtaining characteristic fingerprint spectra in negative ion mode, which were then integrated with multivariate analysis to explore variations between water extract of propolis (WEP) and ethanol extract of propolis (EEP). Furthermore, we categorized propolis samples based on different climate zones and colors, screening 10 differential metabolites among propolis from various climate zones, and 11 differential metabolites among propolis samples of different color. By employing machine learning models, we achieved high-precision discrimination and prediction between samples from different climate zones and colors, achieving predictive accuracies of 95.6% and 85.6%, respectively. These results highlight the significant potential of the nanoESI-MS coupled with machine learning methodology for precise classification within the realm of food products.

Advanced detection tools in food fraud: A systematic review for holistic and rational detection method based on research and patents

Modern food chain supply management necessitates the dire need for mitigating food fraud and adulterations. This holistic review addresses different advanced detection technologies coupled with chemometrics to identify various types of adulterated foods. The data on research, patent and systematic review analyses (2018-2023) revealed both destructive and non-destructive methods to demarcate a rational approach for food fraud detection in various countries. These intricate hygiene standards and AI-based technology are also summarized for further prospective research. Chemometrics or AI-based techniques for extensive food fraud detection are demanded. A systematic assessment reveals that various methods to detect food fraud involving multiple substances need to be simple, expeditious, precise, cost-effective, eco-friendly and non-intrusive. The scrutiny resulted in 39 relevant experimental data sets answering key questions. However, additional research is necessitated for an affirmative conclusion in food fraud detection system with modern AI and machine learning approaches.

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

Neurosurgeons receive extensive technical training, which equips them with the knowledge and skills to specialise in various fields and manage the massive amounts of information and decision-making required throughout the various stages of neurosurgery, including preoperative, intraoperative, and postoperative care and recovery. Over the past few years, artificial intelligence (AI) has become more useful in neurosurgery. AI has the potential to improve patient outcomes by augmenting the capabilities of neurosurgeons and ultimately improving diagnostic and prognostic outcomes as well as decision-making during surgical procedures. By incorporating AI into both interventional and non-interventional therapies, neurosurgeons may provide the best care for their patients. AI, machine learning (ML), and deep learning (DL) have made significant progress in the field of neurosurgery. These cutting-edge methods have enhanced patient outcomes, reduced complications, and improved surgical planning.

Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures

Objective

Osteoporosis is a common skeletal disease that greatly increases the risk of pathologic fractures and accounts for approximately 700,000 vertebral compression fractures (VCFs) annually in the United States. Cement augmentation procedures such as balloon kyphoplasty (KP) and percutaneous vertebroplasty (VP) have demonstrated efficacy in the treatment of VCFs, however, some studies report rates of readmission as high as 10.8% following such procedures. The purpose of this study was to employ Machine Learning (ML) algorithms to predict 30-day hospital readmission following cement augmentation procedures for the treatment of VCFs using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database.

Methods

ACS-NSQIP was queried to identify patients undergoing either KP or VP from 2011 to 2014. Three ML algorithms were constructed and tasked with predicting post-operative readmissions within this cohort of patients. Results: Postoperative pneumonia, ASA Class 2 designation, age, partially-dependent functional status, and a history of smoking were independently identified as highly predictive of readmission by all ML algorithms. Among these variables postoperative pneumonia (p < 0.01), ASA Class 2 designation (p < 0.01), age (p = 0.002), and partially-dependent functional status (p < 0.01) were found to be statistically significant. Predictions were generated with an average AUC value of 0.757 and an average accuracy of 80.5%.

Conclusions

Postoperative pneumonia, ASA Class 2 designation, partially-dependent functional status, and age are perioperative variables associated with 30-day readmission following cement augmentation procedures. The use of ML allows for quantification of the relative contributions of these variables toward producing readmission.

Integration of machine learning models with microsatellite markers: New avenue in world grapevine germplasm characterization

Development of efficient analytical techniques is required for effective interpretation of biological data to take novel hypotheses and finding the critical predictive patterns. Machine Learning algorithms provide a novel opportunity for development of low-cost and practical solutions in biology. In this study, we proposed a new integrated analytical approach using supervised machine learning algorithms and microsatellites data of worldwide vitis populations. A total of 1378 wild (V. vinifera spp. sylvestris) and cultivated (V. vinifera spp. sativa) accessions of grapevine were investigated using 20 microsatellite markers. Data cleaning, feature selection, and supervised machine learning classification models vis, Naive Bayes, Support Vector Machine (SVM) and Tree Induction methods were implied to find most indicative and diagnostic alleles to represent wild/cultivated and originated geography of each population. Our combined approaches showed microsatellite markers with the highest differentiating capacity and proved efficiency for our pipeline of classification and prediction of vitis accessions. Moreover, our study proposed the best combination of markers for better distinguishing of populations, which can be exploited in future germplasm conservation and breeding programs.

Water quality prediction based on sparse dataset using enhanced machine learning

Water quality in surface bodies remains a pressing issue worldwide. While some regions have rich water quality data, less attention is given to areas that lack sufficient data. Therefore, it is crucial to explore novel ways of managing source-oriented surface water pollution in scenarios with infrequent data collection such as weekly or monthly. Here we showed sparse-dataset-based prediction of water pollution using machine learning. We investigated the efficacy of a traditional Recurrent Neural Network alongside three Long Short-Term Memory (LSTM) models, integrated with the Load Estimator (LOADEST). The research was conducted at a river-lake confluence, an area with intricate hydrological patterns. We found that the Self-Attentive LSTM (SA-LSTM) model outperformed the other three machine learning models in predicting water quality, achieving Nash-Sutcliffe Efficiency (NSE) scores of 0.71 for CODMn and 0.57 for NH3N when utilizing LOADEST-augmented water quality data (referred to as the SA-LSTM-LOADEST model). The SA-LSTM-LOADEST model improved upon the standalone SA-LSTM model by reducing the Root Mean Square Error (RMSE) by 24.6% for CODMn and 21.3% for NH3N. Furthermore, the model maintained its predictive accuracy when data collection intervals were extended from weekly to monthly. Additionally, the SA-LSTM-LOADEST model demonstrated the capability to forecast pollution loads up to ten days in advance. This study shows promise for improving water quality modeling in regions with limited monitoring capabilities.

Federated learning for medical image analysis: A survey

Machine learning in medical imaging often faces a fundamental dilemma, namely, the small sample size problem. Many recent studies suggest using multi-domain data pooled from different acquisition sites/centers to improve statistical power. However, medical images from different sites cannot be easily shared to build large datasets for model training due to privacy protection reasons. As a promising solution, federated learning, which enables collaborative training of machine learning models based on data from different sites without cross-site data sharing, has attracted considerable attention recently. In this paper, we conduct a comprehensive survey of the recent development of federated learning methods in medical image analysis. We have systematically gathered research papers on federated learning and its applications in medical image analysis published between 2017 and 2023. Our search and compilation were conducted using databases from IEEE Xplore, ACM Digital Library, Science Direct, Springer Link, Web of Science, Google Scholar, and PubMed. In this survey, we first introduce the background of federated learning for dealing with privacy protection and collaborative learning issues. We then present a comprehensive review of recent advances in federated learning methods for medical image analysis. Specifically, existing methods are categorized based on three critical aspects of a federated learning system, including client end, server end, and communication techniques. In each category, we summarize the existing federated learning methods according to specific research problems in medical image analysis and also provide insights into the motivations of different approaches. In addition, we provide a review of existing benchmark medical imaging datasets and software platforms for current federated learning research. We also conduct an experimental study to empirically evaluate typical federated learning methods for medical image analysis. This survey can help to better understand the current research status, challenges, and potential research opportunities in this promising research field.

Metabolism-triggered sensor array aided by machine learning for rapid identification of pathogens

Chemical-nose strategy has achieved certain success in the discrimination and identification of pathogens. However, this strategy usually relies on non-specific interactions, which are prone to be significantly disturbed by the change of environment thus limiting its practical usefulness. Herein, we present a novel chemical-nose sensing approach leveraging the difference in the dynamic metabolic variation during peptidoglycan metabolism among different species for rapid pathogen discrimination. Pathogens were first tethered with clickable handles through metabolic labeling at two different acidities (pH = 5 and 7) for 20 and 60 min, respectively, followed by click reaction with fluorescence up-conversion nanoparticles to generate a four-dimensional signal output. This discriminative multi-dimensional signal allowed eight types of model bacteria to be successfully classified within the training set into strains, genera, and Gram phenotypes. As the difference in signals of the four sensing channels reflects the difference in the amount/activity of enzymes involved in metabolic labeling, this strategy has good anti-interference capability, which enables precise pathogen identification within 2 h with 100% accuracy in spiked urinary samples and allows classification of unknown species out of the training set into the right phenotype. The robustness of this approach holds significant promise for its widespread application in pathogen identification and surveillance.

Development of a regional-based predictive model of incidence of traumatic spinal cord injury using machine learning algorithms

Objective

To develop a predictive model of incidence of traumatic spinal cord injury (TSCI).

Methods

The data for training the model included both the incidence data and the covariates. The incidence data were extracted from systematic reviews and the covariates were extracted from data available in the international road federation database. Then the feature processing measures were taken. First we defined a hyper-parameter, missing-value threshold, in order to eliminate features that exceed this threshold. To tackle the problem of overfitting of model we determined the Pearson correlation of features and excluded those with more than 0.7 correlation. After feature selection three different models including simple linear regression, support vector regression, and multi-layer perceptron were examined to fit the purposes of this study. Finally, we evaluated the model based on three standard metrics: Mean Absolute Error, Root Mean Square Error, and R2.

Results

Our machine-learning based model could predict the incidence rate of TSCI with the mean absolute error of 4.66. Our model found "Vehicles in use, Total vehicles/Km of roads", "Injury accidents/100 Million Veh-Km", "Vehicles in use, Vans, Pick-ups, Lorries, Road Tractors", "Inland surface Passengers Transport (Mio Passenger-Km), Rail", and "% paved" as top predictors of transport-related TSCI (TRTSCI).

Conclusions

Our model is proved to have a high accuracy to predict the incidence rate of TSCI for countries, especially where the main etiology of TSCI is related to road traffic injuries. Using this model, we can help the policymakers for resource allocation and evaluation of preventive measures.

Heterojunction of MXenes and MN4-graphene: Machine learning to accelerate the design of bifunctional oxygen electrocatalysts

Oxygen reduction reaction (ORR) and oxygen evolution reaction (OER) are essential for the development of excellent bifunctional electrocatalysts, which are key functions in clean energy production. The emphasis of this study lies in the rapid design and investigation of 153 MN4-graphene (Gra)/ MXene (M2NO) electrocatalysts for ORR/OER catalytic activity using machine learning (ML) and density functional theory (DFT). The DFT results indicated that CoN4-Gra/Ti2NO had both good ORR (0.37 V) and OER (0.30 V) overpotentials, while TiN4-Gra/M2NO and MN4-Gra/Cr2NO had high overpotentials. Our research further indicated orbital spin polarization and d-band centers far from the Fermi energy level, affecting the adsorption energy of oxygen-containing intermediates and thus reducing the catalytic activity. The ML results showed that the gradient boosting regression (GBR) model successfully predicted the overpotentials of the monofunctional catalysts RhN4-Gra/Ti2NO (ORR, 0.39 V) and RuN4-Gra/W2NO (OER, 0.45 V) as well as the overpotentials of the bifunctional catalyst RuN4-Gra/W2NO (ORR, 0.39 V; OER, 0.45 V). The symbolic regression (SR) algorithm was used to construct the overpotential descriptors without environmental variable features to accelerate the catalyst screening and shorten the trial-and-error costs from the source, providing a reliable theoretical basis for the experimental synthesis of MXene heterostructures.

Structural or/and functional MRI-based machine learning techniques for attention-deficit/hyperactivity disorder diagnosis: A systematic review and meta-analysis

BACKGROUND

The aim of this study was to investigate the diagnostic value of ML techniques based on sMRI or/and fMRI for ADHD.

METHODS

We conducted a comprehensive search (from database creation date to March 2024) for relevant English articles on sMRI or/and fMRI-based ML techniques for diagnosing ADHD. The pooled sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), summary receiver operating characteristic (SROC) curve and area under the curve (AUC) were calculated to assess the diagnostic value of sMRI or/and fMRI-based ML techniques. The I2 test was used to assess heterogeneity and the source of heterogeneity was investigated by performing a meta-regression analysis. Publication bias was assessed using the Deeks funnel plot asymmetry test.

RESULTS

Forty-three studies were included in the systematic review, 27 of which were included in our meta-analysis. The pooled sensitivity and specificity of sMRI or/and fMRI-based ML techniques for the diagnosis of ADHD were 0.74 (95 % CI 0.65-0.81) and 0.75 (95 % CI 0.67-0.81), respectively. SROC curve showed that AUC was 0.81 (95 % CI 0.77-0.84). Based on these findings, the sMRI or/and fMRI-based ML techniques have relatively good diagnostic value for ADHD.

LIMITATIONS

Our meta-analysis specifically focused on ML techniques based on sMRI or/and fMRI studies. Since EEG-based ML techniques are also used for diagnosing ADHD, further systematic analyses are necessary to explore ML methods based on multimodal medical data.

CONCLUSION

sMRI or/and fMRI-based ML technique is a promising objective diagnostic method for ADHD.

Label-free plasmonic spectral profiling of serum DNA

Genetic and epigenetic modifications are linked to the activation of oncogenes and inactivation of tumor suppressor genes. Likewise, the associated molecular alternations can best inform precision medicine for personalized tumor treatment. Therefore, performing characterization of genetic and epigenetic alternations at the molecular level represents a crucial step in early diagnosis and/or therapeutics of cancer. However, the prevailing methods for DNA analysis involve a series of tedious and complicated steps, in which important genetic and epigenetic information could be lost or altered. To provide a potential approach for non-invasive, direct, and efficient DNA analysis, herein, we present a promising strategy for label-free molecular profiling of serum DNA in its pristine form by fusing surface-enhanced Raman spectroscopy with machine learning on a superior plasmonic nanostructured platform. Using DNA methylation and single-point mutation as two case studies, the presented strategy allows a well-balanced sensitive and specific detection of epigenetic and genetic changes at the single-nucleotide level in serum. We envision the presented label-free strategy could serve as a versatile tool for direct molecular profiling in pristine forms of a wide range of biological markers and aid biomedical diagnostics as well as therapeutics.

Infrared spectroscopy-based machine learning algorithms for rapid detection of Klebsiella pneumoniae isolated directly from patients' urine and determining its susceptibility to antibiotics

Among the most prevalent and detrimental bacteria causing urinary tract infections (UTIs) is Klebsiella (K.) pneumoniae. A rapid determination of its antibiotic susceptibility can enhance patient treatment and mitigate the spread of resistant strains. In this study, we assessed the viability of using infrared spectroscopy-based machine learning as a rapid and precise approach for detecting K. pneumoniae bacteria and determining its susceptibility to various antibiotics directly from a patient's urine sample. In this study, 2333 bacterial samples, including 636 K. pneumoniae were investigated using infrared micro-spectroscopy. The obtained spectra (27996spectra) were analyzed with XGBoost classifier, achieving a success rate exceeding 95 % for identifying K. pneumoniae. Moreover, this method allows for the simultaneous determination of K. pneumoniae susceptibility to various antibiotics with sensitivities ranging between 74 % and 81 % within approximately 40 min after receiving the patient's urine sample.

Early prediction of long-term survival of patients with nasopharyngeal carcinoma by multi-parameter MRI radiomics

Purpose

The objective is to create a comprehensive model that integrates clinical, semantic, and radiomics features to forecast the 5-year progression-free survival (PFS) of individuals diagnosed with non-distant metastatic Nasopharyngeal Carcinoma (NPC).

Methods

In a retrospective analysis, we included clinical and MRI data from 313 patients diagnosed with primary NPC. Patient classification into progressive and non-progressive categories relied on the occurrence of recurrence or distant metastasis within a 5-year timeframe. Initial screening comprised clinical features and statistically significant image semantic features. Subsequently, MRI radiomics features were extracted from all patients, and optimal features were selected to formulate the Rad-Score.Combining Rad-Score, image semantic features, and clinical features to establish a combined model Evaluation of predictive efficacy was conducted using ROC curves and nomogram specific to NPC progression. Lastly, employing the optimal ROC cutoff value from the combined model, patients were dichotomized into high-risk and low-risk groups, facilitating a comparison of 10-year overall survival (OS) between the groups.

Results

The combined model showcased superior predictive performance for NPC progression, reflected by AUC values of 0.84, an accuracy rate of 81.60%, sensitivity at 0.77, and specificity at 0.81 within the training group. In the test set, the AUC value reached 0.81, with an accuracy of 74.6%, sensitivity at 0.82, and specificity at 0.66.

Conclusion

The amalgamation of Rad-Score, clinical, and imaging semantic features from multi-parameter MRI exhibited significant promise in prognosticating 5-year PFS for non-distant metastatic NPC patients. The combined model provided quantifiable data for informed and personalized diagnosis and treatment planning.

Machine learning based on functional and structural connectivity in mild cognitive impairment

OBJECTIVE

Alzheimer's disease (AD) is a chronic, degenerative neurological disorder characterized by progressive cognitive decline and mental behavioral abnormalities. Mild cognitive impairment (MCI) is regarded as a transitional stage in the progression from normal elderly individuals to patients with AD. While studies have identified abnormalities in brain connectivity in patients with MCI, including functional and structural connectivity, accurately identifying patients with MCI in clinical screening remains challenging. We hypothesized that utilizing machine learning (ML) based on both functional and structural connectivity could yield meaningful results in distinguishing between patients with MCI and normal elderly individuals, so as to provide valuable information for early diagnosis and precise evaluation of patients with MCI.

METHODS

Following clinical criteria, we recruited 32 patients with MCI for the patient group, and 32 normal elderly individuals for the control group. All subjects underwent examinations for resting-state functional magnetic resonance imaging (rs-fMRI) and diffusion tensor imaging (DTI). Subsequently, significant functional and structural connectivity features were selected and combined with a support vector machine for classification of the patient and control groups.

RESULTS

We observed significantly different functional connectivity in the frontal lobe and putamen between the MCI group and normal controls. The results based on functional connectivity features demonstrated a classification accuracy of 71.88% and an area under the curve (AUC) value of 0.78. In terms of structural connectivity, we found that decreased fractional anisotropy in patients with MCI was significantly associated with Montreal Cognitive Assessment scores, specifically in regions such as the precuneus and cingulate gyrus. The classification results using the structural connectivity feature yielded an accuracy of 92.19% and an AUC value of 0.99. Lastly, combining functional and structural connectivity features resulted in a classification accuracy and AUC value of 93.75% and 0.99, respectively.

CONCLUSIONS

In this study, we demonstrated a high classification performance, underscoring the potential of both brain functional and structural connectivity in distinguishing patients with MCI from normal elderly individuals. Furthermore, the integration of functional connectivity and structural connectivity features indicated that utilizing rs-fMRI and DTI could enhance the accuracy and specificity of identifying patients with MCI compared with relying on a single neuroimaging technique.

CheekAge: a next-generation buccal epigenetic aging clock associated with lifestyle and health

Epigenetic aging clocks are computational models that predict age using DNA methylation information. Initially, first-generation clocks were developed to make predictions using CpGs that change with age. Over time, next-generation clocks were created using CpGs that relate to both age and health. Since existing next-generation clocks were constructed in blood, we sought to develop a next-generation clock optimized for prediction in cheek swabs, which are non-invasive and easy to collect. To do this, we collected MethylationEPIC data as well as lifestyle and health information from 8045 diverse adults. Using a novel simulated annealing approach that allowed us to incorporate lifestyle and health factors into training as well as a combination of CpG filtering, CpG clustering, and clock ensembling, we constructed CheekAge, an epigenetic aging clock that has a strong correlation with age, displays high test-retest reproducibility across replicates, and significantly associates with a plethora of lifestyle and health factors, such as BMI, smoking status, and alcohol intake. We validated CheekAge in an internal dataset and multiple publicly available datasets, including samples from patients with progeria or meningioma. In addition to exploring the underlying biology of the data and clock, we provide a free online tool that allows users to mine our methylomic data and predict epigenetic age.

Predictive modeling of antidepressant efficacy based on cognitive neuropsychological theory

BACKGROUND

We aimed to develop a clinical predictive model based on the cognitive neuropsychological (CNP) theory and machine-learning to examine SSRI efficacy in the treatment of MDD.

METHODS

Baseline assessments including clinical symptoms (HAMD, HAMA, BDI, and TEPS scores), negative biases (NEO-PI-R-N and NCPBQ scores), sociodemographic characteristics (social support and SES), and a 5-min eye-opening resting-state EEG were completed by 69 participants with first-episode major depressive disorder (MDD) and 36 healthy controls. The clinical symptoms and negative bias were again assessed after an 8-week treatment of depression with selective serotonin reuptake inhibitors (SSRIs). A multi-modality machine-learning model was developed to predict the effectiveness of SSRI antidepressants.

RESULTS

At baseline, we observed significant differences between MDD patients and healthy controls in terms of social support, clinical symptoms, and negative bias characteristics (p < 0.001). A negative association was found (p < 0.05) between neuroticism and alpha asymmetry in both the central and central-parietal areas, as well as between negative cognitive processing bias and alpha asymmetry in the parietal region. Compared to responders, non-responders exhibited less negative cognitive processing bias and greater alpha asymmetry in both central and central-parietal regions. Importantly, we developed a multi-modality machine-learning model with 83 % specificity using the above salient features.

CONCLUSIONS

Research results support the CNP theory of depression treatment. To some extent, the multimodal clinical model constructed based on the CNP theory effectively predicted the efficacy of this treatment in this population.

LIMITATIONS

Small sample and only focus on the mechanisms of delayed-onset SSRI treatment.

Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: A systematic review

BACKGROUND

Oral Potentially Malignant Disorders (OPMDs) refer to a heterogenous group of clinical presentations with heightened rate of malignant transformation. Identification of risk levels in OPMDs is crucial to determine the need for active intervention in high-risk patients and routine follow-up in low-risk ones. Machine learning models has shown tremendous potential in several areas of dentistry that strongly suggest its application to estimate rate of malignant transformation of precancerous lesions.

METHODS

A comprehensive literature search was performed on Pubmed/MEDLINE, Web of Science, Scopus, Embase, Cochrane Library database to identify articles including machine learning models and algorithms to predict malignant transformation in OPMDs. Relevant bibliographic data, study characteristics, and outcomes were extracted for eligible studies. Quality of the included studies was assessed through the IJMEDI checklist.

RESULTS

Fifteen articles were found suitable for the review as per the PECOS criteria. Amongst all studies, highest sensitivity (100%) was recorded for U-net architecture, Peaks Random forest model, and Partial least squares discriminant analysis (PLSDA). Highest specificity (100%) was noted for PLSDA. Range of overall accuracy in risk prediction was between 95.4% and 74%.

CONCLUSION

Machine learning proved to be a viable tool in risk prediction, demonstrating heightened sensitivity, automation, and improved accuracy for predicting transformation of OPMDs. It presents an effective approach for incorporating multiple variables to monitor the progression of OPMDs and predict their malignant potential. However, its sensitivity to dataset characteristics necessitates the optimization of input parameters to maximize the efficiency of the classifiers.

Evaluation of D-dimer and prothrombin time in alcohol related liver cirrhosis with comparison of machine learning analyses

OBJECTIVES

Liver cirrhosis (LC) can be caused by obesity, alcohol consumption, viral infection, and autoimmune disease. Early diagnosis and management of LC is important for patient quality of life. Non-invasive diagnostic methods are useful for predicting the current status and mortality risk of LC. The purpose of this study is to identify relevant diagnostic factors measured in routine laboratory test of alcohol-related liver cirrhosis (ALC) patients.

METHODS

This study analyzed data from 127 patients with ALC, including their laboratory test results and clinical information, including coagulation parameters, hematologic parameters, and biochemical parameters. These data were used to compare the performance of the prediction models from three machine learning algorithms including K-nearest neighbor (KNN), support vector machine (SVM), and random forest (RF).

RESULTS

Higher Model for End-stage Liver Disease (MELD) score were associated with prothrombin time (PT) and D-dimer. Logistic and multiple linear regression analyses revealed significant factors predicting mortality in the MELD group. Machine learning approaches were used to predict death in ALC patients using some laboratory parameters associated with mortality. The prediction model based on SVM exhibited better prediction performance than others.

CONCLUSION

PT and D-dimer were the factors that were most strongly associated with 90-day mortality, and machine learning methods can create prediction models with good predictive power.

Comparison of prediction models for soy protein isolate hydrolysates bitterness built using sensory, spectrofluorometric and chromatographic data from varying enzymes and degree of hydrolysis

The bitterness of soy protein isolate hydrolysates prepared using five proteases at varying degree of hydrolysis (DH) and its relation to physicochemical properties, i.e., surface hydrophobicity (H0), relative hydrophobicity (RH), and molecular weight (MW), were studied and developed for predictive modelling using machine learning. Bitter scores were collected from sensory analysis and assigned as the target, while the physicochemical properties were assigned as the features. The modelling involved data pre-processing with local outlier factor; model development with support vector machine, linear regression, adaptive boosting, and K-nearest neighbors algorithms; and performance evaluation by 10-fold stratified cross-validation. The results indicated that alcalase hydrolysates were the most bitter, followed by protamex, flavorzyme, papain, and bromelain. Distinctive correlation results were found among the physicochemical properties, influenced by the disparity of each protease. Among the features, the combination of RH-MW fitted various classification models and resulted in the best prediction performance.

Improved method for stress detection using bio-sensor technology and machine learning algorithms

Maintaining an optimal stress level is vital in our lives, yet many individuals struggle to identify the sources of their stress. As emotional stability and mental awareness become increasingly important, wearable medical technology has gained popularity in recent years. This technology enables real-time monitoring, providing medical professionals with crucial physiological data to enhance patient care. Current stress-detection methods, such as ECG, BVP, and body movement analysis, are limited by their rigidity and susceptibility to noise interference. To overcome these limitations, we introduce STRESS-CARE, a versatile stress detection sensor employing a hybrid approach. This innovative system utilizes a sweat sensor, cutting-edge context identification methods, and machine learning algorithms. STRESS-CARE processes sensor data and models environmental fluctuations using an XG Boost classifier. By combining these advanced techniques, we aim to revolutionize stress detection, offering a more adaptive and robust solution for improved stress management and overall well-being.•In the proposed method, we introduce a state-of-the-art stress detection device with Galvanic Skin Response (GSR) sweat sensors, outperforming traditional Electrocardiogram (ECG) methods while remaining non-invasive•Integrating machine learning, particularly XG-Boost algorithms, enhances detection accuracy and reliability.•This study sheds light on noise context comprehension for various wearable devices, offering crucial guidance for optimizing stress detection in multiple contexts and applications.

Enhancement of handwritten text recognition using AI-based hybrid approach

Handwritten text recognition (HTR) within computer vision and image processing stands as a prominent and challenging research domain, holding significant implications for diverse applications. Among these, it finds usefulness in reading bank checks, prescriptions, and deciphering characters on various forms. Optical character recognition (OCR) technology, specifically tailored for handwritten documents, plays a pivotal role in translating characters from a range of file formats, encompassing both word and image documents. Challenges in HTR encompass intricate layout designs, varied handwriting styles, limited datasets, and less accuracy achieved. Recent advancements in Deep Learning and Machine Learning algorithms, coupled with the vast repositories of unprocessed data, have propelled researchers to achieve remarkable progress in HTR. This paper aims to address the challenges in handwritten text recognition by proposing a hybrid approach. The primary objective is to enhance the accuracy of recognizing handwritten text from images. Through the integration of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) with a Connectionist Temporal Classification (CTC) decoder, the results indicate substantial improvement. The proposed hybrid model achieved an impressive 98.50% and 98.80% accuracy on the IAM and RIMES datasets, respectively. This underscores the potential and efficacy of the consecutive use of these advanced neural network architectures in enhancing handwritten text recognition accuracy. •The proposed method introduces a hybrid approach for handwritten text recognition, employing CNN and BiLSTM with CTC decoder.•Results showcase a remarkable accuracy improvement of 98.50% and 98.80% on IAM and RIMES datasets, emphasizing the potential of this model for enhanced accuracy in recognizing handwritten text from images.