Machine learning model for predicting malaria using clinical information

Plasma immune profiling combined with machine learning contributes to diagnosis and prognosis of active pulmonary tuberculosis

Tuberculosis (TB) remains one of the deadliest chronic infectious diseases globally. Early diagnosis not only prevents the spread of TB but also ensures effective treatment. However, the absence of non-sputum-based diagnostic tests often leads to delayed TB diagnoses. Inflammation is a hallmark of TB, we aimed to identify biomarkers associated with TB based on immune profiling. We collected 222 plasma samples from healthy controls (HCs), disease controls (non-TB pneumonia; PN), patients with TB (TB), and cured TB cases (RxTB). A high-throughput protein detection technology, multiplex proximity extension assays (PEA), was applied to measure the levels of 92 immune proteins. Based on differential analysis and the correlation with TB severity, we selected 9 biomarkers (CXCL9, PDL1, CDCP1, CCL28, CCL23, CCL19, MMP1, IFNγ and TRANCE) and explored their diagnostic capabilities through 7 machine learning methods. We identified combination of these 9 biomarkers that distinguish TB cases from controls with an area under the receiver operating characteristic curve (AUROC) of 0.89-0.99, with a sensitivity of 82-93% at a specificity of 88-92%. Moreover, the model excels in distinguishing severe TB cases, achieving AUROC exceeding 0.95, sensitivities and specificities exceeding 93.3%. In summary, utilizing targeted proteomics and machine learning, we identified a 9 plasma proteins signature that demonstrates significant potential for accurate TB diagnosis and clinical outcome prediction.

Machine learning for predicting Plasmodium liver stage development in vitro using microscopy imaging

Malaria, a significant global health challenge, is caused by Plasmodium parasites. The Plasmodium liver stage plays a pivotal role in the establishment of the infection. This study focuses on the liver stage development of the model organism Plasmodium berghei, employing fluorescent microscopy imaging and convolutional neural networks (CNNs) for analysis. Convolutional neural networks have been recently proposed as a viable option for tasks such as malaria detection, prediction of host-pathogen interactions, or drug discovery. Our research aimed to predict the transition of Plasmodium-infected liver cells to the merozoite stage, a key development phase, 15 hours in advance. We collected and analyzed hourly imaging data over a span of at least 38 hours from 400 sequences, encompassing 502 parasites. Our method was compared to human annotations to validate its efficacy. Performance metrics, including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were evaluated on an independent test dataset. The outcomes revealed an AUC of 0.873, a sensitivity of 84.6%, and a specificity of 83.3%, underscoring the potential of our CNN-based framework to predict liver stage development of P. berghei. These findings not only demonstrate the feasibility of our methodology but also could potentially contribute to the broader understanding of parasite biology.

A multiplex microbial profiling system for the identification of the source of body fluid and skin samples

Determining the source of body fluids is crucial in forensic investigations, as it provides valuable information about suspects and the nature of the crime. Microbial markers that trace the source of tissues and body fluids based on site specificity and temporal stability are often used effectively for this purpose. In this study, a multiplex system comprising seven microbial markers (Finegoldia magna, Corynebacterium tuberculostearicum, Cutibacterium acnes, Haemophilus parainfluenzae, Streptococcus oralis, Prevotella melaninogenica and Faecalibacterium prausnitzii) was developed to distinguish between skin, saliva, and feces samples. Based on these markers, the system produces electropherograms that are specific for each sample type. We collected 492 samples from six different skin sites (palm, antecubital crease, inguinal crease, cheek, upper back, and toe web space), the buccal mucosa, and stool were collected to further test the system. Beta diversity analysis revealed distinct clustering among the three sample groups. Additionally, skin microenvironment cluster analysis was used to identify skin sites accurately. This analysis classified skin samples into four distinct microenvironments: dry, moist, oily, and foot. Finally, we established a machine learning prediction model based on random forest regression to identify the skin microenvironment, achieving an overall prediction accuracy of 79 %. The multiplex system developed in this study accurately identifies the sources of body fluids, and the skin microenvironment. These findings offer new insights into the application of microbial markers in forensic science.

Explainable machine learning and online calculators to predict heart failure mortality in intensive care units

AIMS

This study aims to develop explainable machine learning models and clinical tools for predicting mortality in patients in the intensive care unit (ICU) with heart failure (HF).

METHODS

Patients diagnosed with HF who experienced their first ICU stay lasting between 24 h and 28 days were selected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. The primary outcome was all-cause mortality within 28 days. Data analysis was performed using Python and R, with feature selection conducted via least absolute shrinkage and selection operator (LASSO) regression. Fifteen models were evaluated, and the most effective model was rendered explainable through the Shapley additive explanations (SHAP) approach. A nomogram was developed based on logistic regression to facilitate interpretation. For external validation, the eICU database was utilized.

RESULTS

After selection, the study included 2343 records, with 1808 surviving and 535 deceased patients. The median age of the study population was 70.00, with ~3/5 males (60.31%). The median length of stay in the ICU was 6.00 days. The median age of the survival group was younger than the non-survival group (69.00 vs. 73.00), and non-survival patients spent longer time in the ICU. Seventy-five features were initially selected, including basic information, vital signs, laboratory tests, haemodynamics and oxygen status. LASSO regression determined the shrinkage parameter α = 0.020, and 44 features were chosen for model construction. The linear discriminant analysis (LDA) model showed the best performance, and the accuracy reached 0.8354 in the training cohort and 0.8563 in the testing cohort. It showed satisfying area under the curve (AUC), recall, precision, F1 score, Cohen's kappa score and Matthew's correlation coefficient. The concordance index (c-index) reached 0.7972 in the training cohort and 0.8125 in the testing cohort. In external validation, the LDA model achieved approximately 0.9 in accuracy, precision, recall and F1 score, with an AUC of 0.79. Univariable analysis was performed in the training cohort. Features that differed significantly between the survival and non-survival groups were subjected to multiple logistic regression. The nomogram built on multiple logistic regression included 14 features and demonstrated excellent performance. The AUC of the nomogram is 0.852 in the training cohort, 0.855 in the internal validation cohort and 0.770 in the external validation cohort. The calibration curve showed good consistency.

CONCLUSIONS

The study developed an LDA and a nomogram model for predicting mortality in HF patients in the ICU. The SHAP approach was employed to elucidate the LDA model, enhancing its utility for clinicians. These models were made accessible online for clinical application.

Using machine learning methods to investigate the impact of age on the causes of death in patients with early intrahepatic cholangiocarcinoma who underwent surgery

BACKGROUND

The impact of age on the causes of death (CODs) in patients with early-stage intrahepatic cholangiocarcinoma (ICC) who had undergone surgery was analyzed in this study.

METHODS

A total of 1555 patients (885 in the older group and 670 in the younger group) were included in this study. Before and after applying inverse probability of treatment weighting (IPTW), the different CODs in the 2 groups were further investigated. Additionally, 7 different machine learning models were used as predictive tools to identify key variables, aiming to evaluate the therapeutic outcome in early ICC patients undergoing surgery.

RESULTS

Before (5.92 vs. 4.08 years, P < 0.001) and after (6.00 vs. 4.08 years, P < 0.001) IPTW, the younger group consistently showed longer overall survival (OS) compared with the older group. Before IPTW, there were no significant differences in cholangiocarcinoma-related deaths (CRDs, P = 0.7) and secondary malignant neoplasms (SMNs, P = 0.78) between the 2 groups. However, the younger group had a lower cumulative incidence of cardiovascular disease (CVD, P = 0.006) and other causes (P < 0.001) compared with the older group. After IPTW, there were no differences between the 2 groups in CRDs (P = 0.2), SMNs (P = 0.7), and CVD (P = 0.1). However, the younger group had a lower cumulative incidence of other CODs compared with the older group (P < 0.001). The random forest (RF) model showed the highest C-index of 0.703. Time-dependent variable importance bar plots showed that age was the most important factor affecting the 2-, 4-, and 6-year survival, followed by stage and size.

CONCLUSIONS

Our study confirmed that younger patients have longer OS compared with older patients. Further analysis of the CODs indicated that older patients are more likely to die from CVDs. The RF model demonstrated the best predictive performance and identified age as the most important factor affecting OS in early ICC patients undergoing surgery.

Application of Eight Machine Learning Algorithms in the Establishment of Infertility and Pregnancy Diagnostic Models: A Comprehensive Analysis of Amino Acid and Carnitine Metabolism

To explore the effects of altered amino acids (AAs) and the carnitine metabolism in non-pregnant women with infertility (NPWI), pregnant women without infertility (PWI) and infertility-treated pregnant women (ITPW) compared with non-pregnant women (NPW, control), and develop more efficient models for the diagnosis of infertility and pregnancy, 496 samples were evaluated for levels of 21 AAs and 55 carnitines using targeted high-performance liquid chromatography with tandem mass spectrometry (HPLC-MS/MS). Three methods were used to screen the biomarkers for modeling, with eight algorithms used to build and validate the model. The ROC, sensitivity, specificity, and accuracy of the infertility diagnosis training model were higher than 0.956, 82.89, 66.64, and 82.57%, respectively, whereas those of the validated model were higher than 0.896, 77.67, 69.72, and 83.38%, respectively. The ROC, sensitivity, specificity, and accuracy of the pregnancy diagnosis training model were >0.994, 96.23, 97.79, and 97.69%, respectively, whereas those of the validated model were >0.572, 96.39, 93.03, and 94.71%, respectively. Our findings indicate that pregnancy may alter the AA and carnitine metabolism in women with infertility to match the internal environment of PWI. The developed model demonstrated good performance and high sensitivity for facilitating infertility and pregnancy diagnosis.

Utilizing radiomics for differential diagnosis of inverted papilloma and chronic rhinosinusitis with polyps based on unenhanced CT scans

To evaluate whether radiomics models based on unenhanced paranasal sinuses CT images could be a useful tool for differentiating inverted papilloma (IP) from chronic rhinosinusitis with polyps (CRSwNP). This retrospective study recruited 240 patients with CRSwNP and 106 patients with IP from three centers. 253 patients from Qilu Hospital were randomly divided into the training set (n = 151) and the internal validation set (n = 102) with a ratio of 6:4. 93 patients from the other two centers were used as the external validation set. The patients with the unilateral disease (n = 115) from Qilu Hospital were selected to further develop a subgroup analysis. Lesion segmentation was manually delineated in CT images. Least absolute shrinkage and selection operator algorithm was performed for feature reduction and selection. Decision tree, support vector machine, random forest, and adaptive boosting regressor were employed to establish the differential diagnosis models. 43 radiomic features were selected for modeling. Among the models, RF achieved the best results, with an AUC of 0.998, 0.943, and 0.934 in the training set, the internal validation set, and the external validation set, respectively. In the subgroup analysis, RF achieved an AUC of 0.999 in the training set and 0.963 in the internal validation set. The proposed radiomics models offered a non-invasion and accurate differential approach between IP and CRSwNP and has some significance in guiding clinicians determining the best treatment plans, as well as predicting the prognosis.

Identification of copper death-associated molecular clusters and immunological profiles for lumbar disc herniation based on the machine learning

Lumbar disc herniation (LDH) is a common clinical spinal disorder, yet its etiology remains unclear. We aimed to explore the role of cuproptosis-related genes (CRGs) and identify potential diagnostic biomarkers. Our analysis involved interrogating the GSE124272 and GSE150408 datasets for differential gene expression profiles associated with CRGs and immune characteristics. Molecular clustering was performed on LDH samples, followed by expression and immune infiltration analyses. Using the WGCNA algorithm, specific genes within CRG clusters were identified. After selecting the most predictive genes from the optimal model, four machine learning models were constructed and validated. This study identified nine CRGs associated with copper-regulated cell death. Two copper-containing molecular clusters linked to death were detected in LDH samples. Elevated expression and immune infiltration levels were found in LDH patients, particularly in CRG cluster C2. Utilizing XGB, five genes were identified for constructing a diagnostic model, achieving an area under the curve values of 0.715. In conclusion, this research provides valuable insights into the association between LDH and copper-regulated cell death, alongside proposing a promising predictive model.

Predicting Unfavorable Pregnancy Outcomes in Polycystic Ovary Syndrome (PCOS) Patients Using Machine Learning Algorithms

Background and Objectives: Polycystic ovary syndrome (PCOS) is a complex disorder that can negatively impact the obstetrical outcomes. The aim of this study was to determine the predictive performance of four machine learning (ML)-based algorithms for the prediction of adverse pregnancy outcomes in pregnant patients diagnosed with PCOS. Materials and Methods: A total of 174 patients equally divided into 2 groups depending on the PCOS diagnosis were included in this prospective study. We used the Mantel-Haenszel test to evaluate the risk of adverse pregnancy outcomes for the PCOS patients and reported the results as a crude and adjusted odds ratio (OR) with a 95% confidence interval (CI). A generalized linear model was used to identify the predictors of adverse pregnancy outcomes in PCOS patients, quantifying their impact as risk ratios (RR) with 95% CIs. Significant predictors were included in four machine learning-based algorithms and a sensitivity analysis was employed to quantify their performance. Results: Our crude estimates suggested that PCOS patients had a higher risk of developing gestational diabetes and had a higher chance of giving birth prematurely or through cesarean section in comparison to patients without PCOS. When adjusting for confounders, only the odds of delivery via cesarean section remained significantly higher for PCOS patients. Obesity was outlined as a significant predictor for gestational diabetes and fetal macrosomia, while a personal history of diabetes demonstrated a significant impact on the occurrence of all evaluated outcomes. Random forest (RF) performed the best when used to predict the occurrence of gestational diabetes (area under the curve, AUC value: 0.782), fetal macrosomia (AUC value: 0.897), and preterm birth (AUC value: 0.901) in PCOS patients. Conclusions: Complex ML algorithms could be used to predict adverse obstetrical outcomes in PCOS patients, but larger datasets should be analyzed for their validation.

A risk prediction model based on machine learning algorithm for parastomal hernia after permanent colostomy

OBJECTIVE

To develop a machine learning-based risk prediction model for postoperative parastomal hernia (PSH) in colorectal cancer patients undergoing permanent colostomy, assisting nurses in identifying high-risk groups and devising preventive care strategies.

METHODS

A case-control study was conducted on 495 colorectal cancer patients who underwent permanent colostomy at the Second Affiliated Hospital of Anhui Medical University from June 2017 to June 2023, with a 1-year follow-up period. Patients were categorized into PSH and non-PSH groups based on PSH occurrence within 1-year post-operation. Data were split into training (70%) and testing (30%) sets. Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, and binary classification prediction models were established using Logistic Regression (LR), Support Vector Classification (SVC), K Nearest Neighbor (KNN), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XgBoost). The binary classification label denoted 1 for PSH occurrence and 0 for no PSH occurrence. Parameters were optimized via 5-fold cross-validation. Model performance was evaluated using Area Under Curve (AUC), specificity, sensitivity, accuracy, positive predictive value, negative predictive value, and F1-score. Clinical utility was evaluated using decision curve analysis (DCA), model explanation was enhanced using shapley additive explanation (SHAP), and model visualization was achieved using a nomogram.

RESULTS

The incidence of PSH within 1 year was 29.1% (144 patients). Among the models tested, the RF model demonstrated the highest discrimination capability with an AUC of 0.888 (95% CI: 0.881-0.935), along with superior specificity, accuracy, sensitivity, and F1 score. It also showed the highest clinical net benefit on the DCA curve. SHAP analysis identified the top 10 influential variables associated with PSH risk: body mass index (BMI), operation duration, history and status of chronic obstructive pulmonary disease (COPD), prealbumin, tumor node metastasis (TNM) staging, stoma site, thickness of rectus abdominis muscle (TRAM), C-reactive protein CRP, american society of anesthesiologists physical status classification (ASA), and stoma diameter. These insights from SHAP plots illustrated how these factors influence individual PSH outcomes. The nomogram was used for model visualization.

CONCLUSION

The Random Forest model demonstrated robust predictive performance and clinical relevance in forecasting colonic PSH. This model aids in early identification of high-risk patients and guides preventive care.

Intelligent classification of major depressive disorder using rs-fMRI of the posterior cingulate cortex

Major Depressive Disorder (MDD) is a widespread psychiatric condition that affects a significant portion of the global population. The classification and diagnosis of MDD is crucial for effective treatment. Traditional methods, based on clinical assessment, are subjective and rely on healthcare professionals' expertise. Recently, there's growing interest in using Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) to objectively understand MDD's neurobiology, complementing traditional diagnostics. The posterior cingulate cortex (PCC) is a pivotal brain region implicated in MDD which could be used to identify MDD from healthy controls. Thus, this study presents an intelligent approach based on rs-fMRI data to enhance the classification of MDD. Original rs-fMRI data were collected from a cohort of 430 participants, comprising 197 patients and 233 healthy controls. Subsequently, the data underwent preprocessing using DPARSF, and the amplitudes of low-frequency fluctuation values were computed to reduce data dimensionality and feature count. Then data associated with the PCC were extracted. After eliminating redundant features, various types of Support Vector Machines (SVMs) were employed as classifiers for intelligent categorization. Ultimately, we compared the performance of each algorithm, along with its respective optimal classifier, based on classification accuracy, true positive rate, and the area under the receiver operating characteristic curve (AUC-ROC). Upon analyzing the comparison results, we determined that the Random Forest (RF) algorithm, in conjunction with a sophisticated Gaussian SVM classifier, demonstrated the highest performance. Remarkably, this combination achieved a classification accuracy of 81.9 % and a true positive rate of 92.9 %. In conclusion, our study improves the classification of MDD by supplementing traditional methods with rs-fMRI and machine learning techniques, offering deeper neurobiological insights and aiding accuracy, while emphasizing its role as an adjunct to clinical assessment.

SHAP based predictive modeling for 1 year all-cause readmission risk in elderly heart failure patients: feature selection and model interpretation

Heart failure (HF) is a significant global public health concern with a high readmission rate, posing a serious threat to the health of the elderly population. While several studies have used machine learning (ML) to develop all-cause readmission risk prediction models for elderly patients with HF, few have integrated ML-selected features with those chosen by human experts to assess HF patients readmission. A retrospective analysis of 8396 elderly HF patients hospitalized at the Affiliated Hospital of North Sichuan Medical College from January 1, 2018 to December 31, 2021 was conducted. Variables selected by XGBoost, LASSO regression, and random forest constituted the machine group, while the human expert group comprised variables chosen by two experienced cardiovascular professors. The variables selected by both groups were combined to form a human-machine collaboration group. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The SHapley Additive exPlanations (SHAP) method was used to elucidate the importance of each predictive feature, explain the impact of individual features on the model, and provide visual representation. A total of 73 features were included for model development. The human-machine collaboration model, utilizing CatBoost, achieved an AUC of 0.83617, an F1-score of 0.73521, and a Brier score of 0.16536 on the validation set. This model demonstrated superior predictive performance compared to those created solely by human experts or machine. The SHAP plot was then used to visually display the feature analysis of the human-machine collaboration model, revealing HGB, NT-proBNP, smoking history, NYHA classification, and LVEF as the 5 most important features. This study indicate that the human-machine collaboration model outperforms those relying solely on human expert selection or machine algorithm at predicting all-cause readmission in elderly HF patients. The application of the SHAP method enhanced the interpretability of the model outcomes, aiding clinicians in accurately pinpointing risk factors associated with HF readmission. This advancement enables the formulation of tailored treatment strategies, offering a more personalized approach to patient care.

Machine Learning for Early Discrimination Between Lung Cancer and Benign Nodules Using Routine Clinical and Laboratory Data

BACKGROUND

Lung cancer poses a global health threat necessitating early detection and precise staging for improved patient outcomes. This study focuses on developing and validating a machine learning-based risk model for early lung cancer screening and staging, using routine clinical data.

METHODS

Two medical center, observational, retrospective studies were conducted, involving 2312 lung cancer patients and 653 patients with benign nodules. Machine learning techniques, including differential analysis and feature selection, were employed to identify key factors for modeling. The study focused on variables such as nodule density, carcinoembryonic antigen (CEA), age, and lifestyle habits. The Logistic Regression model was utilized for early diagnoses, and the XGBoost model was utilized for staging based on selected features.

RESULTS

For early diagnoses, the Logistic Regression model achieved an area under the curve (AUC) of 0.716 (95% confidence interval [CI] 0.607-0.826), with 0.703 sensitivity and 0.654 specificity. The XGBoost model excelled in distinguishing late-stage from early-stage lung cancer, exhibiting an AUC of 0.913 (95% CI 0.862-0.963), with 0.909 sensitivity and 0.814 specificity. These findings highlight the model's potential for enhancing diagnostic accuracy and staging in lung cancer.

CONCLUSION

This study introduces a novel machine learning-based risk model for early lung cancer screening and staging, leveraging routine clinical information and laboratory data. The model shows promise in enhancing accuracy, mitigating overdiagnosis, and improving patient outcomes.

Upper gastrointestinal haemorrhage patients' survival: A causal inference and prediction study

BACKGROUND

Upper gastrointestinal (GI) bleeding is a common medical emergency. This study aimed to develop models to predict critically ill patients with upper GI bleeding in-hospital and 30-day survival, identify the correlation factor and infer the causality.

METHODS

A total of 2898 patients with upper GI bleeding were included from the Medical Information Mart for Intensive Care-IV and eICU-Collaborative Research Database, respectively. To identify the most critical factors contributing to the prognostic model, we used SHAP (SHapley Additive exPlanations) for machine learning interpretability. We performed causal inference using inverse probability weighting for survival-associated prognostic factors.

RESULTS

The optimal model using the light GBM (gradient boosting algorithm) algorithm achieved an AUC of .93 for in-hospital survival, .81 for 30-day survival in internal testing and .87 for in-hospital survival in external testing. Important factors for in-hospital survival, according to SHAP, were SOFA (Sequential organ failure assessment score), GCS (Glasgow coma scale) motor score and length of stay in ICU (Intensive critical care). In contrast, essential factors for 30-day survival were SOFA, length of stay in ICU, total bilirubin and GCS verbal score. Our model showed improved performance compared to SOFA alone.

CONCLUSIONS

Our interpretable machine learning model for predicting in-hospital and 30-day mortality in critically ill patients with upper gastrointestinal bleeding showed excellent accuracy and high generalizability. This model can assist clinicians in managing these patients to improve the discrimination of high-risk patients.

Ensemble multiclassification model for predicting developmental toxicity in zebrafish

In recent years, with the rapid development of society, organic compounds have been released into aquatic environments in various forms, posing a significant threat to the survival of aquatic organisms. The assessment of developmental toxicity is an important part of environmental safety risk systems, helping to identify the potential impacts of organic compounds on the embryonic development of aquatic organisms and enabling early detection and warning of potential ecological risks. Additionally, binary classification models cannot accurately classify organic compounds. Therefore, it is crucial to construct a multiclassification model for predicting the developmental toxicity of organic compounds. In this study, binary and multiclassification models were developed based on the ToxCast™ Phase I chemical library and literature data. The random forest, support vector machine, extreme gradient boosting, adaptive gradient boosting, and C5.0 decision tree algorithms, as well as 8 types of molecular fingerprint were used to establish a multiclassification base model for predicting developmental toxicity through 5-fold cross-validation and external validation. Ultimately, a multiclassification ensemble model was derived through a voting method. The performance of the binary ensemble model, as measured by the balanced accuracy, was 0.918, while that of the multiclassification model was 0.819. The developmental toxicity voting ensemble model (DT-VEM) achieved accuracies of 0.804, 0.834, and 0.855. Furthermore, by utilizing the XGBoost machine learning algorithm to construct separate models for molecular descriptors and substructure molecular fingerprints, we identified several substructures and physical properties related to developmental toxicity. Our research contributes to a more detailed classification of developmental toxicity, providing a new and valuable tool for predicting the developmental toxicity effects of unknown compounds. This supplement addresses the limitations of previous tools, as it offers an enhanced ability to predict potential developmental toxicity in novel compounds.

Construction of the prediction model for multiple myeloma based on machine learning

INTRODUCTION

The global burden of multiple myeloma (MM) is increasing every year. Here, we have developed machine learning models to provide a reference for the early detection of MM.

METHODS

A total of 465 patients and 150 healthy controls were enrolled in this retrospective study. Based on the variable screening strategy of least absolute shrinkage and selection operator (LASSO), three prediction models, logistic regression (LR), support vector machine (SVM), and random forest (RF), were established combining complete blood count (CBC) and cell population data (CPD) parameters in the training set (210 cases), and were verified in the validation set (90 cases) and test set (165 cases). The performance of each model was analyzed using receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA). Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC) were applied to evaluate the models. Delong test was used to compare the AUC of the models.

RESULTS

Six parameters including RBC (1012/L), RDW-CV (%), IG (%), NE-WZ, LY-WX, and LY-WZ were screened out by LASSO to construct the model. Among the three models, the AUC of RF model in the training set, validation set, and test set were 0.956, 0.892, and 0.875, which were higher than those of LR model (0.901, 0.849, and 0.858) and SVM model (0.929, 0.868, and 0.846). Delong test showed that there were significant differences among the models in the training set, no significant differences in the validation set, and significant differences only between SVM and RF models in the test set. The calibration curve and DCA showed that the three models had good validity and feasibility, and the RF model performed best.

CONCLUSION

The proposed RF model may be a useful auxiliary tool for rapid screening of MM patients.

Predicting malaria outbreak in The Gambia using machine learning techniques

Malaria is the most common cause of death among the parasitic diseases. Malaria continues to pose a growing threat to the public health and economic growth of nations in the tropical and subtropical parts of the world. This study aims to address this challenge by developing a predictive model for malaria outbreaks in each district of The Gambia, leveraging historical meteorological data. To achieve this objective, we employ and compare the performance of eight machine learning algorithms, including C5.0 decision trees, artificial neural networks, k-nearest neighbors, support vector machines with linear and radial kernels, logistic regression, extreme gradient boosting, and random forests. The models are evaluated using 10-fold cross-validation during the training phase, repeated five times to ensure robust validation. Our findings reveal that extreme gradient boosting and decision trees exhibit the highest prediction accuracy on the testing set, achieving 93.3% accuracy, followed closely by random forests with 91.5% accuracy. In contrast, the support vector machine with a linear kernel performs less favorably, showing a prediction accuracy of 84.8% and underperforming in specificity analysis. Notably, the integration of both climatic and non-climatic features proves to be a crucial factor in accurately predicting malaria outbreaks in The Gambia.

Community screening for dementia among older adults in China: a machine learning-based strategy

BACKGROUND

Dementia is a leading cause of disability in people older than 65 years worldwide. However, diagnosing dementia in its earliest symptomatic stages remains challenging. This study combined specific questions from the AD8 scale with comprehensive health-related characteristics, and used machine learning (ML) to construct diagnostic models of cognitive impairment (CI).

METHODS

The study was based on the Shenzhen Healthy Ageing Research (SHARE) project, and we recruited 823 participants aged 65 years and older, who completed a comprehensive health assessment and cognitive function assessments. Permutation importance was used to select features. Five ML models using BalanceCascade were applied to predict CI: a support vector machine (SVM), multilayer perceptron (MLP), AdaBoost, gradient boosting decision tree (GBDT), and logistic regression (LR). An AD8 score ≥ 2 was used to define CI as a baseline. SHapley Additive exPlanations (SHAP) values were used to interpret the results of ML models.

RESULTS

The first and sixth items of AD8, platelets, waist circumference, body mass index, carcinoembryonic antigens, age, serum uric acid, white blood cells, abnormal electrocardiogram, heart rate, and sex were selected as predictive features. Compared to the baseline (AUC = 0.65), the MLP showed the highest performance (AUC: 0.83 ± 0.04), followed by AdaBoost (AUC: 0.80 ± 0.04), SVM (AUC: 0.78 ± 0.04), GBDT (0.76 ± 0.04). Furthermore, the accuracy, sensitivity and specificity of four ML models were higher than the baseline. SHAP summary plots based on MLP showed the most influential feature on model decision for positive CI prediction was female sex, followed by older age and lower waist circumference.

CONCLUSIONS

The diagnostic models of CI applying ML, especially the MLP, were substantially more effective than the traditional AD8 scale with a score of ≥ 2 points. Our findings may provide new ideas for community dementia screening and to promote such screening while minimizing medical and health resources.

Machine learning approach to identify malaria risk in travelers using real-world evidence

Background

Pre-travel consultation and chemoprophylaxis measures for malaria are a key component in the prevention of imported malaria in travelers. In this study we report a predictive tool for assessing personalized malaria risk in travelers based on the analysis of electronic medical records from travel consultations. The tool aims to guide physicians in the recommendation of appropriate prophylaxis prior to their trip. We also provide best-practice recommendations for pre-processing noisy and highly sparse real world evidence data.

Methods

We leveraged a large EMR dataset, containing demographic information about travelers and their destination. The data has been previously preprocessed using various strategies to handle missing and unbalanced data. We compared multiple machine learning approaches to assess the risk of malaria acquisition in travelers during their travels. Additionally, a feature importance analysis was performed using SHAP (SHapley Additive Explanations) values to identify patterns associated with malaria risk.

Results

Our study revealed that our XGB models achieved high predictive capacity (AUC >0.80). The most significant features predicting malaria infection during travel included travel destinations with low malaria risk, vaccination history, number of countries visited, age, and trip duration. Remarkably, we were able to obtain a reduced model with only five features. When comparing this model with a population of travelers recommended for malaria chemoprophylaxis, we observed that it was deemed necessary in only 40% of these travelers. This suggests that 60% received chemoprophylaxis despite having a low personalized risk of malaria.

Conclusion

We have developed an algorithmic tool that utilizes a concise survey to generate a personalized travel risk assessment, effectively minimizing the prescription of unnecessary malaria chemoprophylaxis. Through the identification of patterns linked to predictions, our model significantly enhances the efficacy of pre-travel consultations.

Comprehensive analysis of immunogenic cell death-related gene and construction of prediction model based on WGCNA and multiple machine learning in severe COVID-19

The death of coronavirus disease 2019 (COVID-19) is primarily due to from critically ill patients, especially from ARDS complications caused by SARS-CoV-2. Therefore, it is essential to contribute an in-depth understanding of the pathogenesis of the disease and to identify biomarkers for predicting critically ill patients at the molecular level. Immunogenic cell death (ICD), as a specific variant of regulatory cell death driven by stress, can induce adaptive immune responses against cell death antigens in the host. Studies have confirmed that both innate and adaptive immune pathways are involved in the pathogenesis of SARS-CoV-2 infection. However, the role of ICD in the pathogenesis of severe COVID-19 has rarely been explored. In this study, we systematically evaluated the role of ICD-related genes in COVID-19. We conducted consensus clustering, immune infiltration analysis, and functional enrichment analysis based on ICD differentially expressed genes. The results showed that immune infiltration characteristics were altered in severe and non-severe COVID-19. In addition, we used multiple machine learning methods to screen for five risk genes (KLF5, NSUN7, APH1B, GRB10 and CD4), which are used to predict COVID-19 severity. Finally, we constructed a nomogram to predict the risk of severe COVID-19 based on the classification and recognition model, and validated the model with external data sets. This study provides a valuable direction for the exploration of the pathogenesis and progress of COVID-19, and helps in the early identification of severe cases of COVID-19 to reduce mortality.

Review of Personalized Medicine and Pharmacogenomics of Anti-Cancer Compounds and Natural Products

In recent years, the FDA has approved numerous anti-cancer drugs that are mutation-based for clinical use. These drugs have improved the precision of treatment and reduced adverse effects and side effects. Personalized therapy is a prominent and hot topic of current medicine and also represents the future direction of development. With the continuous advancements in gene sequencing and high-throughput screening, research and development strategies for personalized clinical drugs have developed rapidly. This review elaborates the recent personalized treatment strategies, which include artificial intelligence, multi-omics analysis, chemical proteomics, and computation-aided drug design. These technologies rely on the molecular classification of diseases, the global signaling network within organisms, and new models for all targets, which significantly support the development of personalized medicine. Meanwhile, we summarize chemical drugs, such as lorlatinib, osimertinib, and other natural products, that deliver personalized therapeutic effects based on genetic mutations. This review also highlights potential challenges in interpreting genetic mutations and combining drugs, while providing new ideas for the development of personalized medicine and pharmacogenomics in cancer study.

MALrisk: a machine-learning–based tool to predict imported malaria in returned travellers with fever

BACKGROUND

Early diagnosis is key to reducing the morbi-mortality associated with P. falciparum malaria among international travellers. However, access to microbiological tests can be challenging for some healthcare settings. Artificial Intelligence could improve the management of febrile travellers.

METHODS

Data from a multicentric prospective study of febrile travellers was obtained to build a machine-learning model to predict malaria cases among travellers presenting with fever. Demographic characteristics, clinical and laboratory variables were leveraged as features. Eleven machine-learning classification models were evaluated by 50-fold cross-validation in a Training set. Then, the model with the best performance, defined by the Area Under the Curve (AUC), was chosen for parameter optimization and evaluation in the Test set. Finally, a reduced model was elaborated with those features that contributed most to the model.

RESULTS

Out of eleven machine-learning models, XGBoost presented the best performance (mean AUC of 0.98 and a mean F1 score of 0.78). A reduced model (MALrisk) was developed using only six features: Africa as a travel destination, platelet count, rash, respiratory symptoms, hyperbilirubinemia and chemoprophylaxis intake. MALrisk predicted malaria cases with 100% (95%CI 96-100) sensitivity and 72% (95%CI 68-75) specificity.

CONCLUSIONS

The MALrisk can aid in the timely identification of malaria in non-endemic settings, allowing the initiation of empiric antimalarials and reinforcing the need for urgent transfer in healthcare facilities with no access to malaria diagnostic tests. This resource could be easily scalable to a digital application and could reduce the morbidity associated with late diagnosis.

Advances in the study of tertiary lymphoid structures in the immunotherapy of breast cancer

Breast cancer, as one of the most common malignancies in women, exhibits complex and heterogeneous pathological characteristics across different subtypes. Triple-negative breast cancer (TNBC) and HER2-positive breast cancer are two common and highly invasive subtypes within breast cancer. The stability of the breast microbiota is closely intertwined with the immune environment, and immunotherapy is a common approach for treating breast cancer.Tertiary lymphoid structures (TLSs), recently discovered immune cell aggregates surrounding breast cancer, resemble secondary lymphoid organs (SLOs) and are associated with the prognosis and survival of some breast cancer patients, offering new avenues for immunotherapy. Machine learning, as a form of artificial intelligence, has increasingly been used for detecting biomarkers and constructing tumor prognosis models. This article systematically reviews the latest research progress on TLSs in breast cancer and the application of machine learning in the detection of TLSs and the study of breast cancer prognosis. The insights provided contribute valuable perspectives for further exploring the biological differences among different subtypes of breast cancer and formulating personalized treatment strategies.

Risk assessment of imported malaria in China: a machine learning perspective

BACKGROUND

Following China's official designation as malaria-free country by WHO, the imported malaria has emerged as a significant determinant impacting the malaria reestablishment within China. The objective of this study is to explore the application prospects of machine learning algorithms in imported malaria risk assessment of China.

METHODS

The data of imported malaria cases in China from 2011 to 2019 was provided by China CDC; historical epidemic data of malaria endemic country was obtained from World Malaria Report, and the other data used in this study are open access data. All the data processing and model construction based on R, and map visualization used ArcGIS software.

RESULTS

A total of 27,088 malaria cases imported into China from 85 countries between 2011 and 2019. After data preprocessing and classification, clean dataset has 765 rows (85 * 9) and 11 cols. Six machine learning models was constructed based on the training set, and Random Forest model demonstrated the best performance in model evaluation. According to RF, the highest feature importance were the number of malaria deaths and Indigenous malaria cases. The RF model demonstrated high accuracy in forecasting risk for the year 2019, achieving commendable accuracy rate of 95.3%. This result aligns well with the observed outcomes, indicating the model's reliability in predicting risk levels.

CONCLUSIONS

Machine learning algorithms have reliable application prospects in risk assessment of imported malaria in China. This study provides a new methodological reference for the risk assessment and control strategies adjusting of imported malaria in China.

Identification of Active Components for Sports Supplements: Machine Learning-Driven Classification and Cell-Based Validation

The identification of active components is critical for the development of sports supplements. However, high-throughput screening of active components remains a challenge. This study sought to construct prediction models to screen active components from herbal medicines via machine learning and validate the screening by using cell-based assays. The six constructed models had an accuracy of >0.88. Twelve randomly selected active components from the screening were tested for their active potency on C2C12 cells, and 11 components induced a significant increase in myotube diameters and protein synthesis. The effect and mechanism of luteolin among the 11 active components as potential sports supplements were then investigated by using immunofluorescence staining and high-content imaging analysis. It showed that luteolin increased the skeletal muscle performance via the activation of PGC-1α and MAPK signaling pathways. Thus, high-throughput prediction models can be effectively used to screen active components as sports supplements.

Enhancing medical image analysis with unsupervised domain adaptation approach across microscopes and magnifications

In the domain of medical image analysis, deep learning models are heralding a revolution, especially in detecting complex and nuanced features characteristic of diseases like tumors and cancers. However, the robustness and adaptability of these models across varied imaging conditions and magnifications remain a formidable challenge. This paper introduces the Fourier Adaptive Recognition System (FARS), a pioneering model primarily engineered to address adaptability in malarial parasite recognition. Yet, the foundational principles guiding FARS lend themselves seamlessly to broader applications, including tumor and cancer diagnostics. FARS capitalizes on the untapped potential of transitioning from bounding box labels to richer semantic segmentation labels, enabling a more refined examination of microscopy slides. With the integration of adversarial training and the Color Domain Aware Fourier Domain Adaptation (F2DA), the model ensures consistent feature extraction across diverse microscopy configurations. The further inclusion of category-dependent context attention amplifies FARS's cross-domain versatility. Evidenced by a substantial elevation in cross-magnification performance from 31.3% mAP to 55.19% mAP and a 15.68% boost in cross-domain adaptability, FARS positions itself as a significant advancement in malarial parasite recognition. Furthermore, the core methodologies of FARS can serve as a blueprint for enhancing precision in other realms of medical image analysis, especially in the complex terrains of tumor and cancer imaging. The code is available at; https://github.com/Mr-TalhaIlyas/FARS.

PDDGCN: A Parasitic Disease-Drug Association Predictor Based on Multi-view Fusion Graph Convolutional Network

The precise identification of associations between diseases and drugs is paramount for comprehending the etiology and mechanisms underlying parasitic diseases. Computational approaches are highly effective in discovering and predicting disease-drug associations. However, the majority of these approaches primarily rely on link-based methodologies within distinct biomedical bipartite networks. In this study, we reorganized a fundamental dataset of parasitic disease-drug associations using the latest databases, and proposed a prediction model called PDDGCN, based on a multi-view graph convolutional network. To begin with, we fused similarity networks with binary networks to establish multi-view heterogeneous networks. We utilized neighborhood information aggregation layers to refine node embeddings within each view of the multi-view heterogeneous networks, leveraging inter- and intra-domain message passing to aggregate information from neighboring nodes. Subsequently, we integrated multiple embeddings from each view and fed them into the ultimate discriminator. The experimental results demonstrate that PDDGCN outperforms five state-of-the-art methods and four compared machine learning algorithms. Additionally, case studies have substantiated the effectiveness of PDDGCN in identifying associations between parasitic diseases and drugs. In summary, the PDDGCN model has the potential to facilitate the discovery of potential treatments for parasitic diseases and advance our comprehension of the etiology in this field. The source code is available at https://github.com/AhauBioinformatics/PDDGCN .

Dual-layer detector spectral CT-based machine learning models in the differential diagnosis of solitary pulmonary nodules

The benign and malignant status of solitary pulmonary nodules (SPNs) is a key determinant of treatment decisions. The main objective of this study was to validate the efficacy of machine learning (ML) models featured with dual-layer detector spectral computed tomography (DLCT) parameters in identifying the benign and malignant status of SPNs. 250 patients with pathologically confirmed SPN were included in this study. 8 quantitative and 16 derived parameters were obtained based on the regions of interest of the lesions on the patients' DLCT chest enhancement images. 6 ML models were constructed from 10 parameters selected after combining the patients' clinical parameters, including gender, age, and smoking history. The logistic regression model showed the best diagnostic performance with an area under the receiver operating characteristic curve (AUC) of 0.812, accuracy of 0.813, sensitivity of 0.750 and specificity of 0.791 on the test set. The results suggest that the ML models based on DLCT parameters are superior to the traditional CT parameter models in identifying the benign and malignant nature of SPNs, and have greater potential for application.

Unleashing the power of artificial intelligence for diagnosing and treating infectious diseases: A comprehensive review

Infectious diseases present a global challenge, requiring accurate diagnosis, effective treatments, and preventive measures. Artificial intelligence (AI) has emerged as a promising tool for analysing complex molecular data and improving the diagnosis, treatment, and prevention of infectious diseases. Computer-aided detection (CAD) using convolutional neural networks (CNN) has gained prominence for diagnosing tuberculosis (TB) and other infectious diseases such as COVID-19, HIV, and viral pneumonia. The review discusses the challenges and limitations associated with AI in this field and explores various machine-learning models and AI-based approaches. Artificial neural networks (ANN), recurrent neural networks (RNN), support vector machines (SVM), multilayer neural networks (MLNN), CNN, long short-term memory (LSTM), and random forests (RF) are among the models discussed. The review emphasizes the potential of AI to enhance the accuracy and efficiency of diagnosis, treatment, and prevention of infectious diseases, highlighting the need for further research and development in this area.

Construction of an Early Alert System for Intradialytic Hypotension before Initiating Hemodialysis Based on Machine Learning

Introduction

Intradialytic hypotension (IDH) is prevalent and associated with high hospitalization and mortality rates. The purpose of this study was to explore the risk factors for IDH and use artificial intelligence to establish an early alert system before hemodialysis sessions to identify patients at high risk of IDH.

Materials and Methods

We obtained data on 314,534 hemodialysis sessions conducted at Sichuan Provincial People's Hospital from the renal disease treatment information system. IDH was defined as a systolic blood pressure drop ≥20 mm Hg, a mean arterial pressure drop ≥10 mm Hg during dialysis, or the occurrence of clinical hypotensive events requiring nursing intervention. After pre-processing, the data were randomly divided into training (80%) and testing (20%) sets. Four interpolation methods, three feature selection methods, and 18 machine learning algorithms were used to construct predictive models. The area under the receiver operating characteristic curve (AUC) was the main indicator for evaluating the performance of the models, while Shapley Additive ExPlanation was used to explain the contribution of each variable to the best predictive model.

Results

A total of 3,906 patients and 314,534 dialysis sessions were included, of which 142,237 cases showed IDH (incidence rate, 45.2%). Nineteen parameters were identified through artificial intelligence feature screening. They included age, pre-dialysis weight, dry weight, pre-dialysis blood pressure, heart rate, prescribed ultrafiltration, blood cell counts (neutrophil, lymphocyte, monocyte, eosinophil, lymphocyte, and platelet counts), hematocrit, serum calcium, creatinine, urea, glucose, and uric acid. Random forest, gradient boosting, and logistic regression were the three best models, and the AUCs were 0.812 (95% confidence interval [CI], 0.811-0.813), 0.748 (95% CI, 0.747-0.749), and 0.743 (95% CI, 0.742-0.744), respectively.

Conclusion

Our dialysis software-based artificial intelligence alert system can be used to predict IDH occurrence, enabling the initiation of relevant interventions.

Prediction of prokaryotic and eukaryotic promoters based on information-theoretic features

Promoters are DNA regulatory elements located near the transcription start site and are responsible for regulating the transcription of genes. DNA fragments arranged in a certain order form specific functional regions with different information contents. Information theory is the science that studies the extraction, measurement and transmission of information. The genetic information contained in DNA follows the general laws of information storage. Therefore, method in information theory can be used for the analysis of promoters carrying genetic information. In this study, we introduced the concept of information theory to the study of promoter prediction. We used 107 features extracted based on information theory methods and a backpropagation neural network to build a classifier. Then, the trained classifier was applied to predict the promoters of 6 organisms. The average AUCs of the 6 organisms obtained by using hold-out validation and ten-fold cross-validation were 0.885 and 0.886, respectively. The results verified the effectiveness of information-theoretic features in promoter prediction. Considering the possible redundancy in the feature set, we performed feature selection and obtained key feature subsets related to promoter characteristics. The results indicate the potential utility of information-theoretic features in promoter prediction.

Risk factor mining and prediction of urine protein progression in chronic kidney disease: a machine learning- based study

BACKGROUND

Chronic kidney disease (CKD) is a global public health concern. Therefore, to provide timely intervention for non-hospitalized high-risk patients and rationally allocate limited clinical resources is important to mine the key factors when designing a CKD prediction model.

METHODS

This study included data from 1,358 patients with CKD pathologically confirmed during the period from December 2017 to September 2020 at Zhongshan Hospital. A CKD prediction interpretation framework based on machine learning was proposed. From among 100 variables, 17 were selected for the model construction through a recursive feature elimination with logistic regression feature screening. Several machine learning classifiers, including extreme gradient boosting, gaussian-based naive bayes, a neural network, ridge regression, and linear model logistic regression (LR), were trained, and an ensemble model was developed to predict 24-hour urine protein. The detailed relationship between the risk of CKD progression and these predictors was determined using a global interpretation. A patient-specific analysis was conducted using a local interpretation.

RESULTS

The results showed that LR achieved the best performance, with an area under the curve (AUC) of 0.850 in a single machine learning model. The ensemble model constructed using the voting integration method further improved the AUC to 0.856. The major predictors of moderate-to-severe severity included lower levels of 25-OH-vitamin, albumin, transferrin in males, and higher levels of cystatin C.

CONCLUSIONS

Compared with the clinical single kidney function evaluation indicators (eGFR, Scr), the machine learning model proposed in this study improved the prediction accuracy of CKD progression by 17.6% and 24.6%, respectively, and the AUC was improved by 0.250 and 0.236, respectively. Our framework can achieve a good predictive interpretation and provide effective clinical decision support.

Machine learning algorithms to predict intraoperative hemorrhage in surgical patients: a modeling study of real-world data in Shanghai, China

BACKGROUND

Prediction tools for various intraoperative bleeding events remain scarce. We aim to develop machine learning-based models and identify the most important predictors by real-world data from electronic medical records (EMRs).

METHODS

An established database of surgical inpatients in Shanghai was utilized for analysis. A total of 51,173 inpatients were assessed for eligibility. 48,543 inpatients were obtained in the dataset and patients were divided into haemorrhage (N = 9728) and without-haemorrhage (N = 38,815) groups according to their bleeding during the procedure. Candidate predictors were selected from 27 variables, including sex (N = 48,543), age (N = 48,543), BMI (N = 48,543), renal disease (N = 26), heart disease (N = 1309), hypertension (N = 9579), diabetes (N = 4165), coagulopathy (N = 47), and other features. The models were constructed by 7 machine learning algorithms, i.e., light gradient boosting (LGB), extreme gradient boosting (XGB), cathepsin B (CatB), Ada-boosting of decision tree (AdaB), logistic regression (LR), long short-term memory (LSTM), and multilayer perception (MLP). An area under the receiver operating characteristic curve (AUC) was used to evaluate the model performance.

RESULTS

The mean age of the inpatients was 53 ± 17 years, and 57.5% were male. LGB showed the best predictive performance for intraoperative bleeding combining multiple indicators (AUC = 0.933, sensitivity = 0.87, specificity = 0.85, accuracy = 0.87) compared with XGB, CatB, AdaB, LR, MLP and LSTM. The three most important predictors identified by LGB were operative time, D-dimer (DD), and age.

CONCLUSIONS

We proposed LGB as the best Gradient Boosting Decision Tree (GBDT) algorithm for the evaluation of intraoperative bleeding. It is considered a simple and useful tool for predicting intraoperative bleeding in clinical settings. Operative time, DD, and age should receive attention.

Does multidimensional daily information predict the onset of myopia? A 1-year prospective cohort study

PURPOSE

This study aimed to develop an interpretable machine learning model to predict the onset of myopia based on individual daily information.

METHOD

This study was a prospective cohort study. At baseline, non-myopia children aged 6-13 years old were recruited, and individual data were collected through interviewing students and parents. One year after baseline, the incidence of myopia was evaluated based on visual acuity test and cycloplegic refraction measurement. Five algorithms, Random Forest, Support Vector Machines, Gradient Boosting Decision Tree, CatBoost and Logistic Regression were utilized to develop different models and their performance was validated by area under curve (AUC). Shapley Additive exPlanations was applied to interpret the model output on the individual and global level.

RESULT

Of 2221 children, 260 (11.7%) developed myopia in 1 year. In univariable analysis, 26 features were associated with the myopia incidence. Catboost algorithm had the highest AUC of 0.951 in the model validation. The top 3 features for predicting myopia were parental myopia, grade and frequency of eye fatigue. A compact model using only 10 features was validated with an AUC of 0.891.

CONCLUSION

The daily information contributed reliable predictors for childhood's myopia onset. The interpretable Catboost model presented the best prediction performance. Oversampling technology greatly improved model performance. This model could be a tool in myopia preventing and intervention that can help identify children who are at risk of myopia, and provide personalized prevention strategies based on contributions of risk factors to the individual prediction result.

Immunogenic cell death-led discovery of COVID-19 biomarkers and inflammatory infiltrates

Immunogenic cell death (ICD) serves a critical role in regulating cell death adequate to activate an adaptive immune response, and it is associated with various inflammation-related diseases. However, the specific role of ICD-related genes in COVID-19 remains unclear. We acquired COVID-19-related information from the GEO database and a total of 14 ICD-related differentially expressed genes (DEGs) were identified. These ICD-related DEGs were closely associated with inflammation and immune activity. Afterward, CASP1, CD4, and EIF2AK3 among the 14 DEGs were selected as feature genes based on LASSO, Random Forest, and SVM-RFE algorithms, which had reliable diagnostic abilities. Moreover, functional enrichment analysis indicated that these feature genes may have a potential role in COVID-19 by being involved in the regulation of immune response and metabolism. Further CIBERSORT analysis demonstrated that the variations in the immune microenvironment of COVID-19 patients may be correlated with CASP1, CD4, and EIF2AK3. Additionally, 33 drugs targeting 3 feature genes had been identified, and the ceRNA network demonstrated a complicated regulative association based on these feature genes. Our work identified that CASP1, CD4, and EIF2AK3 were diagnostic genes of COVID-19 and correlated with immune activity. This study presents a reliable diagnostic signature and offers an overview to investigate the mechanism of COVID-19.

A Diagnostic Classifier Based on Circulating miRNA Pairs for COPD Using a Machine Learning Approach

Chronic obstructive pulmonary disease (COPD) is highly underdiagnosed, and early detection is urgent to prevent advanced progression. Circulating microRNAs (miRNAs) have been diagnostic candidates for multiple diseases. However, their diagnostic value has not yet been fully established in COPD. The purpose of this study was to develop an effective model for the diagnosis of COPD based on circulating miRNAs. We included circulating miRNA expression profiles of two independent cohorts consisting of 63 COPD and 110 normal samples, and then we constructed a miRNA pair-based matrix. Diagnostic models were developed using several machine learning algorithms. The predictive performance of the optimal model was validated in our external cohort. In this study, the diagnostic values of miRNAs based on the expression levels were unsatisfactory. We identified five key miRNA pairs and further developed seven machine learning models. The classifier based on LightGBM was selected as the final model with the area under the curve (AUC) values of 0.883 and 0.794 in test and validation datasets, respectively. We also built a web tool to assist diagnosis for clinicians. Enriched signaling pathways indicated the potential biological functions of the model. Collectively, we developed a robust machine learning model based on circulating miRNAs for COPD screening.

Demand prediction of medical services in home and community-based services for older adults in China using machine learning

Background

Home and community-based services are considered an appropriate and crucial caring method for older adults in China. However, the research examining demand for medical services in HCBS through machine learning techniques and national representative data has not yet been carried out. This study aimed to address the absence of a complete and unified demand assessment system for home and community-based services.

Methods

This was a cross-sectional study conducted on 15,312 older adults based on the Chinese Longitudinal Healthy Longevity Survey 2018. Models predicting demand were constructed using five machine-learning methods: Logistic regression, Logistic regression with LASSO regularization, Support Vector Machine, Random Forest, and Extreme Gradient Boosting (XGboost), and based on Andersen's behavioral model of health services use. Methods utilized 60% of older adults to develop the model, 20% of the samples to examine the performance of models, and the remaining 20% of cases to evaluate the robustness of the models. To investigate demand for medical services in HCBS, individual characteristics such as predisposing, enabling, need, and behavior factors constituted four combinations to determine the best model.

Results

Random Forest and XGboost models produced the best results, in which both models were over 80% at specificity and produced robust results in the validation set. Andersen's behavioral model allowed for combining odds ratio and estimating the contribution of each variable of Random Forest and XGboost models. The three most critical features that affected older adults required medical services in HCBS were self-rated health, exercise, and education.

Conclusion

Andersen's behavioral model combined with machine learning techniques successfully constructed a model with reasonable predictors to predict older adults who may have a higher demand for medical services in HCBS. Furthermore, the model captured their critical characteristics. This method predicting demands could be valuable for the community and managers in arranging limited primary medical resources to promote healthy aging.

Machine learning to predict in-hospital cardiac arrest from patients presenting to the emergency department

In-hospital cardiac arrest (IHCA) in the emergency department (ED) is not uncommon but often fatal. Using the machine learning (ML) approach, we sought to predict ED-based IHCA (EDCA) in patients presenting to the ED based on triage data. We retrieved 733,398 ED records from a tertiary teaching hospital over a 7 year period (Jan. 1, 2009-Dec. 31, 2015). We included only adult patients (≥ 18 y) and excluded cases presenting as out-of-hospital cardiac arrest. Primary outcome (EDCA) was identified via a resuscitation code. Patient demographics, triage data, and structured chief complaints (CCs), were extracted. Stratified split was used to divide the dataset into the training and testing cohort at a 3-to-1 ratio. Three supervised ML models were trained and performances were evaluated and compared to the National Early Warning Score 2 (NEWS2) and logistic regression (LR) model by the area under the receiver operating characteristic curve (AUC). We included 316,465 adult ED records for analysis. Of them, 636 (0.2%) developed EDCA. Of the constructed ML models, Random Forest outperformed the others with the best AUC result (0.931, 95% CI 0.911-0.949), followed by Gradient Boosting (0.930, 95% CI 0.909-0.948) and Extra Trees classifier (0.915, 95% CI 0.892-0.936). Although the differences between each of ML models and LR (AUC: 0.905, 95% CI 0.882-0.926) were not significant, all constructed ML models performed significantly better than using the NEWS2 scoring system (AUC 0.678, 95% CI 0.635-0.722). Our ML models showed excellent discriminatory performance to identify EDCA based only on the triage information. This ML approach has the potential to reduce unexpected resuscitation events if successfully implemented in the ED information system.

Integrating Structured and Unstructured EHR Data for Predicting Mortality by Machine Learning and Latent Dirichlet Allocation Method

An ICU is a critical care unit that provides advanced medical support and continuous monitoring for patients with severe illnesses or injuries. Predicting the mortality rate of ICU patients can not only improve patient outcomes, but also optimize resource allocation. Many studies have attempted to create scoring systems and models that predict the mortality of ICU patients using large amounts of structured clinical data. However, unstructured clinical data recorded during patient admission, such as notes made by physicians, is often overlooked. This study used the MIMIC-III database to predict mortality in ICU patients. In the first part of the study, only eight structured variables were used, including the six basic vital signs, the GCS, and the patient's age at admission. In the second part, unstructured predictor variables were extracted from the initial diagnosis made by physicians when the patients were admitted to the hospital and analyzed using Latent Dirichlet Allocation techniques. The structured and unstructured data were combined using machine learning methods to create a mortality risk prediction model for ICU patients. The results showed that combining structured and unstructured data improved the accuracy of the prediction of clinical outcomes in ICU patients over time. The model achieved an AUROC of 0.88, indicating accurate prediction of patient vital status. Additionally, the model was able to predict patient clinical outcomes over time, successfully identifying important variables. This study demonstrated that a small number of easily collectible structured variables, combined with unstructured data and analyzed using LDA topic modeling, can significantly improve the predictive performance of a mortality risk prediction model for ICU patients. These results suggest that initial clinical observations and diagnoses of ICU patients contain valuable information that can aid ICU medical and nursing staff in making important clinical decisions.

Machine Learning Logistic Regression Model for Early Decision Making in Referral of Children with Cervical Lymphadenopathy Suspected of Lymphoma

While cervical lymphadenopathy is common in children, a decision model for detecting high-grade lymphoma is lacking. Previously reported individual lymphoma-predicting factors and multivariate models were not sufficiently discriminative for clinical application. To develop a diagnostic scoring tool, we collected data from all children with cervical lymphadenopathy referred to our national pediatric oncology center within 30 months (n = 182). Thirty-nine putative lymphoma-predictive factors were investigated. The outcome groups were classical Hodgkin lymphoma (cHL), nodular lymphocyte-predominant Hodgkin lymphoma (NLPHL), non-Hodgkin lymphoma (NHL), other malignancies, and a benign group. We integrated the best univariate predicting factors into a multivariate, machine learning model. Logistic regression allocated each variable a weighing factor. The model was tested in a different patient cohort (n = 60). We report a 12-factor diagnostic model with a sensitivity of 95% (95% CI 89-98%) and a specificity of 88% (95% CI 77-94%) for detecting cHL and NHL. Our 12-factor diagnostic scoring model is highly sensitive and specific in detecting high-grade lymphomas in children with cervical lymphadenopathy. It may enable fast referral to a pediatric oncologist in patients with high-grade lymphoma and may reduce the number of referrals and unnecessary invasive procedures in children with benign lymphadenopathy.

Machine Learning Models for Predicting Adverse Pregnancy Outcomes in Pregnant Women with Systemic Lupus Erythematosus

Predicting adverse outcomes is essential for pregnant women with systemic lupus erythematosus (SLE) to minimize risks. Applying statistical analysis may be limited for the small sample size of childbearing patients, while the informative medical records could be provided. This study aimed to develop predictive models applying machine learning (ML) techniques to explore more information. We performed a retrospective analysis of 51 pregnant women exhibiting SLE, including 288 variables. After correlation analysis and feature selection, six ML models were applied to the filtered dataset. The efficiency of these overall models was evaluated by the Receiver Operating Characteristic Curve. Meanwhile, real-time models with different timespans based on gestation were also explored. Eighteen variables demonstrated statistical differences between the two groups; more than forty variables were screened out by ML variable selection strategies as contributing predictors, while the overlap of variables were the influential indicators testified by the two selection strategies. The Random Forest (RF) algorithm demonstrated the best discrimination ability under the current dataset for overall predictive models regardless of the data missing rate, while Multi-Layer Perceptron models ranked second. Meanwhile, RF achieved best performance when assessing the real-time predictive accuracy of models. ML models could compensate the limitation of statistical methods when the small sample size problem happens along with numerous variables acquired, while RF classifier performed relatively best when applied to such structured medical records.

Machine Learning Approaches for the Prediction of Hepatitis B and C Seropositivity

(1) Background: The identification of patients at risk for hepatitis B and C viral infection is a challenge for the clinicians and public health specialists. The aim of this study was to evaluate and compare the predictive performances of four machine learning-based models for the prediction of HBV and HCV status. (2) Methods: This prospective cohort screening study evaluated adults from the North-Eastern and South-Eastern regions of Romania between January 2022 and November 2022 who underwent viral hepatitis screening in their family physician's offices. The patients' clinical characteristics were extracted from a structured survey and were included in four machine learning-based models: support vector machine (SVM), random forest (RF), naïve Bayes (NB), and K nearest neighbors (KNN), and their predictive performance was assessed. (3) Results: All evaluated models performed better when used to predict HCV status. The highest predictive performance was achieved by KNN algorithm (accuracy: 98.1%), followed by SVM and RF with equal accuracies (97.6%) and NB (95.7%). The predictive performance of these models was modest for HBV status, with accuracies ranging from 78.2% to 97.6%. (4) Conclusions: The machine learning-based models could be useful tools for HCV infection prediction and for the risk stratification process of adult patients who undergo a viral hepatitis screening program.

Prediction of HELLP Syndrome Severity Using Machine Learning Algorithms-Results from a Retrospective Study

(1) Background: HELLP (hemolysis, elevated liver enzymes, and low platelets) syndrome is a rare and life-threatening complication of preeclampsia. The aim of this study was to evaluate and compare the predictive performances of four machine learning-based models for the prediction of HELLP syndrome, and its subtypes according to the Mississippi classification; (2) Methods: This retrospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between January 2007 and December 2021. The patients' clinical and paraclinical characteristics were included in four machine learning-based models: decision tree (DT), naïve Bayes (NB), k-nearest neighbors (KNN), and random forest (RF), and their predictive performance were assessed; (3) Results: Our results showed that HELLP syndrome was best predicted by RF (accuracy: 89.4%) and NB (accuracy: 86.9%) models, while DT (accuracy: 91%) and KNN (accuracy: 87.1%) models had the highest performance when used to predict class 1 HELLP syndrome. The predictive performance of these models was modest for class 2 and 3 of HELLP syndrome, with accuracies ranging from 65.2% and 83.8%; (4) Conclusions: The machine learning-based models could be useful tools for predicting HELLP syndrome, and its most severe form-class 1.

Towards digital diagnosis of malaria: How far have we reached?

The need for precise and early diagnosis of malaria and its distinction from other febrile illnesses is no doubt a prerequisite, primarily when standard rapid diagnostic tests (RDTs) cannot be totally relied upon. At the time of disease outbreaks, the pressure on hospital staff remains high and the chances of human error increase. Therefore, in the era of digitalisation of medicine as well as diagnostic approaches, various technologies such as artificial intelligence (AI) and machine learning (ML) should be deployed to further aid the diagnosis, especially in endemic and epidemic situations. Computational techniques are now more at the forefront than ever, and the interest in developing such efficient technologies is continuously increasing. A comprehensive understanding of these digital technologies is needed to maintain the scientific rigour in these attempts. This would enhance the implementation of these novel technologies for malaria diagnosis. This review highlights the progression, strengths, and limitations of various computing techniques so far employed to diagnose malaria.

Identification of copper death-associated molecular clusters and immunological profiles in rheumatoid arthritis

Objective

An analysis of the relationship between rheumatoid arthritis (RA) and copper death-related genes (CRG) was explored based on the GEO dataset.

Methods

Based on the differential gene expression profiles in the GSE93272 dataset, their relationship to CRG and immune signature were analysed. Using 232 RA samples, molecular clusters with CRG were delineated and analysed for expression and immune infiltration. Genes specific to the CRGcluster were identified by the WGCNA algorithm. Four machine learning models were then built and validated after selecting the optimal model to obtain the significant predicted genes, and validated by constructing RA rat models.

Results

The location of the 13 CRGs on the chromosome was determined and, except for GCSH. LIPT1, FDX1, DLD, DBT, LIAS and ATP7A were expressed at significantly higher levels in RA samples than in non-RA, and DLST was significantly lower. RA samples were significantly expressed in immune cells such as B cells memory and differentially expressed genes such as LIPT1 were also strongly associated with the presence of immune infiltration. Two copper death-related molecular clusters were identified in RA samples. A higher level of immune infiltration and expression of CRGcluster C2 was found in the RA population. There were 314 crossover genes between the 2 molecular clusters, which were further divided into two molecular clusters. A significant difference in immune infiltration and expression levels was found between the two. Based on the five genes obtained from the RF model (AUC = 0.843), the Nomogram model, calibration curve and DCA also demonstrated their accuracy in predicting RA subtypes. The expression levels of the five genes were significantly higher in RA samples than in non-RA, and the ROC curves demonstrated their better predictive effect. Identification of predictive genes by RA animal model experiments was also confirmed.

Conclusion

This study provides some insight into the correlation between rheumatoid arthritis and copper mortality, as well as a predictive model that is expected to support the development of targeted treatment options in the future.

Application of machine and deep learning algorithms in optical microscopic detection of Plasmodium: A malaria diagnostic tool for the future

Machine and deep learning techniques are prevalent in the medical discipline due to their high level of accuracy in disease diagnosis. One such disease is malaria caused by Plasmodium falciparum and transmitted by the female anopheles mosquito. According to the World Health Organisation (WHO), millions of people are infected annually, leading to inevitable deaths in the infected population. Statistical records show that early detection of malaria parasites could prevent deaths and machine learning (ML) has proved helpful in the early detection of malarial parasites. Human error is identified to be a major cause of inaccurate diagnostics in the traditional microscopy malaria diagnosis method. Therefore, the method would be more reliable if human expert dependency is restricted or entirely removed, and thus, the motivation of this paper. This study presents a systematic review to understand the prevalent machine learning algorithms applied to a low-cost, portable optical microscope in the automation of blood film interpretation for malaria parasite detection. Peer-reviewed papers were downloaded from selected reputable databases eg. Elsevier, IEEExplore, Pubmed, Scopus, Web of Science, etc. The extant literature suggests that convolutional neural network (CNN) and its variants (deep learning) account for 41.9% of the microscopy malaria diagnosis using machine learning with a prediction accuracy of 99.23%. Thus, the findings suggest that early detection of the malaria parasite has improved through the application of CNN and other ML algorithms on microscopic malaria parasite detection.

A hybrid breast cancer classification algorithm based on meta-learning and artificial neural networks

The incidence of breast cancer in women has surpassed that of lung cancer as the world’s leading new cancer case. Regular screening and measures become an effective way to prevent breast cancer and also provide a good foundation for later treatment. Women should receive regular checkups in the hospital after reaching a certain age. The use of computer-aided technology can improve the accuracy and efficiency of physicians’ decision-making. Data pre-processing is required before data analysis, and 16 features are selected using a correlation-based feature selection method. In this paper, meta-learning and Artificial Neural Networks (ANN) are combined to create a hybrid algorithm. The proposed hybrid algorithm for predicting breast cancer was attempted to achieve 98.74% accuracy and 98.02% F1-score by creating a combination of various meta-learning models whose output was used as input features for creating ANN models. Therefore, the hybrid algorithm proposed in this paper can obtain better prediction results than a single model.

Applying an Improved Stacking Ensemble Model to Predict the Mortality of ICU Patients with Heart Failure

Cardiovascular diseases have been identified as one of the top three causes of death worldwide, with onset and deaths mostly due to heart failure (HF). In ICU, where patients with HF are at increased risk of death and consume significant medical resources, early and accurate prediction of the time of death for patients at high risk of death would enable them to receive appropriate and timely medical care. The data for this study were obtained from the MIMIC-III database, where we collected vital signs and tests for 6699 HF patient during the first 24 h of their first ICU admission. In order to predict the mortality of HF patients in ICUs more precisely, an integrated stacking model is proposed and applied in this paper. In the first stage of dataset classification, the datasets were subjected to first-level classifiers using RF, SVC, KNN, LGBM, Bagging, and Adaboost. Then, the fusion of these six classifier decisions was used to construct and optimize the stacked set of second-level classifiers. The results indicate that our model obtained an accuracy of 95.25% and AUROC of 82.55% in predicting the mortality rate of HF patients, which demonstrates the outstanding capability and efficiency of our method. In addition, the results of this study also revealed that platelets, glucose, and blood urea nitrogen were the clinical features that had the greatest impact on model prediction. The results of this analysis not only improve the understanding of patients' conditions by healthcare professionals but allow for a more optimal use of healthcare resources.

ISTRF: Identification of sucrose transporter using random forest

Sucrose transporter (SUT) is a type of transmembrane protein that exists widely in plants and plays a significant role in the transportation of sucrose and the specific signal sensing process of sucrose. Therefore, identifying sucrose transporter is significant to the study of seed development and plant flowering and growth. In this study, a random forest-based model named ISTRF was proposed to identify sucrose transporter. First, a database containing 382 SUT proteins and 911 non-SUT proteins was constructed based on the UniProt and PFAM databases. Second, k-separated-bigrams-PSSM was exploited to represent protein sequence. Third, to overcome the influence of imbalance of samples on identification performance, the Borderline-SMOTE algorithm was used to overcome the shortcoming of imbalance training data. Finally, the random forest algorithm was used to train the identification model. It was proved by 10-fold cross-validation results that k-separated-bigrams-PSSM was the most distinguishable feature for identifying sucrose transporters. The Borderline-SMOTE algorithm can improve the performance of the identification model. Furthermore, random forest was superior to other classifiers on almost all indicators. Compared with other identification models, ISTRF has the best general performance and makes great improvements in identifying sucrose transporter proteins.