Diagnosis of Diabetes Mellitus Using Gradient Boosting Machine (LightGBM)

A machine learning approach to feature selection and uncertainty analysis for biogas production in wastewater treatment plants

The growing demand for efficient waste management solutions and renewable energy sources has driven research into predicting biogas production at wastewater treatment plants. This study outlines a methodology starting with data collection from a full-scale plant, followed by detailed analysis to resolve potential issues. A notable advancement is the use of a robust machine learning model, fine-tuned with advanced optimization techniques. To enhance its utility, prediction intervals were incorporated to quantify uncertainty, providing decision-makers with reliable insights. Results revealed that the developed model performed well, explaining 82% of the variability in test data and delivering predictions closely aligned with actual biogas production. This reliability empowers more confident decision-making in wastewater treatment operations. The study also identified key factors influencing biogas output, categorizing them intosludge characteristics, operational practices, and sludge quantity. By focusing on most important adjustable parameters, operators can optimize processes and significantly improve biogas yields. This predictive capability, combined with an understanding of influencing factors and quantified reliability, offers notable advantages. It enables operators to enhance biogas production while providing decision-makers with reliable predictions to guide policy and resource management. These developments contribute to more sustainable and efficient waste management practices.

Multimodal machine learning-based model for differentiating nontuberculous mycobacteria from mycobacterium tuberculosis

Objective

To develop and evaluate the effectiveness of multimodal machine learning approach for the differentiation of NTM from MTB.

Methods

The clinical data and CT images of 175 patients were retrospectively obtained. We established clinical data-based model, radiomics-based model, and multimodal (clinical plus radiomics) model gradually using 5 machine learning algorithms (Logistic, XGBoost, AdaBoost, RandomForest, and LightGBM). Optimal algorithm in each model was selected after evaluating the differentiation performance both in training and validation sets. The model performance was further verified using external new MTB and NTM patient data. Performance was also compared with the existing approaches and model.

Results

The clinical data-based model contained age, gender, and IL-6, and the RandomForest algorithm achieved the optimal learning model. Two key radiomics features of CT images were identified and then used to establish the radiomics model, finding that model from Logistic algorithm was the optimal. The multimodal model contained age, IL-6, and the 2 radiomics features, and the optimal model was from LightGBM algorithm. The optimal multimodal model had the highest AUC value, accuracy, sensitivity, and negative predictive value compared with the optimal clinical or radiomics models, and its' favorable performance was also verified in the external test dataset (accuracy = 0.745, sensitivity = 0.900). Additionally, the performance of multimodal model was better than that of the radiologist, NGS detection, and existing machine learning model, with an increased accuracy of 26, 4, and 6%, respectively.

Conclusion

This is the first study to establish multimodal model to distinguish NTM from MTB and it performs well in differentiating them, which has the potential to aid clinical decision-making for experienced radiologists.

Predicting major adverse cardiac events in diabetes and chronic kidney disease: a machine learning study from the Silesia Diabetes-Heart Project

BACKGROUND

People living with diabetes mellitus (DM) and chronic kidney disease (CKD) are at significantly high risk of cardiovascular events (CVEs), however the predictive performance of traditional risk prediction methods are limited.

METHODS

We utilised machine learning (ML) model to predict CVEs in persons with DM and CKD from the Silesia Diabetes-Heart Project, a routine standard of care dataset. CVEs were defined as composite of nonfatal myocardial infarction, new onset heart failure, nonfatal stroke, incident atrial fibrillation, undergoing percutaneous coronary intervention or coronary artery bypass grafting, hospitalisation or death due to cardiovascular disease. Five ML models (Logistic regression [LR], Random forest [RF], Support vector classification [SVC], Light gradient boosting machine [LGBM], and eXtreme gradient boosting machine [XGBM]) were constructed. The predictive performance of the five ML models was compared and the model interpretability were evaluated by Shapley Additive exPlanations (SHAP).

RESULTS

A total of 1,116 people with DM and CKD out of 3,056 with DM were included (median age 67 [IQR 57-76] years; 57% men). The incidence of CVEs was 14.1% (157/1,116) during a median of 3.1 years follow-up period. Ten important features were identified through univariate Logistic regression, Boruta, and Least Absolute Shrinkage and Selection Operator [LASSO] regression. Among the five ML models based on these features, LGBM had the highest area under curve [AUC] (AUC = 0.740, 95% Confidence Interval [CI] 0.738-0.743), followed by LR (AUC = 0.621, 95% CI 0.618-0.623), RF (AUC = 0.707, 95% CI 0.704-0.709), SVC (AUC = 0.707, 95% CI 0.704-0.710), and XGBM (AUC = 0.710, 95% CI 0.707-0.713). Meanwhile, LGBM had relatively higher Recall (0.739), F1-score (0.820), and G-mean (0.826). The SHAP plot of LGBM revealed that estimated glomerular filtration rate (eGFR), age, and triglyceride glucose index were the three most important features for predicting CVEs.

CONCLUSION

Ten features-based ML models, especially the LGBM model, had acceptable performance in predicting CVEs in persons with DM and CKD. A decrease in eGFR, aging, and elevated inflammatory markers significantly enhanced the predictive capability of the model. Future external validation of our model is required prior to implementation in a clinical environment.

Prediction of stunting and its socioeconomic determinants among adolescent girls in Ethiopia using machine learning algorithms

BACKGROUND

Stunting is a vital indicator of chronic undernutrition that reveals a failure to reach linear growth. Investigating growth and nutrition status during adolescence, in addition to infancy and childhood is very crucial. However, the available studies in Ethiopia have been usually focused in early childhood and they used the traditional stastical methods. Therefore, this study aimed to employ multiple machine learning algorithms to identify the most effective model for the prediction of stunting among adolescent girls in Ethiopia.

METHODS

A total of 3156 weighted samples of adolescent girls aged 15-19 years were used from the 2016 Ethiopian Demographic and Health Survey dataset. The data was pre-processed, and 80% and 20% of the observations were used for training, and testing the model, respectively. Eight machine learning algorithms were included for consideration of model building and comparison. The performance of the predictive model was evaluated using evaluation metrics value through Python software. The synthetic minority oversampling technique was used for data balancing and Boruta algorithm was used to identify best features. Association rule mining using an Apriori algorithm was employed to generate the best rule for the association between the independent feature and the targeted feature using R software.

RESULTS

The random forest classifier (sensitivity = 81%, accuracy = 77%, precision = 75%, f1-score = 78%, AUC = 85%) outperformed in predicting stunting compared to other ML algorithms considered in this study. Region, poor wealth index, no formal education, unimproved toilet facility, rural residence, not used contraceptive method, religion, age, no media exposure, occupation, and having one or more children were the top attributes to predict stunting. Association rule mining was identified the top seven best rules that most frequently associated with stunting among adolescent girls in Ethiopia.

CONCLUSION

The random forest classifier outperformed in predicting and identifying the relevant predictors of stunting. Results have shown that machine learning algorithms can accurately predict stunting, making them potentially valuable as decision-support tools for the relevant stakeholders and giving emphasis for the identified predictors could be an important intervention to halt stunting among adolescent girls.

Predicting rapid decline in kidney function among type 2 diabetes patients: A machine learning approach

Background

Diabetic kidney disease (DKD) is one of the typical complications of type 2 diabetes (T2D), with approximately 10 % of DKD patients experiencing a Rapid decline (RD) in kidney function. RD leads to an increased risk of poor outcomes such as the need for dialysis. Albuminuria is a known kidney damage biomarker for DKD, yet RD cases do not always show changes in albuminuria, and the exact mechanism of RD remains unclear. Previous studies focused on a limited number of laboratory tests, no comprehensive study targeting a wide range of laboratory tests has been done. We target to develop a model that predicts RD among T2D and points to key laboratory tests of interest in understanding RD from various laboratory tests.

Methods

Our machine learning model predicts whether RD, as represented via eGFR, will happen within 1 year. Additionally, the model uses Recursive feature elimination with cross-validation (RFECV) to eliminate the features that do not contribute to the prediction. We trained and assessed the model using 1202 types of laboratory tests from 3438 diabetes patients at the University of Tokyo Hospital.

Result

The means (95 % confidence interval) of the receiver operating characteristic area under the curve (ROC-AUC), precision-recall area under the curve, accuracy rate, and F1-score of an 8-feature-model were 0.820 (0.811, 0.829), 0.430 (0.410, 0.451), 0.754 (0.747, 0.761), and 0.500 (0.485, 0.515), respectively. The RFECV revealed that 7 test types (MCH, γ-GTP, Cre, HbA1c, HDL-C, eGFR, and Hct) contributed to RD prediction. The model's ROC-AUC of 0.820 improves on the ROC-AUC of 0.775 seen in previous studies.

Conclusion

The proposed model accurately predicts RD among diabetes patients and helps physicians focus on inhibiting progression of kidney damage. The contributing laboratory tests may serve as alternative biomarkers for DKD.

Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning

The aim of this study was to develop and validate a machine learning-based mortality risk prediction model for patients with severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU). We collected data from two centers as the development and external validation cohorts. Variables were screened using the Recursive Feature Elimination method. Five machine learning algorithms were used to build predictive models. Models were evaluated through nested cross-validation to select the best one. The model was interpreted using Shapley Additive Explanations. We selected the optimal model to generate the web calculator. A total of 23 predictive features were selected. The Light Gradient Boosting Machine (LightGBM) model had an area under the receiver operating characteristic curve (AUC) of 0.842 (95% CI: 0.757-0.927), with an external 5-fold cross-validation average AUC of 0.842 ± 0.038, which was superior to the other models. External validation results also demonstrated good performance by the LightGBM model with an AUC of 0.856 (95% CI: 0.792-0.921). Based on this, we generated a web calculator by combining five high importance predictive factors. The LightGBM model was confirmed to be efficient and stable in predicting the mortality risk of patients with SCAP admitted to the ICU. The web calculator based on the LightGBM model can provide clinicians with a prognostic evaluation tool.

Using Machine Learning and Artificial Intelligence to Predict Diabetes Mellitus among Women Population

BACKGROUND

Diabetes Mellitus is a chronic health condition (long-lasting) due to inadequate control of blood levels of glucose. This study presents a prediction of Type 2 Diabetes Mellitus among women using various Machine Learning Algorithms deployed to predict the diabetic condition. A University of California Irvine Diabetes Mellitus Dataset posted in Kaggle was used for analysis.

METHODS

The dataset included eight risk factors for Type 2 Diabetes Mellitus prediction, including Age, Systolic Blood Pressure, Glucose, Body Mass Index, Insulin, Skin Thickness, Diabetic Pedigree Function, and Pregnancy. R language was used for the data visualization, while the algorithms considered for the study are Logistic Regression, Support Vector Machines, Decision Trees and Extreme Gradient Boost. The performance analysis of these algorithms on various classification metrics is also presented here, considering the Area Under the Curve and Receiver Operating Characteristics score is the best for Extreme Gradient Boost with 85%, followed by Support Vector Machines and Decision Trees.

RESULTS

The Logistic Regression is showing low performance. But the Decision Trees and Extreme Gradient Boost show promising performance against all the classification metrics. But the Support Vector Machines offers a lower support value; hence it cannot be claimed to be a good classifier. The model showed that the most significant predictors of Type 2 Diabetes Mellitus were strongly correlated with Glucose Levels and mediumly correlated with Body Mass Index, whereas Age, Skin Thickness, Systolic Blood Pressure, Insulin, Pregnancy, and Pedigree Function were less significant. This type of real-time analysis has proved that the symptoms of Type 2 Diabetes Mellitus in women fall entirely different compared to men, which highlights the importance of Glucose Levels and Body Mass Index in women.

CONCLUSION

The prediction of Type 2 Diabetes Mellitus helps public health professionals to help people by suggesting proper food intake and adjusting lifestyle activities with good fitness management in women to make glucose levels and body mass index controlled. Therefore, the healthcare systems should give special attention to diabetic conditions in women to reduce exacerbations of the disease and other associated symptoms. This work attempts to predict the occurrence of Type 2 Diabetes Mellitus among women on their behavioral and biological conditions.

Predicting Live Weight for Female Rabbits of Meat Crosses From Body Measurements Using LightGBM, XGBoost and Support Vector Machine Algorithms

Prediction of body weight (BW) using biometric measurements is an important tool especially for animal welfare and automatic phenotyping tools that needs mathematical models. In this study, it was aimed to predict the BW using body length (BL), chest girth (CG) and width of the waist (WW) for rabbits of the maternal form of Hyla NG. The standard rabbit-raising practices were applied for the animals. A highly efficient gradient-boosting decision tree (LightGBM), eXtreme gradient-boosting (XGBoost) and support vector machine (SVM) algorithms were evaluated and compared to the prediction of BW. The coefficient of determination, root mean square error and mean absolute error values were used as comparison criteria. The results showed that LightGBM, XGBoost and SVM algorithms were well fit for the BW using the biometric measures with over 95% accuracy for both train and test sets. The BL was determined as the most explanatory variable on body weight.

LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study

Respiratory diseases pose a significant global health burden, with challenges in early and accurate diagnosis due to overlapping clinical symptoms, which often leads to misdiagnosis or delayed treatment. To address this issue, we developed LungDiag, an artificial intelligence (AI)-based diagnostic system that utilizes natural language processing (NLP) to extract key clinical features from electronic health records (EHRs) for the accurate classification of respiratory diseases. This study employed a large cohort of 31,267 EHRs from multiple centers for model training and internal testing. Additionally, prospective real-world validation was conducted using 1142 EHRs from three external centers. LungDiag demonstrated superior diagnostic performance, achieving an F1 score of 0.711 for top 1 diagnosis and 0.927 for top 3 diagnoses. In real-world testing, LungDiag outperformed both human experts and ChatGPT 4.0, achieving an F1 score of 0.651 for top 1 diagnosis. The study emphasizes the potential of LungDiag as an effective tool to support physicians in diagnosing respiratory diseases more accurately and efficiently. Despite the promising results, further large-scale multicenter validation with larger sample sizes is still needed to confirm its clinical utility and generalizability.

A Data-Driven Approach to Predicting Recreational Activity Participation Using Machine Learning

Purpose: With the popularity of recreational activities, the study aimed to develop prediction models for recreational activity participation and explore the key factors affecting participation in recreational activities. Methods: A total of 12,712 participants, excluding individuals under 20, were selected from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2018. The mean age of the sample was 46.86 years (±16.97), with a gender distribution of 6,721 males and 5,991 females. The variables included demographic, physical-related variables, and lifestyle variables. This study developed 42 prediction models using six machine learning methods, including logistic regression, Support Vector Machine (SVM), decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). The relative importance of each variable was evaluated by permutation feature importance. Results: The results illustrated that the LightGBM was the most effective algorithm for predicting recreational activity participation (accuracy: .838, precision: .783, recall: .967, F1-score: .865, AUC: .826). In particular, prediction performance increased when the demographic and lifestyle datasets were used together. Next, as the result of the permutation feature importance based on the top models, education level and moderate-vigorous physical activity (MVPA) were found to be essential variables. Conclusion: These findings demonstrated the potential of a data-driven approach utilizing machine learning in a recreational discipline. Furthermore, this study interpreted the prediction model through feature importance analysis to overcome the limitation of machine learning interpretability.

Stacking model framework reveals clinical biochemical data and dietary behavior features associated with type 2 diabetes: A retrospective cohort study

Background: Type 2 diabetes mellitus (T2DM) is the most common type of diabetes, accounting for around 90% of all diabetes. Studies have found that dietary habits and biochemical metabolic changes are closely related to T2DM disease surveillance, but early surveillance tools are not specific and have lower accuracy. This paper aimed to provide a reliable artificial intelligence model with high accuracy for the clinical diagnosis of T2DM. Methods: A cross-sectional dataset comprising 8981 individuals from the First Affiliated Hospital of Guangxi Medical University was analyzed by a model fusion framework. The model includes four machine learning (ML) models, which used the stacking method. The ability to leverage the strengths of different algorithms to capture complex patterns in the data can effectively combine questionnaire data and blood test data to predict diabetes. Results: The experimental results show that the stacking model achieves significant prediction results in diabetes detection. Compared with the single machine learning algorithm, the stacking model has improved in the metrics of accuracy, recall, and F1-score. The test set accuracy is 0.90, and the precision, recall, F1-score, area under the curve, and average precision (AP) are 0.91, 0.90, 0.90, 0.90, and 0.85, respectively. Additionally, this study showed that HbA1c (P < 0.001,OR = 2.203), fasting blood glucose (FBG) (P < 0.001,OR = 1.586), Ph2BG (P < 0.001,OR = 1.190), age (P < 0.001,OR = 1.018), Han nationality (P < 0.001,OR = 1.484), and carbonate beverages (P = 0.001,OR = 1.347) were important predictors of T2DM. Conclusion: This study demonstrates that stacking models show great potential in diabetes detection, and by integrating multiple machine learning algorithms, stacking models can significantly improve the accuracy and stability of diabetes prediction and provide strong support for disease prevention, early diagnosis, and individualized treatment.

A Novel Hybrid Model for Automatic Non-Small Cell Lung Cancer Classification Using Histopathological Images

Background/Objectives: Despite recent advances in research, cancer remains a significant public health concern and a leading cause of death. Among all cancer types, lung cancer is the most common cause of cancer-related deaths, with most cases linked to non-small cell lung cancer (NSCLC). Accurate classification of NSCLC subtypes is essential for developing treatment strategies. Medical professionals regard tissue biopsy as the gold standard for the identification of lung cancer subtypes. However, since biopsy images have very high resolutions, manual examination is time-consuming and depends on the pathologist's expertise. Methods: In this study, we propose a hybrid model to assist pathologists in the classification of NSCLC subtypes from histopathological images. This model processes deep, textural and contextual features obtained by using EfficientNet-B0, local binary pattern (LBP) and vision transformer (ViT) encoder as feature extractors, respectively. In the proposed method, each feature matrix is flattened separately and then combined to form a comprehensive feature vector. The feature vector is given as input to machine learning classifiers to identify the NSCLC subtype. Results: We set up 13 different training scenarios to test 4 different classifiers: support vector machine (SVM), logistic regression (LR), light gradient boosting machine (LightGBM) and extreme gradient boosting (XGBoost). Among these scenarios, we obtained the highest classification accuracy (99.87%) with the combination of EfficientNet-B0 + LBP + ViT Encoder + SVM. The proposed hybrid model significantly enhanced the classification accuracy of NSCLC subtypes. Conclusions: The integration of deep, textural, and contextual features assisted the model in capturing subtle information from the images, thereby reducing the risk of misdiagnosis and facilitating more effective treatment planning.

FMI-CAECD: Fusing Multi-Input Convolutional Features with Enhanced Channel Attention for Cardiovascular Diseases Prediction

Cardiovascular diseases (CVD) have become a major public health problem affecting the national economy and social development, and have become one of the major causes of death. Therefore, the prevention, control and risk assessment of CVD have been increasingly emphasized. However, current CVD prediction models face limitations in capturing complex relationships within physiological data, potentially hindering accurate risk assessment. This study addresses this gap by proposing a novel Framework for Multi-Input, One-dimensional Convolutional Neural Network (1D-CNN) with Attention Mechanism for CVD (FMI-CAECD). This framework leverages the feature extraction capabilities of Convolutional Neural Network (CNN) alongside an Attention Mechanism to adaptively identify critical features and non-linear relationships within the data. Additionally, Shapley Additive Explanations (SHAP) analysis is incorporated to provide deeper insights into individual feature importance for disease prediction. Performance evaluation on the BRFSS 2022 dataset demonstrates that FMI-CAECD achieves superior accuracy (97.45%), sensitivity (96.84%), specificity (95.07%), and F1-score (92.44%) compared to traditional machine learning baselines and other deep learning models. These findings suggest that FMI-CAECD offers a promising approach for CVD risk assessment.

Using machine learning approaches to develop a fast and easy-to-perform diagnostic tool for patients with light chain amyloidosis: a retrospective real-world study

Immunoglobulin light chain (AL) amyloidosis is a severe disorder caused by the accumulation of amyloid fibrils, leading to organ failure. Early diagnosis is crucial to prevent irreversible damage, yet it remains a challenge due to nonspecific symptoms that often appear later in the disease progression. A retrospective study analyzed data collected from 133 AL amyloidosis patients and 271 non-AL patients with similar symptoms but different diagnoses between January 1st, 2017, and September 30th, 2022. Demographic data and laboratory test results were collected. Subsequently, significant features were identified by both logistic regression and independent expert clinical ability. Eventually, logistic regression and four machine learning (ML) algorithms were employed to construct a diagnostic model, utilizing fivefold cross-validation and blind set testing to identify the optimal model. The study successfully identified nine independent predictors of AL amyloidosis patients with kidney or cardiac involvement, respectively. Two models were developed to identify key features that distinguish AL amyloidosis from nephrotic syndrome and hypertrophic cardiomyopathy, respectively. The light gradient boosting machine (LightGBM) model emerged as the most effective, demonstrating superior performance with the area under curve (AUC) of 0.90 in both models, alongside high sensitivity, specificity, and F1-score. This research highlights the potential of using a machine learning-based LightGBM model to facilitate early and accurate diagnosis of AL amyloidosis. The model's effectiveness suggests it could be a valuable tool in clinical settings, aiding in the timely identification of AL amyloidosis among patients with non-specific symptoms. Further validation in diverse populations is recommended to establish its universal applicability.

Machine learning-based prediction of pulmonary embolism to reduce unnecessary computed tomography scans in gastrointestinal cancer patients: a retrospective multicenter study

This study aimed to develop a machine learning (ML) model for predicting pulmonary embolism (PE) in patients with gastrointestinal cancers, a group at increased risk for PE. We conducted a retrospective, multicenter study analyzing patients who underwent computed tomographic pulmonary angiography (CTPA) between 2010 and 2020. The study utilized demographic and clinical data, including the Wells score and D-dimer levels, to train a random forest ML model. The model's effectiveness was assessed using the area under the receiver operating curve (AUROC). In total, 446 patients from hospital A and 139 from hospital B were included. The training set consisted of 356 patients from hospital A, with internal validation on 90 and external validation on 139 patients from hospital B. The model achieved an AUROC of 0.736 in hospital A and 0.669 in hospital B. The ML model significantly reduced the number of patients recommended for CTPA compared to the conventional diagnostic strategy (hospital A; 100.0% vs. 91.1%, P < 0.001, hospital B; 100.0% vs. 93.5%, P = 0.003). The results indicate that an ML-based prediction model can reduce unnecessary CTPA procedures in gastrointestinal cancer patients, highlighting its potential to enhance diagnostic efficiency and reduce patient burden.

Machine Learning Diagnostic Model for Early Stage NSTEMI: Using hs-cTnI 1/2h Changes and Multiple Cardiovascular Biomarkers

BACKGROUND

This study demonstrates differences in the distribution of multiple cardiovascular biomarkers between non-ST-segment elevation myocardial infarction (NSTEMI) and unstable angina (UA) patients. Diagnostic machine learning predictive models measured at the time of admission and 1/2 h post-admission, achieving competitive diagnostic predictive results.

OBJECTIVE

This study aims to explore the diagnostic value of changes in high-sensitivity cardiac troponin I (hs-cTnI) levels in patients with suspected NSTEMI.

METHODS

A total of 267 patients presented with chest pain, requiring confirmation of acute coronary syndrome (ACS) subtypes (NSTEMI vs. UA). Hs-cTnI and other cardiac markers, such as creatine kinase-MB (CK-MB) and Myoglobin (Myo), were analyzed. Machine learning techniques were employed to assess the application of hs-cTnI level changes in the clinical diagnosis of NSTEMI.

RESULTS

Levels of CK-MB, Myo, hs-cTnI measured at admission, hs-cTnI measured 1-2 h after admission, and NT-proBNP in NSTEMI patients were significantly higher than those in UA patients (p < 0.001). There was a positive correlation between hs-cTnI and CK-MB, as well as Myo (R = 0.72, R = 0.51, R = 0.60). The optimal diagnostic model, Hybiome_1/2h, demonstrated an F1-Score of 0.74, an AUROC of 0.96, and an AP of 0.89.

CONCLUSIONS

This study confirms the significant value of hs-cTnI as a sensitive marker of myocardial injury in the diagnosis of NSTEMI. Continuous monitoring of hs-cTnI levels enhances the accuracy of distinguishing NSTEMI from UA. The models indicate that the Hybiome hs-cTnI assays perform comparably well to the Beckman assays in predicting NSTEMI. Moreover, incorporating hs-cTnI measurements taken 1-2 h post-admission significantly enhances the model's effectiveness.

18F-Fluoro-2-Deoxyglucose Positron Emission Tomography/Computed Tomography Measures of Spatial Heterogeneity for Predicting Platinum Resistance of High-Grade Serous Ovarian Cancer

BACKGROUND

The purpose of this study is to construct models for predicting platinum resistance in high-grade serous ovarian cancer (HGSOC) derived from quantitative spatial heterogeneity indicators obtained from 18F-FDG PET/CT images.

METHODS

A retrospective study was conducted on patients diagnosed with HGSOC. Quantitative indicators of spatial heterogeneity were generated using conventional features and Haralick texture features from both CT and PET images. Three groups of predictive models (conventional, heterogeneity, and integrated) were built. Each group's optimal model was the one with the highest area under curve (AUC). Postoperative immunohistochemical staining for Ki-67 and p53 was conducted. The correlation between the heterogeneity indicators and scores for Ki-67 and p53 was assessed by Spearman's correlation coefficient (ρ).

RESULTS

A total of 286 patients (54.6 ± 9.3 years) were enrolled. And 107 spatial heterogeneity indicators were extracted. The optimal models for each group were obtained using the Gradient Boosting Machine (GBM) algorithm. There was an AUC of 0.790 (95% CI: 0.696, 0.885) in the conventional model for the validation set, and an AUC of 0.904 (95% CI: 0.842, 0.966) in the heterogeneity model for the validation set. The integrated model achieved the highest predictive performance, with an AUC value of 0.928 (95% CI: 0.872, 0.984) for the validation set. Spearman's correlation showed that HU_Kurtosis had the strongest correlation with p53 scores with ρ = 0.718, while cluster site entropy had the strongest correlation with Ki-67 scores with ρ = 0.753.

CONCLUSIONS

Adding quantitative spatial heterogeneity indicators derived from PET/CT images can improve the prediction of platinum resistance in patients with HGSOC. Spatial heterogeneity indicators were related to Ki-67 and p53 scores.

Diabetes prediction model based on GA-XGBoost and stacking ensemble algorithm

Diabetes, as an incurable lifelong chronic disease, has profound and far-reaching effects on patients. Given this, early intervention is particularly crucial, as it can not only significantly improve the prognosis of patients but also provide valuable reference information for clinical treatment. This study selected the BRFSS (Behavioral Risk Factor Surveillance System) dataset, which is publicly available on the Kaggle platform, as the research object, aiming to provide a scientific basis for the early diagnosis and treatment of diabetes through advanced machine learning techniques. Firstly, the dataset was balanced using various sampling methods; secondly, a Stacking model based on GA-XGBoost (XGBoost model optimized by genetic algorithm) was constructed for the risk prediction of diabetes; finally, the interpretability of the model was deeply analyzed using Shapley values. The results show: (1) Random oversampling, ADASYN, SMOTE, and SMOTEENN were used for data balance processing, among which SMOTEENN showed better efficiency and effect in dealing with data imbalance. (2) The GA-XGBoost model optimized the hyperparameters of the XGBoost model through a genetic algorithm to improve the model's predictive accuracy. Combined with the better-performing LightGBM model and random forest model, a two-layer Stacking model was constructed. This model not only outperforms single machine learning models in predictive effect but also provides a new idea and method in the field of model integration. (3) Shapley value analysis identified features that have a significant impact on the prediction of diabetes, such as age and body mass index. This analysis not only enhances the transparency of the model but also provides more precise treatment decision support for doctors and patients. In summary, this study has not only improved the accuracy of predicting the risk of diabetes by adopting advanced machine learning techniques and model integration strategies but also provided a powerful tool for the early diagnosis and personalized treatment of diabetes.

Personalized Prediction of Long-Term Renal Function Prognosis Following Nephrectomy Using Interpretable Machine Learning Algorithms: Case-Control Study

BACKGROUND

Acute kidney injury (AKI) is a common adverse outcome following nephrectomy. The progression from AKI to acute kidney disease (AKD) and subsequently to chronic kidney disease (CKD) remains a concern; yet, the predictive mechanisms for these transitions are not fully understood. Interpretable machine learning (ML) models offer insights into how clinical features influence long-term renal function outcomes after nephrectomy, providing a more precise framework for identifying patients at risk and supporting improved clinical decision-making processes.

OBJECTIVE

This study aimed to (1) evaluate postnephrectomy rates of AKI, AKD, and CKD, analyzing long-term renal outcomes along different trajectories; (2) interpret AKD and CKD models using Shapley Additive Explanations values and Local Interpretable Model-Agnostic Explanations algorithm; and (3) develop a web-based tool for estimating AKD or CKD risk after nephrectomy.

METHODS

We conducted a retrospective cohort study involving patients who underwent nephrectomy between July 2012 and June 2019. Patient data were randomly split into training, validation, and test sets, maintaining a ratio of 76.5:8.5:15. Eight ML algorithms were used to construct predictive models for postoperative AKD and CKD. The performance of the best-performing models was assessed using various metrics. We used various Shapley Additive Explanations plots and Local Interpretable Model-Agnostic Explanations bar plots to interpret the model and generated directed acyclic graphs to explore the potential causal relationships between features. Additionally, we developed a web-based prediction tool using the top 10 features for AKD prediction and the top 5 features for CKD prediction.

RESULTS

The study cohort comprised 1559 patients. Incidence rates for AKI, AKD, and CKD were 21.7% (n=330), 15.3% (n=238), and 10.6% (n=165), respectively. Among the evaluated ML models, the Light Gradient-Boosting Machine (LightGBM) model demonstrated superior performance, with an area under the receiver operating characteristic curve of 0.97 for AKD prediction and 0.96 for CKD prediction. Performance metrics and plots highlighted the model's competence in discrimination, calibration, and clinical applicability. Operative duration, hemoglobin, blood loss, urine protein, and hematocrit were identified as the top 5 features associated with predicted AKD. Baseline estimated glomerular filtration rate, pathology, trajectories of renal function, age, and total bilirubin were the top 5 features associated with predicted CKD. Additionally, we developed a web application using the LightGBM model to estimate AKD and CKD risks.

CONCLUSIONS

An interpretable ML model effectively elucidated its decision-making process in identifying patients at risk of AKD and CKD following nephrectomy by enumerating critical features. The web-based calculator, found on the LightGBM model, can assist in formulating more personalized and evidence-based clinical strategies.

Artificial intelligence-driven transformations in diabetes care: a comprehensive literature review

Artificial intelligence (AI) has been applied in healthcare for diagnosis, treatments, disease management, and for studying underlying mechanisms and disease complications in diseases like diabetes and metabolic disorders. This review is a comprehensive overview of various applications of AI in the healthcare system for managing diabetes. A literature search was conducted on PubMed to locate studies integrating AI in the diagnosis, treatment, management and prevention of diabetes. As diabetes is now considered a pandemic now so employing AI and machine learning approaches can be applied to limit diabetes in areas with higher prevalence. Machine learning algorithms can visualize big datasets, and make predictions. AI-powered mobile apps and the closed-loop system automated glucose monitoring and insulin delivery can lower the burden on insulin. AI can help identify disease markers and potential risk factors as well. While promising, AI's integration in the medical field is still challenging due to privacy, data security, bias, and transparency. Overall, AI's potential can be harnessed for better patient outcomes through personalized treatment.

A Real-World Study on the Short-Term Efficacy of Amlodipine in Treating Hypertension Among Inpatients

Purpose

Hospitalized hypertensive patients rely on blood pressure medication, yet there is limited research on the sole use of amlodipine, despite its proven efficacy in protecting target organs and reducing mortality. This study aims to identify key indicators influencing the efficacy of amlodipine, thereby enhancing treatment outcomes.

Patients and Methods

In this multicenter retrospective study, 870 hospitalized patients with primary hypertension exclusively received amlodipine for the first 5 days after admission, and their medical records contained comprehensive blood pressure records. They were categorized into success (n=479) and failure (n=391) groups based on average blood pressure control efficacy. Predictive models were constructed using six machine learning algorithms. Evaluation metrics encompassed the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). SHapley Additive exPlanations (SHAP) analysis assessed feature contributions to efficacy.

Results

All six machine learning models demonstrated superior predictive performance. Following variable reduction, the model predicting amlodipine efficacy was reconstructed using these algorithms, with the light gradient boosting machine (LightGBM) model achieving the highest overall performance (AUC = 0.803). Notably, amlodipine showed enhanced efficacy in patients with low platelet distribution width (PDW) values, as well as high hematocrit (HCT) and thrombin time (TT) values.

Conclusion

This study utilized machine learning to predict amlodipine's effectiveness in hypertension treatment, pinpointing key factors: HCT, PDW, and TT levels. Lower PDW, along with higher HCT and TT, correlated with enhanced treatment outcomes. This facilitates personalized treatment, particularly for hospitalized hypertensive patients undergoing amlodipine monotherapy.

Identification of programmed cell death-related genes and diagnostic biomarkers in endometriosis using a machine learning and Mendelian randomization approach

Background

Endometriosis (EM) is a prevalent gynecological disorder frequently associated with irregular menstruation and infertility. Programmed cell death (PCD) is pivotal in the pathophysiological mechanisms underlying EM. Despite this, the precise pathogenesis of EM remains poorly understood, leading to diagnostic delays. Consequently, identifying biomarkers associated with PCD is critical for advancing the diagnosis and treatment of EM.

Methods

This study used datasets from the Gene Expression Omnibus (GEO) to identify differentially expressed genes (DEGs) following preprocessing. By cross-referencing these DEGs with genes associated with PCD, differentially expressed PCD-related genes (DPGs) were identified. Enrichment analyses for KEGG and GO pathways were conducted on these DPGs. Additionally, Mendelian randomization and machine learning techniques were applied to identify biomarkers strongly associated with EM.

Results

The study identified three pivotal biomarkers: TNFSF12, AP3M1, and PDK2, and established a diagnostic model for EM based on these genes. The results revealed a marked upregulation of TNFSF12 and PDK2 in EM samples, coupled with a significant downregulation of AP3M1. Single-cell analysis further underscored the potential of TNFSF12, AP3M1, and PDK2 as biomarkers for EM. Additionally, molecular docking studies demonstrated that these genes exhibit significant binding affinities with drugs currently utilized in clinical practice.

Conclusion

This study systematically elucidated the molecular characteristics of PCD in EM and identified TNFSF12, AP3M1, and PDK2 as key biomarkers. These findings provide new directions for the early diagnosis and personalized treatment of EM.

Enhancing Type 2 Diabetes Treatment Decisions With Interpretable Machine Learning Models for Predicting Hemoglobin A1c Changes: Machine Learning Model Development

BACKGROUND

Type 2 diabetes (T2D) is a significant global health challenge. Physicians need to assess whether future glycemic control will be poor on the current trajectory of usual care and usual-care treatment intensifications so that they can consider taking extra treatment measures to prevent poor outcomes. Predicting poor glycemic control from trends in hemoglobin A1c (HbA1c) levels is difficult due to the influence of seasonal fluctuations and other factors.

OBJECTIVE

We sought to develop a model that accurately predicts poor glycemic control among patients with T2D receiving usual care.

METHODS

Our machine learning model predicts poor glycemic control (HbA1c≥8%) using the transformer architecture, incorporating an attention mechanism to process irregularly spaced HbA1c time series and quantify temporal relationships of past HbA1c levels at each time point. We assessed the model using HbA1c levels from 7787 patients with T2D seeing specialist physicians at the University of Tokyo Hospital. The training data include instances of poor glycemic control occurring during usual care with usual-care treatment intensifications. We compared prediction accuracy, assessed with the area under the receiver operating characteristic curve, the area under the precision-recall curve, and the accuracy rate, to that of LightGBM.

RESULTS

The area under the receiver operating characteristic curve, the area under the precision-recall curve, and the accuracy rate (95% confidence limits) of the proposed model were 0.925 (95% CI 0.923-0.928), 0.864 (95% CI 0.852-0.875), and 0.864 (95% CI 0.86-0.869), respectively. The proposed model achieved high prediction accuracy comparable to or surpassing LightGBM's performance. The model prioritized the most recent HbA1c levels for predictions. Older HbA1c levels in patients with poor glycemic control were slightly more influential in predictions compared to patients with good glycemic control.

CONCLUSIONS

The proposed model accurately predicts poor glycemic control for patients with T2D receiving usual care, including patients receiving usual-care treatment intensifications, allowing physicians to identify cases warranting extraordinary treatment intensifications. If used by a nonspecialist, the model's indication of likely future poor glycemic control may warrant a referral to a specialist. Future efforts could incorporate diverse and large-scale clinical data for improved accuracy.

Personalized prediction of mortality in patients with acute ischemic stroke using explainable artificial intelligence

BACKGROUND

Research into the acute kidney disease (AKD) after acute ischemic stroke (AIS) is rare, and how clinical features influence its prognosis remain unknown. We aim to employ interpretable machine learning (ML) models to study AIS and clarify its decision-making process in identifying the risk of mortality.

METHODS

We conducted a retrospective cohort study involving AIS patients from January 2020 to June 2021. Patient data were randomly divided into training and test sets. Eight ML algorithms were employed to construct predictive models for mortality. The performance of the best model was evaluated using various metrics. Furthermore, we created an artificial intelligence (AI)-driven web application that leveraged the top ten most crucial features for mortality prediction.

RESULTS

The study cohort consisted of 1633 AIS patients, among whom 257 (15.74%) developed subacute AKD, 173 (10.59%) experienced AKI recovery, and 65 (3.98%) met criteria for both AKI and AKD. The mortality rate stood at 4.84%. The LightGBM model displayed superior performance, boasting an AUROC of 0.96 for mortality prediction. The top five features linked to mortality were ACEI/ARE, renal function trajectories, neutrophil count, diuretics, and serum creatinine. Moreover, we designed a web application using the LightGBM model to estimate mortality risk.

CONCLUSIONS

Complete renal function trajectories, including AKI and AKD, are vital for fitting mortality in AIS patients. An interpretable ML model effectively clarified its decision-making process for identifying AIS patients at risk of mortality. The AI-driven web application has the potential to contribute to the development of personalized early mortality prevention.

Mining Bovine Milk Proteins for DPP-4 Inhibitory Peptides Using Machine Learning and Virtual Proteolysis

Dipeptidyl peptidase-IV (DPP-4) enzyme inhibitors are a promising category of diabetes medications. Bioactive peptides, particularly those derived from bovine milk proteins, play crucial roles in inhibiting the DPP-4 enzyme. This study describes a comprehensive strategy for DPP-4 inhibitory peptide discovery and validation that combines machine learning and virtual proteolysis techniques. Five machine learning models, including GBDT, XGBoost, LightGBM, CatBoost, and RF, were trained. Notably, LightGBM demonstrated superior performance with an AUC value of 0.92 ± 0.01. Subsequently, LightGBM was employed to forecast the DPP-4 inhibitory potential of peptides generated through virtual proteolysis of milk proteins. Through a series of in silico screening process and in vitro experiments, GPVRGPF and HPHPHL were found to exhibit good DPP-4 inhibitory activity. Molecular docking and molecular dynamics simulations further confirmed the inhibitory mechanisms of these peptides. Through retracing the virtual proteolysis steps, it was found that GPVRGPF can be obtained from β-casein through enzymatic hydrolysis by chymotrypsin, while HPHPHL can be obtained from κ-casein through enzymatic hydrolysis by stem bromelain or papain. In summary, the integration of machine learning and virtual proteolysis techniques can aid in the preliminary determination of key hydrolysis parameters and facilitate the efficient screening of bioactive peptides.

Machine learning-based analysis for prediction of surgical necrotizing enterocolitis in very low birth weight infants using perinatal factors: a nationwide cohort study

Early prediction of surgical necrotizing enterocolitis (sNEC) in preterm infants is important. However, owing to the complexity of the disease, identifying infants with NEC at a high risk for surgical intervention is difficult. We developed a machine learning (ML) algorithm to predict sNEC using perinatal factors obtained from the national cohort registry of very low birth weight (VLBW) infants. Data were collected from the medical records of 16,385 VLBW infants registered in the Korean Neonatal Network (KNN). Infants who underwent surgical intervention were identified with sNEC, and infants who received medical treatment, with medical NEC (mNEC). We used 38 variables, including maternal, prenatal, and postnatal factors that were obtained within 1 week of birth, for training. A total of 1085 patients had NEC (654 with sNEC and 431 with mNEC). VLBW infants showed a higher incidence of sNEC at a lower gestational age (GA) (p < 0.001). Our proposed ensemble model showed an area under the receiver operating characteristic curve of 0.721 for sNEC prediction.    Conclusion: Proposed ensemble model may help predict which infants with NEC are likely to develop sNEC. Through early prediction and prompt intervention, prognosis of sNEC may be improved. What is Known: • Machine learning (ML)-based techniques have been employed in NEC research for prediction, diagnosis, and prognosis, with promising outcomes. • While most studies have utilized abdominal radiographs and clinical manifestations of NEC as data sources, and have demonstrated their usefulness, they may prove weak in terms of early prediction. What is New: • We analyzed the perinatal factors of VLBW infants acquired within 7 days of birth and used ML-based analysis to identify which infants with NEC are vulnerable to clinical deterioration and at high risk for surgical intervention using nationwide cohort data.

Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines

This paper presents the results of a study on data preprocessing and modeling for predicting corrosion in water pipelines of a steel industrial plant. The use case is a cooling circuit consisting of both direct and indirect cooling. In the direct cooling circuit, water comes into direct contact with the product, whereas in the indirect one, it does not. In this study, advanced machine learning techniques, such as extreme gradient boosting and deep neural networks, have been employed for two distinct applications. Firstly, a virtual sensor was created to estimate the corrosion rate based on influencing process variables, such as pH and temperature. Secondly, a predictive tool was designed to foresee the future evolution of the corrosion rate, considering past values of both influencing variables and the corrosion rate. The results show that the most suitable algorithm for the virtual sensor approach is the dense neural network, with MAPE values of (25 ± 4)% and (11 ± 4)% for the direct and indirect circuits, respectively. In contrast, different results are obtained for the two circuits when following the predictive tool approach. For the primary circuit, the convolutional neural network yields the best results, with MAPE = 4% on the testing set, whereas for the secondary circuit, the LSTM recurrent network shows the highest prediction accuracy, with MAPE = 9%. In general, models employing temporal windows have emerged as more suitable for corrosion prediction, with model performance significantly improving with a larger dataset.

Machine learning model based on radiomics features for AO/OTA classification of pelvic fractures on pelvic radiographs

Depending on the degree of fracture, pelvic fracture can be accompanied by vascular damage, and in severe cases, it may progress to hemorrhagic shock. Pelvic radiography can quickly diagnose pelvic fractures, and the Association for Osteosynthesis Foundation and Orthopedic Trauma Association (AO/OTA) classification system is useful for evaluating pelvic fracture instability. This study aimed to develop a radiomics-based machine-learning algorithm to quickly diagnose fractures on pelvic X-ray and classify their instability. data used were pelvic anteroposterior radiographs of 990 adults over 18 years of age diagnosed with pelvic fractures, and 200 normal subjects. A total of 93 features were extracted based on radiomics:18 first-order, 24 GLCM, 16 GLRLM, 16 GLSZM, 5 NGTDM, and 14 GLDM features. To improve the performance of machine learning, the feature selection methods RFE, SFS, LASSO, and Ridge were used, and the machine learning models used LR, SVM, RF, XGB, MLP, KNN, and LGBM. Performance measurement was evaluated by area under the curve (AUC) by analyzing the receiver operating characteristic curve. The machine learning model was trained based on the selected features using four feature-selection methods. When the RFE feature selection method was used, the average AUC was higher than that of the other methods. Among them, the combination with the machine learning model SVM showed the best performance, with an average AUC of 0.75±0.06. By obtaining a feature-importance graph for the combination of RFE and SVM, it is possible to identify features with high importance. The AO/OTA classification of normal pelvic rings and pelvic fractures on pelvic AP radiographs using a radiomics-based machine learning model showed the highest AUC when using the SVM classification combination. Further research on the radiomic features of each part of the pelvic bone constituting the pelvic ring is needed.

Heavy Metal Concentration Estimation for Different Farmland Soils Based on Projection Pursuit and LightGBM with Hyperspectral Images

Heavy metal pollution in farmland soil threatens soil environmental quality. It is an important task to quickly grasp the status of heavy metal pollution in farmland soil in a region. Hyperspectral remote sensing technology has been widely used in soil heavy metal concentration monitoring. How to improve the accuracy and reliability of its estimation model is a hot topic. This study analyzed 440 soil samples from Sihe Town and the surrounding agricultural areas in Yushu City, Jilin Province. Considering the differences between different types of soils, a local regression model of heavy metal concentrations (As and Cu) was established based on projection pursuit (PP) and light gradient boosting machine (LightGBM) algorithms. Based on the estimations, a spatial distribution map of soil heavy metals in the region was drawn. The findings of this study showed that considering the differences between different soils to construct a local regression estimation model of soil heavy metal concentration improved the estimation accuracy. Specifically, the relative percent difference (RPD) of As and Cu element estimations in black soil increased the most, by 0.30 and 0.26, respectively. The regional spatial distribution map of heavy metal concentration derived from local regression showed high spatial variability. The number of characteristic bands screened by the PP method accounted for 10-13% of the total spectral bands, effectively reducing the model complexity. Compared with the traditional machine model, the LightGBM model showed better estimation ability, and the highest determination coefficients (R2) of different soil validation sets reached 0.73 (As) and 0.75 (Cu), respectively. In this study, the constructed PP-LightGBM estimation model takes into account the differences in soil types, which effectively improves the accuracy and reliability of hyperspectral image estimation of soil heavy metal concentration and provides a reference for drawing large-scale spatial distributions of heavy metals from hyperspectral images and mastering soil environmental quality.

Prediction and analysis of risk factors for diabetic retinopathy based on machine learning and interpretable models

Objective

Diabetic retinopathy is one of the major complications of diabetes. In this study, a diabetic retinopathy risk prediction model integrating machine learning models and SHAP was established to increase the accuracy of risk prediction for diabetic retinopathy, explain the rationality of the findings from model prediction and improve the reliability of prediction results.

Methods

Data were preprocessed for missing values and outliers, features selected through information gain, a diabetic retinopathy risk prediction model established using the CatBoost and the outputs of the mode interpreted using the SHAP model.

Results

One thousand early warning data of diabetes complications derived from diabetes complication early warning dataset from the National Clinical Medical Sciences Data Center were used in this study. The CatBoost-based model for diabetic retinopathy prediction performed the best in the comparative model test. ALB_CR, HbA1c, UPR_24, NEPHROPATHY and SCR were positively correlated with diabetic retinopathy, while CP, HB, ALB, DBILI and CRP were negatively correlated with diabetic retinopathy. The relationships between HEIGHT, WEIGHT and ESR characteristics and diabetic retinopathy were not significant.

Conclusion

The risk factors for diabetic retinopathy include poor renal function, elevated blood glucose level, liver disease, hematonosis and dysarteriotony, among others. Diabetic retinopathy can be prevented by monitoring and effectively controlling relevant indices. In this study, the influence relationships between the features were also analyzed to further explore the potential factors of diabetic retinopathy, which can provide new methods and new ideas for the early prevention and clinical diagnosis of subsequent diabetic retinopathy.

Predictive model and risk analysis for coronary heart disease in people living with HIV using machine learning

OBJECTIVE

This study aimed to construct a coronary heart disease (CHD) risk-prediction model in people living with human immunodeficiency virus (PLHIV) with the help of machine learning (ML) per electronic medical records (EMRs).

METHODS

Sixty-one medical characteristics (including demography information, laboratory measurements, and complicating disease) readily available from EMRs were retained for clinical analysis. These characteristics further aided the development of prediction models by using seven ML algorithms [light gradient-boosting machine (LightGBM), support vector machine (SVM), eXtreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), decision tree, multilayer perceptron (MLP), and logistic regression]. The performance of this model was assessed using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was further applied to interpret the findings of the best-performing model.

RESULTS

The LightGBM model exhibited the highest AUC (0.849; 95% CI, 0.814-0.883). Additionally, the SHAP plot per the LightGBM depicted that age, heart failure, hypertension, glucose, serum creatinine, indirect bilirubin, serum uric acid, and amylase can help identify PLHIV who were at a high or low risk of developing CHD.

CONCLUSION

This study developed a CHD risk prediction model for PLHIV utilizing ML techniques and EMR data. The LightGBM model exhibited improved comprehensive performance and thus had higher reliability in assessing the risk predictors of CHD. Hence, it can potentially facilitate the development of clinical management techniques for PLHIV care in the era of EMRs.

Employing supervised machine learning algorithms for classification and prediction of anemia among youth girls in Ethiopia

In developing countries, one-quarter of young women have suffered from anemia. However, the available studies in Ethiopia have been usually used the traditional stastical methods. Therefore, this study aimed to employ multiple machine learning algorithms to identify the most effective model for the prediction of anemia among youth girls in Ethiopia. A total of 5642 weighted samples of young girls from the 2016 Ethiopian Demographic and Health Survey dataset were utilized. The data underwent preprocessing, with 80% of the observations used for training the model and 20% for testing. Eight machine learning algorithms were employed to build and compare models. The model performance was assessed using evaluation metrics in Python software. Various data balancing techniques were applied, and the Boruta algorithm was used to select the most relevant features. Besides, association rule mining was conducted using the Apriori algorithm in R software. The random forest classifier with an AUC value of 82% outperformed in predicting anemia among all the tested classifiers. Region, poor wealth index, no formal education, unimproved toilet facility, rural residence, not used contraceptive method, religion, age, no media exposure, occupation, and having more than 5 family size were the top attributes to predict anemia. Association rule mining was identified the top seven best rules that most frequently associated with anemia. The random forest classifier is the best for predicting anemia. Therefore, making it potentially valuable as decision-support tools for the relevant stakeholders and giving emphasis for the identified predictors could be an important intervention to halt anemia among youth girls.

Combining artificial neural networks and a marginal structural model to predict the progression from depression to Alzheimer's disease

Introduction

Decades of research in population health have established depression as a likely precursor to Alzheimer's disease. A combination of causal estimates and machine learning methods in artificial intelligence could identify internal and external mediating mechanisms that contribute to the likelihood of progression from depression to Alzheimer's disease.

Methods

We developed an integrated predictive model, combining the marginal structural model and an artificial intelligence predictive model, distinguishing between patients likely to progress from depressive states to Alzheimer's disease better than each model alone.

Results

The integrated predictive model achieved substantial clinical relevance when using the area under the curve measure. It performed better than the traditional statistical method or a single artificial intelligence method alone.

Discussion

The integrated predictive model could form a part of a clinical screening tool that identifies patients who are likely to progress from depression to Alzheimer's disease for early behavioral health interventions. Given the high costs of treating Alzheimer's disease, our model could serve as a cost-effective intervention for the early detection of depression before it progresses to Alzheimer's disease.

Heart failure survival prediction using novel transfer learning based probabilistic features

Heart failure is a complex cardiovascular condition characterized by the heart's inability to pump blood effectively, leading to a cascade of physiological changes. Predicting survival in heart failure patients is crucial for optimizing patient care and resource allocation. This research aims to develop a robust survival prediction model for heart failure patients using advanced machine learning techniques. We analyzed data from 299 hospitalized heart failure patients, addressing the issue of imbalanced data with the Synthetic Minority Oversampling (SMOTE) method. Additionally, we proposed a novel transfer learning-based feature engineering approach that generates a new probabilistic feature set from patient data using ensemble trees. Nine fine-tuned machine learning models are built and compared to evaluate performance in patient survival prediction. Our novel transfer learning mechanism applied to the random forest model outperformed other models and state-of-the-art studies, achieving a remarkable accuracy of 0.975. All models underwent evaluation using 10-fold cross-validation and tuning through hyperparameter optimization. The findings of this study have the potential to advance the field of cardiovascular medicine by providing more accurate and personalized prognostic assessments for individuals with heart failure.

MIBPred: Ensemble Learning-Based Metal Ion-Binding Protein Classifier

In biological organisms, metal ion-binding proteins participate in numerous metabolic activities and are closely associated with various diseases. To accurately predict whether a protein binds to metal ions and the type of metal ion-binding protein, this study proposed a classifier named MIBPred. The classifier incorporated advanced Word2Vec technology from the field of natural language processing to extract semantic features of the protein sequence language and combined them with position-specific score matrix (PSSM) features. Furthermore, an ensemble learning model was employed for the metal ion-binding protein classification task. In the model, we independently trained XGBoost, LightGBM, and CatBoost algorithms and integrated the output results through an SVM voting mechanism. This innovative combination has led to a significant breakthrough in the predictive performance of our model. As a result, we achieved accuracies of 95.13% and 85.19%, respectively, in predicting metal ion-binding proteins and their types. Our research not only confirms the effectiveness of Word2Vec technology in extracting semantic information from protein sequences but also highlights the outstanding performance of the MIBPred classifier in the problem of metal ion-binding protein types. This study provides a reliable tool and method for the in-depth exploration of the structure and function of metal ion-binding proteins.

Assessment of Sepsis Risk at Admission to the Emergency Department: Clinical Interpretable Prediction Model

This study aims to develop an interpretable prediction model based on explainable artificial intelligence to predict bacterial sepsis and discover important biomarkers. A total of 1572 adult patients, 560 of whom were sepsis positive and 1012 of whom were negative, who were admitted to the emergency department with suspicion of sepsis, were examined. We investigated the performance characteristics of sepsis biomarkers alone and in combination for confirmed sepsis diagnosis using Sepsis-3 criteria. Three different tree-based algorithms-Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost)-were used for sepsis prediction, and after examining comprehensive performance metrics, descriptions of the optimal model were obtained with the SHAP method. The XGBoost model achieved accuracy of 0.898 (0.868-0.929) and area under the ROC curve (AUC) of 0.940 (0.898-0.980) with a 95% confidence interval. The five biomarkers for predicting sepsis were age, respiratory rate, oxygen saturation, procalcitonin, and positive blood culture. SHAP results revealed that older age, higher respiratory rate, procalcitonin, neutrophil-lymphocyte count ratio, C-reactive protein, plaque, leukocyte particle concentration, as well as lower oxygen saturation, systolic blood pressure, and hemoglobin levels increased the risk of sepsis. As a result, the Explainable Artificial Intelligence (XAI)-based prediction model can guide clinicians in the early diagnosis and treatment of sepsis, providing more effective sepsis management and potentially reducing mortality rates and medical costs.

Dual view deep learning for enhanced breast cancer screening using mammography

Breast cancer has the highest incidence rate among women in Ethiopia compared to other types of cancer. Unfortunately, many cases are detected at a stage where a cure is delayed or not possible. To address this issue, mammography-based screening is widely accepted as an effective technique for early detection. However, the interpretation of mammography images requires experienced radiologists in breast imaging, a resource that is limited in Ethiopia. In this research, we have developed a model to assist radiologists in mass screening for breast abnormalities and prioritizing patients. Our approach combines an ensemble of EfficientNet-based classifiers with YOLOv5, a suspicious mass detection method, to identify abnormalities. The inclusion of YOLOv5 detection is crucial in providing explanations for classifier predictions and improving sensitivity, particularly when the classifier fails to detect abnormalities. To further enhance the screening process, we have also incorporated an abnormality detection model. The classifier model achieves an F1-score of 0.87 and a sensitivity of 0.82. With the addition of suspicious mass detection, sensitivity increases to 0.89, albeit at the expense of a slightly lower F1-score of 0.79.

Automated Preoperative and Postoperative Volume Estimates Risk of Retreatment in Chronic Subdural Hematoma: A Retrospective, Multicenter Study

BACKGROUND AND OBJECTIVES

Several neurosurgical pathologies, ranging from glioblastoma to hemorrhagic stroke, use volume thresholds to guide treatment decisions. For chronic subdural hematoma (cSDH), with a risk of retreatment of 10%-30%, the relationship between preoperative and postoperative cSDH volume and retreatment is not well understood. We investigated the potential link between preoperative and postoperative cSDH volumes and retreatment.

METHODS

We performed a retrospective chart review of patients operated for unilateral cSDH from 4 level 1 trauma centers, February 2009-August 2021. We used a 3-dimensional deep learning, automated segmentation pipeline to calculate preoperative and postoperative cSDH volumes. To identify volume thresholds, we constructed a receiver operating curve with preoperative and postoperative volumes to predict cSDH retreatment rates and selected the threshold with the highest Youden index. Then, we developed a light gradient boosting machine to predict the risk of cSDH recurrence.

RESULTS

We identified 538 patients with unilateral cSDH, of whom 62 (12%) underwent surgical retreatment within 6 months of the index surgery. cSDH retreatment was associated with higher preoperative (122 vs 103 mL; P < .001) and postoperative (62 vs 35 mL; P < .001) volumes. Patients with >140 mL preoperative volume had nearly triple the risk of cSDH recurrence compared with those below 140 mL, while a postoperative volume >46 mL led to an increased risk for retreatment (22% vs 6%; P < .001). On multivariate modeling, our model had an area under the receiver operating curve of 0.76 (95% CI: 0.60-0.93) for predicting retreatment. The most important features were preoperative and postoperative volume, platelet count, and age.

CONCLUSION

Larger preoperative and postoperative cSDH volumes increase the risk of retreatment. Volume thresholds may allow identification of patients at high risk of cSDH retreatment who would benefit from adjunct treatments. Machine learning algorithm can quickly provide accurate estimates of preoperative and postoperative volumes.

Assessing the Influence of Sensor-Induced Noise on Machine-Learning-Based Changeover Detection in CNC Machines

The noise in sensor data has a substantial impact on the reliability and accuracy of (ML) algorithms. A comprehensive framework is proposed to analyze the effects of diverse noise inputs in sensor data on the accuracy of ML models. Through extensive experimentation and evaluation, this research examines the resilience of a LightGBM ML model to ten different noise models, namely, Flicker, Impulse, Gaussian, Brown, Periodic, and others. A thorough analytical approach with various statistical metrics in a Monte Carlo simulation setting was followed. It was found that the Gaussian and Colored noise were detrimental when compared to Flicker and Brown, which are identified as safe noise categories. It was interesting to find a safe threshold limit of noise intensity for the case of Gaussian noise, which was missing in other noise types. This research work employed the use case of changeover detection in (CNC) manufacturing machines and the corresponding data from the publicly funded research project (OBerA).

Enhancing blood flow prediction in multi-exposure laser speckle contrast imaging through ensemble learning with K-mean clustering

Purpose.Accurately visualizing and measuring blood flow is of utmost importance in maintaining optimal health and preventing the onset of various chronic diseases. One promising imaging technique that aids in visualizing perfusion in biological tissues is Multi-exposure Laser Speckle Contrast Imaging (MELSCI). MELSCI technique allows real-time quantitative measurements using multiple exposure times to obtain precise and reliable blood flow data. Additionally, the application of machine learning (ML) techniques can further enhance the accuracy of blood flow prediction in this imaging modality.Method.Our study focused on developing and evaluating Ensemble Learning ML techniques along with clustering algorithms for predicting blood flow rates in MELSCI. The effectiveness of these techniques was assessed using performance parameters, including accuracy, F1-score, precision, recall, specificity, and classification error rate.Result.Notably, the study revealed that Ensemble Learning with clustering emerged as the most accurate technique, achieving an impressive accuracy rate of 98.5%. Furthermore, it demonstrated a high recall of more than 91%, F1-score, the precision of more than 90%, higher specificity of 99%, and least classification error of 1.5%, highlighting its suitability and sustainability for flow prediction in MELSCI.Conclusion.The study's findings imply that Ensemble Learning can significantly contribute to enhancing the accuracy of blood flow prediction in MELSCI. This advancement holds substantial promise for healthcare professionals and researchers, as it facilitates improved understanding and assessment of perfusion within biological tissues, which will contribute to the maintenance of good health and prevention of chronic diseases.

Predicting Pathological Response to Preoperative Chemotherapy in Pancreatic Ductal Adenocarcinoma Using Post-Chemotherapy Computed Tomography Radiomics

INTRODUCTION

Assessing the response to preoperative treatment in pancreatic cancer provides valuable information for guiding subsequent treatment strategies. The present study aims to develop and validate a computed tomography (CT) radiomics-based machine learning (ML) model for predicting pathological response (PR) to preoperative chemotherapy in pancreatic ductal adenocarcinoma (PDAC).

METHODS

Retrospective data were analyzed from 86 PDAC patients undergoing neoadjuvant or conversion chemotherapy followed by surgical resection from January 2018 to May 2023. The cohort was randomly divided into training (70%, n = 60) and testing (30%, n = 26) sets. Favorable PR was defined as Evans grade IIb or greater. Radiomic features were extracted from post-chemotherapy CT images, and dimensionality reduction was performed using the least absolute shrinkage and selection operator (LASSO) logistic regression. Four ML classifiers (Light Gradient Boosting Machine (LGBM), Random Forest, AdaBoost, and Quadratic Discriminant Analysis) were evaluated for predicting a favorable PR. Model performance was primarily assessed using the area under the receiver operating characteristic curve (AUC), Brier score, and decision curve analysis.

RESULTS

Forty-one (47.7%) patients had a favorable PR. LASSO analysis on the training set identified five radiomic features. The LGBM model demonstrated the best performance, with a training AUC of 0.902 and a testing AUC of 0.923. It also exhibited the lowest Brier scores, both in training (0.136) and testing (0.135). Decision curve analysis further confirmed its clinical potential.

CONCLUSION

The CT radiomics-based ML model exhibited promising performance in predicting PR in PDAC after neoadjuvant/conversion chemotherapy. This suggests clinical utility in optimizing surgical candidates and timing of surgery, leading to personalized treatment strategies.

Machine Learning for Predicting Postoperative Atrial Fibrillation After Cardiac Surgery: A Scoping Review of Current Literature

Postoperative atrial fibrillation (POAF) occurs in up to 20% to 55% of patients who underwent cardiac surgery. Machine learning (ML) has been increasingly employed in monitoring, screening, and identifying different cardiovascular clinical conditions. It was proposed that ML may be a useful tool for predicting POAF after cardiac surgery. An electronic database search was conducted on Medline, EMBASE, Cochrane, Google Scholar, and ClinicalTrials.gov to identify primary studies that investigated the role of ML in predicting POAF after cardiac surgery. A total of 5,955 citations were subjected to title and abstract screening, and ultimately 5 studies were included. The reported incidence of POAF ranged from 21.5% to 37.1%. The studied ML models included: deep learning, decision trees, logistic regression, support vector machines, gradient boosting decision tree, gradient-boosted machine, K-nearest neighbors, neural network, and random forest models. The sensitivity of the reported ML models ranged from 0.22 to 0.91, the specificity from 0.64 to 0.84, and the area under the receiver operating characteristic curve from 0.67 to 0.94. Age, gender, left atrial diameter, glomerular filtration rate, and duration of mechanical ventilation were significant clinical risk factors for POAF. Limited evidence suggest that machine learning models may play a role in predicting atrial fibrillation after cardiac surgery because of their ability to detect different patterns of correlations and the incorporation of several demographic and clinical variables. However, the heterogeneity of the included studies and the lack of external validation are the most important limitations against the routine incorporation of these models in routine practice. Artificial intelligence, cardiac surgery, decision tree, deep learning, gradient-boosted machine, gradient boosting decision tree, k-nearest neighbors, logistic regression, machine learning, neural network, postoperative atrial fibrillation, postoperative complications, random forest, risk scores, scoping review, support vector machine.

A proposed tree-based explainable artificial intelligence approach for the prediction of angina pectoris

Cardiovascular diseases (CVDs) are a serious public health issue that affects and is responsible for numerous fatalities and impairments. Ischemic heart disease (IHD) is one of the most prevalent and deadliest types of CVDs and is responsible for 45% of all CVD-related fatalities. IHD occurs when the blood supply to the heart is reduced due to narrowed or blocked arteries, which causes angina pectoris (AP) chest pain. AP is a common symptom of IHD and can indicate a higher risk of heart attack or sudden cardiac death. Therefore, it is important to diagnose and treat AP promptly and effectively. To forecast AP in women, we constructed a novel artificial intelligence (AI) method employing the tree-based algorithm known as an Explainable Boosting Machine (EBM). EBM is a machine learning (ML) technique that combines the interpretability of linear models with the flexibility and accuracy of gradient boosting. We applied EBM to a dataset of 200 female patients, 100 with AP and 100 without AP, and extracted the most relevant features for AP prediction. We then evaluated the performance of EBM against other AI methods, such as Logistic Regression (LR), Categorical Boosting (CatBoost), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Light Gradient Boosting Machine (LightGBM). We found that EBM was the most accurate and well-balanced technique for forecasting AP, with accuracy (0.925) and Youden's index (0.960). We also looked at the global and local explanations provided by EBM to better understand how each feature affected the prediction and how each patient was classified. Our research showed that EBM is a useful AI method for predicting AP in women and identifying the risk factors related to it. This can help clinicians to provide personalized and evidence-based care for female patients with AP.

Evaluation of atopic dermatitis severity using artificial intelligence

Atopic dermatitis is a prevalent and persistent chronic inflammatory skin disorder that poses significant challenges when it comes to accurately assessing its severity. The aim of this study was to evaluate deep learning models for automated atopic dermatitis severity scoring using a dataset of Aceh ethnicity individuals in Indonesia. The dataset of clinical images was collected from 250 patients at Dr. Zainoel Abidin Hospital, Banda Aceh, Indonesia and labeled by dermatologists as mild, moderate, severe, or none. Five pretrained convolutional neural networks (CNN) architectures were evaluated: ResNet50, VGGNet19, MobileNetV3, MnasNet, and EfficientNetB0. The evaluation metrics, including accuracy, precision, sensitivity, specificity, and F1-score, were employed to assess the models. Among the models, ResNet50 emerged as the most proficient, demonstrating an accuracy of 89.8%, precision of 90.00%, sensitivity of 89.80%, specificity of 96.60%, and an F1-score of 89.85%. These results highlight the potential of incorporating advanced, data-driven models into the field of dermatology. These models can serve as invaluable tools to assist dermatologists in making early and precise assessments of atopic dermatitis severity and therefore improve patient care and outcomes.

Machine learning-based models for the prediction of breast cancer recurrence risk

Breast cancer is the most common malignancy diagnosed in women worldwide. The prevalence and incidence of breast cancer is increasing every year; therefore, early diagnosis along with suitable relapse detection is an important strategy for prognosis improvement. This study aimed to compare different machine algorithms to select the best model for predicting breast cancer recurrence. The prediction model was developed by using eleven different machine learning (ML) algorithms, including logistic regression (LR), random forest (RF), support vector classification (SVC), extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), decision tree, multilayer perceptron (MLP), linear discriminant analysis (LDA), adaptive boosting (AdaBoost), Gaussian naive Bayes (GaussianNB), and light gradient boosting machine (LightGBM), to predict breast cancer recurrence. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score were used to evaluate the performance of the prognostic model. Based on performance, the optimal ML was selected, and feature importance was ranked by Shapley Additive Explanation (SHAP) values. Compared to the other 10 algorithms, the results showed that the AdaBoost algorithm had the best prediction performance for successfully predicting breast cancer recurrence and was adopted in the establishment of the prediction model. Moreover, CA125, CEA, Fbg, and tumor diameter were found to be the most important features in our dataset to predict breast cancer recurrence. More importantly, our study is the first to use the SHAP method to improve the interpretability of clinicians to predict the recurrence model of breast cancer based on the AdaBoost algorithm. The AdaBoost algorithm offers a clinical decision support model and successfully identifies the recurrence of breast cancer.

Discovery of potential RIPK1 inhibitors by machine learning and molecular dynamics simulations

Receptor-interacting serine/threonine-protein kinase 1 (RIPK1) plays a crucial role in inflammation and cell death, so it is a promising candidate for the treatment of autoimmune, inflammatory, neurodegenerative, and ischemic diseases. So far, there are no approved RIPK1 inhibitors available. In this study, four machine learning algorithms were employed (random forest, extra trees, extreme gradient boosting and light gradient boosting machine) to predict small molecule inhibitors of RIPK1. The statistical metrics revealed similar performance and demonstrated outstanding predictive capabilities in all four models. Molecular docking and clustering analysis were employed to confirm six compounds that are structurally distinct from existing RIPK1 inhibitors. Subsequent molecular dynamics simulations were performed to evaluate the binding ability of these compounds. Utilizing the Shapley additive explanation (SHAP) method, the 1855 bit has been identified as the most significant molecular fingerprint fragment. The findings propose that these six small molecules exhibit promising potential for targeting RIPK1 in associated diseases. Notably, the identification of Cpd-1 small molecule (ZINC000085897746) from the Musa acuminate highlights its natural product origin, warranting further attention and investigation.

Skin Lesion Classification and Detection Using Machine Learning Techniques: A Systematic Review

Skin lesions are essential for the early detection and management of a number of dermatological disorders. Learning-based methods for skin lesion analysis have drawn much attention lately because of improvements in computer vision and machine learning techniques. A review of the most-recent methods for skin lesion classification, segmentation, and detection is presented in this survey paper. The significance of skin lesion analysis in healthcare and the difficulties of physical inspection are discussed in this survey paper. The review of state-of-the-art papers targeting skin lesion classification is then covered in depth with the goal of correctly identifying the type of skin lesion from dermoscopic, macroscopic, and other lesion image formats. The contribution and limitations of various techniques used in the selected study papers, including deep learning architectures and conventional machine learning methods, are examined. The survey then looks into study papers focused on skin lesion segmentation and detection techniques that aimed to identify the precise borders of skin lesions and classify them accordingly. These techniques make it easier to conduct subsequent analyses and allow for precise measurements and quantitative evaluations. The survey paper discusses well-known segmentation algorithms, including deep-learning-based, graph-based, and region-based ones. The difficulties, datasets, and evaluation metrics particular to skin lesion segmentation are also discussed. Throughout the survey, notable datasets, benchmark challenges, and evaluation metrics relevant to skin lesion analysis are highlighted, providing a comprehensive overview of the field. The paper concludes with a summary of the major trends, challenges, and potential future directions in skin lesion classification, segmentation, and detection, aiming to inspire further advancements in this critical domain of dermatological research.

Artificial intelligence based system for predicting permanent stoma after sphincter saving operations

Although the goal of rectal cancer treatment is to restore gastrointestinal continuity, some patients with rectal cancer develop a permanent stoma (PS) after sphincter-saving operations. Although many studies have identified the risk factors and causes of PS, few have precisely predicted the probability of PS formation before surgery. To validate whether an artificial intelligence model can accurately predict PS formation in patients with rectal cancer after sphincter-saving operations. Patients with rectal cancer who underwent a sphincter-saving operation at Taipei Medical University Hospital between January 1, 2012, and December 31, 2021, were retrospectively included in this study. A machine learning technique was used to predict whether a PS would form after a sphincter-saving operation. We included 19 routinely available preoperative variables in the artificial intelligence analysis. To evaluate the efficiency of the model, 6 performance metrics were utilized: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiving operating characteristic curve. In our classification pipeline, the data were randomly divided into a training set (80% of the data) and a validation set (20% of the data). The artificial intelligence models were trained using the training dataset, and their performance was evaluated using the validation dataset. Synthetic minority oversampling was used to solve the data imbalance. A total of 428 patients were included, and the PS rate was 13.6% (58/428) in the training set. The logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest, decision tree and light gradient boosting machine (LightGBM) algorithms were employed. The accuracies of the logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest (RF), decision tree (DT) and light gradient boosting machine (LightGBM) models were 70%, 76%, 89%, 93%, 95%, 79% and 93%, respectively. The area under the receiving operating characteristic curve values were 0.79 for the LR model, 0.84 for the GNB, 0.95 for the XGB, 0.95 for the GB, 0.99 for the RF model, 0.79 for the DT model and 0.98 for the LightGBM model. The key predictors that were identified were the distance of the lesion from the anal verge, clinical N stage, age, sex, American Society of Anesthesiologists score, and preoperative albumin and carcinoembryonic antigen levels. Integration of artificial intelligence with available preoperative data can potentially predict stoma outcomes after sphincter-saving operations. Our model exhibited excellent predictive ability and can improve the process of obtaining informed consent.

Systemic lupus erythematosus with high disease activity identification based on machine learning

OBJECTIVE

Clinical evaluation of systemic lupus erythematosus (SLE) disease activity is limited and inconsistent, and high disease activity significantly, seriously impacts on SLE patients. This study aims to generate a machine learning model to identify SLE patients with high disease activity.

METHOD

A total of 1014 SLE patients with low disease activity and 453 SLE patients with high disease activity were included. A total of 94 clinical, laboratory data and 17 meteorological indicators were collected. After data preprocessing, we use mutual information and multisurf to evaluate and select the importance of features. The selected features are used for machine learning modeling. Performance of the model is evaluated and verified by a series of binary classification indicators.

RESULTS

We screened out hematuria, proteinuria, pyuria, low complement, precipitation, sunlight and other features for model construction by integrated feature selection. After hyperparameter optimization, the LGB has the best performance (ROC: AUC = 0.930; PRC: AUC = 0.911, APS = 0.913; balance accuracy: 0.856), and the worst is the naive bayes (ROC: AUC = 0.849; PRC: AUC = 0.719, APS = 0.714; balance accuracy: 0.705). Finally, the selection of features has good consistency in the composite feature importance bar plot.

CONCLUSION

We identify SLE patients with high disease activity by a simple machine learning pipeline, especially the LGB model based on the characteristics of proteinuria, hematuria, pyuria and other feathers screened out by collective feature selection.

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.