OBJECTIVE

To develop and evaluate the diagnostic performance of an automated machine learning (AutoML) model for the detection of referable diabetic retinopathy (refDR) in ultrawide field (UWF) retinal images from local Philippine retinal image datasets.

A Google AutoML Vision model was trained using 2000 UWF images with a 50/50 ratio of refDR/non-refDR. Images were labeled according to the Early Treatment Diabetic Retinopathy Study (ETDRS) severity grading. RefDR was defined as moderate nonproliferative DR or worse. The dataset was split with 80% for training, 10% for validation, and 10% for testing. Two sets of published UWF image sets were used for external validation. Sensitivity and specificity were calculated in accordance with United States Food and Drug Administration (US FDA) performance requirements of 0.85 and 0.825, respectively.

The area under the precision-recall curve was 0.998. External validation against two datasets showed a sensitivity/specificity of 0.88/0.83 (95% CI 0.80-0.94/0.74-0.89) and 0.83/0.80 (95% CI 0.74-0.89/0.72-0.86), respectively. Positive and negative predictive values were 0.81/0.89 (95% CI 0.73-0.89/0.82-0.94) and 0.75/0.86 (95% CI 0.66-0.83/0.79-0.91), respectively.

The pilot performance of the custom AutoML model constructed using local Philippine data approaches US FDA requirements for the diagnosis of referable DR. The ease of use and intuitiveness of the platform, combined with its performance, support the potential of no-code AI in the detection of refDR.

Humans ; Parkinson Disease/diagnosis* ; Machine Learning

Humans ; Monocytes ; Machine Learning ; HIV Infections/genetics*

The present study aims to establish comprehensive evaluation models of physical fitness of the elderly based on machine learning, and provide an important basis to monitor the elderly's physique. Through stratified sampling, the elderly aged 60 years and above were selected from 10 communities in Nanchang City. The physical fitness of the elderly was measured by the comprehensive physical assessment scale based on our previous study. Fuzzy neural network (FNN), support vector machine (SVM) and random forest (RF) models for comprehensive physical evaluation of the elderly people in communities were constructed respectively. The accuracy, sensitivity and specificity of the comprehensive physical fitness evaluation models constructed by FNN, SVM and RF were above 0.85, 0.75 and 0.89, respectively, with the FNN model possessing the best prediction performance. FNN, RF and SVM models are valuable in the comprehensive evaluation and prediction of physical fitness, which can be used as tools to carry out physical evaluation of the elderly.
Aged ; Humans ; Physical Fitness ; Neural Networks, Computer ; Exercise ; Machine Learning

Humans ; Aged ; Built Environment ; Exercise ; Machine Learning ; China

To realize the non-destructive and rapid origin discrimination of Poria cocos in batches, this study established the P. cocos origin recognition model based on hyperspectral imaging combined with machine learning. P. cocos samples from Anhui, Fujian, Guangxi, Hubei, Hunan, Henan and Yunnan were used as the research objects. Hyperspectral data were collected in the visible and near infrared band(V-band, 410-990 nm) and shortwave infrared band(S-band, 950-2 500 nm). The original spectral data were divided into S-band, V-band and full-band. With the original data(RD) of different bands, multiplicative scatter correction(MSC), standard normal variation(SNV), S-G smoothing(SGS), first derivative(FD), second derivative(SD) and other pretreatments were carried out. Then the data were classified according to three different types of producing areas: province, county and batch. The origin identification model was established by partial least squares discriminant analysis(PLS-DA) and linear support vector machine(LinearSVC). Finally, confusion matrix was employed to evaluate the optimal model, with F1 score as the evaluation standard. The results revealed that the origin identification model established by FD combined with LinearSVC had the highest prediction accuracy in full-band range classified by province, V-band range by county and full-band range by batch, which were 99.28%, 98.55% and 97.45%, respectively, and the overall F1 scores of these three models were 99.16%, 98.59% and 97.58%, respectively, indicating excellent performance of these models. Therefore, hyperspectral imaging combined with LinearSVC can realize the non-destructive, accurate and rapid identification of P. cocos from different producing areas in batches, which is conducive to the directional research and production of P. cocos.
Hyperspectral Imaging ; Wolfiporia ; China ; Least-Squares Analysis ; Support Vector Machine

This study aimed to establish a method based on machine learning technology for accurately predicting the commodity specifications of Fritillariae Cirrhosae Bulbus and explore the application of data augmentation technology in the field of drug analysis. The correlation optimized warping(COW) algorithm was used to perform peak calibration on the UPLC-QDA multi-channel superimposed data of 30 batches of samples, and the data were normalized. Through unsupervised learning methods such as clustering analysis, principal component analysis(PCA), and correlation analysis, the general characteristics of the data were understood. Then, the logistic regression algorithm was used for supervised learning on the data, and the condition tabular generative adversarial networks(CTGAN) was used to generate a large amount of data. Logistic regression classification models were trained separately using the real data and the data generated by CTGAN, and these models were evaluated. The logistic regression model trained with real data achieved cross-validation and test set accuracies of 0.95 and 1.00, respectively, while the logistic regression model trained with both real and CTGAN-generated data achieved cross-validation and test set accuracies of 0.99 and 1.00, respectively. The results indicate that machine learning can accurately predict the classification of Songbei, Qingbei, and Lubeibased on UPLC-QDA detection data. CTGAN-generated data can partially compensate for the lack of data in drug analysis, improving the accuracy and predictive ability of machine learning models.
Drugs, Chinese Herbal ; Fritillaria ; Technology ; Machine Learning ; Plant Roots

Keloids are benign skin tumors resulting from the excessive proliferation of connective tissue in wound skin. Precise prediction of keloid risk in trauma patients and timely early diagnosis are of paramount importance for in-depth keloid management and control of its progression. This study analyzed four keloid datasets in the high-throughput gene expression omnibus (GEO) database, identified diagnostic markers for keloids, and established a nomogram prediction model. Initially, 37 core protein-encoding genes were selected through weighted gene co-expression network analysis (WGCNA), differential expression analysis, and the centrality algorithm of the protein-protein interaction network. Subsequently, two machine learning algorithms including the least absolute shrinkage and selection operator (LASSO) and the support vector machine-recursive feature elimination (SVM-RFE) were used to further screen out four diagnostic markers with the highest predictive power for keloids, which included hepatocyte growth factor (HGF), syndecan-4 (SDC4), ectonucleotide pyrophosphatase/phosphodiesterase 2 (ENPP2), and Rho family guanosine triphophatase 3 (RND3). Potential biological pathways involved were explored through gene set enrichment analysis (GSEA) of single-gene. Finally, univariate and multivariate logistic regression analyses of diagnostic markers were performed, and a nomogram prediction model was constructed. Internal and external validations revealed that the calibration curve of this model closely approximates the ideal curve, the decision curve is superior to other strategies, and the area under the receiver operating characteristic curve is higher than the control model (with optimal cutoff value of 0.588). This indicates that the model possesses high calibration, clinical benefit rate, and predictive power, and is promising to provide effective early means for clinical diagnosis.
Humans ; Keloid/genetics* ; Nomograms ; Algorithms ; Calibration ; Machine Learning

Heart valve disease (HVD) is one of the common cardiovascular diseases. Heart sound is an important physiological signal for diagnosing HVDs. This paper proposed a model based on combination of basic component features and envelope autocorrelation features to detect early HVDs. Initially, heart sound signals lasting 5 minutes were denoised by empirical mode decomposition (EMD) algorithm and segmented. Then the basic component features and envelope autocorrelation features of heart sound segments were extracted to construct heart sound feature set. Then the max-relevance and min-redundancy (MRMR) algorithm was utilized to select the optimal mixed feature subset. Finally, decision tree, support vector machine (SVM) and k-nearest neighbor (KNN) classifiers were trained to detect the early HVDs from the normal heart sounds and obtained the best accuracy of 99.9% in clinical database. Normal valve, abnormal semilunar valve and abnormal atrioventricular valve heart sounds were classified and the best accuracy was 99.8%. Moreover, normal valve, single-valve abnormal and multi-valve abnormal heart sounds were classified and the best accuracy was 98.2%. In public database, this method also obtained the good overall accuracy. The result demonstrated this proposed method had important value for the clinical diagnosis of early HVDs.
Humans ; Heart Sounds ; Heart Valve Diseases/diagnosis* ; Algorithms ; Support Vector Machine ; Signal Processing, Computer-Assisted

OBJECTIVE: To review the current applications of machine learning in orthopaedic trauma and anticipate its future role in clinical practice. METHODS: A comprehensive literature review was conducted to assess the status of machine learning algorithms in orthopaedic trauma research, both nationally and internationally. RESULTS: The rapid advancement of computer data processing and the growing convergence of medicine and industry have led to the widespread utilization of artificial intelligence in healthcare. Currently, machine learning plays a significant role in orthopaedic trauma, demonstrating high performance and accuracy in various areas including fracture image recognition, diagnosis stratification, clinical decision-making, evaluation, perioperative considerations, and prognostic risk prediction. Nevertheless, challenges persist in the development and clinical implementation of machine learning. These include limited database samples, model interpretation difficulties, and universality and individualisation variations. CONCLUSION The expansion of clinical sample sizes and enhancements in algorithm performance hold significant promise for the extensive application of machine learning in supporting orthopaedic trauma diagnosis, guiding decision-making, devising individualized medical strategies, and optimizing the allocation of clinical resources.
Artificial Intelligence ; Orthopedics ; Machine Learning ; Algorithms