bims-aukdir 2025-05-04 papers

bims-aukdir

Biomed News

on Automated knowledge discovery in diabetes research

Issue of 2025–05–04
twelve papers selected by
Mott Given

A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images.
EfficientNetB0-Based End-to-End Diagnostic System for Diabetic Retinopathy Grading and Macular Edema Detection.
Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study.
Machine Learning-Driven Identification of Hematological and Immunological Biomarkers for Predicting Proliferative Diabetic Retinopathy Progression.
Diagnostic utility of artificial intelligence software through non-mydriatic digital retinography in the screening of diabetic retinopathy: an overview of reviews.
Predicting Visual Acuity after Retinal Vein Occlusion Anti-VEGF Treatment: Development and Validation of an Interpretable Machine Learning Model.
Artificial Intelligence as a Tool for Self-Care in Patients with Type 1 and Type 2 Diabetes-An Integrative Literature Review.
Engineering novel features for diabetes complication prediction using synthetic electronic health records.
A Biomarker-Driven and Interpretable Machine Learning Model for Diagnosing Diabetes Mellitus.
Detection of Center-Involved Diabetic Macular Edema with Visual Impairment using Multimodal Artificial Intelligence Algorithms.
Development and validation of machine learning models for predicting low muscle mass in patients with obesity and diabetes.
A Deep Sparse Capsule Network for Non-Invasive Blood Glucose Level Estimation Using a PPG Sensor.

Sci Rep. 2025 Apr 30. 15(1): 15166

A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images.

Mishmala Sushith, A Sathiya, V Kalaipoonguzhali, V Sathya.

  Recent advancements in deep learning have significantly impacted medical image processing domain, enabling sophisticated and accurate diagnostic tools. This paper presents a novel hybrid deep learning framework that combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for diabetic retinopathy (DR) early detection and progression monitoring using retinal fundus images. Utilizing the sequential nature of disease progression, the proposed method integrates temporal information across multiple retinal scans to enhance detection accuracy. The proposed model utilizes publicly available DRIVE and Kaggle diabetic retinopathy datasets to evaluate the performance. The benchmark datasets provide a diverse set of annotated retinal images and the proposed hybrid model employs a CNN to extract spatial features from retinal images. The spatial feature extraction is enhanced by multi-scale feature extraction to capture fine details and broader patterns. These enriched spatial features are then fed into an RNN with attention mechanism to capture temporal dependencies so that most relevant data aspects can be considered for analysis. This combined approach enables the model to consider both current and previous states of the retina, improving its ability to detect subtle changes indicative of early-stage DR. Proposed model experimental evaluation demonstrate the superior performance over traditional deep learning models like CNN, RNN, InceptionV3, VGG19 and LSTM in terms of both sensitivity and specificity, achieving 97.5% accuracy on the DRIVE dataset, 94.04% on the Kaggle dataset, 96.9% on the Eyepacs Dataset. This research work not only advances the field of automated DR detection but also provides a framework for utilizing temporal information in medical image analysis.

Keywords:  Convolutional neural network; Deep learning; Diabetic retinopathy; Recurrent neural network; Retinal fundus images; Temporal analysis

DOI:  https://doi.org/10.1038/s41598-025-99309-w
Diabetes Metab Syndr Obes. 2025 ;18 1311-1321

EfficientNetB0-Based End-to-End Diagnostic System for Diabetic Retinopathy Grading and Macular Edema Detection.

Xin Long, Fan Gan, Huimin Fan, WeiGuo Qin, Xiaonan Li, Rui Ma, Leran Wang, Rui Hu, Yilin Xie, Lei Chen, Jian Cao, Yinan Shao, Kangcheng Liu, Zhipeng You.

   Purpose: This study aims to develop and validate a deep learning-based automated diagnostic system that utilizes fluorescein angiography (FFA) images for the rapid and accurate diagnosis of diabetic retinopathy (DR) and its complications.
Methods: We collected 19,031 FFA images from 2753 patients between June 2017 and March 2024 to construct and evaluate our analytical framework. The images were preprocessed and annotated for training and validating the deep learning model. The study employed a two-stage deep learning system: the first stage used EfficientNetB0 for a five-class classification task to differentiate between normal retinal conditions, various stages of DR, and post-laser treatment status; the second stage focused on images classified as abnormal in the first stage, further detecting the presence of diabetic macular edema (DME). Model performance was evaluated using multiple classification metrics, including accuracy, AUC, precision, recall, F1-score, and Cohen's kappa coefficient.
Results: In the first stage, the model achieved an accuracy of 0.7036 and an AUC of 0.9062 on the test set, demonstrating high accuracy and discriminative ability. In the second stage, the model achieved an accuracy of 0.7258 and an AUC of 0.7530, performing well. Additionally, through Grad-CAM (gradient-weighted class activation mapping), we visualized the most influential image regions in the model's decision-making process, enhancing the model's interpretability.
Conclusion: This study successfully developed an end-to-end DR diagnostic system based on the EfficientNetB0 model. The system not only automates the grading of FFA images but also detects DME, significantly reducing the time required for image interpretation by clinicians and providing an effective tool to improve the efficiency and accuracy of DR diagnosis.

Keywords:  DME; DR; EfficientNetB0; FFA; deep learning; diabetic macular edema; diabetic retinopathy; fluorescein angiography

DOI:  https://doi.org/10.2147/DMSO.S506494
Lancet Digit Health. 2025 Apr 30. pii: S2589-7500(25)00040-8. [Epub ahead of print] 100868

Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study.

Ziyao Meng, Zhouyu Guan, Shujie Yu, Yilan Wu, Yaoning Zhao, Jie Shen, Cynthia Ciwei Lim, Tingli Chen, Dawei Yang, An Ran Ran, Feng He, Haslina Hamzah, Sarkaaj Singh, Anis Syazwani Abd Raof, Jian Wen Samuel Lee-Boey, Soo-Kun Lim, Xufang Sun, Shuwang Ge, Gang Xu, Hua Su, Yang Cheng, Feng Lu, Xiaofei Liao, Hai Jin, Chenxin Deng, Lei Ruan, Cuntai Zhang, Chan Wu, Rongping Dai, Yixiao Jin, Wenxiao Wang, Tingyao Li, Ruhan Liu, Jiajia Li, Jia Shu, Yuwei Lu, Xiangning Wang, Qiang Wu, Yiming Qin, Jin Tang, Xiaohua Sheng, Qiong Jiao, Xiaokang Yang, Minyi Guo, Gareth J McKay, Ruth E Hogg, Gerald Liew, Evelyn Yi Lyn Chee, Wynne Hsu, Mong Li Lee, Simon Szeto, Andrea O Y Luk, Juliana C N Chan, Carol Y Cheung, Gavin Siew Wei Tan, Yih-Chung Tham, Ching-Yu Cheng, Charumathi Sabanayagam, Lee-Ling Lim, Weiping Jia, Huating Li, Bin Sheng, Tien Yin Wong.

BACKGROUND: Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images.
METHODS: In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD; and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up.
FINDINGS: For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838-0·846) on the internal validation dataset and AUCs of 0·791-0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825-0·966) on the internal validation dataset and AUCs of 0·733-0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD with higher sensitivity (89·8% vs 66·3%, p<0·0001). In the longitudinal study, participants with isolated diabetic nephropathy and participants with NDKD identified by DeepDKD had a significant difference in renal function outcomes (proportion of estimated glomerular filtration rate decline: 27·45% vs 52·56%, p=0·0010).
INTERPRETATION: Among diverse multi-ethnic populations with diabetes, a retinal image-based AI-deep learning system showed its potential for detecting DKD and differentiating isolated diabetic nephropathy from NDKD in clinical practice.
FUNDING: National Key R & D Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation, Shanghai Municipal Key Clinical Specialty, Shanghai Research Centre for Endocrine and Metabolic Diseases, Innovative research team of high-level local universities in Shanghai, Noncommunicable Chronic Diseases-National Science and Technology Major Project, Clinical Special Program of Shanghai Municipal Health Commission, and the three-year action plan to strengthen the construction of public health system in Shanghai.

DOI: https://doi.org/10.1016/j.landig.2025.02.008
Curr Eye Res. 2025 Apr 29. 1-10

Machine Learning-Driven Identification of Hematological and Immunological Biomarkers for Predicting Proliferative Diabetic Retinopathy Progression.

Sibo Zhao.

   PURPOSE: Proliferative Diabetic Retinopathy (PDR) is a severe complication of diabetes characterized by neovascularization and retinal detachment, leading to significant vision loss. This study investigates the predictive power of hematological and immunological markers in PDR progression.
METHODS: Data from 126 patients were analyzed using advanced machine learning techniques, including LASSO regression, elastic net modeling, and backward stepwise regression.
RESULTS: The findings identified age, gender, IL-1, and lymphocyte count (LYM) as significant predictors of PDR, with a high AUC value of 0.839 from the ROC curve analysis. These markers, particularly cytokines in the aqueous humor and peripheral blood, offer a convenient and rapid method for early detection and risk assessment of PDR.
CONCLUSIONS: Despite the limitations of being a cross-sectional study with a relatively small sample size, the results highlight the clinical significance of these biomarkers and underscore the need for further validation in larger, more diverse populations. This study contributes to the development of targeted interventions and improved management strategies for diabetic retinopathy, emphasizing the importance of immunological health in disease progression.

Keywords:  Proliferative diabetic retinopathy; biomarkers; machine learning

DOI:  https://doi.org/10.1080/02713683.2025.2498035
Eye (Lond). 2025 Apr 29.

Diagnostic utility of artificial intelligence software through non-mydriatic digital retinography in the screening of diabetic retinopathy: an overview of reviews.

Agustín Ciapponi, Jamile Ballivian, Carolina Gentile, Jhonatan R Mejia, Jessica Ruiz-Baena, Ariel Bardach.

OBJECTIVE: To evaluate the capability of artificial intelligence (AI) in screening for diabetic retinopathy (DR) utilizing digital retinography captured by non-mydriatic (NM) ≥45° cameras, focusing on diagnosis accuracy, effectiveness, and clinical safety.
METHODS: We performed an overview of systematic reviews (SRs) up to May 2023 in Medline, Embase, CINAHL, and Web of Science. We used AMSTAR-2 tool to assess the reliability of each SR. We reported meta-analysis estimates or ranges of diagnostic performance figures.
RESULTS: Out of 1336 records, ten SRs were selected, most deemed low or critically low quality. Eight primary studies were included in at least five of the ten SRs and 125 in less than five SRs. No SR reported efficacy, effectiveness, or safety outcomes. The sensitivity and specificity for referable DR were 68-100% and 20-100%, respectively, with an AUROC range of 88 to 99%. For detecting DR at any stage, sensitivity was 79-100%, and specificity was 50-100%, with an AUROC range of 93 to 98%.
CONCLUSIONS: AI demonstrates strong diagnostic potential for DR screening using NM cameras, with adequate sensitivity but variable specificity. While AI is increasingly integrated into routine practice, this overview highlights significant heterogeneity in AI models and the cameras used. Additionally, our study enlightens the low quality of existing systematic reviews and the significant challenge of integrating the rapidly growing volume of emerging evidence in this field. Policymakers should carefully evaluate AI tools in specific contexts, and future research must generate updated high-quality evidence to optimize their application and improve patient outcomes.

DOI: https://doi.org/10.1038/s41433-025-03809-y
J Med Syst. 2025 Apr 29. 49(1): 57

Predicting Visual Acuity after Retinal Vein Occlusion Anti-VEGF Treatment: Development and Validation of an Interpretable Machine Learning Model.

Chunlan Liang, Lian Liu, Tianqi Zhao, Weiyun Ouyang, Guocheng Yu, Jun Lyu, Jingxiang Zhong.

  Accurate prediction of post-treatment visual acuity in macular edema secondary to retinal vein occlusion (RVO-ME) is critical for optimizing anti-VEGF therapy and improving clinical outcomes. While machine learning (ML) has shown promise in ophthalmic prognostication, existing models often lack interpretability and clinical applicability for RVO management. This study developed and validated an interpretable ML model to predict visual acuity changes in RVO patients following anti-VEGF treatment. Using retrospective data from 259 RVO patients at the First Affiliated Hospital of Jinan University, we identified key predictive features through the Boruta algorithm and evaluated eight ML algorithms. The Extreme Gradient Boosting (XGBoost) model emerged as optimal, achieving an AUC of 0.91 (95% CI: 0.85-0.96) in the testing cohort with 0.83 accuracy, 0.88 sensitivity, 0.73 specificity, 0.87 F1 score, and 0.14 Brier score. Critical predictors included baseline visual acuity, systolic blood pressure (SBP), age, diabetic retinal inner layer dysfunction (DRIL), and disease subtype. Shapley Additive exPlanations (SHAP) analysis revealed baseline visual acuity as the most influential prognostic factor, followed by SBP and age. Our model seeks to bridge the critical gaps in current research: (1) systematically comparing the applicability and effects of different ML algorithms in RVO-ME visual acuity prediction, and (2) inherent interpretability through SHAP value visualization. The combination of high predictive performance (AUC > 0.9) with inherent clinical transparency may enable the practical implementation of this tool in guiding anti-VEGF treatment decisions. Future validation in multicenter cohorts could further strengthen its generalizability for personalized RVO management.

Keywords:  Anti-VEGF; Extreme Gradient Boosting; Interpretable machine learning; Retinal vein occlusion; Visual acuity prediction

DOI:  https://doi.org/10.1007/s10916-025-02190-3
Healthcare (Basel). 2025 Apr 21. pii: 950. [Epub ahead of print]13(8):

Artificial Intelligence as a Tool for Self-Care in Patients with Type 1 and Type 2 Diabetes-An Integrative Literature Review.

Vera Persson, Ulrica Lovén Wickman.

  Background/Objectives: Diabetes is a common public health disease that affects patients mentally, physically, and economically. It requires lifestyle changes such as blood sugar control and regular contact with healthcare services. Artificial intelligence has developed rapidly in many different areas in recent years, including healthcare and nursing. The aim of this study is to explore how artificial intelligence can be used as a tool for patients with diabetes mellitus. Methods: An integrative literature review design was chosen according to Whittemore and Knafl (2005). Electronic searches in databases were conducted across Pub-Med, CINAHL Complete (EBSCO), and ACM Digital Library until September 2024. A total set of quantitative and qualitative articles (n = 15) was selected and reviewed using a Mixed Method Appraisal Tool. Results: Artificial intelligence is an effective tool for patients with diabetes mellitus, and various models are used. Three themes emerged: artificial intelligence as a tool for blood sugar monitoring for patients with diabetes mellitus, artificial intelligence as a decision support for diabetic wounds and complications, and patients' requests for artificial intelligence capabilities in relation to tools. Artificial intelligence can create better conditions for patient self-care. Conclusions: Artificial intelligence is a valuable tool for patients with diabetes mellitus and enables the district nurse to focus more on person-centered care. The technology facilitates the patient's blood sugar monitoring. However, more research is needed to ensure the safety of AI technology, the protection of patient privacy, and clarification of laws and regulations within diabetes care.

Keywords:  artificial intelligence; diabetes mellitus; district nurse; machine intelligence; nurse’s role; review

DOI:  https://doi.org/10.3390/healthcare13080950
Front Genet. 2025 ;16 1451290

Engineering novel features for diabetes complication prediction using synthetic electronic health records.

Daniel Voskergian, Burcu Bakir-Gungor, Malik Yousef.

  Diabetes significantly affects millions of people worldwide, leading to substantial morbidity, disability, and mortality rates. Predicting diabetes-related complications from health records is crucial for early prevention and for the development of effective treatment plans. In order to predict four different complications of diabetes mellitus, i.e., retinopathy, chronic kidney disease, ischemic heart disease, and amputations, this study introduces a novel feature engineering approach. While developing the classification models, we utilize XGBoost feature selection method and various supervised machine learning algorithms, including Random Forest, XGBoost, LogitBoost, AdaBoost, and Decision Tree. These models were trained on synthetic electronic health records (EHR) generated by dual-adversarial autoencoders. These EHRs represent nearly 1 million synthetic patients derived from an authentic cohort of 979,308 individuals with diabetes. The variables considered in the models were the age range accompanied by chronic diseases that occur during patient visits starting from the onset of diabetes. Throughout the experiments, XGBoost and Random Forest demonstrated the best overall prediction performance. The final models, which are tailored to each complication and trained using our feature engineering approach, achieved an accuracy between 69% and 77% and an AUC between 77% and 84% using cross-validation, while the partitioned validation approach yielded an accuracy between 59% and 78% and an AUC between 66% and 85%. These findings imply that the performance of our method surpass the performance of the traditional Bag-of-Features approach, highlighting the effectiveness of our approach in enhancing model accuracy and robustness.

Keywords:  diabetes complications; feature engineering; feature selection; machine learning; predictive modeling; risk prediction; synthetic electronic health records (EHRs)

DOI:  https://doi.org/10.3389/fgene.2025.1451290
Food Sci Nutr. 2025 May;13(5): e70234

A Biomarker-Driven and Interpretable Machine Learning Model for Diagnosing Diabetes Mellitus.

Zhihui Xiao, Mingfu Wang, Yueliang Zhao, Hui Wang.

  Diabetes is one of the leading causes of death and disability worldwide. Developing earlier and more accurate diagnosis methods is crucial for clinical prevention and treatment of diabetes. Here, data on biochemical indicators and physiological characteristics of 4335 participants from the National Health and Nutrition Examination Survey (NHANES) database from 2017 to 2020 were collected. After data preprocessing, the dataset was randomly divided into a training set (70%) and a test set (30%); then the Boruta algorithm was used to screen feature indicators on the training set. Next, three machine learning algorithms, including Random Forest (RF), Multi-Layer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost) were employed to build predictive models through 10-fold cross-validation on the training dataset, followed by performance evaluation on the test dataset. The RF model exhibited the best performance, with an area under the curve (AUC) of 0.958 (95% CI: 0.943-0.973), a recall of 0.897, a specificity and F1 score of 0.916 and 0.747, respectively, and an overall accuracy of 0.913. Moreover, SHapley Additive exPlanations (SHAP) and Partial Dependency Plots (PDP) were applied to interpret the RF model to analyze the risk factors for diabetes. Glycohemoglobin, glucose, fasting glucose, age, cholesterol, osmolality, BMI, blood urea nitrogen, and insulin were found to exert the greatest influence on the prevalence of diabetes. Collectively, the RF model has considerable application prospects for the diagnosis of diabetes and can serve as a valuable supplementary tool for clinical diagnosis and risk assessment in diabetes.

Keywords:  biomarker‐driven; diabetes mellitus; interpretable; machine learning; prediction model

DOI:  https://doi.org/10.1002/fsn3.70234
Ophthalmol Retina. 2025 Apr 24. pii: S2468-6530(25)00173-3. [Epub ahead of print]

Detection of Center-Involved Diabetic Macular Edema with Visual Impairment using Multimodal Artificial Intelligence Algorithms.

Tien-En Tan, Yi Pin Ng, Claire Calhoun, Jia Quan Chaung, Jie Yao, Yan Wang, Liangli Zhen, Xinxing Xu, Yong Liu, Rick Sm Goh, Gabriele Piccoli, Stela Vujosevic, Gavin Sw Tan, Jennifer K Sun, Daniel Sw Ting.

PURPOSE: To develop artificial intelligence (AI) models for automated detection of center-involved diabetic macular edema (CI-DME) with visual impairment using color fundus photographs (CFP) and optical coherence tomography (OCT) scans.
DESIGN: AI effort using pooled data from multi-center studies.
PARTICIPANTS: Datasets consisted of diabetic participants with or without CI-DME, who had CFP, OCT, and best corrected visual acuity (BCVA) obtained after manifest refraction. The development dataset was from DRCR Retina Network clinical trials, external testing dataset 1 was from the Singapore National Eye Centre, Singapore, and external testing dataset 2 was from the Eye Clinic, IRCCS MultiMedica, Milan, Italy.
METHODS: AI models were trained to detect CI-DME, visual impairment (BCVA 20/32 or worse), and CI-DME with visual impairment, using CFPs alone, OCTs alone, and both CFPs and OCTs together (multimodal). Data from 1,007 eyes were used to train and validate the algorithms, and data from 448 eyes were used for testing.
MAIN OUTCOME MEASURES: Area under the receiver operating characteristic curve (AUC) values.
RESULTS: In the primary testing set, the CFP model, OCT model, and multimodal model had AUCs of 0.848 (95% CI 0.787-0.900), 0.913 (95% CI 0.870-0.947), and 0.939 (95% CI 0.906-0.964), respectively, for detection of CI-DME with visual impairment. In external testing dataset 1, the CFP, OCT, and multimodal models had AUCs of 0.756 (95% CI 0.624-0.870), 0.949 (95% CI 0.889-0.989), and 0.917 (95% CI 0.837-0.979), respectively, for detection of CI-DME with visual impairment. In external testing dataset 2, the CFP, OCT, and multimodal models had AUCs of 0.881 (95% CI 0.822-0.940), 0.828 (95% CI 0.749-0.905), and 0.907 (95% CI 0.852-0.952), respectively, for detection of CI-DME with visual impairment.
CONCLUSION: The AI models showed good diagnostic performance for detection of CI-DME with visual impairment. The multimodal (CFP and OCT) model did not offer additional benefit over the OCT model alone. If validated in prospective studies, these AI models could potentially help to improve triage and detection of patients who require prompt treatment.

DOI: https://doi.org/10.1016/j.oret.2025.04.016
Lipids Health Dis. 2025 Apr 29. 24(1): 162

Development and validation of machine learning models for predicting low muscle mass in patients with obesity and diabetes.

Jiaying Ge, Siqi Sun, Jiangping Zeng, Yujie Jing, Huihui Ma, Chunhua Qian, Ran Cui, Shen Qu, Hui Sheng.

   BACKGROUND AND AIMS: Low muscle mass (LMM) is a critical complication in patients with obesity and diabetes, exacerbating metabolic and cardiovascular risks. Novel obesity indices, such as the body roundness index (BRI), conicity index, and relative fat mass, have shown promise for assessing body composition. This study aimed to investigate the associations of these indices with LMM and to develop machine learning models for accurate and accessible LMM prediction.
METHOD: Data from NHANES 2011-2018 (n = 2,176) were analyzed. Obesity was defined by body fat percentage, and LMM was determined using skeletal muscle mass index thresholds adjusted for BMI. Predictive models were developed using logistic regression, random forest, and other algorithms, with feature selection via LASSO regression. Validation included NHANES 2005-2006 data (n = 310). Model performance was evaluated using AUROC, Brier scores, and SHapley Additive exPlanations (SHAP) for feature importance.
RESULTS: BRI was independently associated with LMM (odds ratio 1.39, 95% confidence interval 1.22-1.58; P < 0.001). Eight features were included in the random forest model, which achieved excellent discrimination (AUROC = 0.721 in the validation set) and calibration (Brier score = 0.184). Feature importance analysis highlighted BRI, creatinine, race, age, and HbA1c as key contributors to the model's predictive performance. SHAP analysis emphasized BRI's role in predicting LMM. An online prediction tool was developed.
CONCLUSIONS: BRI is a significant predictor of LMM in patients with obesity and diabetes. The random forest model demonstrated strong performance and offers a practical tool for early LMM detection, supporting clinical decision-making and personalized interventions.

Keywords:  Diabetes; Low muscle mass; Machine learning; NHANES; Obesity

DOI:  https://doi.org/10.1186/s12944-025-02577-8
Sensors (Basel). 2025 Mar 18. pii: 1868. [Epub ahead of print]25(6):

A Deep Sparse Capsule Network for Non-Invasive Blood Glucose Level Estimation Using a PPG Sensor.

Narmatha Chellamani, Saleh Ali Albelwi, Manimurugan Shanmuganathan, Palanisamy Amirthalingam, Emad Muteb Alharbi, Hibah Qasem Salman Alatawi, Kousalya Prabahar, Jawhara Bader Aljabri, Anand Paul.

  Diabetes, a chronic medical condition, affects millions of people worldwide and requires consistent monitoring of blood glucose levels (BGLs). Traditional invasive methods for BGL monitoring can be challenging and painful for patients. This study introduces a non-invasive, deep learning (DL)-based approach to estimate BGL using photoplethysmography (PPG) signals. Specifically, a Deep Sparse Capsule Network (DSCNet) model is proposed to provide accurate and robust BGL monitoring. The proposed model's workflow includes data collection, preprocessing, feature extraction, and predictions. A hardware module was designed using a PPG sensor and Raspberry Pi to collect patient data. In preprocessing, a Savitzky-Golay filter and moving average filter were applied to remove noise and preserve pulse form and high-frequency components. The DSCNet model was then applied to predict the sugar level. Two models were developed for prediction: a baseline model, DSCNet, and an enhanced model, DSCNet with self-attention. DSCNet's performance was evaluated using Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Relative Difference (MARD), and coefficient of determination (R2), yielding values of 3.022, 0.05, 0.058, 0.062, 10.81, and 0.98, respectively.

Keywords:  DSCNet; PPG sensor; blood glucose level; deep learning; non-invasive

DOI:  https://doi.org/10.3390/s25061868