Bioengineering

This paper re-imagines a world of abundance in the treatment of chronic diseases such as Tpe 2 Diabetes. It asks: what if preventive and diagnostic remedies were widely made available across the world, informed by the latest medical research? As Proof-of-Concept of a proposed solution, the paper describes the development and validation of a local Large Language Models (local-LLMs) based on Graph-based Retrieval-Augmented Generation (GraphRAG) for managing Gestational Diabetes Mellitus (GDM). The research thus seeks new insights into optimizing GDM treatment through a knowledge graph architecture, contributing to a deeper understanding of how artificial intelligence can extend medical expertise to underserved populations globally. The study employs an agile, prototyping approach utilizing GraphRAG to enhance knowledge graphs by integrating retrieval-based and generative artificial intelligence techniques. Training data was from academic papers published between January 2000 and May 2024 using the Semantic Scholar API and analyzed by mapping complex associations within GDM management to create a comprehensive knowledge graph architecture. It is categorically stated that, since the primary research objective was to establish the feasibility of a GraphRAG local-LLM PoC, no human subjects nor actual patient datasets were used. Empirical results indicate that the GraphRAG-based Proof of Concept outperforms open-source LLMs such as ChatGPT, Claude, and BioMistral across key evaluation metrics. Specifically, GraphRAG achieves superior accuracy with BLEU scores of 0.99, Jaccard similarity of 0.98, and BERT scores of 0.98, offering significant implications for personalized medical insights that enhance diagnostic accuracy and treatment efficacy. This research offers a novel perspective on applying GraphRAG-enabled LLM technologies to GDM management, providing valuable insights that extend current understanding of AI applications in healthcare. The studys findings contribute to advancing the feasibility of GenAI for proactive GDM treatment and extending medical expertise to underserved populations globally.

AimsLarge language models (LLMs), exemplified by ChatGPT have recently emerged as potential solutions to challenges of traditional diabetes education. This study aimed to explore the feasibility and utility of ChatGPT application in diabetes education. MethodsWe conducted a multi-dataset, multi-reviewer study. In the retrospective dataset evaluation, 85 questions covering seven aspects of diabetes education were collected. Three physicians evaluate the ChatGPT responses for reproducibility, relevance, correctness, helpfulness, and safety, while twelve laypersons evaluated the readability, helpfulness, and trustworthiness of the responses. In the real-world dataset evaluation, three individuals with type 2 diabetes (a newly diagnosed patient, a patient with diabetes for 20 years and on oral anti-diabetic medications, and a patient with diabetes for 40 years and on insulin therapy) posed their questions. The helpfulness and trustworthiness of responses from ChatGPT and physicians were assessed. ResultsIn the retrospective dataset evaluation, physicians rated ChatGPT responses for relevance (5.98/6.00), correctness (5.69/6.00), helpfulness (5.75/6.00), and safety (5.95/6.00), while the ratings by laypersons for readability, helpfulness, and trustworthiness were 5.21/6.00, 5.02/6.00, and 4.99/6.00, respectively. In the real-world dataset evaluation, ChatGPT responses received lower ratings compared to physicians responses (helpfulness: 4.18 vs. 4.91, P <0.001; trustworthiness: 4.80 vs. 5.20, P = 0.042). However, when carefully crafted prompts were utilized, the ratings of ChatGPT responses were comparable to those of physicians. ConclusionsThe results show that the application of ChatGPT in addressing typical diabetes education questions is feasible, and carefully crafted prompts are crucial for satisfactory ChatGPT performance in real-world personalized diabetes education. Whats new?O_LIThis is the first study covering evaluations by doctors, laypersons and patients to explore ChatGPT application in diabetes education. This multi-reviewer evaluation approach provided a multidimensional understanding of ChatGPTs capabilities and laid the foundation for subsequent clinical evaluations. C_LIO_LIThis study suggested that the application of ChatGPT in addressing typical diabetes education questions is feasible, and carefully crafted prompts are crucial for satisfactory ChatGPT performance in real-world personalized diabetes education. C_LIO_LIResults of layperson evaluation revealed that human factors could result in disparities of evaluations. Further concern of trust and ethical issues in AI development are necessary. C_LI

In this paper, we are introducing a novel model of artificial intelligence, the functional neural network for modeling of human decision-making processes. This neural network is composed of multiple artificial neurons racing in the network. Each of these neurons has a similar structure programmed independently by the users and composed of an intention wheel, a motor core and a sensory core representing the user itself and racing at a specific velocity. The mathematics of the neurons formulation and the racing mechanism of multiple nodes in the network will be discussed, and the group decision process with fuzzy logic and the transformation of these conceptual methods into practical methods of simulation and in operations will be developed. Eventually, we will describe some possible future research directions in the fields of finance, education and medicine including the opportunity to design an intelligent learning agent with application in business operations supervision. We believe that this functional neural network has a promising potential to transform the way we can compute decision-making and lead to a new generation of neuromorphic chips for seamless human-machine interactions.

IntroductionThyroid ultrasound provides valuable insights for thyroid disorders but is hampered by subjectivity. Automated analysis utilizing large datasets holds immense promise for objective and standardized assessment in screening, thyroid nodule classification, and treatment monitoring. However, there remains a significant gap in the development of applications for the automated analysis of Hashimotos thyroiditis (HT) using ultrasound. ObjectiveTo develop an automated thyroid ultrasound analysis (ATUS) algorithm using the C# programming language to detect and quantify ultrasonographic characteristics associated with HT. Materials and MethodsThis study describes the development and evaluation of an ATUS algorithm using C#. The algorithm extracte relevant features (texture, vascularization, echogenicity) from preprocessed ultrasound images and utilizes machine learning techniques to classify them as "normal" or indicative of HT. The model is trained and validated on a comprehensive dataset, with performance assessed through metrics like accuracy, sensitivity, and specificity. The findings highlight the potential for this C#-based ATUS algorithm to offer objective and standardized assessment for HT diagnosis. ResultsThe program preprocesses images (grayscale conversion, normalization, etc.), segments the thyroid region, extracts features (texture, echogenicity), and utilizes a pre-trained model for classification ("normal" or "suspected Hashimotos thyroiditis"). Using a sample image, the program successfully preprocessed, segmented, and extracted features. The predicted classification ("suspected HT") with high probability (0.92) aligns with the pre-established diagnosis, suggesting potential for objective HT assessment. ConclusionC#-based ATUS algorithm successfully detects and quantifies Hashimotos thyroiditis features, showcasing the potential of advanced programming in medical image analysis.

The purpose of this paper is to present a detailed investigation of the advantages of employing GraphLIME (Local Interpretable Model Explanations for Graph Neural Networks) for the trustworthy prediction of diabetes mellitus. Our pursuit involves identifying the strengths of GraphLIME combined with the attention-mechanism over the standard coupling of deep learning neural networks with the original LIME method. The system build this way, provided us a proficient method for extracting the most relevant features and applying the attention mechanism exclusively to those features. We have closely monitored the performance metrics of the two approaches and conducted a comparative analysis. Leveraging attention mechanisms, we have achieved an accuracy of 92.6% for the addressed problem. The models performance is meticulously demonstrated throughout the study, and the results are furthermore evaluated using the Receiver Operating Characteristic (ROC) curve. By implementing this technique on a dataset of 768 patients diagnosed with or without diabetes mellitus, we have successfully boosted the models performance by over 18%.

This study explores Artificial Intelligence (AI)s transformative role in diabetes care and monitoring, focusing on innovations that optimize patient outcomes. AI, particularly machine learning and deep learning, significantly enhances early detection of complications like diabetic retinopathy and improves screening efficacy. The methodology employs a bibliometric analysis using Scopus, VOSviewer, and Publish or Perish, analyzing 235 articles from 2023-2025. Results indicate a strong interdisciplinary focus, with Computer Science and Medicine being dominant subject areas (36.9% and 12.9% respectively). Bibliographic coupling reveals robust international collaborations led by the U.S. (1558.52 link strength), UK, and China, with key influential documents by Zhu (2023c) and Annuzzi (2023). This research highlights AIs impact on enhancing monitoring, personalized treatment, and proactive care, while acknowledging challenges in data privacy and ethical deployment. Future work should bridge technological advancements with real-world implementation to create equitable and efficient diabetes care systems.

Autism Spectrum Disorder (ASD) is a neurological condition that affects the brain, leading to challenges in speech, communication, social interaction, repetitive behaviors, and motor skills. This research aims to develop a deep learning based model for the accurate diagnosis and classification of autistic symptoms in children, thereby benefiting both patients and their families. Existing literature indicates that classification methods typically analyze region based summaries of Functional Magnetic Resonance Imaging (fMRI). However, few studies have explored the diagnosis of ASD using brain imaging. The complexity and heterogeneity of biomedical data modeling for big data analysis related to ASD remain unclear. In the present study, the Autism Brain Imaging Data Exchange 1 (ABIDE-1) dataset was utilized, comprising 1,112 participants, including 539 individuals with ASD and 573 controls from 17 different sites. The dataset, originally in NIfTI format, required conversion to a computer-readable extension. For ASD classification, the researcher proposed and implemented a VGG20 architecture. This deep learning VGG20 model was applied to neuroimages to distinguish ASD from the non ASD cases. Four evaluation metrics were employed which are recall, precision, F1-score, and accuracy. Experimental results indicated that the proposed model achieved an accuracy of 61%. Prior to this work, machine learning algorithms had been applied to the ABIDE-1 dataset, but deep learning techniques had not been extensively utilized for this dataset and the methods implied in this study as this research is conducted to facilitate the early diagnosis of ASD.

BackgroundPlatelet-derived Growth factors play key roles in tissue repair and regeneration, yet conventional platelet-rich plasma (PRP) formulations release these mediators inconsistently in vivo due to variability in platelet yield and activation dynamics. To overcome this limitation, direct administration of concentrated platelet-derived growth factor preparations has gained interest, though current manufacturing approaches for human platelet lysate (hPL), growth factor concentrates (GFC), and conditioned serum remain constrained by batch variability, incomplete platelet degranulation, and reliance on anticoagulants. Here, we examine alternative platelet activation workflows to establish a standardized, efficient, and reproducible method for high-yield growth factor recovery suitable for translational and clinical applications. MethodsNine GFC production protocols were compared, employing different combinations of freeze-thaw (FT) cycling, glass bead (GB) agitation, calcium (Ca2) activation, and a novel Enriched Growth Factor (Enriched-GF) method. The objective was to identify a protocol capable of maximizing growth factor yield within a three-hour workflow. Optimal Ca2 concentrations and GB conditions were determined from prior optimization studies and integrated into the Enriched-GF processing scheme. Platelet concentrates (n = 10 per protocol) were processed under each condition, and growth factor levels were quantified using ELISA. ResultsGrowth factor yields differed significantly across protocols. The greatest and most consistent increases in growth factor release were observed with the Enriched-GF method combining GB activation, FT cycling, and Ca2 stimulation. This approach resulted in markedly elevated concentrations of key regenerative mediators, including enhanced EGF release, a 4.5-fold increase in PDGF, maximal TGF-{beta} liberation, and a four-fold increase in FGF2 relative to conventional platelet lysate or conditioned serum preparations. These results were reproducible across independent donor pools, demonstrating robustness and batch-to-batch consistency. ConclusionWe describe a rapid and reproducible method for producing highly concentrated platelet-derived growth factors using a combined GB-FT-Ca2 activation strategy. The Enriched-GF protocol consistently outperformed existing platelet lysate, conditioned serum, and conventional GFC preparation methods, yielding a standardized product with enhanced growth factor content. This Enriched-GF approach offers a clinically practicable solution for applications in regenerative medicine requiring reliable and high-yield growth factor delivery. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=111 SRC="FIGDIR/small/712883v1_ufig1.gif" ALT="Figure 1"> View larger version (21K): org.highwire.dtl.DTLVardef@1f059d9org.highwire.dtl.DTLVardef@9aeffforg.highwire.dtl.DTLVardef@27cd1org.highwire.dtl.DTLVardef@150b7d1_HPS_FORMAT_FIGEXP M_FIG C_FIG Schematic overview of platelet concentrate preparation from whole blood and the generation of different platelet lysates and growth factor-enriched serum using freeze-thaw, calcium gluconate, and glass bead activation methods.

IntroductionExisting saliency detection algorithms in the literature have ignored the importance of time. They create a static saliency map for the whole recording time. However, bottom-up and top-down attention continuously compete and the salient regions change through time. In this paper, we propose an unsupervised algorithm to predict the dynamic evolution of bottom-up saliency in images. MethodWe compute the variation of low-level features within non-overlapping patches of the input image. A patch with higher variation is considered more salient. We use a threshold to ignore less salient parts and create a map. A weighted sum of this map and its center of mass is calculated to provide the saliency map. The threshold and weights are set dynamically. We use the MIT1003 and DOVES datasets for evaluation and break the recording to multiple 100ms or 500ms-time intervals. A separate ground-truth is created for each interval. Then, the predicted dynamic saliency map is compared to the ground-truth using Normalized Scanpath Saliency, Kullback-Leibler divergence, Similarity, and Linear Correlation Coefficient metrics. ResultsThe proposed method outperformed the competitors on DOVES dataset. It also had an acceptable performance on MIT1003 especially within 0-400ms after stimulus onset. ConclusionThis dynamic algorithm can predict an images salient regions better than the static methods as saliency detection is inherently a dynamic process. This method is biologically-plausible and in-line with the recent findings of the creation of a bottom-up saliency map in the primary visual cortex or superior colliculus.

Preoperative prediction of disease-free survival of gastric cancer is significantly important in clinical practice. Existing studies showed the potentials of CT images in identifying predicting the disease-free survival of gastric cancer. However, no studies to date have combined deep features with radiomics features and clinical features. In this study, we proposed a model which embedded radiomics features and clinical features into deep learning model for improving the prediction performance. Our models showed a 3%-5% C-index improvement and 10% AUC improvement in predicting DFS and disease event. Interpretation analysis including T-SNE visualization and Grad-CAM visualization revealed that the model extract biologically meaning features, which are potentially useful in predicting disease trajectory and reveal tumor heterogeneity. The embedding of radiomics features and clinical features into deep learning model could guide the deep learning to learn biologically meaningful information and further improve the performance on the DFS prediction of gastric cancer. The proposed model would be extendable to related problems, at least in few-shot medical image learning. Key PointsO_LIAn integration model combining deep features, radiomics features and clinical parameters improved disease-free-survival prediction of gastric cancer by 3%-5% C-index. C_LIO_LIEmbedding radiomics and clinical features into deep learning model through concatenation and loss design improved feature extraction ability of deep network. C_LIO_LIThe model revealed disease progression trajectory and tumor heterogeneity. C_LI

O_FIG O_LINKSMALLFIG WIDTH=146 HEIGHT=200 SRC="FIGDIR/small/24319623v1_ufig1.gif" ALT="Figure 1"> View larger version (44K): org.highwire.dtl.DTLVardef@805345org.highwire.dtl.DTLVardef@db004dorg.highwire.dtl.DTLVardef@1f0cbfaorg.highwire.dtl.DTLVardef@1dfb41d_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOGraphical AbstractC_FLOATNO C_FIG HighlightsO_LIConducted a systematic review of the existing literature, focusing on Polycystic Ovary Syndrome intelligent detection, and constructed the comprehensive taxonomy for PCOS detection features to date, providing a standardized reference for future research. C_LIO_LISystematically evaluated the capabilities and limitations of current intelligent PCOS detection tools, offering valuable guidance for the development of more efficient and accurate tools. C_LIO_LIThoroughly analyzed the current status of 12 publicly available datasets used for PCOS detection, providing clear directions for future dataset development in this field. C_LIO_LIMade the analysis results publicly available, providing data resources and references for researchers, with the aim of advancing the field of intelligent PCOS detection. C_LI Recent research in the field of Polycystic Ovary Syndrome (PCOS) detection has increasingly utilized intelligent algorithms for automated diagnosis. These intelligent PCOS detection methods can assist doctors in diagnosing patients earlier and more efficiently, thereby improving the accuracy of diagnosis. However, there are notable barriers in the field of intelligent PCOS detection, including the lack of a standardized taxonomy for features, inadequate research on the current status of available datasets, and insufficient understanding of the capabilities of existing intelligent detection tools. To overcome these barriers, we propose for the first time an analytical framework for the current status of PCOS diagnostic research and construct a comprehensive taxonomy of detection features, encompassing 110 features across eight categories. This taxonomy has been recognized by industry experts. Based on this taxonomy, we analyze the capabilities of current intelligent detection tools and assess the status of available datasets. The results indicate that 12 publicly available datasets, the overall coverage rate is only 52% compared to the known 110 features, with a lack of multimodal datasets, outdated updates and unclear license information. These issues directly impact the detection capabilities of the tools. Furthermore, among the 45 detection tools require substantial computational resources, lack multimodal data processing capabilities, and have not undergone clinical validation. Based on these findings, we highlight future challenges in this domain. This study provides critical insights and directions for PCOS intelligent detection field.

Optical coherence tomography angiography is a noninvasive imaging modality to establish the diagnosis of retinal vascular diseases. However, angiography images are significantly interfered if patients jitter or blink. In this study, a novel retinal image analysis method to accurately detect blood vessels and compensate the effect of interference was proposed. We call this the patch U-Net compensation (PUC) system, which is based on the famous U-Net. Several techniques, including a better training mechanism, direction criteria, area criteria, gap criteria, and probability map criteria, have been proposed to improve its accuracy. Simulations show that the proposed PUC achieves much better performance than state-of-art methods.

Recent advances in deep learning and artificial intelligence techniques have obtained notable progress in automated embryo image analysis. However, most current research focuses on blastocyst-stage embryo evaluation (more than 5 days after in vitro fertilization), which may reduce the number of transferable embryos and increase the risk of canceled circles. Therefore, this paper aims to investigate the possibility of evaluating blastocyst development at the cleavage stage with deep neural networks (DNNs). To this end, we collect a dataset that consists of time-lapse images of more than 500 embryos (about 194k frames in total). We evaluate several widely used DNNs on the dataset, including those of single-frame architectures and multi-frame architectures. Experimental results show that the accuracy of different DNNs varies from 66.42% to 77.74% and we also provide the possible reasons behind the performance gap. Our dataset and code will be published soon to facilitate related research.

AbstractHuman pluripotent stem cell (hPSC)-derived cardiac organoid is the most recent three-dimensional tissue structure that mimics the structure and functionality of the human heart and plays a pivotal role in modeling heart development and disease. The hPSC-derived cardiac organoids are commonly characterized by bright-field microscopic imaging for tracking daily organoid differentiation and morphology formation. Although the brightfield microscope provides essential information about hPSC- derived cardiac organoids, such as morphology, size, and general structure, it does not extend our understanding of cardiac organoids on cell type-specific distribution and structure. Then, fluorescence microscopic imaging is required to identify the specific cardiovascular cell types in the hPSC-derived cardiac organoids by fluorescence immunostaining fixed organoid samples or fluorescence reporter imaging of live organoids. Both approaches require extra steps of experiments and techniques and do not provide general information on hPSC-derived cardiac organoids from different batches of differentiation and characterization, which limits the biomedical applications of hPSC-derived cardiac organoids. This research addresses this limitation by proposing a comprehensive workflow for colorizing phase contrast images of cardiac organoids from brightfield microscopic imaging using conditional Generative Adversarial Networks (GANs) to provide cardiovascular cell type-specific information in hPSC-derived cardiac organoids. By infusing these phase contrast images with accurate fluorescence colorization, our approach aims to unlock the hidden wealth of cell type, structure, and further quantifications of fluorescence intensity and area, for better characterizing hPSC-derived cardiac organoids.

Process flow diagrams like caremaps are common in clinical practice guidelines and treatment texts. However, their context is often limited to a single diagnostic or treatment event. While a method has been proposed for creating a health and disease lifecycle called the health condition timeline (HCT), that method is yet to be demonstrated for an entire health condition. This paper investigates development of an HCT for gestational diabetes mellitus (GDM), and whether the HCT and caremaps it incorporates can be used to support patient care to develop decision support tools. We show that this approach can be used to expedite development of clinical decision-support and clinician- and patient-facing applications. Caremaps, HCT and the decision support tools created with them could improve patient awareness for their condition and reduce the impact of their disease on themselves and the limited resources of our healthcare systems.

PurposeEmploy fuzzy logic to auxiliary in identification and diagnosis the gravity of diabetic retinopathy (DR). MethodsA cross-sectional study was performed, being assessed 100 diabetes mellitus patients with DR. The following ultrasound findings were measured employing a semi-quantitative punctuation method: vitreous hemorrhage, posterior vitreous detachment, epiretinal fibrosis, retinal detachment. The fundus photography (FP) aspects evaluated for diagnosis of DR were at least four or more microaneurysms with or without hard or soft exudates, and neovascularization, graded using the Early Treatment of Diabetic Retinopathy Scale. With the combination between ultrasound punctuation and FP aspects through fuzzy logic, a classification for DR has been built. ResultsMicroaneurysms were the findings which presented the better interaction with the DR severity on ultrasound, while the hard exudates showed the minors estimation errors when compared to soft exudates. A classification for DR was suggested based on the 95% confidence interval of number of microaneurysms: mild group (< 24.6); moderately mild (24.6 - 48.0); moderate (48.1 - 64.5); moderately severe (64.6 - 77.0); severe (77.1 - 92.7); and very severe (> 92.7). ConclusionBy the fuzzy logic, a DR classification was constructed supported on number of microaneurysms measurement with a simple practical application.

Early detection is key for treating those diagnosed with specific learning disorder, which includes problems with spelling, grammar, punctuation, clarity and organization of written expression. Intervening early can prevent potential negative consequences from this disorder. Deep convolutional neural networks (CNNs) perform better than human beings in many visual tasks such as making a medical diagnosis from visual data. The purpose of this study was to evaluate the ability of a deep CNN to detect students with a diagnosis of specific learning disorder from their handwriting. The MobileNetV2 deep CNN architecture was used by applying transfer learning. The model was trained using a data set of 497 images of handwriting samples from students with a diagnosis of specific learning disorder, as well as those without this diagnosis. The detection of a specific learning disorder yielded on the validation set a mean area under the receiver operating characteristics curve of 0.89. This is a novel attempt to detect students with the diagnosis of specific learning disorder using deep learning. Such a system as was built for this study, may potentially provide fast initial screening of students who may meet the criteria for a diagnosis of specific learning disorder. We wish to thank teaching assistant Karin Volovik for her assistance in gathering and processing data for this study.

BackgroundBiophysical factors such as shape and mechanical forces are known to play crucial roles in stem cell differentiation, embryogenesis and neurodevelopment. However, the complexity and experimental challenges capturing such early stages of development, and ethical concerns associated with human embryo and fetal research, limit our understanding of how these factors affect human brain organogenesis. Human cerebral organoids (hCO) are attractive models due to their ability to model important brain regions and transcriptomics of early in vivo brain development. Furthermore, they provide three-dimensional environments that better mimic the in vivo environment. To date, they have been used to understand the effects of genetics and soluble factors on neurodevelopment. Establishing links between spatial factors and hCO development will require the development of new approaches. ResultsHere, we investigated the effects of early geometric confinements on transcriptomic changes during hCO differentiation. Using a custom and tunable agarose microwell platform we generated embryoid bodies (EB) of diverse shapes and then further differentiated those EBs to whole brain hCOs. Our results showed that the microwells did not have negative gross impacts on the ability of the hCOs to differentiate generally towards neural fates, and there were clear shape dependent effects on neural lineage specification. In particular, we observed that non-spherical shapes showed signs of altered neurodevelopmental kinetics and favored the development of medial ganglionic eminence-associated brain regions and cell types over cortical regions. ConclusionsThe findings presented here suggest a role for spatial factors in brain region specification during hCO development. Understanding these spatial patterning factors will not only improve understanding of in vivo development and differentiation, but also provide important handles with which to advance and improve control over human model systems for in vitro applications.

MotivationNo biomarkers and systems, including leukocyte count and flow cytometry, can be used to measure tissue injury for diagnosing inflammation. A fixed space-time continuum (S{tau}C) biomarker can address this issue. A leukocyte continuum (LC) is a biomarker forming a S{tau}C capable of measuring injury by operators and equations for a self-operating computation. ResultsA self-operating computer (SOC) LC as a water treatment for leukocyte(s) was generated using leukocyte(s). String leukocyte continuum (StrLC), single-layer leukocyte (SLL) and multilayer leukocyte continuum (MLC) were demonstrated in various LCs using an equation with a primitive-operator. In the SOC, the LC is the inflammation graph of the operation result. The relative differential equation (RDE) shows how to recognize the LC not as a model in the conventional-other-operating-computer (cOOC), but as an actual arithmetic unit with a display unit. The SOC shows the essential nature in real time.

Diabetes Mellitus (DM) is a metabolic disorder characterized by hyperglycemia, with type 1 characterized as an autoimmune destruction of pancreatic beta cells and type 2 characterized by insulin resistance with progressive beta cell dysfunction. This study applied an existing binary classification algorithm (ALTARN) to accurately predict DM. ALTARN, as a tabular attention residual neural network, uses residual connection to find complex patterns present in tabular columns. We achieved an average training accuracy of 75.22%. Furthermore, a robust set of validation metrics was obtained via five-fold stratified cross-validation, yielding an average accuracy of 74.61%, an average precision of 72.36%, a mean recall of 79.69%, and a mean F1 score of 75.83%.