Medicine in Novel Technology and Devices最新文献

{"title":"Artificial intelligence in pharmaceutical sciences: A comprehensive review","authors":"Priyanka Kandhare,&nbsp;Mrunal Kurlekar,&nbsp;Tanvi Deshpande,&nbsp;Atmaram Pawar","doi":"10.1016/j.medntd.2025.100375","DOIUrl":"10.1016/j.medntd.2025.100375","url":null,"abstract":"<div><div>The integration of artificial intelligence (AI) and machine learning (ML) into pharmaceutical sciences has catalyzed transformative advancements across drug discovery, clinical development, manufacturing, and post-market surveillance. This review comprehensively examines AI's role in modern pharmacotherapy, beginning with its historical evolution in life sciences and progressing to cutting-edge applications such as AlphaFold-driven protein modeling, natural language processing (NLP) for biomedical literature mining, and AI-augmented pharmacovigilance. Methodologically, we synthesize interdisciplinary insights from peer-reviewed literature (2013–2023), highlighting innovations in cheminformatics (e.g., QSAR, RDKit), predictive toxicology, and personalized medicine. Case studies illustrate AI's capacity to compress drug development timelines, as seen in COVID-19 repurposing efforts and <em>de novo</em> kinase inhibitor design. However, challenges persist, including algorithmic bias, regulatory ambiguities, and the “black-box” nature of deep learning models. By critically evaluating successes and limitations, this review underscores AI's potential to redefine pharmaceutical innovation while advocating for robust frameworks to ensure ethical, transparent, and clinically translatable AI deployment.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100375"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Micro-CT and histological evaluation of alveolar ridge preservation with Bio-Oss® and THE Graft®: A randomized controlled trial","authors":"Lurong Jia ,&nbsp;Tong Wang ,&nbsp;Kai Dong ,&nbsp;Quanlin Chen ,&nbsp;Chao Wang ,&nbsp;Wenjuan Zhou ,&nbsp;Zhonghao Liu","doi":"10.1016/j.medntd.2025.100377","DOIUrl":"10.1016/j.medntd.2025.100377","url":null,"abstract":"<div><div>This randomized clinical trial aimed to compare volumetric changes and histological characteristics of new bone in extraction sockets grafted with Bio-Oss® or THE Graft®. Furthermore, it sought to further assess the quality and quantity of bone regeneration at 3- and 6-month intervals. Thirty-two patients requiring single-tooth extraction (excluding third molars) and ridge preservation in preparation for subsequent implant placement were randomized to receive either graft material (Bio-Oss® or THE Graft®) covered by a collagen membrane. At 3 months, BV/TV was higher in the DBBM groups than in the DPBM groups, while mineralized bone proportions were similar between groups. By 6 months, BV/TV remained significantly higher in DPBM groups than in the DBBM groups, and a higher proportion of mineralized bone was observed in the DPBM groups. Both groups showed increasing BV/TV and mineralized bone over time. In conclusion, both Bio-Oss® and THE Graft® effectively promoted socket bone regeneration, with healing time influencing bone formation. Long-term results suggest THE Graft® may enhance mineralized bone percentage more than Bio-Oss®.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100377"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144471606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnosis of different types of single suture craniosynostosis in infants with deep learning techniques","authors":"Amir Hossein Zinati ,&nbsp;Maliheh Sabeti ,&nbsp;Hossein Kamyab ,&nbsp;Ehsan Moradi","doi":"10.1016/j.medntd.2025.100370","DOIUrl":"10.1016/j.medntd.2025.100370","url":null,"abstract":"<div><div>Craniosynostosis (CSO) is characterized by premature fusion of skull sutures in infants. This early closure of one or more main sutures can lead to various skull and facial deformities and may cause developmental delay in children. Early diagnosis, crucial for effective treatment, traditionally relies on physical examination and 3D cranial imaging, which are often inaccurate or with the risk of X-ray exposure. This study presents a fully-automated deep learning-based method for diagnosing common types of single suture CSO using routine digital photographs of infants' heads. We employed a two-stage approach involving head segmentation and CSO type classification. First, mask region-based convolutional neural network (Mask R-CNN) was used for accurate head segmentation, achieving an average precision of 97.60 ​% and an average recall of 96.20 ​%. The segmented images were then classified into different CSO types using a modified VGG11 neural network. The classifier attained a training accuracy of 99.74 ​% and a test accuracy of 94.44 ​%, with high sensitivity and specificity for uni-coronal, metopic, and sagittal types. Our method illustrates high reliability and accuracy, offering non-invasive, accessible and accurate diagnostic instrument for early detection and patient screening.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100370"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144239833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mouse stem cell derived-synthetic embryo models: a tool to study early embryo development","authors":"Jianwen Li,&nbsp;Zhaotong Lin,&nbsp;Yixuan Yao,&nbsp;Jing Du","doi":"10.1016/j.medntd.2025.100393","DOIUrl":"10.1016/j.medntd.2025.100393","url":null,"abstract":"<div><div>Different stem cells can be aggregated to promote development into synthetic embryo in vitro culture systems, providing a clear understanding of early embryonic development. Recent researches indicate that with the advancement of culture conditions, stem cells can self-organize to entire synthetic embryos closely resembling natural embryos, and recapitulate essential events in the embryonic development process, even neurulation and early organogenesis. Here, we provide a comprehensive overview of the cellular characteristics of stem cells and research progress of synthetic embryos, and further discuss the challenging issues that need to be solved. Therefore, synthetic embryo has significant applicational value in the field of embryonic development and stem cell biology.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100393"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144907098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Additive manufacturing in bone science: A cutting-edge review of its potential and progress","authors":"Md Shakil Chowdhury ,&nbsp;Md Shah Oliullah ,&nbsp;Md Zisat Hossen ,&nbsp;Mehedi Hasan Manik ,&nbsp;MD Abu Hurayra ,&nbsp;Md. Zobair Al Mahmud ,&nbsp;Nayem Hossain ,&nbsp;Md Hosne Mobarak ,&nbsp;Md Didarul Islam","doi":"10.1016/j.medntd.2025.100379","DOIUrl":"10.1016/j.medntd.2025.100379","url":null,"abstract":"<div><div>In the medical industry, additive manufacturing, or AM, sometimes referred to as 3D printing, has completely changed bone regeneration and healing. With the use of this technology, complex scaffolds and implants that nearly resemble natural bone structures may be created. Orthopedic patient-specific solutions may be created by utilizing a variety of AM processes, including as fused deposition modeling, stereolithography, and selective laser sintering. Compared to conventional bone grafting techniques, AM lowers risks while promoting cellular development, differentiation, and osseointegration. When bioactive chemicals are used with biocompatible materials like metals, ceramics, and polymers, bone tissue engineering becomes even more effective. The potential of AM in bone regeneration is reviewed in this research along with an analysis of its uses, benefits, and new materials. Issues including material constraints, expenses, and regulatory issues are discussed, and suggestions for more study are included. AM has the potential to significantly improve clinical procedures and patient outcomes by revolutionizing the fields of bone tissue engineering and orthopedic implants.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100379"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Constant and cyclic shear stress regulate collagen fibers self-assembly","authors":"Chunyang Ma ,&nbsp;Shuaiyin Liu ,&nbsp;Jiangxue Wang ,&nbsp;Xiaolin Guo ,&nbsp;Yixing Ren ,&nbsp;Xufeng Niu","doi":"10.1016/j.medntd.2025.100384","DOIUrl":"10.1016/j.medntd.2025.100384","url":null,"abstract":"<div><div>Collagen fibers are a key structural component in the plaques of atherosclerosis (AS), playing a vital role in regulating plaque stability. Investigating the factors that affect collagen fiber self-assembly and their mechanisms not only aid in assessing disease risk but also provide a theoretical basis for developing new therapeutic strategies. In this study, the plaque development patterns of high-fat diet fed ApoE^−/− mice were observed, and an in vitro simulation system was constructed to conduct further research. Experimental findings indicate that the application of constant shear stress is detrimental to collagen self-assembly, and the hindrance effect increases with the magnitude of the shear stress. Periodic shear stress exhibits a dual effect on collagen fiber self-assembly. Although the applied shear stress partially impedes the assembly process, it also disrupts structural networks that inhibit collagen organization, thereby enabling continued assembly. Compared to constant shear stress, periodic shear stress is more conducive to collagen fiber growth. These results deepen the understanding of collagen self-assembly and provide new theoretical foundations for disease treatment.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100384"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144595728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MBTC-Net: Multimodal brain tumor classification from CT and MRI scans using deep neural network with multi-head attention mechanism","authors":"Satrajit Kar,&nbsp;Pawan Kumar Singh","doi":"10.1016/j.medntd.2025.100382","DOIUrl":"10.1016/j.medntd.2025.100382","url":null,"abstract":"<div><div>Brain tumors pose a singularly formidable threat in contemporary healthcare due to their diverse histological profiles and unpredictable clinical behavior. Their spectrum ranges from slow-growing benign tumors to highly aggressive malignancies in sensitive anatomical locations. This necessitates an intensified focus on their pathophysiology and demands precise characterization for patient-specific therapeutic solutions. Techniques to correctly identify brain tumors using artificial intelligence are often employed for addressing segmentation and detection tasks; however, the lack of generalizable results hinders medical practitioners from incorporating them into the diagnostic process. Predominantly reliant on Magnetic Resonance Imaging, research on other imaging methods like Positron Emission Tomography &amp; Computed Tomography, is scarce due to a dearth of open-access datasets. Our study proposes a robust MBTC-Net framework by leveraging EfficientNetV2B0 for extracting high-dimensional feature maps, followed by reshaping into sequences and applying multi-head attention to capture contextual dependencies. After reintroducing the attention output into a spatial structure, we perform average pooling before transitioning to dense layers, enhanced with batch normalization and dropout. The model is fine-tuned with the Adamax optimizer to classify various kinds of brain tumors using softmax from T1-weighted, T1 Contrast-Enhanced, &amp; T2-weighted MRI sequences and CT scans. To reduce the risk of overfitting, measures such as stratified 5-fold cross-validation have been extensively implemented across 3 open-access Kaggle datasets, obtaining 97.54 ​% (15-class), 97.97 ​% (6-class), and 99.34 ​% (2-class) accuracies, respectively. We have also applied Grad-CAM to decipher and visually analyze the predictions made by this framework. This research underscores the need for multimodal training of CT scans and MRI sequences for deploying a sturdy framework in real-time environments and advancing the well-being of patients.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100382"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Peripheral hemodynamic effects of synchronizing intermittent compression with cardiac pulsation","authors":"Chenxiao Huang ,&nbsp;Pengyu Guo ,&nbsp;Ruya Li ,&nbsp;Yubo Fan","doi":"10.1016/j.medntd.2025.100388","DOIUrl":"10.1016/j.medntd.2025.100388","url":null,"abstract":"<div><div>Intermittent pneumatic compression (IPC) is a noninvasive therapy choice for patients with peripheral arterial diseases, which typically inflates cuffs with a fixed compression period to facilitate peripheral perfusion. The fixed compression period ignores the synergistic effect between human cardiac pulsation and external intermittent compression, limiting the potential of IPC therapy. Meanwhile, existing IPC devices cannot directly assess peripheral perfusion in the target lower limb to provide feedback for adjusting treatment parameters and improving therapeutic efficacy. This work develops a cardiac cycle-synchronous IPC prototype, featuring an innovative flexible perfusion sensor module that enables real-time synchronization of compression with local blood perfusion distribution. By continuously monitoring peripheral perfusion distribution, the system adjusts compression timing based on real-time data, offering enhanced therapeutic efficacy compared to traditional fixed-period IPC treatments. We compare the therapeutic efficacy between an asynchronous mode and three cardiac cycle-synchronous modes. The results of on-body experiments show that the systole synchronous mode outperforms other modes, significantly improving the peripheral perfusion index (PPI) and augmentation index compared to the resting state. On the control side, the PPI had no significant difference between rest and treatment phase, which suggests that IPC treatment would not damage the peripheral blood perfusion on other body parts. The developed cardiac cycle-synchronous IPC prototype demonstrates that a good synchronization between the compression and the cardiac cycle might bring better therapeutic efficacy. The proposed prototype and the exploration of cardiac cycle-synchronous IPC therapy strategies are conducive to the development of non-invasive and intelligent therapies.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100388"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144766659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synergistic laser and haptic therapy for pain relief and muscle relaxation of forearm flexors","authors":"Allwyn Gnanadas ,&nbsp;Immanuvel Jashper ,&nbsp;Muthuraj B ,&nbsp;Sivashanmugam M","doi":"10.1016/j.medntd.2025.100390","DOIUrl":"10.1016/j.medntd.2025.100390","url":null,"abstract":"<div><div>—In the realm of pain relief and therapy treatment, traditional single modality treatment approaches do not suffice in offering meaningful and long-lasting therapeutic effects. A modified treatment method with the laser and haptic activations within a single, hand-held device to enhance the synergistic effect during treatment is designed. It has been established that a laser, either red or infrared, is effective for promoting collagen synthesis and healing wounds by utilizing light to alter chemical and structural components at the cellular level. Alternatively, muscles are made to relax and blood flow is enhanced by apt haptic stimulation of blood circulation through proper placement of the inducing electrode. The combination therapy device merges these modalities into a ‘therapy gun’ that proves to be very effective. Though the comprehensive study and effect of the entire musculature is very cumbersome, we have focused on the most commonly used muscle groups, the flexor muscles of the forearm. The results are tested and validated using multiple biosignal study including electromyography (EMG) and endodermal activity (EDA) and the muscle load activities manipulated from the EMG. The intensity and time of treatment shall be changed depending on the patient's requirements. Post-treatment, following therapy, the EMG results showed a marked reduction in muscle activation, with an MVC of 1.350 ​mV and a decrease in RMS values, reflecting muscle relaxation. The PSD of the EMG signal shifted towards lower frequencies, confirming reduced muscle activity. Similarly, post-treatment EDA results demonstrated a decrease in skin conductance, with values stabilizing around 4.976 ​S, reflecting a return to baseline levels of physiological arousal. The histogram and PSD of the EDA signal showed a shift towards lower frequencies, consistent with the calming effects of the vibration therapy.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100390"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Medicine in novel technology and devices quantitative study and evaluation of ankle joint motor-cognitive dual-task post-stroke using eye-tracking technology","authors":"Yutong Feng ,&nbsp;Hongbei Meng ,&nbsp;Zihe Zhao ,&nbsp;Xiaomeng Wang ,&nbsp;Xiaoxue Zhai ,&nbsp;Yansong Hu ,&nbsp;Guanyu Wang ,&nbsp;Bo Peng ,&nbsp;Wenyu Yang ,&nbsp;Xuemeng Li ,&nbsp;Wenxin Tao ,&nbsp;Shuo Gao ,&nbsp;Yu Pan","doi":"10.1016/j.medntd.2025.100387","DOIUrl":"10.1016/j.medntd.2025.100387","url":null,"abstract":"<div><div>Dual-task ability is crucial for daily life, but sensory, cognitive, and motor impairments often reduce performance in patients, significantly impacting their quality of life. To evaluate and restore this ability, this study proposes an eye-tracking-based dual-task training system for ankle movement and cognition. The system is designed to capture and analyze real-time ankle and eye movement parameters, integrating these with traditional clinical scales to offer a multidimensional, objective, and quantitative evaluation standard. Reliability and criterion validity analyses involving 20 healthy adults and 30 stroke patients demonstrated that 88.2 ​% of the evaluation parameters exhibited high consistency, with 55.8 ​% showing a moderate correlation with clinical benchmark scales (p ​&lt; ​0.05). Notably, the Montreal Cognitive Assessment (MOCA), dual-task cost percentage, and TUG-subtraction task duration were identified as key indicators of dual-task ability, while the Self-Rating Anxiety Scale showed lower sensitivity. Furthermore, foot and ankle motion parameters exhibited a strong correlation with balance and fall risk, effectively serving as predictors of motor function recovery and fall risk in stroke patients. The system provides an innovative, quantitative tool for assessing lower limb dual-task ability, facilitating the identification of dual-task performance differences among stroke patients. It supports the development of evidence-based rehabilitation strategies, with the potential to enhance long-term functional recovery and improve patients' quality of life.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100387"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}