Can some algorithms of machine learning identify osteoporosis patients after training and testing some clinical information about patients?

Objective: This study was designed to establish a diagnostic model for osteoporosis by collecting clinical information from patients with and without osteoporosis. Various machine learning algorithms were employed for training and testing the model, evaluating its performance, and conducting validations to explore the most suitable machine learning algorithm.

Methods: Clinical information, including demographic data, examination results, medical history, and laboratory test results, was collected from inpatients with and without osteoporosis.

Flexible Pressure Sensors for Optimizing Pressure Garment Therapy in Periarticular Scar Treatment: Preclinical and Clinical Applications.

Pressure garment therapy is a common strategy for controlling hypertrophic scars; however, insufficient pressure due to reduced elasticity or joint movement limits its effectiveness around joints. The FlexiForce B201 pressure sensor offers precise pressure measurements, thereby demonstrating a promising solution. This study used a Bama pig scar model with an untreated group, a pressure garment group, and a pressure monitoring group that was treated with FlexiForce B201 sensors and pressure garments.

Case report: A novel intronic likely pathogenic variant (c.941+75G > T) associated with congenital eyelid coloboma in one of the identical twin sisters.

Background: Congenital eyelid coloboma (CEC) is a rare genetic disease, manifesting as a congenital partial or total defect of the eyelid. In this study, we report a pedigree with CEC caused by a novel pathogenic variant in .

Case Report: The proband was a 3-year-old girl who presented with a congenital coloboma of the left upper eyelid, accompanied by hypoplasia of the ipsilateral eyebrow.

Association between transcription factors expression and growth patterns of nonfunctioning pituitary adenomas.

Transcription factors (TFs), including steroidogenic factor-1 (SF-1), T-box transcription factor (TPIT) and pituitary transcription factor-1 (PIT-1), play a pivotal role in the cytodifferentiation of adenohypophysis. However, the impact of TFs on the growth patterns of nonfunctioning pituitary adenomas (NFPAs) remains unclear. This study aims to investigate the correlation between the expression of TFs and NFPAs growth patterns.

RNF123 inhibits cell viability, cell cycle and colony formation of breast cancer by inhibiting glycolysis via ubiquitination of PFKP.

E3 ubiquitin ligases have the potential to modulate key oncogenic pathways. RING finger protein 123 (RNF123), as an E3 ubiquitin ligase, has been functioned as a tumor suppressor. This study was designed to explore the role of RNF123 in breast cancer.

ST3GAL4 promotes tumorigenesis in breast cancer by enhancing aerobic glycolysis.

Sialyltransferases are enzymes that play a crucial role in regulating cancer progression by modifying glycoproteins through sialylation. In particular, the ST3 beta-galactoside alpha-2,3-sialyltransferase 4 (ST3GAL4) enzyme is known to be upregulated in breast cancer, but its specific biological functions have not been fully understood. This study aimed to investigate the impact and mechanisms of ST3GAL4 on aerobic glycolysis in breast cancer.

Recovering skin-nerve interaction by nanoscale metal-organic framework for diabetic ulcers healing.

Skin-nerve interaction plays an important role in promoting wound healing. However, in diabetic ulcers (DUs), the diabetic periphery neuropathy and excessive levels of reactive oxygen species (ROS) block skin-nerve interaction and further impede the DUs healing. Herein, we developed a nanoscale metal-organic framework loaded with nerve growth factor (NGF/Ce-UiO-66, denoted NGF/CU) for the treatment of DUs.

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization.

Training Deep Neural Networks (DNNs) with adversarial examples often results in poor generalization to test-time adversarial data. This paper investigates this issue, known as adversarially robust generalization, through the lens of Rademacher complexity. Building upon the studies by Khim and Loh (2018); Yin et al.

GPNMB Modulates Autophagy to Enhance Functional Recovery After Spinal Cord Injury in Rats.

Spinal cord injury (SCI) severely affects the quality of life and autonomy of patients, and effective treatments are currently lacking. Autophagy, an essential cellular metabolic process, plays a crucial role in neuroprotection and repair after SCI. Glycoprotein non-metastatic melanoma protein B (GPNMB) has been shown to promote neural regeneration and synapse reconstruction, potentially through the facilitation of autophagy.

Hybrid Electrically Conductive Hydrogels with Local Nerve Growth Factor Release Facilitate Peripheral Nerve Regeneration.

It is challenging to treat peripheral nerve injury (PNI) clinically. As the gold standard for peripheral nerve repair, autologous nerve grafting remains a critical limitation, including tissue availability, donor-site morbidity, immune rejection, . Recently, conductive hydrogels (CHs) have shown potential applications in neural bioengineering due to their good conductivity, biocompatibility, and low immunogenicity.

A law of data separation in deep learning.

While deep learning has enabled significant advances in many areas of science, its black-box nature hinders architecture design for future artificial intelligence applications and interpretation for high-stakes decision-makings. We addressed this issue by studying the fundamental question of how deep neural networks process data in the intermediate layers. Our finding is a simple and quantitative law that governs how deep neural networks separate data according to class membership throughout all layers for classification.

Operative treatment of cystic prolactinomas: a retrospective study.

Background: The optimal therapeutic approach for cystic prolactinomas remains unclear. This study aimed to evaluate the remission rates of prolactinoma patients after surgical treatment and the risk factors affecting postoperative remission in cystic prolactinoma patients.

Methods: The clinical data were retrospectively compiled from 141 patients with prolactinomas (including 41 cases of cystic prolactinomas, 21 cases of solid microprolactinomas and 79 cases of solid macroprolactinomas) who underwent transsphenoidal surgery (TSS) between April 2013 and October 2021 at the First Affiliated Hospital of Sun Yat-sen University.

Drug suspending during wound healing effectively weakens immunosuppression-related complications by preserving CD8 T cell function.

Immunosuppressive medications, which interfere with the activation and proliferation of T and B cells, increase the risk of wound healing complications. To address it, this study aimed to validate the feasibility of drug suspending during wound healing, whilst exploring the mechanisms exerted by T cells, which are important in the wound healing process. For this, a mouse skin wound model was set up.

Endogenous Electric Field-Coupled PD@BP Biomimetic Periosteum Promotes Bone Regeneration through Sensory Nerve via Fanconi Anemia Signaling Pathway.

To treat bone defects, repairing the nerve-rich periosteum is critical for repairing the local electric field. In this study, an endogenous electric field is coupled with 2D black phosphorus electroactive periosteum to explore its role in promoting bone regeneration through nerves. Scanning electron microscopy (SEM) and transmission electron microscopy (TEM) are used to characterize the electrically active biomimetic periosteum.

Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?

A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often originate from distinct yet not entirely unrelated probability distributions, and personalization is, therefore, necessary to achieve optimal results from each individual's perspective. In this paper, we show how the excess risks of personalized federated learning using a smooth, strongly convex loss depend on data heterogeneity from a minimax point of view, with a focus on the FedAvg algorithm (McMahan et al., 2017) and pure local training (i.

Photosensitive and Conductive Hydrogel Induced Innerved Bone Regeneration for Infected Bone Defect Repair.

Repairing infected bone defects is a challenge in the field of orthopedics because of the limited self-healing capacity of bone tissue and the susceptibility of refractory materials to bacterial activity. Innervation is the initiating factor for bone regeneration and plays a key regulatory role in subsequent vascularization, ossification, and mineralization processes. Infection leads to necrosis of local nerve fibers, impeding the repair of infected bone defects.

Multifunctional hydrogel loaded with 4-octyl itaconate exerts antibacterial, antioxidant and angiogenic properties for diabetic wound repair.

Cutaneous wound healing, especially diabetic wound healing, is a common clinical problem. Reactive oxygen species (ROS) and bacterial infection are two major factors in the induction of oxidative stress and inflammation, leading to impeded angiogenesis and wound healing. However, it is still very difficult to reverse the harsh microenvironment of chronic inflammation and excessive oxidative stress on diabetic wound.

Small Intestinal Submucosa Biomimetic Periosteum Promotes Bone Regeneration.

Background: Critical bone defects are a significant problem in clinics. The periosteum plays a vital role in bone regeneration. A tissue-engineered periosteum (TEP) has received increasing attention as a novel strategy for bone defect repairs.

Magnesium-based materials in orthopaedics: material properties and animal models.

As a new generation of medical metal materials, degradable magnesium-based materials have excellent mechanical properties and osteogenic promoting ability, making them promising materials for the treatment of refractory bone diseases. Animal models can be used to understand and evaluate the performance of materials in complex physiological environments, providing relevant data for preclinical evaluation of implants and laying the foundation for subsequent clinical studies. To date, many researchers have studied the biocompatibility, degradability and osteogenesis of magnesium-based materials, but there is a lack of review regarding the effects of magnesium-based materials in vivo.