Approach For Diagnosis Research Articles

Wavelet-Convolutional Neural Network: An Improved Deep Learning Model for Breast Cancer Detection from Histopathology Images

Background: Invasive ductal carcinoma (IDC) is a prevalent type of breast cancer with significant mortality rates. Early detection is crucial for effective treatment options. Deep learning techniques have shown promise in medical image analysis, but further improvements are needed. Methods: A Wavelet-Convolutional Neural Network (WCNN) is proposed, incorporating wavelet filters and convolutional filters in each layer to capture both frequency and spatial domain features. The processed images resulted from both types of filters are combined and passed through a MaxPooling layer to extract salient features. Four such hybrid layers are considered for extracting effective features. This novel approach allows the model to effectively learn multi-scale representations, leading to improved performance in breast cancer classification tasks. The model was trained and evaluated on a publicly available breast histopathology image dataset. Results: The proposed WCNN achieved a classification accuracy of 98.4% for breast cancer detection, outperforming existing state-of-the-art models. Conclusion: The WCNN framework demonstrates the potential of combining wavelet and convolutional filters for improved breast cancer detection, offering a promising approach for early diagnosis and better patient outcomes.

Advancements in Diagnosis and Treatment of Cardiac Sarcomas: A Comprehensive Review.

Cardiac sarcomas are rare, aggressive malignancies originating from various cardiac cell types, presenting significant challenges in both diagnosis and treatment. This comprehensive review explores recent advancements in diagnosis and treatment of cardiac angiosarcoma, fibrosarcoma, leiomyosarcoma, and rhabdomyosarcoma. And we briefly discuss the exceedingly rare occurrence of cardiac osteosarcoma and present our perspectives on its treatment. Development of these tumors is influenced by genetic mutations, environmental factors, and chromosomal abnormalities, necessitating a multidisciplinary approach for accurate diagnosis and management. Advanced imaging techniques, biomarkers, and immunohistochemical analysis assist in confirming the diagnosis and guiding treatment decisions. Surgical resection, adjuvant therapies, and personalized treatment strategies based on genetic profiling offer promising avenues for improving patient outcomes. Emerging therapeutic approaches, such as targeted therapies and immunotherapies, have shown promising progress in recent years. Despite these advancements, the prognosis for patient with cardiac sarcomas remains poor, highlighting the urgent need for continued research to refine treatment methods and enhance long-term survival outcomes. Ongoing efforts and clinical trials are essential for advancing the management of these rare and aggressive tumors, ultimately improving quality of life for affected patients.

The Interconnection between Obstructive Sleep Apnea and Persistent Atrial Fibrillation: Pathophysiology, Clinical Implications, and Management Strategies

Obstructive sleep apnea (OSA) is a prevalent sleep disorder characterized by intermittent upper airway obstruction, resulting in recurrent hypoxemia, hypercapnia, and sleep fragmentation. Emerging evidence highlights a significant association between OSA and persistent atrial fibrillation (AF), a complex arrhythmia with substantial morbidity and mortality. This relationship is underpinned by multifaceted pathophysiological mechanisms, including autonomic nervous system dysregulation, structural and electrical cardiac remodeling, systemic inflammation, and heightened oxidative stress. Patients with coexistent OSA and AF exhibit a more challenging clinical course with higher rates of arrhythmia recurrence and resistance to conventional therapies such as antiarrhythmic drugs and catheter ablation. This review explores the intricate interplay between OSA and persistent AF, emphasizing the role of continuous positive airway pressure (CPAP) therapy in modifying arrhythmogenic risk and improving cardiovascular outcomes. Furthermore, the article discusses the importance of multidisciplinary approaches for diagnosis and management, integrating cardiological and sleep medicine perspectives. Understanding this bidirectional relationship is crucial for tailoring therapeutic strategies aimed at mitigating the burden of AF in patients with OSA.

A STUDY OF IMPACT OF CBNAAT IN THE DIAGNOSIS OF TUBERCULOSIS AT A RURAL BASED TERTIARY CARE TEACHING CENTRE IN INDIA

Introduction: India has the highest number of TB cases in the world and it kills more adults than any other infectious disease. The Whole genome sequencing (WGS) and its utility product the GeneXpert MTB/RIF was adopted as integral part of NTEP for quick diagnosis of MTB with resistance to rifampine. Aim & Objective: To assess the impact of CBNAAT on the other modalities i.e. smear microscopy and conventional culture and sensitivity. Material Method: This is a prospective observational, cohort study conducted at RDGMC Ujjain, MP with an enrollment of 200 cases (150 PTB and 50 EPTB) that underwent all the three investigations to fulfill inclusion criteria after a prior approval of the ethic committee and patients consent. Result: Most the cases were in productive age group of and about 66% cases had low BMI and required nutritional support. The Microscopic sensitivity and specificity were 43% and 100% as against 97% and 90% that of CBNAAT. Discussion: The yield of CBNAAT is superior and promising in smear negative, EPTB and immuno-compromised cases being of pauci bacilli status. A meticulous investigation is required for those cases that are smear positive but CBNAAT negative cases for the presence of NTM infection. A CBNAAT reporting that of very low and indeterminate is to be repeated and supportive/ or additional clinical and or radiologic findings should be incorporated. Conclusion: CBNAAT should be mandatory for the entire suspect TB cases especially for EPTB, children and immune-compromised individuals. CBNAAT has certain limitations i.e. it cannot detect drug resistance other than rifampin and non tubercular mycobacterium (NTM). The best approach for diagnosis of EPTB is to combined CBNAAT, histopathology and AFB culture. However the conventional culture and sensitivity with LJ media is gold standard cannot be over looked.

Origin and In-Office Treatment of Retrograde Cricopharyngeus Dysfunction.

Retrograde cricopharyngeus dysfunction (R-CPD) is an emerging disorder associated with disabling symptoms. The origin of R-CPD remains unknown. To investigate the development of symptoms, diagnosis approach, and therapeutic outcomes of R-CPD in patients treated with in-office botulinum toxin injection (BTI) into the cricopharyngeus. This was a case series including patients with R-CPD who were consecutively and prospectively recruited from April 2022 to May 2024 in an academic hospital. Semistructured interviews were conducted to collect and analyze data on each patient's clinical history, potential causes or factors associated with R-CPD development, diagnostic approaches, and symptom presentation. Clinic-based (in-office) BTI into the cricopharyngeus. Associations with laryngopharyngeal reflux disease, patients' Reflux Symptom Score-12 (RSS-12), and BTI effectiveness, revisions, and complications were evaluated. The case series comprised 106 patients with R-CPD treated with BTI (52 females [49.1%] and 54 males [51.9%]). Their mean (SD) age at symptom onset was 13.6 (7.7) years, and at diagnosis, 30.4 (6.4) years. Sixty-eight patients (64.2%) had potential congenital R-CPD, according to the parents' testimonies. A family history was reported in 18 of 62 cases (29.0%). In 105 cases (99.1%), patients made the diagnosis themselves despite medical consultations (n = 162), empirical treatments (n = 113), and additional examinations (n = 92). The cumulative success rate of BTI was 90.6% (96 of 106 patients). In 26 cases (24.5%), additional injections were administered to address the symptoms. Family history of R-CPD was a negative predictor of single-BTI success. Dysphagia was the primary adverse effect occurring after 89 of 126 BTIs (70.6%) and lasted a mean (SD) of 16.3 (12.0) days. In 10 cases, operating-room BTI was administered after primary in-office BTI. R-CPD is an emerging and poorly known disorder associated with high rates of ineffective consultations, additional examinations, and self-diagnosis by patients. In-office BTI was associated with a high rate of partial or total symptom relief and long-term effectiveness.

P-1974. Surface Protein Profiling of Extracellular Vesicles: A Novel Biomarker Approach for Long COVID Diagnosis?

Abstract Background Extracellular vehicles (EVs) are lipid bilayer vesicles secreted by all cell types into the circulation. EVs carry an array of biomolecules indicative of their origin cells and act as cargo vesicles capable of delivering proteins, mitochondria, and viral particles. However, whether long COVID affects the profile of plasma EVs remains unknown. Methods Plasma samples were selected from the Stanford repositories of Long COVID participants—seventy-six plasma samples from patients with documented SARS-CoV-2 infection. Twenty-five participants had full recovery (10 months post-infection, Stanford Lambda Trial), 24 patients with Long COVID with CFS phenotype and 27 with ME/CFS from the Stanford Long COVID clinic. Plasma EVs were isolated using size-exclusion columns (qEV, Izon Science). The positivity for surface markers and mitochondrial membrane potentials of the plasma EVs were evaluated by flow cytometry. Samples were stained with pre-titrated volumes of the following fluorochrome-conjugated monoclonal antibodies: CD45 leukocytes, CD3/T cells, CD20/B cells, CD14/Monocytes, CD16/NK cells, CD144/endothelial cells, CD41a/Platelets, CD56/neural cell adhesion molecule (NCAM), and Mitotracker deep red/mitochondrial membrane potential. Results The total EV counts and the proportion of mitochondria-positive were decreased in Long COVID group compared to the COVID recovery group (5.02 x 106 vs. 1.92 x 107 /mL, and 42.7 vs. 56.7%, respectively). Compared with the recovery group, Monocyte and NK cell-derived EVs were significantly increased, whereas Endothelial cell-derived EVs were decreased in the Long COVID group. The EVs from the Long COVID group consistently exhibited lower positivity of mitochondrial membrane potential regardless of the parental cells. No difference was observed in plasma EVs derived from NCAM positive cells. NK cell proportion is the only difference between LC/CSF and CSF (P= 0.046). Conclusion Patients with Long COVID showed alterations in plasma EV profiles. These findings may offer insights into the pathogenesis of long COVID. Disclosures All Authors: No reported disclosures

Adrenal Venous Sampling in the Investigation of Hyperaldosteronism: A Retrospective Practice Review from a Large Academic Medical Center.

Hyperaldosteronism involves complex, multidisciplinary management, including clinical testing, radiological exams, and adrenal venous sampling (AVS). This study assesses AVS outcomes at a large referral center, focusing on cannulation success, lateralization of aldosterone-producing adenomas, and correlation with radiological and surgical findings. A retrospective review of 153 patients who underwent AVS from September 2016 to January 2024 was conducted. Data included aldosterone and cortisol levels, procedural details, and outcomes. AVS success was determined by aldosterone-to-cortisol ratios and cortisol levels confirming adequate cannulation. Of the 153 patients, 49.9% had lateralized adenomas (51.3% left, 48.7% right), while 39.9% had bilateral adrenal hyperplasia. In 10.8% of cases, AVS was inconclusive or unsuccessful. Right adrenal vein cannulation required more attempts due to anatomical challenges. Aldosterone levels were higher in right adrenal adenomas compared to left, though cortisol levels did not predict laterality or hyperplasia. There was strong concordance between AVS, radiological, and surgical findings, except for bilateral hyperplasia cases. This large series highlights AVS's central role in diagnosing hyperaldosteronism, with significant insights into cannulation challenges and biochemical correlations. The study underscores the importance of a multidisciplinary approach for accurate diagnosis and effective management.

EEG-derived brainwave patterns for depression diagnosis via hybrid machine learning and deep learning frameworks

In the fields of engineering, science, technology, and medicine, artificial intelligence (AI) has made significant advancements. In particular, the application of AI techniques in medicine, such as machine learning (ML) and deep learning (DL), is rapidly growing and offers great potential for aiding physicians in the early diagnosis of illnesses. Depression, one of the most prevalent and debilitating mental illnesses, is projected to become the leading cause of disability worldwide by 2040. For early diagnosis, a patient-friendly, cost-effective approach based on readily observable and objective indicators is essential. The objective of this research is to develop machine learning and deep learning techniques that utilize electroencephalogram (EEG) signals to diagnose depression. Different statistical features were extracted from the EEG signals and fed into the models. Three classifiers were constructed: 1D Convolutional Neural Network (1DCNN), Support Vector Machine (SVM), and Logistic Regression (LR). The methods were tested on a dataset comprising EEG signals from 34 patients with Major Depressive Disorder (MDD) and 30 healthy subjects. The signals were collected under three distinct conditions: TASK, when the subject was performing a task; Eye Close (EC), when the subject’s eyes were closed; and Eye Open (EO), when the subject’s eyes were open. All three classifiers were applied to each of the three types of signals, resulting in nine (3 × 3) experiments. The results showed that TASK signals yielded the highest accuracies of 88.4%, 89.3%, and 90.21% for LR, SVM, and 1DCNN, respectively, compared to EC and EO signals. Additionally, the proposed methods outperformed some state-of-the-art approaches. These findings highlight the potential of EEG-based approaches for the clinical diagnosis of depression and provide promising avenues for further research. Additionally, the proposed methodology demonstrated statistically significant improvements in classification accuracy, with p-values < 0.05, ensuring robustness and reliability.

Evaluation Of Diagnosis And Treatment Approaches Related To Iron Deficiency Of Family Physicians

Background Anaemia is defined by the World Health Organization (WHO) as a hemoglobin value below 13 g/dL in men and 12 g/dL in women. It is a serious public health problem that can significantly affect the quality of life. Methods Our study, whose universe consists of family physicians who actively work in family health centers in Rize province, was conducted in 2021. After being informed about our study, 81 family physicians who agreed to participate voluntarily were included. Results Our research is a cross-sectional descriptive type of research. A 20-question survey prepared by scanning the literature was presented as a data collection tool. While 73 (90.1%) participants are general practitioners, 8 (8.9%) are family medicine specialists. The rate of physicians correctly knowing the ferritin value to diagnose iron deficiency anemia in a patient without acute infection was 70.4% (n: 57). After the diagnosis of iron deficiency anemia, physicians recommended gastrointestinal system screening in 39.5% (n: 32) of all men and 87.7% (n: 71) of postmenopausal women. The rate of recommending treatment for 3-6 months after the hemoglobin level returned to normal was 93.8% (n: 76). Conclusion Based on the data we obtained, it was seen that family physicians’ knowledge level about iron deficiency anemia management was insufficient, and there were deficiencies in the diagnosis and treatment processes. For this reason, interactive, applied training programs should be organized.

P-749. Prognostic Determinants in Patients with Necrotizing Fasciitis in a Referral Hospital in Nicaragua

Abstract Background Necrotizing fasciitis is a serious condition in which timely diagnosis and therapeutic approaches, both medical and surgical, play an essential role in prognosis. In Nicaragua, the prognostic determinants for this clinical condition in different hospital institutions have not been formally evaluated. The aim of this study was to establish factors that could be determinant for the prognosis of patients with necrotizing fasciitis in a national referral hospital.Table 1.Organ Failure at the Admission in Patients with Necrotizing Fasciitis Methods This is a retrospective, cross-sectional, analytical study. It was conducted with patients over 15 years of age with a diagnosis of necrotizing fasciitis hospitalized between January 201 and December 2023 in Dr. Fernando Vélez Paiz Hospital in Managua, Nicaragua. Clinical factors such as comorbidities or organ failure on admission, as well as the LRINEC score, and the times of administration of the first dose of antibiotic and surgical intervention were analyzed and correlated with the clinical outcome of the patients.Table 2.Potentials Prognosis Determinants in Necrotizing Fasciitis that were Evaluated Results A total of 45 patients were included in the study, 60% of whom were women. The mean age was 56.0 ± 14.6 years-old. 86.7% of patients had at least one comorbidity. At the time of diagnosis, 31.1% of patients had renal insufficiency, 24.4% had shock, and 15.6% had altered state of consciousness (Table 1). 25 patients died for a mortality rate of 44.4%. The mean time from suspected diagnosis and administration of the first dose of antibiotics was 2.5 ± 1.4 hours (Table 2). Only 20% of patients received the first dose of the antibiotic at the first hour. 17.8% of patients underwent surgery within 6 hours of diagnosis. There was no association between prognosis and the time of initiation of antibiotic therapy and the time of initiation of surgical treatment after diagnosis of necrotizing fasciitis, probably due to a problem of sample size. 60% of the deceased had LRINEC ≥ 8 points, while only 28% in the group of survivors, OR(95%CI): 3.85 (1.10-13.46) (Table 3).Table 3.LRINEC and Mortality in Patients with Necrotizing Fasciitis Conclusion Patients with necrotizing fasciitis mostly have comorbidity, mainly diabetes, and almost a quarter of them have shock and a third have renal failure. A LRINEC score greater than or equal to 8 points significantly increases the risk of death in this type of patient. Disclosures All Authors: No reported disclosures

APD-L1-facilitated theranostic and tumor microenvironment remodeling of pancreatic cancer via docetaxel-loaded phase-transformation nanoparticles triggered by low-intensity pulsed ultrasound

Early diagnosis of pancreatic ductal adenocarcinoma (PDAC) is challenging because of its depth, which often leads to misdiagnosis during ultrasound examinations. The unique PDAC tumor microenvironment (TME) is characterized by significant fibrous tissue growth, and high interstitial pressure hinders drug penetration into tumors. Additionally, hypoxia and immune suppression within the tumor contribute to poor responses to radiotherapy and chemotherapy, ultimately leading to an unfavorable prognosis. In this study, aPD-L1-modified docetaxel and perfluoropentane-loaded liquid‒vapor phase-transformation lipid nanoparticles (aPDL1-DTX/PFP@Lipid) were synthesized and had an average diameter of 61.63 nm with 84.3% antibody modification. We demonstrated that the nanoparticles (NPs) exhibited excellent PDAC-targeting capabilities both in vitro and in vivo. Upon exposure to low-intensity pulsed ultrasound (LIPUS) stimulation, the NPs underwent a phase transformation to form microbubbles with substantial molecular ultrasound diagnostic effects, and combined treatment resulted in a tumor growth inhibition rate of 88.91%. This treatment strategy also led to the infiltration of CD8+ T cells, the downregulation of Treg cells, the promotion of M1 macrophage polarization, the inhibition of fibrosis to reduce tumor stromal pressure, and the facilitation of perfluoropentane (PFP) gasification to release O2 and improve tumor hypoxia. In conclusion, aPD-L1-modified liquid‒vapor phase-transformation nanoparticles loaded with docetaxel (DTX) and PFP were successfully combined with ultrasound for the molecular diagnosis and targeted treatment of PDAC. aPDL1-DTX/PFP@Lipid could reshape the PDAC TME, offering a new approach for ultrasound-mediated diagnosis and treatment with promising clinical applications.Graphical

Novel Winding Method for Enhanced Fault Diagnosis of IPMSMs Using Variable Reluctance Resolvers and Improved Robustness

Recently, the rapid proliferation of eco-friendly mobility solutions has driven an increasing demand for high-efficiency, high-power, compact, and reliable traction motors. In the eco-friendly mobility sector, electric mobility commonly employs Interior Permanent Magnet Synchronous Motors (IPMSMs) due to their high efficiency, high power, and compact size. However, ensuring reliability requires effective fault diagnosis. Among various faults, eccentricity in traction motors can degrade performance characteristics, including vibration, noise, and torque precision, thereby impairing driving performance. This paper proposes a novel winding method for Variable Reluctance (VR) resolvers and introduces a fault diagnosis approach for eccentricity using Finite Element Method (FEM) analysis. By employing this novel winding method, the direction of eccentricity occurrence can be effectively identified. Additionally, this method demonstrates robustness against defects, such as open-circuit faults, compared to a conventional winding method. Therefore, the proposed winding method contributes to improving the reliability and stability of IPMSMs through fault diagnosis and ensures robustness against open-circuit faults in the VR resolver.

Potential Effects of Statistical complexity measure in improving the fault diagnosis performance under speed fluctuations

Abstract Many research studies are performed in extracting non-stationary signal properties such as instantaneous frequency (IF) and envelope to diagnose machinery faults under time-varying speed conditions. But accurate IF extraction is difficult from such complex fluctuating signals to identify the faults efficiently. Therefore, this paper proposes the Statistical Complexity Measure (SCM) as a feature that evaluates the randomness and complexity without any additional requirement, providing an outstanding result in multi-component fault detection under speed fluctuations. Primarily, the influence of SCM is proved by ranking the features with the help of the Random Forest (RF) algorithm. The fault classification of individual signal characteristics confirms its ranking order as well. Then, it is targeted towards the efficacy of the signal fusion approach in multicomponent fault diagnosis. Focusing on the essence of SCM, it is merged with the other three signal properties based on the ranking technique to investigate which one of the feature compositions is more advantageous. The machine learning classifier, SVM-RBF, achieves 94.7%, which proves the potential effects of SCM features in the industrial rotational machinery component under variable speed operating conditions.

ILC3 Function as a Double-Edged Sword in EV71 Infection

Enterovirus 71 (EV71) is a common pathogen responsible for hand, foot, and mouth disease (HFMD), leading to severe neurological complications and even death. However, the mechanisms underlying severe EV71-induced disease remain unclear, and no effective specific treatments are available. In this study, we successfully infected mice of different ages using a mouse-adapted EV71 strain, resulting in disease and mortality. We compared immune system responses between infected and uninfected mice of different ages to identify key pathogenic targets during EV71 infection. Our findings revealed that the level of Group 3 Innate Lymphoid Cells (ILC3s) in mice negatively correlated with the severity of disease induced by EV71 infection. We conducted anti-ILC3 cytokine injections and cytokine neutralizing antibody experiments on 14-day-old EV71-infected mice. The results showed that the cytokine IL-17 secreted by ILC3 cells had a mild protective effect, while IL-22 promoted inflammatory responses. Our research demonstrates that ILC3 cells play a dual role in EV71 infection. These findings not only clarify key immune factors in the progression of EV71-induced disease but also provide a promising approach for the early diagnosis and treatment of severe EV71 infections.

GenAI synthesis of histopathological images from Raman imaging for intraoperative tongue squamous cell carcinoma assessment

The presence of a positive deep surgical margin in tongue squamous cell carcinoma (TSCC) significantly elevates the risk of local recurrence. Therefore, a prompt and precise intraoperative assessment of margin status is imperative to ensure thorough tumor resection. In this study, we integrate Raman imaging technology with an artificial intelligence (AI) generative model, proposing an innovative approach for intraoperative margin status diagnosis. This method utilizes Raman imaging to swiftly and non-invasively capture tissue Raman images, which are then transformed into hematoxylin-eosin (H&E)-stained histopathological images using an AI generative model for histopathological diagnosis. The generated H&E-stained images clearly illustrate the tissue’s pathological conditions. Independently reviewed by three pathologists, the overall diagnostic accuracy for distinguishing between tumor tissue and normal muscle tissue reaches 86.7%. Notably, it outperforms current clinical practices, especially in TSCC with positive lymph node metastasis or moderately differentiated grades. This advancement highlights the potential of AI-enhanced Raman imaging to significantly improve intraoperative assessments and surgical margin evaluations, promising a versatile diagnostic tool beyond TSCC.

Near-Infrared Photothermally Assisted Nanoprobes Boost Signal Amplification for Fluorescence Imaging and Urinalysis of Tumor.

Early diagnosis of tumors allows effective treatment of primary cancers through localized therapeutic interventions. However, developing diagnostic tools for sensitive, simple, and early tumor (especially less than 2 mm in diameter) detection remains a challenge. Herein, we presented a biomarker-activatable nanoprobe that enabled a near-infrared (NIR) photothermally amplified signal for fluorescence imaging and urinalysis of tumor. This activatable nanoprobe was constructed by encapsulating renal-clearable NIR ZW800 dyes into a CuS@mSiO2 core-shell nanoparticle with hyaluronic acid. The nanoprobes could accumulate at the tumor site and respond to tumor-associated hyaluronidase, undergoing in situ enzyme-catalyzed decapsulation to release renal-clearable ZW800 dyes for fluorescence imaging and uranalysis of tumor in living mice. Notedly, with the aid of NIR laser irradiation, the photothermal effect of CuS core boosted signal amplification for tumor diagnosis via photothermally enhanced ZW800 release, providing high specificity and sensitivity. On account of the biomarker specificity and the spatiotemporally controlled NIR irradiation, the nanoprobes could selectively activate their NIR fluorescence (NIRF) signal to visualize tumors in living mice and allow for the easy translation of the nanoprobe as artificial urinary biomarker probes for in vitro diagnosis of tumor progression. In 4T1 tumor-bearing mice models, the activatable nanoprobes enabled ultrasensitive detection of tumors (1.9 mm in diameter). This study offers a noninvasive and photothermally signal-amplified approach for early tumor diagnosis via NIRF imaging or simple urine tests.

Non-Invasive Retinal Biomarkers for Early Diagnosis of Alzheimer’s Disease

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder of the brain associated with ageing and is the most prevalent form of dementia, affecting an estimated 55 million people worldwide, with projections suggesting this number will exceed 150 million by 2050. With its increasing prevalence, AD represents a significant global health challenge with potentially serious social and economic consequences. Diagnosing AD is particularly challenging as it requires timely recognition. Currently, there is no effective therapy for AD; however, certain medications may help slow its progression. Existing diagnostic methods such as magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), and biomarker analysis in cerebrospinal fluid tend to be expensive and invasive, making them impractical for widespread use. Consequently, research into non-invasive biomarkers that enable early detection and screening for AD is a crucial area of contemporary clinical investigation. One promising approach for the early diagnosis of AD may be retinal imaging. As an extension of the central nervous system, the retina offers a distinctive opportunity for non-invasive brain structure and function assessment. Considering their shared embryological origins and the vascular and immunological similarities between the eye and brain, alterations in the retina may indicate pathological changes in the brain, including those specifically related to AD. Studies suggest that structural and vascular changes in the retina, particularly within the neuronal network and blood vessels, may act as markers of cerebral changes caused by AD. These retinal alterations have the potential to act as biomarkers for early diagnosis. Since AD is typically diagnosed only after a significant neuronal loss has occurred, identifying early diagnostic markers could enable timely intervention and help prevent disease progression. Non-invasive retinal imaging techniques, such as optical coherence tomography (OCT) and OCT angiography, provide accessible methods for the early detection of changes linked to AD. This review article focuses on the potential of retinal imaging as a non-invasive biomarker for early diagnosis of AD. Investigating the ageing of the retina and its connections to neurodegenerative processes could significantly enhance the diagnosis, monitoring, and treatment of AD, paving the way for new diagnostic and therapeutic approaches.

Enhancing early breast cancer detection with APE1-triggered oligonucleotide probes and graphene oxide: The impact of variable AP site modification on sensitivity and specificity.

There is a critical need for inclusive diagnostic platforms to enhance the accuracy of early breast cancer detection. Dysregulated microRNA-1246 (miR-1246), closely linked to the disease progression and recurrence, has emerged as a promising diagnostic and prognostic biomarker for BC. However, achieving simple, rapid, and ultrasensitive quantification of serum miRNAs remains significant challenge. In this study, we present an innovative detection platform triggered by endogenous DNA repair enzyme apurinic/apyrimidinic endonuclease 1 (APE1). This platform utilizes an oligonucleotide probe with variable modified AP sites (denoted as AOP) coupled with graphene oxide (GO) for quantifying miR-1246. Our in vitro experiments reveal that the proposed method employing the AOP2 probe with two AP sites exhibits exceptional selectivity and sensitivity. The method achieves a detection limit as low as 2.3 pM towards miR-1246, which is approximately 260-fold more sensitive than the enzyme-free system. RT-qPCR experiments further validate the accuracy and practicability of the AOP2-based platform. In clinical trials, our platform has successfully differentiated between BC patients and normal healthy controls. In conclusion, we have established an integrated biosensing technology for PCR-free, non-invasive liquid biopsies of miR-1246, offering a promising approach for BC diagnosis.

Joint Ability Assessment for Talent Recruitment: A Neural Cognitive Diagnosis Approach

Ability assessment is a critical task in talent recruitment that aims to identify the most suitable job candidates by evaluating the alignment of their skills with job requirements. Indeed, traditional ability assessment involves multiple staffing processes with various forms of evaluation methods, such as written tests and face-to-face interviews, which usually result in fragmented, noisy, and inconsistent conclusions. Therefore, a long-standing challenge in talent recruitment is how to comprehensively evaluate candidates by integrating multi-source heterogeneous assessment results. To this end, in this paper, we propose a holistic framework, JCD-TR ( J oint C ognitive D iagnosis for T alent R ecruitment), for enhancing the performance of ability assessment in talent recruitment by jointly modeling the multi-source heterogeneous assessment results. Specifically, we first construct a skill graph based on the co-occurrence relations of skills in multi-source recruitment data. Along this line, we can learn the skill representations that maintain both the semantic and structural information with graph embedding. Then, we design a multi-source candidate ability profiling module with the guidance of item response theory in psychometrics and the neural topic model. As a result, the candidates’ ability profiles can be explored from their resumes, written tests, and interview assessment data, respectively. Furthermore, we propose a joint cognitive diagnosis module by integrating those multi-view ability profiles and skill representations to assess the candidates’ skill proficiency state. Extensive experiments on a real-world dataset demonstrate the effectiveness of our JCD-TR.

DGA-Based Fault Diagnosis Using Self-Organizing Neural Networks with Incremental Learning

Power transformers are vital components of electrical power systems, ensuring reliable and efficient energy transfer between high-voltage transmission and low-voltage distribution networks. However, they are prone to various faults, such as insulation breakdowns, winding deformations, partial discharges, and short circuits, which can disrupt electrical service, incur significant economic losses, and pose safety risks. Traditional fault diagnosis methods, including visual inspection, dissolved gas analysis (DGA), and thermal imaging, face challenges such as subjectivity, intermittent data collection, and reliance on expert interpretation. To address these limitations, this paper proposes a novel distributed approach for multi-fault diagnosis of power transformers based on a self-organizing neural network combined with data augmentation and incremental learning techniques. The proposed framework addresses critical challenges, including data quality issues, computational complexity, and the need for real-time adaptability. Data cleaning and preprocessing techniques improve the reliability of input data, while data augmentation generates synthetic samples to mitigate data imbalance and enhance the recognition of rare fault patterns. A two-stage classification model integrates unsupervised and supervised learning, with k-means clustering applied in the first stage for initial fault categorization, followed by a self-organizing neural network in the second stage for refined fault diagnosis. The self-organizing neural network dynamically suppresses inactive nodes and optimizes its training parameter set, reducing computational complexity without sacrificing accuracy. Additionally, incremental learning enables the model to continuously adapt to new fault scenarios without modifying its architecture, ensuring real-time performance and adaptability across diverse operational conditions. Experimental validation demonstrates the effectiveness of the proposed method in achieving accurate, efficient, and adaptive fault diagnosis for power transformers, outperforming traditional and conventional machine learning approaches. This work provides a robust framework for integrating advanced machine learning techniques into power system monitoring, paving the way for automated, real-time, and reliable transformer fault diagnosis systems.