Neuro-ophthalmic disorders feature complex etiology. Certain ocular manifestations may hint at severe neurological diseases. Current clinical practice faces no shortage of diagnostic examinations. The core challenge consists in inadequate recognition, integration and interpretation of multifaceted information during initial consultation and non-specialist visits, potentially resulting in misdiagnosis, missed diagnosis, delayed referral and excessive examinations. Artificial intelligence has demonstrated promising performance in optic disc lesion detection, image interpretation of optic neuropathy, visual field analysis, as well as eye movement and pupillary function evaluation. Nevertheless, AI is not intended to replace specialists to deliver definitive diagnoses. Instead, it helps boost early detection of high-risk signs, facilitates analysis of complicated test results, and aids clinical decision-making, patient referral and follow-up management. This article elaborates on the application prospects, existing dilemmas and translational strategies of artificial intelligence in neuro-ophthalmology, aiming to offer references for relevant research and clinical practice.

Integrating EEG microstate dynamics in a stacked ensemble for neurodiagnostic ASD assessment.

This study investigates factors contributing to delays in breast cancer diagnosis in Bangladesh and their impact on cancer staging. Early detection is crucial for effective treatment, yet many women in low- and middle-income countries (LMICs) are diagnosed at advanced stages, resulting in poorer outcomes. A cross-sectional study was conducted at two major cancer care facilities in Dhaka. Women aged 18 and older with suspected or confirmed breast cancer were included. Data were collected using a structured questionnaire on sociodemographic and clinical variables. Total delay, defined as the time from symptom recognition to treatment initiation, was categorized into patient delay (symptom recognition to first medical consultation) and provider delay (first consultation to treatment start). Multivariable logistic regression analyses identified factors associated with these delays. Among 355 participants, 55.7% experienced total delays of over 4 months, with the highest delays in stage III cases (51.5%) due to patient delays. Key factors contributing to patient delay included low education (AOR: 1.43, 95% CI: 1.17-3.05), low monthly income (AOR: 3.41, 95% CI: 1.65-7.30), and absence of breast pain (AOR: 0.50, 95% CI: 0.26-0.96). Provider delays were significantly associated with rural residence (AOR: 3.07, 95% CI: 1.49-6.98) and the presence of nipple discharge (AOR: 2.92, 95% CI: 1.04-8.06). Total delays were most prevalent among patients from the Rangpur division (AOR: 5.87, 95% CI: 2.11-6.59), those residing in rural areas (AOR: 2.74, 95% CI: 1.40-5.52), and individuals with low education (AOR: 2.33, 95% CI: 1.09-5.11). Clinical factors such as breast pain (AOR: 2.34, 95% CI: 1.22-4.60) were also significantly associated with delay, along with discomfort discussing symptoms with a spouse (AOR: 2.16, 95% CI: 1.03-4.68). Additionally, nearly 80% of patients delayed seeking medical attention due to the belief that symptoms would resolve spontaneously, while 75% cited negligence and 65.5% reported financial barriers. Significant delays in breast cancer diagnosis in Bangladesh are driven by socio-economic factors and inadequate healthcare access. Increasing public awareness, especially in rural areas, and improving healthcare accessibility are essential to facilitate early detection. Expanding screening programs and training healthcare providers in early cancer detection are critical to improving patient outcomes.

Enhancing prediabetes and diabetes detection through a machine learning-enabled self-assessment approach.

A dysregulated host response to infection results in sepsis, where the mortality rate is high. A crucial component of managing sepsis is early detection and diagnosis. Advanced Haematology analyzers use volume, conductivity, and scatter (VCS) parameters to measure monocyte distribution width (MDW). An abnormal monocyte distribution width (MDW) greater than 20 U is considered a sign of sepsis. This study was done to utilize the potential of MDW as an early sepsis marker in ICU patients. Venous blood samples were collected from seventy-four patients suspected of having sepsis during a two-year prospective observational study. Sepsis cases were identified using the Systemic Inflammatory Response Syndrome (SIRS) criteria. Patients who received blood transfusions were excluded from this study. The DxH900 Haematology Analyzer (Beckman Coulter Inc., Miami, FL) was used to measure the MDW value. Procalcitonin (PCT), C-reactive protein (CRP), and total leucocyte count (TLC) were among the other conventional biomarkers of sepsis that were assessed. Seventy-four patients met the criteria for sepsis, of which twenty-three had septic shock. MDW was highest for patients in septic shock (P-value = 0.018). We have observed that as TLC, CRP, and PCT levels increased, so did MDW. As the SIRS score rose, it was discovered that the mean MDW value increased. In advanced Haematology analyzers, MDW, a new hematological parameter, is computed along with the complete blood count. When combined with other sepsis biomarkers, MDW is anticipated to be a helpful indicator for early sepsis screening in intensive care unit patients.

Chronic heart failure (CHF) is a condition affecting millions worldwide, characterized by the heart's reduced ability to pump blood efficiently. Conventional diagnostics, such as imaging and ECG assessments, can be time-consuming and expensive, often identifying CHF only after significant progression. Early detection is crucial for improving treatment options and reducing healthcare costs. Heart rate variability (HRV), which measures the variation in time intervals between heartbeats, is emerging as a non-invasive and cost-effective biomarker for CHF detection. HRV reflects the autonomic nervous system's regulatory functions, often impaired in CHF patients. This study aims to assess advanced HRV measures for earlier CHF detection. The research involved examining CHF patients (N = 934, Age 65 ± 12) compared to healthy controls (N = 274, Age 43 ± 17). Data was sourced from Physionet and the Telemetric and Holter ECG Warehouse, with RR interval (RRI) data extracted from 24-h Holter recordings. The study utilized dynamical detrended fluctuation analysis (DDFA), which considers changes in RRI correlations over time and scale, resulting in scaling exponent α(t,s). This was further aggregated into scale and heart rate (HR)-dependent forms, α(HR,s), classified using XGBoost ensemble method with 10-fold nested cross-validation. The classifier achieved 97% sensitivity and 90% specificity for distinguishing between CHF and control groups. Sensitivity and specificity remained consistent across subgroup analyses based on beta blocker medication and NYHA class. This method demonstrated high classification accuracy, suggesting potential utility for early CHF detection, independent of CHF severity.

Early detection is critical to improving childhood cancer survival. In 2013, the Pan American Health Organization published the Integrated Management of Childhood Illnesses-Cancer manual. We found that only 13% (n = 21/161) of primary care providers (PCPs) in southwestern Colombia were familiar with this manual. In response, we iteratively co-developed an e-learning curriculum (S-IMCICA) with PCPs, oncologists, and health educators, and applied usability testing for refinement (five iterations; usability testing in 919 PCPs). Usability testing showed mean increases in knowledge of 21%-24% (60%-65% vs. 81%-89%; p < 0.01) and excellent usability ratings. Our user-centered e-learning curriculum contributes to building capacity among PCPs for early childhood cancer detection in low- and middle-income countries.

Artificial intelligence in biomaterials for oral oncology.

The InAdvance Study addresses the critical need for comprehensive data and biospecimen collection from individuals at elevated risk for cancer. Despite the existence of numerous biobanks for patients with cancer and individuals at average risk for cancer, a gap persists in resources targeting individuals with an elevated risk for cancer. The InAdvance Study is longitudinally collecting biospecimens and health data from individuals with a range of cancer risk factors to facilitate collaborative research in cancer early detection and interception. Patient populations include those with precancerous or precursor lesions (e.g., oral precursor lesions and Barrett's esophagus), hereditary cancer risk, personal or family history of cancer, or a history of exposures associated with cancer risk. Additionally, we are enrolling patients receiving multicancer early detection (MCED) tests, family members of elevated risk participants, and controls. Key goals include optimized biospecimen collection through standardized procedures, participant enrollment and engagement through an online platform, and standardized scalable procedures. Data are compiled into a central repository, and researchers can request access through a streamlined data request process. Since April 2023, 1,415 participants have enrolled in the study. In total, 817 (58%) completed the baseline survey, and 816 (58%) gave a baseline blood sample. The InAdvance Study's comprehensive approach provides a framework for basic, population, and translational studies to elucidate the molecular and environmental factors that drive cancer development. Comprehensive data and biospecimen biorepositories are critical to informing strategies for early detection, risk stratification, early interception for risk mitigation, and improved outcomes for higher-risk populations.

Patients with a history of esophageal squamous cell carcinoma or pharyngeal cancer are at high risk of laryngopharyngeal cancers, particularly in the hypopharynx. However, adequate hypopharyngeal visualization during esophagogastroduodenoscopy is challenging because of anatomical constraints. We evaluated the utility of the Modified Killian method for hypopharyngeal visualization during esophagogastroduodenoscopy in high-risk patients. The Modified Killian method had previously been used at our institution for high-risk patients with esophageal and head and neck cancers. In this retrospective comparative study, data were collected from 45 high-risk patients who underwent pharyngeal examination using the Modified Killian method after the conventional method during a single esophagogastroduodenoscopy session. The primary endpoint was the hypopharyngeal visibility score (scale 1-5). Secondary endpoints included visibility of other pharyngeal areas, procedure time, lesion detection, and adverse events. The Modified Killian method without the Valsalva maneuver yielded higher hypopharyngeal visibility scores than the conventional method (median [interquartile range, IQR]: 2.0 [2.0-4.0] vs. 1.0 [1.0-2.0]; p < 0.001). The Modified Killian method further improved visibility (median [IQR]: 4.0 [3.0-5.0]; p < 0.001 vs. conventional). No significant differences were observed in visibility of the oropharynx or vallecula. The procedure time was longer for the Modified Killian method (237 vs. 134s; p < 0.001). Three intraepithelial hypopharyngeal carcinomas missed by the conventional method were detected with the Modified Killian method. No adverse events occurred. The Modified Killian method, particularly its positional component alone, improves hypopharynx visualization and may contribute to early cancer detection without compromising observation of other pharyngeal areas.

This study explores the process of adopting and maintaining breast self-examination (BSE), a key method for early breast cancer detection in women, using the Transtheoretical Model (TTM) as a theoretical framework. Conducted between February and April 2021 via digital platforms, the study recruited participants through WhatsApp, Instagram, and e-mail. Custom-designed TTM-based scales targeting BSE behavior were administered. Data were analyzed using IBM SPSS 22 and AMOS 22. Validity analyses included content, criterion, and construct validity, employing both exploratory and confirmatory factor analyses. Reliability was assessed through Cronbach's alpha, split-half method, Hotelling's T², item-total correlations, intra-class correlation coefficients, and standard error calculations. The results demonstrated that the developed scales are valid and reliable tools for measuring behavioral change related to BSE. This study underscores the utility of the Transtheoretical Model in understanding women's health behavior and provides a solid basis for future BSE-focused health education and intervention programs.

Clinical validation of PEA-driven Olink proteomic discovery: INPP1 and ARHGAP25 serum biomarkers improve early breast cancer diagnosis.

Bladder cancer is associated with substantial morbidity and long-term surveillance burden, particularly for patients with non-muscle-invasive disease, with significant impact on quality of life. In 2019, Bessa et al. [1] published the first stakeholder-driven (patients and healthcare professionals) consensus outlining the top 10 research priorities in bladder cancer. These 10 research priorities could be categorised into three research themes: predictive and prognostic biomarkers, optimisation of diagnostic pathways, and surveillance following radical therapy [1]. Their work represented a landmark shift towards the systematic integration of patient, clinical, and scientific perspectives in shaping the research agenda. Recognising rapid advancements in genomic biomarker discovery [2], molecular profiling [3], and novel therapeutics [4] in the years since, notwithstanding the effects of the global pandemic, we conducted an updated consensus exercise to reassess contemporary research needs. Using an interactive survey methodology adapted from the original study, we engaged 27 individuals including healthcare professionals, researchers across a spectrum of disciplines, charities, and patient advocates in live polling and facilitated discussion, evidence review, and iterative ranking of pertinent research questions. Rankings from the updated exercise were compared with those from 2019 to assess changes in emphasis over time. This updated prioritisation highlights an ongoing shift towards a biomarker-led, precision-medicine research agenda in bladder cancer. While not intended to define clinical standards, the findings provide direction for future translational studies, biomarker validation efforts, and trial design, with relevance to the risk-adapted management of both non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC). The most highly ranked research question focused on whether validated urinary biomarkers could substitute or reduce the frequency of cystoscopy follow-up in patients with high-risk NMIBC. The burden of frequent cystoscopy (citing discomfort, anxiety, procedural risks) and the cumulative resource impact on healthcare systems remains an issue. Compared with the Bessa et al. [1] findings, the strength of preference for non-invasive approaches has intensified, reflecting increasing patient awareness of emerging biomarker technologies. Eight of the top 10 priorities (compared to six in 2019) directly involved biomarker development, validation, or implementation. These include biomarkers for NMIBC surveillance and metastatic disease, diagnostic markers to improve early detection, molecular profiling and genomic stratification of NMIBC and MIBC, predictive biomarkers for neoadjuvant chemotherapy and immunotherapy, and biomarkers supporting early cystectomy decision-making. This biomarker-driven vision demonstrates an enhanced translational focus within the bladder cancer community and aligns strongly with contemporary precision-medicine frameworks [5, 6]. Patient advocacy input continues to indicate emphasis on quality-of-life considerations including reduced invasiveness, acceptability of tests, and minimisation of procedure-related burden. These values influence the importance of non-invasive diagnostics, early detection, and timely, personalised treatment strategies. Similar to the 2019 review, patient perspectives helped ensure that priorities reflected real-world needs rather than solely technological potential. Several newly elevated priorities reflect the rapid evolution of therapy and molecular oncology for risk stratification (Table 1). Priorities focused on therapy include predictive biomarkers for neoadjuvant therapy (recognising the heterogeneous response to chemotherapy and immunotherapy) and integration of molecular profiling (particularly to guide treatment selection in high-risk NMIBC and MIBC). Considerations around risk include genomic risk stratification and enabling identification of patients at high risk of progression. These themes collectively indicate increasing integration of genomic and molecular tools into clinical decision-making, signalling a maturation of precision urology. The priority areas identified have both immediate and long-term implications for clinical practice. Immediate benefits from translational innovations that are available now include reduced cystoscopy burden, improved patient experience and acceptability, and potential cost reductions for healthcare systems [2]. Long-term benefits include personalised treatment pathways informed by molecular features and/or liquid biopsies [2, 3, 7], improved survival through refined therapy selection, and enhanced quality of life via minimisation of invasive procedures. The consensus also underscores the need for multicentre biomarker validation studies, real-world implementation research, and integration of genomic, transcriptomic and liquid biopsy data into risk-stratified clinical pathways. Stakeholders highlighted the importance of robust evidence generation, pragmatic study design, and widespread adoption of quality-of-life metrics in future trials. Overall, this updated exercise confirms the enduring relevance of the original priorities while demonstrating an evolution towards a biomarker-led and molecularly-profiled personalised approach to bladder cancer research. The prioritised themes provide a clear roadmap for clinicians, researchers, funders, and policymakers to reduce the burden of bladder cancer. Continued stakeholder engagement, dedicated funding for biomarker validation, and coordinated multicentre collaboration will be essential for translating these priorities into improved patient outcomes. Richard T. Bryan is an unpaid charity trustee for Action Bladder Cancer UK (UK), an advisory board member for Nonacus Limited (UK), and receives consultancy fees from Cystotech ApS (Denmark) and Nonacus Limited (UK). The remaining authors have no disclosures.

Integrating multi-omics and artificial intelligence for personalized breast cancer management: A guide to clinicians.

Cardiometabolic disease develops over decades, yet most research emphasizes markers of disease risk in those with established disease or focuses primarily on traditional risk factors (e.g., low-density lipoprotein, fasted blood glucose). Meanwhile, indicators of early cardiometabolic dysfunction in young adults are not well-characterized but are crucial for advancing early detection and prevention efforts. The present review addresses this gap in the literature by providing a synthesis of subclinical indicators of early cardiometabolic dysfunction in young adults, including pathophysiological vascular/endothelial, metabolic, inflammatory, and neuroendocrine indicators, as well as newly emerging targets. Importantly, it is well-established that cardiometabolic risk and disease differ by biological sex. This review also incorporates sex-specific considerations where possible to address this difference. This review summarizes the available literature regarding subclinical indicators of early cardiometabolic dysfunction, aiming to improve the mechanistic understanding of cardiometabolic disease pathogenesis and offer a novel conceptual framework to advance how researchers and clinicians approach early detection and prevention of cardiometabolic dysfunction and disease.

The application of machine learning-assisted serum SERS technology in the early screening and prognosis evaluation of osteoporosis.

Cuproptosis-related circulating non-coding RNAs as diagnostic and prognostic biomarkers in oncology.

Changing epidemiology of sinonasal cancer in the United States.

AI-enhanced non-invasive diagnosis of chronic kidney disease using LIBS of fingernail biomarkers.

This study aims to investigate the association between triglyceride-glucose (TyG) index and risk of CVD using explainable survival analysis method based on 2011 to 2020 China Health and Retirement Longitudinal Study (CHARLS) data. We enrolled 7,721 participants in a prospective cohort. A Lasso Cox model was implemented to select covariates for constructing the multivariate Cox regression model. Restricted cubic splines (RCS) analysis was performed to explore dose-response relationship. In addition, we utilized explainable machine learning methods to analyse the Cox model. During 9-year follow-up, 1,895 (24.5%) participants developed CVD. Nine variables including TyG index, age, BMI, WC, SBP, history of hypertension, liver disease and kidney disease and antihypertensive medication were retained to establish the Cox model. HRs (95% CIs) for CVD were 1.21 (1.06-1.39), 1.26 (1.10-1.44), and 1.22 (1.06-1.40) for Q2 to Q4 groups compared with Q1. Result of RCS showed that the Q1 group had lowest risk. Time-dependent feature importance analysis showed that age and history of hypertension were two most important risk factors based on Brier score and C/D AUC. All variables in the coxph model gain importance over time. Routine measurement of the TyG index may aid in the early detection and risk stratification of CVD in the aging population.