Search Results (551)

Background/Objectives: The demand for accessible and reliable digital health services has increased significantly in recent years, particularly in regions facing physician shortages. HomeDOCtor, a conversational AI platform developed in Slovenia, addresses this need with a nationally adapted architecture that combines retrieval-augmented generation (RAG) and a Redis-based vector database of curated medical guidelines. The objective of this study was to assess the performance and impact of HomeDOCtor in providing AI-powered healthcare assistance. Methods: HomeDOCtor is designed for human-centered communication and clinical relevance, supporting multilingual and multimedia citizen inputs while being available 24/7. It was tested using a set of 100 international clinical vignettes and 150 internal medicine exam questions from the University of Ljubljana to validate its clinical performance. Results: During its six-month nationwide deployment, HomeDOCtor received overwhelmingly positive user feedback with minimal criticism, and exceeded initial expectations, especially in light of widespread media narratives warning about the risks of AI. HomeDOCtor autonomously delivered localized, evidence-based guidance, including self-care instructions and referral suggestions, with average response times under three seconds. On international benchmarks, the system achieved ≥95% Top-1 diagnostic accuracy, comparable to leading medical AI platforms, and significantly outperformed stand-alone ChatGPT-4o in the national context (90.7% vs. 80.7%, p = 0.0135). Conclusions: Practically, HomeDOCtor eases the burden on healthcare professionals by providing citizens with 24/7 autonomous, personalized triage and self-care guidance for less complex medical issues, ensuring that these cases are self-managed efficiently. The system also identifies more serious cases that might otherwise be neglected, directing them to professionals for appropriate care. Theoretically, HomeDOCtor demonstrates that domain-specific, nationally adapted large language models can outperform general-purpose models. Methodologically, it offers a framework for integrating GDPR-compliant AI solutions in healthcare. These findings emphasize the value of localization in conversational AI and telemedicine solutions across diverse national contexts. Full article

Background/Objectives: Romania remains a tuberculosis (TB) hotspot in the European Union, yet host-derived factors of poor outcomes are poorly characterised. We quantified circulating pro-inflammatory cytokines and examined their interplay with behavioural risk factors, the nutritional status, and the clinical course in adults hospitalised with pulmonary TB. We analysed 80 adults with microbiologically confirmed pulmonary TB and 40 respiratory symptom controls; four TB patients (5%) died during hospitalisation, all within 10 days of admission. Methods: A retrospective analytical case–control study was conducted at the Constanța regional TB referral centre (October 2020—October 2023). Patients with smear- or culture-confirmed TB were frequency-matched by sex, 10-year age band, and BMI class to culture-negative respiratory controls at a 2:1 ratio. The patients’ serum interferon-γ (IFN-γ), interleukin-1α (IL-1α), interleukin-1β (IL-1β), and tumour-necrosis-factor-α (TNF-α) were quantified within 24 h of admission; the neutrophil/lymphocyte ratio (NLR) was extracted from full blood counts. Independent predictors of in-hospital mortality were identified by multivariable logistic regression; factors associated with the length of stay (LOS) were modelled with quasi-Poisson regression. Results: The median TNF-α (24.1 pg mL⁻¹ vs. 16.2 pg mL⁻¹; p = 0.009) and IL-1β (5.34 pg mL⁻¹ vs. 3.67 pg mL⁻¹; p = 0.008) were significantly higher in the TB cases than in controls. TNF-α was strongly correlated with IL-1β (ρ = 0.80; p < 0.001), while NLR showed weak concordance with multiplex cytokine patterns. Among the patients with TB, four early deaths (5%) exhibited a tripling of TNF-α (71.4 pg mL⁻¹) and a doubling of NLR (7.8) compared with the survivors. Each 10 pg mL⁻¹ rise in TNF-α independently increased the odds of in-hospital death by 1.8-fold (95% CI 1.1–3.0; p = 0.02). The LOS (median 29 days) was unrelated to the smoking, alcohol, or comorbidity load, but varied across BMI strata: underweight, 27 days; normal weight, 30 days; overweight, 23 days (Kruskal–Wallis p = 0.03). In a multivariable analysis, under-nutrition (BMI < 18.5 kg m⁻²) prolonged the LOS by 19% (IRR 1.19; 95% CI 1.05–1.34; p = 0.004) independently of the disease severity. Conclusions: A hyper-TNF-α/IL-1β systemic signature correlates with early mortality in Romanian pulmonary TB, while under-nutrition is the dominant modifiable determinant of prolonged hospitalisation. Admission algorithms that pair rapid TNF-α testing with systematic nutritional assessment could enable targeted host-directed therapy trials and optimise bed utilisation in high-burden settings. Full article

Background/Objectives: Immune checkpoint inhibitors have significantly transformed the treatment paradigm of advanced melanoma, leading to substantial improvements in survival outcomes. However, this therapeutic success is accompanied by a spectrum of treatment-related adverse events, some of which are increasingly recognised as enduring and non-reversible. Whilst early-onset immune-related toxicities have been well characterized, late-onset toxicities, often emerging in patients with long-term disease control, remain understudied and are frequently overlooked. Methods: To address this knowledge gap, we conducted a retrospective multicentre study in three UK tertiary referral centres, exploring immune-related adverse events in 246 patients with melanoma who received immune checkpoint inhibitors in the advanced setting. We defined late-onset immune-related adverse events as those occurring at least 3 months after the last cycle of immune checkpoint inhibitors. Results: Although most patients experienced early-onset toxicity, almost 15% of patients developed late-onset immune-related adverse events, including skin rash, colitis, hepatitis, and arthritis, among others. These were often challenging to manage and necessitated the use of systemic steroids. Up to 2% of patients presented ultra-late-onset toxicities, defined as those events occurring at least 12 months after treatment completion. Conclusions: This study provides valuable insights into the characteristics of late-onset immune-related adverse events. To further advance our understanding of these late-onset toxicities, dedicated prospective studies are needed to assess risk factors associated with their development and their impact on quality of life. Additionally, translational research focused on finding predictive biomarkers is essential to identify patients at a higher risk of developing delayed adverse events and to understand how best to manage them. Full article

This study applies stochastic discrete event modeling to demonstrate that reducing wait times for specialized outpatient clinics in the Costa Rican public healthcare system is possible. The classification process identified four medical specialties with the longest wait times. It includes the creation of a separate queuing theory model for each specialty. The birth and death model allowed for estimating the number of arrivals and consultations in the simulation. Validation was performed by comparing the model’s input and output data with real-world statistical reports. An analysis of medical specialists revealed that approximately 22% of patients referred to secondary care did not require specialized medical consultation. Through simulation and the use of stochastic input data, patient waiting times decreased. In an optimistic scenario, waiting times decreased steadily across all specialties over 24 months. Ophthalmology and orthopedics reduced their waiting times to less than 300 days. Otorhinolaryngology decreased from 370 to 250 days, and urology showed the most significant improvement, decreasing from 350 to 100 days in the first year and remaining stable. This evidence transforms the traditional paradigm of increasing capacity as the only solution to the waiting list problem and positions improving the referral process as an alternative. To achieve these results, the study highlights the importance of implementing improved triage protocols in primary care, integrating decision-support tools for general practitioners using machine learning, for example, to reduce unnecessary referrals. Training programs and feedback mechanisms could also align referral practices with specialty criteria. While these strategies were not implemented in this study, the simulation results provide a solid basis for their design and future evaluation. Full article

This perspective paper presents a first-person account of life with motor neurone disease (MND). Through the lens of lived experience, it explores the complex and often prolonged diagnostic journey, shaped in part by the protective grip of denial. This paper then delves into the emotional impact of MND on the individual and their close relationships, capturing the strain on identity and family dynamics. It also highlights the vital role of the multidisciplinary team in providing support throughout the journey. A central focus of the paper is the personal journey of voice banking. It reflects on the restorative experience of reclaiming a pre-disease voice through tools such as ElevenLabs^TM. This narrative underscores the critical importance of early intervention and timely access to voice banking, positioning voice not only as a tool for communication but also as a powerful anchor of identity, dignity, and agency. The paper concludes by highlighting key systemic gaps in MND care. It calls for earlier referral to speech pathology, earlier access to voice banking, access to psychological support from the time of diagnosis, and better integration between research and clinical care. Full article

Background: Gorlin–Goltz syndrome (GGS), also known as basal cell nevus syndrome or nevoid basal cell carcinoma syndrome, is a rare genetic disorder caused by mutations in the PTCH1, PTCH2, or SUFU genes, leading to an increased risk of neoplasms. Craniofacial anomalies are among the most common features of GGS. This paper aimed to highlight the similarities and differences in clinical presentation across different ages and to emphasize the importance of including all family members in the diagnostic process. The diagnosis can often be initiated by a dentist through routine radiographic imaging. Case Presentation: We present a 17-year longitudinal follow-up of a male patient with recurrent multiple odontogenic keratocysts and other manifestations consistent with GGS. Nearly 20 years later, the patient’s mother presented with similar clinical features suggestive of GGS. Diagnostic imaging, including contrast-enhanced computed tomography (CT), cone-beam CT, magnetic resonance imaging, and orthopantomography, was performed, and the diagnosis was confirmed through genetic testing. Interdisciplinary management included age-appropriate surgical and dermatological treatments tailored to lesion severity. Conclusions: Given the frequent involvement of the stomatognathic system in GGS, dentists play a critical role in early detection and referral. Comprehensive family-based screening is essential for timely diagnosis, improved monitoring, and effective management of this multisystem disorder. Full article

Background/Objectives: International guidelines recommend the combined use of the General Movement Assessment (GMA), Hammersmith Infant Neurological Examination (HINE), and magnetic resonance imaging (MRI) to support early and accurate diagnosis of cerebral palsy (CP). However, their implementation remains inconsistent. This study aimed to map their reported global use and identify associated enablers and barriers. Methods: A scoping review was conducted following JBI and PRISMA-ScR guidelines. Systematic searches were performed in PubMed, Cochrane, PEDro, ProQuest, Web of Science, and Scopus. Eligible studies were charted and thematically analyzed, focusing on tools use and implementation factors at individual, organizational, and system levels. Results: Fourteen articles (seven surveys, seven implementation studies) from seven countries met the inclusion criteria. While awareness of GMA, HINE, and MRI was generally high, routine clinical use was limited—particularly outside structured implementation initiatives. Major barriers emerged at the system level (e.g., limited training access, time constraints, lack of standardized referral pathways) and social level (e.g., unclear leadership and coordination). Conclusions: The limited integration of GMA, HINE, and MRI into routine practice reflects a persistent “know–do” gap in early CP detection. Since implementation is shaped by the dynamic interplay of capability, opportunity, and motivation, bridging this gap demands sustained and equitable action—by addressing system-wide barriers, supporting professional development, and embedding early detection within national care pathways. Full article

Background: Around one-quarter of all people in the developed world die of cancer, with primary care being the main setting in which the disease is first suspected because the majority of patients consult a general practitioner (GP) when they present with symptoms. Diagnostic delay may thus be attributable to the patient, the GP, or the healthcare system. While some findings suggest that as much as half of the total delay consists of patient delay, more research is nonetheless needed into how GPs can facilitate access to diagnostic evaluation when patients experience symptoms. Methods: A retrospective observational study will be conducted to evaluate a cohort of patients diagnosed with cancer, with data being obtained from both primary and specialised care settings. Different time intervals will be analysed, dating from onset of first symptoms to diagnosis or initiation of treatment, and will be classified as: patient interval; primary-care interval; healthcare-system interval; diagnostic interval; treatment interval; and total interval. Study variables will include patient characteristics (socio-demographic, risk factors, morbidity, etc.), tumour characteristics (tumour stage, symptom onset, alarm symptoms, etc.), and healthcare characteristics (place of initial consultation, referral to specialised care, etc.). Discussion: The study will describe diagnostic delays in patients with cancer in primary care, considering the time elapsed between symptom onset and initial consultation, request for tests and/or patient referral, first evaluation in the hospital setting, and date of diagnostic confirmation and treatment initiation. Additionally, the study will make it possible to identify the patient-, healthcare-, and disease-related variables that intervene in the duration of such delays. Full article

Background/Objectives: Infantile hemangioma (IH) is a common vascular tumor in neonates, influenced by multiple prenatal and perinatal factors. This study aimed to identify risk factors in both infants and mothers, assess their link to clinical characteristics and severity, and evaluate treatment outcomes when systemic propranolol therapy was administered. Methods: We conducted a retrospective observational study analyzing 43 infants under 12 months, including 11 neonates (<28 days) diagnosed with IH. Maternal and neonatal factors, diagnostic timelines, clinical presentation, and treatment efficacy were examined. Data analysis included descriptive statistics, focusing on gestational age, birth weight, Apgar scores, and the Infantile Hemangioma Referral Score (IHReS). Results: The study found a female predominance and a correlation between IH and pre-term birth (50%) and low birth weight (<2760 g, 51.16%). Maternal anemia (23%) and gestational hypertension (9%) were present in the cohort, but no statistical association with IH severity was found. A significant number (44.18%) were diagnosed within the first two weeks postpartum. The IHReS was inversely correlated with Apgar scores, with newborns scoring above 8 having a lower IHReS. Treatment with propranolol (1–3 mg/kg/day) was highly effective, resulting in significant lesion regression in most patients. Mild complications included sleep disturbances (12%) and diarrhea (9%). The most affected areas were the face/eyelid (32.55%), limbs (18.6%), and anterior thorax. Additionally, 42% of cases had an IHReS above 4, with multiple hemangiomas increasing severity. Conclusions: IH was common in pre-term and low-birth-weight infants, whereas the maternal comorbidities observed in this small cohort did not show a definitive association, underscoring the need for controlled studies. Early diagnosis, risk stratification, and timely propranolol therapy are crucial in achieving favorable outcomes. Further research is needed to assess long-term effects and evaluate risks of treatment rebound. Full article

Peripheral artery disease (PAD) is associated with an elevated risk of major adverse cardiovascular events (MACE). Despite this, few reliable biomarkers exist to identify patients at heightened risk of MACE. Growth differentiation factor 15 (GDF15), a stress-responsive cytokine implicated in inflammation, atherosclerosis, and thrombosis, has been broadly studied in cardiovascular disease but remains underexplored in PAD. This study aimed to evaluate the prognostic utility of GDF15 for predicting 2-year MACE in PAD patients using explainable statistical and machine learning approaches. We conducted a prospective analysis of 1192 individuals (454 with PAD and 738 without PAD). At study entry, patient plasma GDF15 concentrations were measured using a validated multiplex immunoassay. The cohort was followed for two years to monitor the occurrence of MACE, defined as stroke, myocardial infarction, or death. Baseline GDF15 levels were compared between PAD and non-PAD participants using the Mann–Whitney U test. A machine learning model based on extreme gradient boosting (XGBoost) was trained to predict 2-year MACE using 10-fold cross-validation, incorporating GDF15 and clinical variables including age, sex, comorbidities (hypertension, diabetes, dyslipidemia, congestive heart failure, coronary artery disease, and previous stroke or transient ischemic attack), smoking history, and cardioprotective medication use. The model’s primary evaluation metric was the F1 score, a validated measurement of the harmonic mean of the precision and recall values of the prediction model. Secondary model performance metrics included precision, recall, positive likelihood ratio (LR+), and negative likelihood ratio (LR-). A prediction probability histogram and Shapley additive explanations (SHAP) analysis were used to assess model discrimination and interpretability. The mean participant age was 70 ± SD 11 years, with 32% (n = 386) female representation. Median plasma GDF15 levels were significantly higher in PAD patients compared to the levels in non-PAD patients (1.29 [IQR 0.77–2.22] vs. 0.99 [IQR 0.61–1.63] pg/mL; p < 0.001). During the 2-year follow-up period, 219 individuals (18.4%) experienced MACE. The XGBoost model demonstrated strong predictive performance for 2-year MACE (F1 score = 0.83; precision = 82.0%; recall = 83.7%; LR+ = 1.88; LR− = 0.83). The prediction histogram revealed distinct stratification between those who did vs. did not experience 2-year MACE. SHAP analysis identified GDF15 as the most influential predictive feature, surpassing traditional clinical predictors such as age, cardiovascular history, and smoking status. This study highlights GDF15 as a strong prognostic biomarker for 2-year MACE in patients with PAD. When combined with clinical variables in an interpretable machine learning model, GDF15 supports the early identification of patients at high risk for systemic cardiovascular events, facilitating personalized treatment strategies including multidisciplinary specialist referrals and aggressive cardiovascular risk reduction therapy. This biomarker-guided approach offers a promising pathway for improving cardiovascular outcomes in the PAD population through precision risk stratification. Full article

Background and Objectives: Bell’s palsy, characterized by acute idiopathic facial nerve paralysis, exhibits variable recovery outcomes influenced by treatment timing, modality, and patient comorbidities. This study aimed to compare the effectiveness of corticosteroid-based treatment (Ear, Nose, and Throat [ENT]), nerve blocks/physical therapy (Pain Medicine), and acupuncture/herbal medicine (Traditional Korean Medicine [KM]) and identify predictors of recovery and recurrence. This retrospective cohort study leverages South Korea’s pluralistic healthcare system, where patients choose specialties, to provide novel insights into departmental treatment outcomes. Materials and Methods: We analyzed 600 patients treated within 72 h of Bell’s palsy onset (2010–2024) at Wonkwang University Hospital, South Korea, using propensity score matching (PSM) (1:1:1) for age, sex, comorbidities, and initial House–Brackmann (HB) grade. The primary outcome was complete recovery (HB grade I) at 6 months; secondary outcomes included recovery time, recurrence, complications, and patient satisfaction. Multivariate logistic regression identified predictors. Results: The ENT group achieved the highest complete recovery rate (87.5%, phi = 0.18) versus Pain Medicine (74.0%) and KM (69.5%) (p < 0.001), with the shortest recovery time (4 weeks, Cohen’s d = 0.65 vs. KM). Synkinesis was lowest in the ENT group (6.0%). ENT treatment (OR: 1.75; 95% CI: 1.29–2.37) and early corticosteroid application (OR: 1.95; 95% CI: 1.42–2.68) predicted recovery. Hypertension (OR: 4.40), hyperlipidemia (OR: 8.20), and diabetes (OR: 1.40) increased recurrence risk. Subgroup analyses showed that ENT treatment was most effective for severe cases (HB grade IV: 90% recovery vs. 65% in KM, p < 0.01). Conclusions: Corticosteroid-based treatment (ENT) yielded superior recovery outcomes. Comorbidity management is critical for recurrence prevention. Early ENT referral and integrated care models are recommended to optimize outcomes in diverse healthcare settings. Full article

Background: Physical activity (PA) is associated with lower mortality and cancer recurrence risks. Although evidence shows health benefits for cancer patients before, during, and immediately after treatment, PA recommendations are not regularly included in the standard care. Objective: The study aimed to identify perceived knowledge, barriers, and facilitators of oncology providers’ PA promotion for cancer patients using the 5A (Assess, Advise, Agree, Assist, and Arrange) framework. Methods: A qualitative research design with a phenomenological approach was adopted. A purposive sample of 16 oncology care providers in Nebraska participated in semi-structured interviews via Zoom/phone. Interviews were audio-recorded, transcribed, and imported into MAXQDA 2024 for thematic analysis. Results: Analysis of the qualitative data identified five themes: (i) Broad and inclusive conceptualizations of PA among oncology care providers suggested that they were able to define PA; (ii) Current Practices in PA Counseling included advising on PA and assessment; (iii) Barriers to PA counseling included lack of guideline awareness, insufficient training, low prioritization, uncertainty about responsibility, time constraints, limited resources, lack of referral systems, patient health conditions, and environmental factors; (iv) Facilitators were identified as acknowledged health benefits for cancer survivors, awareness of PA recommendations, access to community resources, and support from interdisciplinary teams; and (v) Expressed desire among oncology care providers for training on incorporating PA into oncology care. Conclusions: Oncology providers recognized PA’s health benefits for cancer survivors but did not promote it due to inadequate knowledge of guidelines and lack of resources. These barriers require improved PA counselling education to help providers incorporate PA into clinical care. Full article

Introduction: Systemic lupus erythematosus (SLE) is associated with infection-related morbidity. The risk of adverse outcomes secondary to infections was exacerbated during the recent COVID-19 pandemic, prompting mass vaccination with the novel mRNA-based and viral-vectored vaccines. Limited data exist on the long-term impact of vaccination in patients with SLE. Methods: A post-vaccine group (PVG, n = 284) from a multicentric cohort of vaccinated patients with SLE from six tertiary referral centres in Northen Italy was compared with a control group (CG, n = 223) of similar demographics observed in the 2015–2019 period to investigate survival, hospitalisation, pregnancy, disease flare, disease progression, infection, and chronic complication accrual rates. Results: We did not observe excess SLE flares, SLE progression, hospitalisation, or pregnancy complications in the PVG. Cardiovascular complications due to comorbidities or to SLE were lower in the PVG than in the CG. Infections were more frequent in the PVG, related to COVID-19 in half of the cases, and were associated with SLE flares. Conclusions: Taken together, these data indicate that anti-COVID-19 vaccines are safe in the long-term when administered to patients with SLE. Stable, non-null rates of chronic comorbidity accrual and hospitalisation point out the existence of persistently unmet needs in patients with SLE. Full article

This article describes a case study of the partnership between Healthy Birth Initiatives, a community-based organization (CBO) and Black-led public health nurse home visiting program, and the maternal health division of the Providence Health System located in the Pacific Northwest. This study’s purpose was to explore the formation, significance, and impact of this partnership from the perspectives of staff and leadership members from both organizations. We conducted a case study through qualitative interviews with staff, participant observation, and debrief of leadership meetings. We completed a hybrid deductive–inductive thematic analysis of the data, followed by member checking with study participants and other key interest holders. Key facilitators of the CBO–health system partnership included the vital role of leaders in prioritizing the partnership; health system willingness to incorporate new information from the CBO to improve care; and health system utilization of resources to institutionalize changes that emerged from this partnership. Challenges to the CBO–health system partnership included CBO resource limitations; fragmented referral processes and information sharing; and the persistence required to nurture the relationship without formalized roles. This study contributes to the literature by offering staff perspectives on how a CBO–health system partnership formed, successes, early lessons learned, and practical suggestions for how to develop stronger alignment to provide culturally responsive patient-centered care to Black families. Full article

Background/Objectives: The prevalence of people with incurable and progressive diseases in primary health care is high. Family doctors and nurses must be active agents in the early identification of palliative needs and the implementation of palliative approaches in cases of low to intermediate complexity. While there is a need for early referral of more complex palliative care (PC) cases to specialized teams, primary health care (PHC) professionals lack the confidence or skill to describe their role. This study sought to explore and describe (a) the practices of PHC professionals regarding their PC provision; (b) the barriers regarding access and referral of patients to specialized PC services; and (c) the strategies used or recommended to mitigate difficulties in accessing and referring to specialized PC. Methods: A descriptive qualitative study was carried out, using five focus groups conducted with nursing and medical staff at three local health units in the central region of Portugal. Semi-structured interviews were conducted, and then recorded, transcribed, and analyzed through a thematic analysis approach. The reporting of this research follows the COREQ checklist. Results: In total, 34 PHC professionals participated in this study. The majority of participants were women (n = 26) and family doctors (n = 24). Their mean age was 43.8 ± 11.9 (range: 29 to 65 years). The findings were organized into three core themes: (1) the contours of palliative action developed by PHC teams; (2) barriers to access and safe transition between PHC and specialized PC; and (3) ways to mitigate difficulties in accessing and referring to specialized PC. Conclusions: Our findings highlight the fundamental role of PHC professionals in providing primary PC, and in identifying PC needs and referring patients to PC early on, while exposing the systemic and interpersonal challenges that hinder these processes. To overcome these challenges, it is essential to invest in the development of integrated care models that promote practical, low-bureaucratic referral processes and capture the human resources necessary for the adequate follow-up of users. Full article