Search Results (474)

Chronic obstructive pulmonary disease (COPD) is a major health burden worldwide and in Taiwan, ranking as the third leading cause of death globally, and its prevalence in Taiwan continues to rise. Readmission within 14 days is a key indicator of disease instability and care efficiency, driven jointly by patient-level physiological vulnerability (such as reduced lung function and multiple comorbidities) and healthcare system-level deficiencies in transitional care. To mitigate the growing burden and improve quality of care, it is urgently necessary to develop an AI-based prediction model for 14-day readmission. Such a model could enable early identification of high-risk patients and trigger multidisciplinary interventions, such as pulmonary rehabilitation and remote monitoring, to effectively reduce avoidable early readmissions. However, medical data are commonly characterized by severe class imbalance, which limits the ability of conventional machine learning methods to identify minority-class cases. In this study, we used real-world clinical data from multiple hospitals in Kaohsiung City to construct a prediction framework that integrates data generation and ensemble learning to forecast readmission risk among patients with chronic obstructive pulmonary disease (COPD). CTGAN and kernel density estimation (KDE) were employed to augment the minority class, and the impact of these two generation approaches on model performance was compared across different augmentation ratios. We adopted a stacking architecture composed of six base models as the core framework and conducted systematic comparisons against the baseline models XGBoost, AdaBoost, Random Forest, and LightGBM across multiple recall thresholds, different feature configurations, and alternative data generation strategies. Overall, the results show that, under high-recall targets, KDE combined with stacking achieves the most stable and superior overall performance relative to the baseline models. We further performed ablation experiments by sequentially removing each base model to evaluate and analyze its contribution. The results indicate that removing KNN yields the greatest negative impact on the stacking classifier, particularly under high-recall settings where the declines in precision and F1-score are most pronounced, suggesting that KNN is most sensitive to the distributional changes introduced by KDE-generated data. This configuration simultaneously improves precision, F1-score, and specificity, and is therefore adopted as the final recommended model setting in this study. Full article

Background: Kidney dysfunction is common in intracerebral hemorrhage (ICH), but it is unclear whether reduced estimated glomerular filtration rate (eGFR) on admission is an independent driver of short-term outcomes or a marker of overall vulnerability. Methods: In this single-center retrospective study, we analyzed the data of consecutive patients with spontaneous ICH. Results: Among 276 patients, 92 (33.3%) presented with eGFR < 60 mL/min/1.73 m² on admission. Only 17/92 (18.5%) had documented pre-existing chronic kidney disease (CKD). Acute kidney injury (AKI) occurred more often in patients with eGFR < 60 mL/min/1.73 m² than in those with eGFR ≥ 60 mL/min/1.73 m² (25.0% vs. 10.3%). In survival models, eGFR ≥ 60 mL/min/1.73 m², predicted higher 90-day survival in the baseline model (OR 3.031, p = 0.013) but was attenuated after adjustment for age and premorbid modified Rankin Scale (mRS) and was no longer independent after additional adjustment for laboratory markers. Across all models, the National Institutes of Health Stroke Scale (NIHSS) score, hematoma volume, and history of coronary artery disease remained robust predictors. Higher leukocyte count predicted lower survival, whereas higher hemoglobin predicted higher survival. Among survivors, favorable functional outcome was independently associated with lower NIHSS, younger age, lower premorbid mRS, and absence of documented CKD. Admission eGFR category was not independently associated. Conclusions: Reduced admission eGFR primarily reflects baseline frailty and systemic derangement rather than an independent determinant of short-term survival after full adjustment, whereas documented CKD is more informative for disability among survivors. AKI occurs more frequently in patients presenting with reduced eGFR, supporting close renal monitoring in acute ICH. Full article

Asthma is a common chronic disease in children, contributing to significant morbidity and healthcare utilization worldwide. The integration of artificial intelligence (AI) and machine learning (ML) into pediatric asthma care is rapidly advancing, offering new opportunities for early diagnosis, risk stratification, and personalized management. AI-driven tools can analyze complex clinical, genetic, and environmental data to identify asthma phenotypes and endotypes, predict exacerbations, and support timely interventions. In pediatric populations, these technologies enable non-invasive diagnostic approaches, remote monitoring through wearable devices, and improved medication adherence via smart inhalers and digital health platforms. Despite these advances, challenges remain, including the need for pediatric-specific datasets, transparency in AI decision-making, and careful attention to data privacy and equity. The integration of AI in pediatric asthma care and into the clinical decision system can offer personalized treatment plans, reducing the burden of the disease both for patients and health professionals. This is a narrative review on the applications of AI and ML in pediatric asthma care. Full article

Background: Although the main target of SARS-CoV-2 is the respiratory system, in some patients, it may affect multiple organ systems, leading to multi-organ failure. Acute kidney injury (AKI) remains one of the most frequent and clinically significant complications of severe COVID-19, with clinical importance extending beyond the acute phase due to its association with long-term renal outcomes and persistent morbidity. The incidence of AKI is particularly high among patients admitted to the intensive care unit (ICU), where its development has been consistently associated with prolonged hospitalization and increased mortality. The primary aim of this study was to determine the incidence of COVID-19-associated AKI, identify factors related to its development and severity, and evaluate mortality as a clinical outcome. Methods: Data from 238 COVID-19 patients monitored in the Intensive Care Unit of Ankara University Ibni Sina Hospital (ISH-ICU) between 1 January 2021 and 1 January 2022 were retrospectively reviewed. Patients were divided into two groups according to the presence of AKI. Those with AKI were staged according to KDIGO criteria (stages 1–2–3). Demographic characteristics, comorbidities, disease severity scores, laboratory parameters, and mortality outcomes were analyzed and compared between groups. Results: AKI was identified in 54.6% of patients. Of the patients with AKI, 32 (13.4%) had stage 1, 25 (10.5%) had stage 2, and 73 (30.7%) had stage 3 AKI. Thirteen patients (5.5%) had already developed AKI at ICU admission. AKI developed at a median of 11 days after symptom onset and 3 days after ICU admission. Advanced age, hypertension, cardiovascular disease, and chronic kidney disease were more frequent in patients with AKI (p < 0.001). Higher Charlson Comorbidity Index (CCI) and Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) scores were observed in patients with stage 3 AKI. Lymphopenia and elevated levels of D-dimer, ferritin, IL-6, CRP, and procalcitonin were significantly higher in patients with stage 3 AKI than in patients with other AKI stages and the non-AKI group. Mortality rates were higher in patients with AKI and increased with advancing AKI stage (p < 0.001). ICU length of stay was significantly longer in the AKI group (p < 0.001). Conclusions: AKI is a common complication among critically ill patients with COVID-19 and is associated with prolonged ICU stay and higher mortality rates, particularly in advanced stages. Early identification of clinical and laboratory factors associated with AKI may support timely risk stratification and targeted management in this high-risk population. Full article

This narrative review examines how immersive virtual and mixed-reality (VR/MR) technologies, combined with AI-driven virtual agents, can support the prevention and long-term management of chronic illness. Chronic diseases represent a significant global health burden, and conventional care models often struggle to sustain patient engagement, motivation, and adherence over time. To address this gap, we conducted a narrative review of reviews and meta-analyses. We selected empirical studies published between 2020 and 2025, identified through searches in PubMed, Web of Science, and Google Scholar. The aim was to capture the state of the art in the integrated use of VR/MR and AI in chronic illness care, and to identify key opportunities, challenges, and considerations relevant to clinical practice. The reviewed evidence indicates that VR/MR interventions consistently enhance engagement, motivation, symptom coping, and emotional well-being, particularly in rehabilitation, pain management, and psychoeducation. At the same time, AI-driven conversational agents and virtual therapists add adaptive feedback, personalization, real-time monitoring, and continuity of care between clinical visits. However, persistent challenges are also reported, including technical limitations such as latency and system dependence, ethical concerns related to data privacy and algorithmic bias, as well as psychosocial risks such as emotional overattachment or discomfort arising from avatar design. Overall, the findings suggest that the most significant clinical value emerges when VR/MR and AI are deployed together rather than in isolation. When implemented with patient-centered design, clinician oversight, and transparent governance, these technologies can meaningfully support more engaging, personalized, and sustainable chronic illness management. Full article

Diabetes is a chronic metabolic disorder that poses a growing global health challenge, currently affecting nearly 500 million people. Over the past four decades, the rising prevalence of diabetes has highlighted the urgent need for innovations in monitoring and management. Traditional enzymatic methods, including those using glucose oxidase, glucose dehydrogenase, and hexokinase, are widely adopted due to their specificity and relative ease of use. However, they are hindered by issues of instability, environmental sensitivity, and interference from other biomolecules. Non-enzymatic sensors, which employ metals and nanomaterials for the direct oxidation of glucose, offer an attractive alternative. These platforms demonstrate higher sensitivity and cost-effectiveness, though they remain under refinement for routine use. Non-invasive glucose detection represents a futuristic leap in diabetes care. By leveraging alternative biofluids such as saliva, tears, sweat, and breath, these methods promise enhanced patient comfort and compliance. Nonetheless, their limited sensitivity continues to challenge widespread adoption. Looking forward, the integration of nanotechnology, wearable biosensors, and artificial intelligence paves the way for personalized, affordable, and patient-centered diabetes management, marking a transformative era in healthcare. This review explores the evolution of glucose monitoring, from early chemical assays to advanced state-of-the-art nanotechnology-based approaches. Full article

Heart failure (HF) and chronic kidney disease (CKD) are prevalent conditions in older adults, often coexisting and significantly increasing the risk of hospitalization, cardiovascular events, and mortality. Traditional hospital-based care, while essential for acute management, is often insufficient to ensure continuity of care and optimal long-term outcomes. Home-based care, although promising for improving quality of life and reducing hospital-acquired complications, faces challenges related to treatment adherence, monitoring, and caregiver support. Recent evidence highlights the potential of multidisciplinary, patient-centered care models integrating physicians, nurses, pharmacists, and family caregivers. Technological innovations, including telemedicine, remote monitoring, mobile health applications, and artificial intelligence, have shown efficacy in early detection of clinical deterioration, improving adherence, and reducing cardiovascular events in HF and CKD patients. Structured patient education, caregiver training, and proactive follow-up are key elements to optimize transitions from hospital to home and to improve long-term outcomes, including reduced rehospitalizations and better quality of life. Future care strategies should focus on personalized, integrated approaches that combine technology, education, and multidisciplinary collaboration to address the complex needs of HF and CKD patients, while mitigating healthcare costs and enhancing overall patient well-being. Full article

Type 2 diabetes mellitus (T2DM) is a growing public health challenge worldwide, disproportionately affecting populations in low- and middle-income countries (LMICs). Poor glycemic control contributes significantly to the global burden of non-communicable diseases (NCDs), increasing morbidity, mortality, and healthcare costs. Understanding behavioral and lifestyle determinants is critical for designing effective public health strategies, particularly in resource-limited settings such as Lesotho. A cross-sectional population-based study was conducted among 184 adults with T2DM attending the out-patient department of Maluti Adventist Hospital, Lesotho. Data was collected using a structured questionnaire and analyzed descriptively with SPSS 26 Variables assessed included sociodemographic, dietary practices, physical activity, behavioral risk factors and self-care knowledge. Participants were predominantly aged 45–69 years (65.2%), with an equal sex distribution. Hypertension was the most prevalent comorbidity (65.2%). Risk factor exposure was widespread, 100% consumed fewer than five daily servings of fruits/vegetables, 95.1% reported insufficient physical activity, and 88.0% had elevated blood pressure. Overall, 86.4% had three or more NCD risk factors. Knowledge levels were intermediate, with 33.2% scoring poor, 52.7% moderate, and only 14.1% good. Glycemic control was suboptimal, with 40.8% uncontrolled. This study highlights the urgent public health need to address lifestyle and behavioral determinants of poor glycemic control in Lesotho. Tailored interventions focusing on dietary education, physical activity promotion, and routine monitoring are essential to reduce NCD risks and improve outcomes. The findings have broader implications for achieving Sustainable Development Goal 3.4 on reducing premature NCD mortality in LMICs. Strengthening culturally sensitive health promotion, community-based interventions, and integrated chronic disease care models could significantly advance diabetes prevention and control in low-resource settings. Full article

Wearable technologies, such as smartwatches, are increasingly used by people with Chronic Obstructive Pulmonary Disease (COPD) for health monitoring and self-management. However, there is limited evidence-informed guidance available to help patients and healthcare practitioners use these tools effectively in everyday life. Objectives: This study aimed to co-create a digital resource for people with COPD and healthcare practitioners to support the use of smartwatches for self-management. Methods: A participatory co-creation methodology was used, based on the Three Co’s Framework (co-define, co-design, co-refine). Participants included people with COPD, carers, family, or friends of people with COPD; healthcare practitioners; and researchers who attended workshops and individual think-aloud interviews to develop a website and video resource. The resource was refined based on real-time feedback. Data were analysed using rapid qualitative analysis. Results: Twenty-one participants engaged and identified key informational needs, including understanding smartwatch features, interpreting health data, and setting personalised goals. The co-created website and video resource were positively received. Participants valued the inclusion of real-life experiences and practical guidance tailored to both patients and healthcare practitioners. Conclusions: This study presents the first co-created resource for COPD and healthcare practitioners on using smartwatches. The co-creation process was successfully delivered online and face-to-face, demonstrating a robust, inclusive approach to managing multiple stakeholders. The resource offers practical value for patients and practitioners and contributes to the growing field of remote interventions for chronic respiratory conditions. Future research is needed to evaluate its effectiveness. Full article

Chagas disease (CD) remains a major global health challenge and requires standardized, multidisciplinary, and evidence-based clinical approaches. This article aims to present and systematize the model of clinical routines developed at the Clinical Research Laboratory on Chagas Disease (Lapclin-Chagas), INI/Fiocruz, for the initial evaluation and longitudinal follow-up of patients with chronic CD. The proposal is intended to serve as a replicable and adaptable framework for referral centers in both endemic and non-endemic settings. Using a descriptive qualitative design, institutional protocols, national and international guidelines, and expert consultations were analyzed to construct a comprehensive care model. The resulting protocol integrates diagnostic pathways (including dual serological confirmation and clinical staging), criteria for etiological treatment, and coordinated multidisciplinary follow-up involving cardiology, gastroenterology, pharmaceutical care, nutrition, psychology, and social support. Specific pathways are also presented for Trypanosoma cruzi (T. cruzi)/HIV coinfection, laboratory accidents, and monitoring of adverse reactions to benznidazole. By consolidating more than three decades of institutional experience into operational workflows, this proposal offers an innovative contribution to the organization of CD care and provides actionable guidance for health systems seeking to improve diagnostic accuracy, therapeutic adherence, patient safety, and long-term outcomes. Full article

A constantly increasing incidence of chronic diseases is a challenge for healthcare worldwide, being directly associated with physical inactivity, which is considered an important cause of most chronic diseases. In contrast, physical exercise has been proven as a powerful instrument of healthcare to protect individuals against health-to-disease transition and against disease progression. Nonetheless, a number of studies warn against inappropriate high-intensity and/or unaccustomed exercise that exceeds an individual’s physical capacity. Indeed, extensive cardiac activity during prolonged exercise leads to significantly increased cardiac dimensions, triggering cardiac complications that may result in arrhythmogenic sudden cardiac death. The remarkable plasticity of mitochondria allows these organelles to sense and adapt to a variety of stressors and respond to stimuli by molecular signalling, regulating bioenergetics and cellular homeostasis, decisive for repair processes, proliferation, apoptosis, and tissue regeneration to combat degeneration, with whole body outcomes. Mitochondria act as biosensors in the human body; they are reactive to stimuli and protective against health-to-disease transition. To perform this life-important function throughout life, mitochondria need supportive measures, including physical activity, considered an essential pillar of mitochondrial medicine. This article highlights reciprocity between the quality of mitochondrial health and homeostasis on one hand and physical fitness and exercise intervention on the other hand. The proposed novelty relates to the monitoring of mitochondrial homeostasis, which is strongly recommended for creating individualised training programmes, and monitoring exercise efficacy during and after the programme is completed. To this end, a patient-friendly non-invasive approach is already established, utilising tear fluid multi-omics, mitochondria as the vital biosensors, and AI-based multi-professional data interpretation. Full article

Background/Objectives: Kidney transplantation remains the most effective treatment for patients with end-stage kidney disease, increasing both survival and quality of life. There are concerns regarding the long-term outcomes of donors in developing countries, as kidney transplants are predominantly performed from living donors. This study was conducted to evaluate the long-term clinical outcomes of living kidney donors, with a particular focus on kidney and cardiovascular health. Methods: We retrospectively reviewed the records of 232 individuals who underwent donor nephrectomy between January 2011 and November 2022. Cardiovascular events, mortality, chronic kidney disease, hypertension, and newly onset diabetes were assessed. Estimated glomerular filtration rate (eGFR) values were employed to monitor kidney function over time. Results: Living kidney donors were monitored for a median of 6 years (IQR: 4–9 years). During the follow-up period, 18.9% of donors experienced a decline in eGFR to below 60 mL/min/1.73 m²; however, none progressed to end-stage kidney disease. Of the cohort, 20 (8.6%) had newly onset proteinuria and none had proteinuria before transplantation. Although there were no recorded deaths from cardiovascular causes, 4.3% of donors experienced major adverse cardiac events. 12.3% of donors had newly diagnosed hypertension following transplantation, and 20.2% of donors had hypertension overall. Lower baseline eGFR, treated as a continuous variable in the logistic regression model, was independently associated with a higher likelihood of post-donation eGFR < 60 mL/min/1.73 m² (OR: 0.91; 95% CI: 0.88–0.94; p < 0.001). Post donation proteinuria (OR: 6.61; 95% CI: 1.98–22.07, p: 0.002) was also identified as independent risk factors for decline in eGFR to below 60 mL/min/1.73 m². Diabetes mellitus was found to be a significant predictor of newly onset hypertension. Conclusions: A considerable percentage of the donors experienced gradual deterioration in kidney function, even though none of them developed kidney failure necessitating dialysis. The prevalence of obesity and chronic kidney disease was higher post-donation compared to the general population, indicating the need for structured long-term monitoring. Full article

Background: A key barrier to realizing the full potential and long-term collection of patient-reported outcomes (PROs) is the limited understanding of user experience (UX) factors that influence sustained patient engagement with digital PRO tools. Most existing research focuses on disease-specific or country-specific solutions, leaving a gap in identifying shared UX determinants that could inform scalable, cross-disease European digital health frameworks. This fragmentation hinders interoperability and increases development costs by requiring separate tools for each context. This case study aims to address this gap by identifying key UX features that optimize PRO collection across diverse chronic conditions in Europe within the Health Outcomes Observatory project, enhancing continuous (primary use) and large-scale (secondary use) data collection. Objective: This study aimed to identify and analyze key UX factors that support adoption and sustained use of PRO collection tools among patients with chronic diseases across multiple European countries. Methods: Patient focus groups were conducted in four chronic disease areas: cancer, inflammatory bowel disease (IBD), and diabetes (type I and II) across six European countries. Participants were recruited purposively through national patient advisory boards to ensure diversity in age, gender, and disease type. Sessions were moderated by trained qualitative researchers following a standardized guide, and discussions were transcribed verbatim and coded in researcher pairs to ensure intercoder reliability through iterative consensus. A modified thematic analysis, guided deductively by the UX Honeycomb model and inductively by emergent themes, was used to identify cross-disease UX determinants. Results: In total, 17 patients and patient representatives participated (76% female; 4 diabetes, 6 IBD and 7 cancer). We identified six core UX factors driving patient engagement for all disease groups: compatibility with other technologies, direct communication with the care team, personalization, ability to share data, the need for educational material and data protection were identified as key aspects of PRO technologies. However, the customizability of the app is crucial. Not all disease groups had the same needs, and participants specifically requested that the app provide information relevant to their own condition. Disease-specific needs, like T1D patients desiring glucose monitoring integration, were identified. IBD patients highlighted flare detection abilities and cancer patients especially sought side-effect comparisons. Conclusions: Our findings indicate that a unified yet customizable PRO platform can address shared UX needs across diseases, improving patient engagement and data quality. Incorporating features such as seamless data transfer, personalization, feedback, and strong privacy measures can foster trust and long-term adoption across European contexts. In addition to some disease-specific issues, most needs for the backbone of the app were shared among the disease areas. This shows that a shared app between diseases might be preferable and, in case of comorbidities, could ease self-management for patients. Last, to ensure full potential for every user and every disease, customization is crucial. Full article

Background: The aim of this study was to investigate the effects of chronic graft-versus-host disease (cGVHD) and its treatment with cyclosporine and extracorporeal photopheresis (ECP) on salivary caries risk factors. Methods: In this exploratory single-centre cross-sectional pilot study, saliva samples from 22 cGVHD patients were analysed for flow rate, pH, buffering capacity, and counts of Streptococcus mutans and Lactobacillus. A detailed dental examination assessed plaque, carious lesions, and their progression. Caries risk was determined based on general health and diet questionnaires and clinical findings. Results: Patients receiving a combination of cyclosporine and ECP had significantly fewer carious teeth, affected tooth surfaces, and non-cavitated carious lesions compared with those treated with ECP alone (Bonferroni test, p = 0.004, p = 0.002, and p < 0.001, respectively). Patients treated with ECP had more carious teeth and affected surfaces than those who did not receive either ECP or cyclosporine (p = 0.008 and p = 0.002), whereas patients treated with cyclosporine only had more non-cavitated lesions than those receiving both cyclosporine and ECP (p < 0.001). A negative correlation was observed between cyclosporine dose and stimulated salivary flow (R = −0.672, p = 0.0486), and a positive correlation between cyclosporine dose and caries risk (R = 0.640, p = 0.0461). Conclusions: The disease and its treatment were associated with reduced salivary flow and increased caries risk. Patients’ oral health should be monitored regularly and managed with care to prevent further deterioration. Full article

The ADRENALINE pilot study explores the role of physical activity in health outcomes among patients with Chronic Lymphocytic Leukemia (CLL), focusing on disease markers, functional capacity, immune parameters, and quality of life. This baseline analysis includes treatment-naïve participants enrolled between September 2023 and August 2024, prior to randomization. Eleven patients (aged 47–78 years) underwent assessments of body composition, cardiovascular fitness, muscular strength, and immune profiling. Quality of life was evaluated using validated questionnaires (FACIT-F, EORTC QLQ-30/CLL17), and daily activity was objectively measured via accelerometry. Correlation analyses examined associations between physical activity, muscle strength, lean mass, and physical aptitude. Despite high self-reported physical function, participants demonstrated suboptimal body composition and cardiovascular fitness. Accelerometry revealed marked sedentary behavior, particularly among females, and overall activity levels were below current recommendations. Moderate-to-vigorous physical activity correlated positively with muscular strength and lean mass. Immune profiling identified a variability in key markers, warranting further investigation of their relationship with physical activity. These findings highlight the need for tailored interventions to increase activity and reduce sedentary time in CLL patients and support incorporating functional and immune monitoring into survivorship care. Full article