Enhance Patient Care Research Articles

DI CVD TRI Layer CX Classifier for Secure IoT Enabled Risk Prediction Model

This paper introduces a novel Di-CVD Tri-Layer CX Classifier, an IoT-integrated and machine learning (ML)-driven framework, to predict the individual and joint risk of diabetes (DB) and heart disease (HD). The proposed model comprises three phases: secure IoT-based data collection using Enhanced BGV encryption with Dynamic Distributed Hashing (DDH); a feature extraction (FE) phase leveraging (IGO) Information Gain Ratio and disease-specific ranking and a three-step classifier—Cm-Ro (FS) feature selection, hierarchical XGBoost classification, and synergistic prioritized risk scoring. By integrating multi-attribute features, rule-free optimization, and enhanced interoperability, the model addresses critical challenges such as heterogeneous data formats, poor feature relevance, and low interoperability in previous studies. When compared to conventional classifiers such as SVM and standard XGBoost, experimental evaluation on the NHANES dataset shows improved performance in terms of accuracy (ACC), recall (R), precision (P), and F1-score. The outcomes validate the framework’s effectiveness in early, secure, and individualized risk prediction, offering substantial support for timely interventions and enhanced patient care.

Hematopoietic Cell Transplantation in Brazil: A National Benchmarking Study Focused on the Foundation for the Accreditation of Cellular Therapy (FACT) Performance Indicators

Systematic evaluation of hematopoietic cell transplantation (HCT) outcomes is essential to improve clinical practice and meet international quality standards. In Brazil, the partnership between the Brazilian Society of Cellular Therapy and Bone Marrow Transplantation (SBTMO) and the Center for International Blood and Marrow Transplant Research (CIBMTR) has advanced national data reporting and benchmarking through the Hematopoietic Cell Transplantation Brazilian Registry (HCTBR). This study reports outcomes from 11,210 first HCTs (5,984 allogeneic; 5,226 autologous) performed between 2012 and 2023 across 44 Brazilian centers. Median recipient age was 29 years for allogeneic and 53 years for autologous transplants. Acute leukemias predominated among allogeneic cases, while multiple myeloma was the most common indication for autologous HCT. Two-year overall survival was 82.0% for autologous and 59.8% for allogeneic transplants, with variation by donor type (matched related 61.8%, mismatched related 54.0%, unrelated 63.3%). Two-year non-relapse mortality was 8.0% and 21.6% for autologous and allogeneic transplants, respectively. The cumulative incidence of grade II–IV acute graft-versus-host disease (GVHD) at two years was 29.9%, with chronic GVHD incidence of 29.5%. Two-year relapse incidence was 24.1% for allogeneic and 25.8% for autologous HCT. Despite challenges within the Brazilian healthcare system, these outcomes align with international registry data. Adequate data completeness supports the robustness of these findings. Our results highlight the quality of Brazilian transplant programs and underscore the value of standardized outcome monitoring to foster continuous improvement. Strengthening center participation, follow-up, and data management remains critical to maintaining registry quality and enhancing patient care.

The imaging support workforce: Stakeholder perceptions of role, impact and career progression.

The imaging support workforce: Stakeholder perceptions of role, impact and career progression.

Cultivating expertise in MRI physics in Mongolia through international collaboration.

Cultivating expertise in MRI physics in Mongolia through international collaboration.

Inside the Pharmacy: A qualitative Study Uncovering Community Pharmacists' Experiences with Paxlovid Prescribing.

Inside the Pharmacy: A qualitative Study Uncovering Community Pharmacists' Experiences with Paxlovid Prescribing.

The role of simulation in medical education, clinical risk management, and enhancing patient care in cardiology

In applied sciences, including medicine, simulation refers to a model of reality that employs a variety of techniques and technologies, along with diverse professional expertise, to facilitate the dynamic analysis and prediction of events or processes based on specific predefined conditions. Simulation is of paramount importance to improve the skills of medical staff, to speed up learning and to optimize clinical practice in different settings, including cardiology. Literature shows that simulation is more effective than other learning strategies, supporting both upgrading of staff's clinical skills and patients' safety, reducing the risk of medical error. Moreover, andragogical principles highlight the need for personalized training programs, in order to meet healthcare professionals' needs, while practicing in a safe environment, improving technical skills, clinical decision making, stress management, cooperation, and teamwork. This review written by the Management and Quality Working Group, by the Young Cardiologists Working Group, and by the Professional Responsibility and Safety of Care Study Group of the the Italian Association of Hospital Cardiologists (ANMCO) highlights the crucial role of simulation in managing high-risk situations commonly encountered in cardiology, emphasizing the importance of continuous high-quality training. It also describes how ANMCO is promoting simulation as a strategy for implementing quality in the field of cardiology.

Empowering advanced practice radiation therapists through medical directives: A progressive step in radiation therapy in Canada.

Empowering advanced practice radiation therapists through medical directives: A progressive step in radiation therapy in Canada.

Patient initiated follow-up for incisional hernia repair

Objectives: This study detailed the outcomes of operatively managed incisional hernia and evaluated the feasibility of patient-initiated follow-up. Methods: A retrospective cohort study was conducted on 71 adult patients (patients) who underwent elective incisional hernia repair from 2021 to 2024 at a tertiary center. Seventy-one adult patients who underwent elective incisional hernia repair and attended follow-up were included in the study. The cohort comprised 45 females (63.4%) and 26 males (36.6%), with a median age of 57 years (range 31–78). The type of hernia repair, postoperative complications, emergency department (ED) visits post-discharge, and outcomes from the first outpatient review were studied. The need for changes in management during follow-up was assessed. Results: Out of 77 patients, 71 patients were included after exclusion of those who had in-hospital complications. Of these, 54 had ventral hernias, nine had post-nephrectomy, four had parastomal, and four combined ventral and parastomal hernias. Only 7 patients (9.9%) required changes in management during the first outpatient clinic appointment (P < 0.05) with median (interquartile range) waiting time of 8(5) weeks. Nine patients (12.7%) visited the ED before their scheduled clinic appointment for pain, seroma, hematoma, or wound complications. Conclusion: The low rate of management changes and limited ED visits suggested that patient patient-initiated follow-up model could safely replace routine follow-up appointments for post-incisional hernia repair. This transition could optimize outpatient services, reduce wait times, and potentially offer cost savings for both healthcare and patients. By minimizing routine appointments, healthcare resources can be allocated more efficiently, enhancing patient care and reducing overall healthcare expenditures.

Exploring Sinomenine: New frontier in early brain injury treatment

Dear Editor, Sinomenium is a rare plant alkaloid that releases histamine upon mast cell degranulation in mammalian tissue, It has been said that roots and the stem of the plant “Sinomenium Acutum” have been traditionally used to cure rheumatoid arthritis and neuralgia [1]. Sinomenium has shown beneficial physiological effects. It tends to possess various properties such as acting as an anti-inflammatory, anti-hypertensive, anti-arrhythmic and can even be utilized as an analgesic [2]. Furthermore, studies have shown that sinomenine can be used to slow tumour growth, its spread, and invasion while promoting cell death and effectively suppressing various types of cancers. Moreover, it has also proven to be favourable for different cardiovascular diseases. Possible drug reactions between sinomenine and other cardiovascular medications suggest promising prospects for its utilisation in the prevention or treatment of atherosclerosis [2,3]. The therapeutic versatility of this plant alkaloid extract has caught the attention of many scientists as a recent study has highlighted the important role of sinomenium in cases of traumatic brain injury. The study analysed how Sinomenine affects early brain injury and its molecular mechanisms after a subarachnoid haemorrhage. As of now, there is no effective treatment for early brain injury from subarachnoid haemorrhage due to its unclear molecular processes. [4]. The study utilized the peri chiasmatic cistern model in rats and injected them with their own blood, the results showed that sinomenium supplementation reduced brain oedema and improved neurological scores. It's proposed that sinomenium could potentially safeguard the brain and enhance neurological functions by suppressing the expression of apoptotic factors induced by early brain injury, moreover, it was also shown that this plant alkaloid could also inhibit microglial inflammatory response through Nrf2 pathway after a subarachnoid haemorrhage [4]. Nrf2 is an important regulator encouraging antioxidant activity, detoxification, and anti-inflammatory responses in cells. It protects multiple organs and plays a crucial role in recovery after subarachnoid haemorrhage. [4, 5]. This discovery could revolutionize emergency/trauma patient management as it can make an impact by enhancing patient care and can drastically increase the survival rate of patients suffering from any sort of traumatic brain injury by rapidly improving patient prognosis and reducing the rate of mortality. ---Continue

Developing a Machine Learning Model for Colon Cancer Detection from Colonoscopy Data

Colon cancer is one of the leading causes of cancer- related deaths globally. Early detection and accurate diagnosis are crucial for improving patient outcomes and survival rates. Colonoscopy remains the gold standard for detecting colon cancer,yet the process is highly dependent on the expertise of the physician and can be time-consuming. In this project, we aim to develop an automated machine learning model for the detection of colon cancer from colonoscopy images and videos. We explore various machine learning techniques, including Con- volutional Neural Networks (CNNs), to analyze colonoscopy data for the identification of polyps, tumors, and other abnormalities indicative of cancerous growths. The dataset used includes a large set of labeled colonoscopy images, and the model is trained to classify the presence of cancerous lesions, distinguishing between benign and malignant cases. Data preprocessing techniques, such as image normalization, augmentation, and segmentation, are employed to improve the accuracy and robustness of the model. The performance of the model is evaluated using standard metrics, including accuracy, precision, recall, and F1 score, with a particular focus on its ability to generalize to unseen data. Preliminary results demonstrate that machine learning models, particularly deep learning approaches, can effectively assist in early colon cancer detection, reducing the burden on healthcare professionals and providing faster, more accurate diagnoses. This research highlights the potential of AI-driven tools in improving colorectal cancer screening processes, ultimately contributing to the reduction of mortality rates and enhancing patient care.

Putting the patient first: Should general practitioners start people with probable Parkinson's disease on levodopa while awaiting diagnostic confirmation?

Parkinson's disease poses challenges for timely diagnosis and specialist care, particularly in rural areas. This paper aims to assist general practitioners (GPs) who wish to collaborate with their patient with probable Parkinson's disease to improve access to appropriate medication when there might be a delay in obtaining a confirmatory diagnosis from a Parkinson's disease specialist. The feasibility and rationale for commencing levodopa as well as an approach to initiating and monitoring its response are discussed. The importance of educating patients and caregivers, encouraging exercise and building a multidisciplinary team to optimise care is also discussed. The literature supports early levodopa initiation in probable Parkinson's disease to improve a patient's quality of life. The presented approach offers GPs effective management strategies that enhance patient care and mitigate the risks of delayed treatment.

A supervised machine learning approach for predicting the need for postsurgical intervention in acromegaly.

Patients with growth hormone (GH)-secreting pituitary adenomas (PAs) experience various symptoms and comorbidities, which can ultimately lead to increased mortality. This study aimed to develop and validate a machine learning (ML) model for predicting long-term outcomes in patients with GH-secreting PAs following endonasal transsphenoidal surgery (ETS). The authors conducted a retrospective three-institution cohort study that included patients with GH-secreting PAs treated with ETS between 2013 and 2023. Clinical, radiological, and biochemical data were collected. The main outcome of interest was the intervention-free rate (IFR) after primary ETS. Supervised ML algorithms, including decision trees and random forests, were developed to predict the IFR. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC) and Shapley Additive Explanations (SHAP) values. The median follow-up for 100 patients with GH-secreting PAs (53% female) was 64 months (range 1-130 months). Additional intervention for persistent or recurrent acromegaly was required in 32% of patients. Following primary ETS alone, the 3-year IFR was 70% and the 5-year IFR was 67%. Multiple ML models were developed and evaluated using AUROCs. The decision tree analysis achieved an accuracy of 81% and emphasized the importance of both gross-total resection (GTR) and patient age in determining the long-term IFR. To better understand the factors that contributed to model performance, SHAP analysis was applied to the best-performing model. The SHAP dependence plots showed that key factors associated with a longer IFR included tumor size < 9 mm, GTR, patient age > 65 years, and Knosp grade 0. This ML model offers a more nuanced and potentially more accurate approach to identify patients more likely to develop recurrent or persistent acromegaly following primary ETS and require additional treatment. Following external validation, this ML model could improve personalized treatment planning and follow-up strategies and enhance patient care and resource allocation in clinical practice.

Regulatory Issues and Challenges to Artificial Intelligence Adoption in Ophthalmology: What Lies Ahead?

Regulatory Issues and Challenges to Artificial Intelligence Adoption in Ophthalmology: What Lies Ahead?

Childhood-Onset Systemic Lupus Erythematosus: Pregnancy and Birth Outcomes in Ontario

ObjectivesChildhood-onset systemic lupus erythematosus (cSLE) is a chronic, multisystem, autoimmune disease. Pregnancy and birth outcomes of cSLE are not well understood. Our objectives were to describe and evaluate pregnancy, neonatal, and maternal outcomes among female cSLE patients in Ontario, and to identify demographic and disease characteristics associated with adverse outcomes.MethodsA population-based retrospective cohort study linked clinical data for eligible female cSLE patients diagnosed between 1985 and 2011 and followed for ≥1 year from date of diagnosis to March 31, 2023, with multiple health administrative datasets housed at the Institute for Clinical Evaluative Sciences. Descriptive statistics, adjusted, and univariate analyses were used to determine significant associations between risk factors (including demographic and early disease characteristics) and adverse outcomes.Results489 female cSLE patients were diagnosed between 1985-2011 and followed for 16.8±7.2 years. A total of 423 pregnancies occurred in 175 women. 131 women had at least 1 live birth while 44 had no live births. 46.1% pregnancies resulted in fetal death (including still birth, miscarriage or abortion), 32% of live births were preterm, and 33.3% of neonates were admitted to neonatal intensive care (Table 1). Our adjusted analysis shows that patients who were older at time of cSLE diagnosis have lower odds of fetal death [OR= 0.87, 95% CI (0.78-0.97)], after controlling for years since cSLE diagnosis, ethnicity, income, anti-dsDNA antibodies, and biopsy-proven lupus nephritis. Our univariate analyses show that odds of preterm birth are higher for patients with non-white ethnicity [OR=2.43, 95% CI (1.22-4.85)], anti-Sm antibodies [OR=2.82, 95% CI (1.43-5.56)], and biopsy-proven lupus nephritis [OR=2.51, 95% CI (1.27-4.98)].Table 1:Pregnancy, neonatal, and maternal outcomes among female cSLE patientsConclusionInvestigating pregnancy, neonatal, and maternal outcomes is crucial for providing targeted health care for cSLE patients and their newborns. Factors such as age at diagnosis, non-white ethnicity, and early disease characteristics like anti-Sm antibodies, and biopsy-proven lupus nephritis are significantly associated with adverse pregnancy and birth outcomes. Understanding these associations will enhance patient care and improve health resource management.

Unveiling the complexities of patient safety in hospital settings: A holistic approach to overcoming challenges.

Unveiling the complexities of patient safety in hospital settings: A holistic approach to overcoming challenges.

Diagnostic efficacy of large language models in the pediatric emergency department: a pilot study

BackgroundThe Pediatric Emergency Department (PED) faces significant challenges, such as high patient volumes, time-sensitive decisions, and complex diagnoses. Large Language Models (LLMs) have the potential to enhance patient care; however, their effectiveness in supporting the diagnostic process remains uncertain, with studies showing mixed results regarding their impact on clinical reasoning. We aimed to assess LLM-based chatbots performance in realistic PED scenarios, and to explore their use as diagnosis-making assistants in pediatric emergency.MethodsWe evaluated the diagnostic effectiveness of 5 LLMs (ChatGPT-4o, Gemini 1.5 Pro, Gemini 1.5 Flash, Llama-3-8B, and ChatGPT-4o mini) compared to 23 physicians (including 10 PED physicians, 6 PED residents, and 7 Emergency Medicine residents). Both LLMs and physicians had to provide one primary diagnosis and two differential diagnoses for 80 real-practice pediatric clinical cases from the PED of a tertiary care Children's Hospital, with three different levels of diagnostic complexity. The responses from both LLMs and physicians were compared to the final diagnoses assigned upon patient discharge; two independent experts evaluated the answers using a five-level accuracy scale. Each physician or LLM received a total score out of 80, based on the sum of all answer points.ResultsThe best performing chatbots were ChatGPT-4o (score: 72.5) and Gemini 1.5 Pro (score: 62.75), the first performing better (p &amp;lt; 0.05) than PED physicians (score: 61.88). Emergency Medicine residents performed worse (score: 43.75) than both the other physicians and chatbots (p &amp;lt; 0.01). Chatbots' performance was inversely proportional to case difficulty, but ChatGPT-4o managed to match the majority of the correct answers even for highly difficult cases.DiscussionChatGPT-4o and Gemini 1.5 Pro could be a valid tool for ED physicians, supporting clinical decision-making without replacing the physician's judgment. Shared protocols for effective collaboration between AI chatbots and healthcare professionals are needed.

Cone Beam Computed Tomography-Guided Online Adaptive Radiation Therapy: Clinical Insights From a Nationwide Staffing Survey.

Cone Beam Computed Tomography-Guided Online Adaptive Radiation Therapy: Clinical Insights From a Nationwide Staffing Survey.

Regional differences in experiences of patients with metastatic breast cancer in the Republic of Ireland and Northern Ireland: a comparative analysis (CTRIAL-IE 23-05).

Metastatic breast cancer (MBC) presents significant psychological, social and financial challenges. Differences in the healthcare systems of the Republic of Ireland (ROI) and Northern Ireland (NI) may impact patient care experiences. This study aimed to explore regional differences in the experiences of patients with MBC between ROI and NI. A patient-developed cross-sectional survey titled 'Patient-led Metastatic Breast Cancer Survey' was administered online to patients with MBC in ROI and NI from July to October 2023. The survey included 76 questions addressing demographics, understanding of diagnosis, mental health, financial burden, time spent managing cancer care (time toxicity), palliative care, sexual health, exercise and access to information. These topics were selected by patients with MBC as being most impactful. Responses from 246 patients (196 ROI, 50 NI) were analysed using descriptive and comparative statistics. Psychological distress was highly prevalent in both regions; however, NI patients were more likely to receive medications for psychological distress (51% NI vs 23.7% ROI, p=0.0008). Financial strain was more pronounced in ROI, with 77.5% feeling they had no control over their medical care spending, compared with 56% of NI patients (p=0.0124). Time toxicity was also higher in ROI, where patients reported more frequent visits to oncology day wards and acute oncology service units (p=0.0012) and spent more time in these settings (p=0.038). Participation in exercise programmes was significantly higher in NI compared with ROI (p<0.0001). Additionally, palliative care referrals were more commonly accepted or considered in NI than in ROI. This study, the first of its kind, highlights important disparities observed in this cohort of patients with MBC across ROI and NI. Bidirectional learning could enhance patient care experiences, with NI potentially focusing on psycho-oncology integration and ROI expanding strategies to reduce time toxicity and financial burden for patients.

The role of glutathione S-transferases in human disease pathogenesis and their current inhibitors.

Glutathione S-transferases (GSTs) are a family of enzymes detoxifying various harmful compounds by conjugating them with glutathione. While primarily beneficial, dysregulation of GST activity or specific isoforms can contribute to disease pathogenesis. The intricate balance of detoxification processes regulated by GSTs is pivotal in cellular homeostasis, whereby dysregulation in these mechanisms can have profound implications for human health. Certain GSTs neutralize carcinogens, shielding cells and potentially preventing tumorigenesis. Polymorphisms in specific GSTs may result in the accumulation of toxic metabolites, exacerbating oxidative stress, inflammation, and DNA damage, notably observed in neurodegenerative diseases like Parkinson's disease. They can also modulate signaling pathways involved in cell proliferation, survival, and apoptosis, with aberrant activity potentially contributing to uncontrolled cell growth and resistance to cell death, thus promoting cancer development. They may also contribute to autoimmune diseases and chronic inflammatory conditions. This knowledge is useful for designing therapeutic interventions and understanding chemoresistance due to GST polymorphisms. A variety of GST inhibitors have been developed and investigated, with researchers actively working on new inhibitors aimed at preventing off-target effects. By leveraging knowledge of the involvement of specific GST isoforms in disease pathogenesis across different populations, more effective and targeted therapeutics can be designed to enhance patient care and improve treatment outcomes.

Pediatric traumatic brain injury: precision risk assessment models and an online calculator for enhanced patient care.

Pediatric traumatic brain injury: precision risk assessment models and an online calculator for enhanced patient care.