Search Results (73)

Hospital readmissions within 30 days of discharge are a key metric of healthcare quality and a major driver of cost. Accurate risk stratification enables targeted home care interventions, such as remote monitoring, timely nurse follow-up, and medication adherence programs, designed to mitigate preventable readmissions. Thus, we conducted a systematic comparison of structured electronic health record (EHR) data and unstructured discharge summaries for predicting 30-day unplanned readmissions. Using the MIMIC-IV database, we integrated admissions, emergency department records, laboratory values, and discharge notes, and we restricted the cohort to ED-based readmissions. Following rigorous preprocessing, we balanced the dataset and split it into training, validation, and test sets at the patient level. Structured features, including the LACE score (length of stay, acuity of admission, comorbidities, and ED utilization) and triage vitals, were modeled with logistic regression, random forest, XGBoost, and LightGBM. Discharge notes were analyzed with ClinicalLongformer to generate contextual embeddings and with Qwen2.5-7B-Instruct for few-shot classification. ClinicalLongformer achieved the best discrimination (AUROC = 0.72, F1 = 0.68), outperforming classical ML baselines (AUROC ≈ 0.65–0.67, F1 ≈ 0.64–0.65). The LLM (Qwen2.5-7B-Instruct) yielded moderate discrimination (AUROC = 0.66, F1 = 0.65) while providing interpretable chain-of-thought rationales. These findings highlight the value of narrative data for risk stratification and suggest that transformer-based language models have the potential to enable scalable, explainable early-warning systems to guide home care and prevent avoidable readmissions. Full article

Background: While mechanical alignment total knee arthroplasty (TKA) has long been the conventional surgical technique in patients with advanced osteoarthritis, kinematic alignment TKA has emerged as a promising alternative, designed to restore the knee’s native pre-arthritic anatomy. Since superiority of either technique remains inconclusive, we aimed to compare immediate and short-term postoperative outcomes of kinematic versus mechanical alignment TKA. Methods: This prospective cohort study was conducted at a tertiary care centre between January 2020 and August 2022, enrolling kinematic and mechanical alignment TKA patients. Outcomes were assessed during hospitalization and at 14 days postoperatively. Data collected included patient-reported outcome measures (PROMs), functional performance evaluations, pain scores, discharge disposition and hospital length of stay. Both univariate and multivariate regression analyses were conducted, adjusting for potential confounders. Results: The study included 103 patients, with 77 who underwent kinematic alignment and 26 mechanical alignment TKA. Patients in the kinematic alignment group demonstrated statistically significant better postoperative outcomes compared to those in the mechanical alignment group. Kinematic alignment TKA patients demonstrated superior functional performance on the Timed Up and Go test immediately postoperatively and were more frequently discharged home rather than to a rehabilitation facility. Hospital stay length and short-term PROMs also favoured the Kinematic alignment TKA group, showing statistically significant higher scores in the Oxford Knee Score, short form-12 Mental Component Summary, and the Knee Injury and Osteoarthritis Outcome Score Symptoms subscale. Conclusions: Kinematic alignment TKA offers superior immediate and short-term outcomes compared to mechanical alignment TKA, with benefits in functional recovery, hospitalization duration, and discharge disposition. This evidence supports kinematic alignment TKA as a viable alternative, aiding in patient and surgeon decision-making. Full article

Trauma often causes long-lasting functional impairment, but the extent varies across populations. This study investigated disability six months after moderate to severe injury and identified sociodemographic and early injury-related predictors, including estimated rehabilitation complexity. Further, we assessed the implementation of direct transfer from acute care in the trauma centre to specialised inpatient rehabilitation, bypassing local hospitals. In this prospective study 398 adults, treated from January 2020 to January 2021 at two Norwegian trauma centres, were included. Self-reported disability was measured using the 12-item World Health Organization Disability Assessment Schedule 2.0. Ordinal logistic regression was applied to identify predictors of the 6-month disability outcome. At follow-up, 22% reported no disability, 49% mild/moderate and 29% severe. In multivariable analyses, low education, comorbidities, number of injuries and higher estimated rehabilitation complexity at discharge from acute care were significantly associated with greater disability. Only 20% were transferred directly to specialised inpatient rehabilitation, while 17% went via local hospitals. Participants with orthopaedic injuries and women were less likely to be transferred directly. In summary, most participants experienced some disability at 6 months. Indirect pathways to specialised rehabilitation via local hospitals remained common. Understanding predictors of disability and optimising rehabilitation pathways may improve trauma rehabilitation outcomes, highlighting the need for guidelines that identify patients with high rehabilitation needs. Full article

Background: The influence of hospitalization owing to pneumonia on changes in body composition has not been specifically reported. We conducted a prospective cohort study of patients with community-acquired pneumonia (CAP) requiring hospitalization to test the hypothesis that hospitalization affects body composition. Methods: Sixty-four consecutive patients with CAP were recruited. Body composition was measured within 24 h of admission and 24 h before discharge using bioelectrical impedance analysis. The association between changes in body composition and variables obtained at admission was investigated. Index values were calculated as weight divided by height squared. Results: The mean age of the patients was 76.0 ± 8.7 years (78.1% males). The median length of hospitalization was 12.0 days. Weight, body mass index (BMI), skeletal muscle (SM), SM index, fat-free mass (FFM), and FFM index significantly decreased (p < 0.001 for each), but fat mass (FM) and FM index did not. The serum total protein level was the only independent predictor of the lowest quartile of change in SM index (<−0.4) after adjusting for age and sex (p = 0.004). Conclusions: In summary, weight and BMI significantly decreased during hospitalization in patients with CAP, which was attributed to SM reduction. Patients with low serum total protein levels on admission were at risk of an accelerated decrease in the SM index. Nutritional intervention and rehabilitation are important for these patients. Full article

Currently, knowledge of the effects of different frequencies of administration of bedside physiotherapy programs (PTPs) on hospitalized COVID-19 patients is limited. Therefore, this study aimed to compare the effects of administering PTPs once or twice during hospitalization versus daily PTPs until discharge. Fifty-two COVID-19 patients were equally assigned to two groups, matched by gender and age (1:1 ratio). Experimental Group 1 (Ex-G1) received PTPs one to two times during hospitalization, while Experimental Group 2 (Ex-G2) received daily PTPs until discharge. The outcomes assessed included the survival rate, length of hospitalization (LoH), intensive care unit (ICU) referrals, and in-hospital complications. Most participants were classified as having mild to moderate COVID-19, with a mean age of 45 years. No significant differences were observed between the groups in all primary outcomes, including the survival rate (p = 1.000), LoH (p = 0.117), ICU referrals (p = 0.313), and complications (p = 0.555). The overall survival rate was 98%. One Ex-G2 participant was referred to the ICU, while complications occurred in two Ex-G1 and four Ex-G2 participants. In summary, for patients with mild to moderate COVID-19, one to two bedside physiotherapy sessions produced comparable results to daily physiotherapy in terms of the survival rate, LoH, ICU referrals, and in-hospital complications. Full article

Sepsis is defined as a life-threatening organ dysfunction caused by a dysregulated host response to infection. The number of patients with sepsis requiring critical care admission is increasing. At the same time, overall mortality from sepsis is declining. With increasing survival to hospital discharge, there are an increasing number of sepsis survivors whose care needs shift from the acute to chronic care settings. Recently, the phrase “post-sepsis syndrome” has emerged to encompass the myriad of complications in patients recovering from sepsis. The aim of this narrative review is to provide a contemporary summary of the available literature on post-sepsis care and highlight areas of ongoing research. There are many incentives for improving the quality of survivorship following sepsis, including individual health-related outcomes (e.g., increased survival, enhanced physical and psychological health) and wider socio-economic benefits (e.g., reduced economic burden on the healthcare systems, reduced physical and psychological burden on carers, ability for individuals (and carers) to return to workforce). Modifiable factors influencing long-term outcomes can be in-hospital or after discharge, when primary care physicians play a pivotal role. Despite national and international guidance being available, this area has been under-recognised historically, despite its profoundly negative impact on both patients and their families or caregivers. Contributing factors likely include the lack of a formally recognised “disease” or pathology, the presence of challenging-to-treat symptoms such as fatigue, weakness and cognitive impairment, and the prevailing assumption that ongoing rehabilitation merely requires time. Our review will focus on the following areas: screening for new cognitive and physical impairments; optimisation of pre-existing comorbidities; transition to primary care; and palliative care. Primary care physicians may have a crucial role to play in improving outcomes in sepsis survivors, and candidate interventions include education on common complications of post-sepsis syndrome. Full article

Objective: Electronic health records (EHRs) are becoming increasingly important in both academic research and business applications. Recent studies indicate that predictive tasks, such as heart failure detection, perform better when the geometric structure of EHR data, including the relationships between diagnoses and treatments, is considered. However, many EHRs lack essential structural information. This study aims to improve predictive accuracy in healthcare by constructing a Patient Knowledge Graph Ensemble Framework (PKGNN) to analyse ICU patient cohorts and predict mortality and hospital readmission outcomes. Methods: This study utilises a cohort of 42,671 patients from the MIMIC-IV dataset to build the PKGNN framework, which consists of three main components: (1) medical note extraction, (2) patient graph construction, and (3) prediction tasks. Advanced Natural Language Processing (NLP) models, including Clinical BERT, BioBERT, and BlueBERT, extract and integrate semantic representations from discharge summaries into a patient knowledge graph. This structured representation is then used to enhance predictive tasks. Results: Performance evaluations on the MIMIC-IV dataset indicate that the PKGNN framework outperforms state-of-the-art baseline models in predicting mortality and 30-day hospital readmission. A thorough framework analysis reveals that incorporating patient graph structures improves prediction accuracy. Furthermore, an ensemble model enhances risk prediction performance and identifies crucial clinical indicators. Conclusions: This study highlights the importance of leveraging structured knowledge graphs in EHR analysis to improve predictive modelling for critical healthcare outcomes. The PKGNN framework enhances the accuracy of mortality and readmission predictions by integrating advanced NLP techniques with patient graph structures. This work contributes to the literature by advancing knowledge graph-based EHR analysis strategies, ultimately supporting better clinical decision-making and risk assessment. Full article

Background/Objectives: This article presents the case of a 31-year-old primigravida who experienced acute liver failure in the 23rd week of pregnancy, along with a review of the literature on this rare condition during pregnancy. The purpose of this publication is to highlight the diagnostic and therapeutic challenges associated with acute liver failure in pregnant women. Methods: The patient presented with jaundice, pruritus, and dark-colored urine. Laboratory tests revealed a significant increase in aminotransferase, bilirubin, and bile acid levels, suggesting liver problems; however, due to the patient’s rapidly deteriorating condition and test results, autoimmune hepatitis was considered. Viral infections and other causes of liver damage were excluded. No clear diagnosis was established. The patient was administered ursodeoxycholic acid and due to her worsening condition, a cesarean section was performed at 23 weeks of gestation. After delivery, the patient’s condition improved, although she did experience cardiac arrest during hospitalization. The patient was discharged with a diagnosis of acute liver failure in the course of an overlap syndrome of autoimmune hepatitis and primary cholangitis or intrahepatic cholestasis of pregnancy. No abnormalities were noted during a follow-up visit 6 weeks after delivery. Despite a detailed case analysis, a final diagnosis was not established, which complicates planning for future pregnancies. Discussion: Several liver conditions can occur during pregnancy, including intrahepatic cholestasis of pregnancy, primary biliary cholangitis, and autoimmune hepatitis. Diagnosing these conditions can be challenging due to overlapping symptoms and metabolic and immunological adaptations during pregnancy that can affect the course of liver diseases. Rapid intervention is crucial to protect the health of both the mother and the fetus. Conclusions: In summary, this article aims to increase awareness of the complexities surrounding acute liver failure during pregnancy, highlighting the diagnostic challenges and importance of prompt medical intervention for the well-being of both the mother and the child. This paper aims to provide a comprehensive overview of the complexities surrounding acute liver failure during pregnancy, aiming to improve the understanding, diagnosis, and management of this condition. Full article

Caudal regression syndrome (CRS) is a malformation that occurs during the fetal period, and is mainly characterized by the incomplete development of the spinal cord (SC), which is often accompanied by other developmental abnormalities. The present study was performed in a 2-month-old boy with CRS, born to a type I diabetic mother, who presented interruption of the SC at the L5–L4 level, pelvic dislocation, sacral agenesis, hypoplastic femurs, lack of innervation of the lower limbs (spastic paraplegia), and a neurogenic bladder and bowel. Given the positive results we obtained in a previous study in a similar case, this patient was treated with GH (0.04 mg/kg/day, 5 days/week), melatonin (20 mg/day), and rehabilitation. The treatment only lasted 18 months, due to family problems. Blood tests and physical examinations were performed every 3 months initially and then every 6 months. Interestingly, despite GH administration, the child presented low plasma glucose and IGF-I values, which did not increase throughout the treatment, although there was significant growth of the patient, also indicated by elevated plasma alkaline phosphatase values. At the end of treatment, the gross motor function test (GMFM)-88 score increased from 0.93 (on admission) to 47.94. Sensory responses appeared in the lower limbs, and the patient was able to move his leg muscles in all directions and control his sphincters. Ten months after discharge, the patient was able to walk only with the aid of a back walker. GH treatment did not produce any adverse effects. In summary, despite the short duration of treatment, GH plus rehabilitation has been useful in innervating distal areas below the level of the incomplete spinal cord in CRS. GH likely acted on ependymal neural stem cells, as the hormone does on neurogenic niches in the brain, and rehabilitation helped achieve near-full functionality. Full article

Background/Objectives: Clavicle injuries are common and seem to be frequently subject to diagnostic misclassification. The accurate identification of clavicle fractures is essential, particularly for registry and Big Data analyses. This study aims to assess the frequency of diagnostic errors in clavicle injury classifications. Methods: This retrospective study analyzed patient data from two Level 1 trauma centers, covering the period from 2008 to 2019. Included were cases with ICD-coded diagnoses of medial, midshaft, and lateral clavicle fractures, as well as sternoclavicular and acromioclavicular joint dislocations. Radiological images were re-evaluated, and discharge summaries, radiological reports, and billing codes were examined for diagnostic accuracy. Results: A total of 1503 patients were included, accounting for 1855 initial injury diagnoses. In contrast, 1846 were detected upon review. Initially, 14.4% of cases were coded as medial clavicle fractures, whereas only 5.2% were confirmed. The misclassification rate was 82.8% for initial medial fractures (p < 0.001), 42.5% for midshaft fractures (p < 0.001), and 34.2% for lateral fractures (p < 0.001). Billing codes and discharge summaries were the most error-prone categories, with error rates of 64% and 36% of all misclassified cases, respectively. Over three-quarters of the cases with discharge summary errors also exhibited errors in other categories, while billing errors co-occurred with other category errors in just over half of the cases (p < 0.001). The likelihood of radiological diagnostic error increased with the number of imaging modalities used, from 19.7% with a single modality to 30.5% with two and 40.7% with three. Conclusions: Our findings indicate that diagnostic misclassification of clavicle fractures is common, particularly between medial and midshaft fractures, often resulting from errors in multiple categories. Further prospective studies are needed, as accurate classification is foundational for the reliable application of Big Data and AI-based analyses in clinical research. Full article

Snakebites caused by Bothrops snakes are the most prevalent in the Amazon region, causing local and systemic complications. Local complications are mostly represented by necrosis, secondary bacterial infection and compartment syndrome. There are reports of long-term disabilities, but their burden is poorly investigated. This study aims to describe and estimate the frequency of physical and sensory long-term disabilities from Bothrops snakebites in the Manaus Region, in the western Brazilian Amazon region. Participants were >18-years individuals that accepted to return to the hospital 3–12 months (average follow-up time of 195 days) after the discharge for neuromusculoskeletal, chronic pain and sensory assessments. Assessment of disability was also performed using the World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0). Factors associated with summary disability using WHODAS 2.0 were identified. Fifty participants were enrolled. A frequency of 20% of the participants reported difficulty in moving the affected limb (20%), and 23.7% reported difficulty in walking. Limitations of daily activities were reported by 26% of the patients. Decreased strength of the affected limb was observed in 22% of the patients. Decreased range of joint motion was seen in 20% of the patients. Chronic pain was reported in 48% of the patients. Tactile sensibility was decreased in 30%, thermal sensibility in 14%, painful sensibility (hypoalgesia) in 12%, kinetic-postural sensibility (hypokinesthesia) in 4% and vibratory sensibility was decreased or abolished in 16% of the participants. Cognition and mobility domains were those with the highest frequencies of participants with any degree of disability, each with 57%. The summary WHODAS 2.0 disability rate was 59%. Age > 59 years (p = 0.02)] was associated with protection against disability. Difficulty in moving the limb (p = 0.05), pain at the affected limb (p < 0.01), limitations of daily activities (p < 0.01) and decreased thermal sensibility (p = 0.05) were significantly associated with disability. The present study consists of the first follow-up investigation involving Bothrops snakebite patients related to long-term disabilities. These findings represent important data on Bothrops snakebites causing clinically significant long-term neuromusculoskeletal and sensory disabilities, resulting in reduced quality of life of the patients. Full article

This study analyzed the trend and factors associated with medical–surgical complications in patients discharged from leprosy multidrug therapy at the Centre Hospitalier Régional Spécialisé (CHRS), in Macenta, Republic of Guinea. This was a retro 2012 (n = 54) and 2013 (n = 35) and then a slight decrease between 2014 (n = 34) and 2017 (n = 26). From 2019 (n = 18) to 2021 (n = 1), a significant d spective study using routine secondary data from 2012 to 2021. The most represented age group ranged from 25 to 59 years (73.8%), with a male predominance of 72.6%. Farmers represented 60.7% of the patients, 74.5% of the patients had plantar wounds, and 48.8% resided in the N’zerekore region. A trend analysis showed an overall significant decrease in the number of patients with complications between ecline was found. In the patients with leprosy reactions, there was a reduction in numbers from 48 in 2012 to 2 in 2014, with a predominance in men. There were significant associations between region, plantar perforation disease (p = 0.013), and physical disability (p = 0.029) and between year and leprosy reaction after the cure (p < 0.001). In summary, there was a high proportion of patients with plantar ulcers, which predominantly affected farmers, and a significant proportion with leprosy reactions and physical disabilities. Community awareness around leprosy and capacity building of the providers in terms of appropriate management may contribute to improving patients’ quality of life. Full article

ANCA-associated vasculitides (AAVs) are rare diseases with a prevalence of less than 200 cases per million persons and an incidence of less than 25 cases per million person-years. Their presenting features can vary from prodromal and nonspecific symptoms to dramatic organ-specific symptoms such as respiratory failure due to diffuse alveolar hemorrhage (DAH) and acute kidney injury (AKI). The latter two are hallmark features of pulmonary-renal syndrome, a potentially fatal condition that necessitates early recognition and treatment in intensive care units (ICUs) and rapid induction of immunosuppressive therapy. Background and case summaries: We described three patients with newly diagnosed AAV during the treatment of critical illness. All patients had DAH and two had AKI. The initial disease severity was extremely high in patients with myeloperoxidase (MPO)-AAV, reaching Sequential Organ Failure Assessment (SOFA) scores of 15 and 14 with predicted mortality ≥ 95.2%. Both patients needed mechanical ventilation, one additional venovenous extracorporeal membrane oxygenation (VV-ECMO), and renal replacement therapy. The patient with proteinase 3 (PR3)-AAV had a less severe disease, SOFA 3, requiring only modest oxygen supplementation and exhibiting only hematuria with normal renal function parameters. Immunosuppressive therapy was initiated during the ICU stay. The patient with the most severe clinical presentation died during the ICU stay because of sepsis, and the other two patients were discharged home. Conclusions: Patients with AAV presenting with pulmonary-renal syndrome necessitate various degrees of organ support. Nevertheless, these patients can be successfully treated in the early, critical stages of the disease and achieve remission. Full article

Background: The increasing rate of intensive care unit (ICU) readmissions poses significant challenges in healthcare, impacting both costs and patient outcomes. Predicting patient readmission after discharge is crucial for improving medical quality and reducing expenses. Traditional analyses of electronic health record (EHR) data have primarily focused on numerical data, often neglecting valuable text data. Methods: This study employs a hybrid model combining BERTopic and Long Short-Term Memory (LSTM) networks to predict ICU readmissions. Leveraging the MIMIC-III database, we utilize both quantitative and text data to enhance predictive capabilities. Our approach integrates the strengths of unsupervised topic modeling with supervised deep learning, extracting potential topics from patient records and transforming discharge summaries into topic vectors for more interpretable and personalized predictions. Results: Utilizing a comprehensive dataset of 36,232 ICU patient records, our model achieved an AUROC score of 0.80, thereby surpassing the performance of traditional machine learning models. The implementation of BERTopic facilitated effective utilization of unstructured data, generating themes that effectively guide the selection of relevant predictive factors for patient readmission prognosis. This significantly enhanced the model’s interpretative accuracy and predictive capability. Additionally, the integration of importance ranking methods into our machine learning framework allowed for an in-depth analysis of the significance of various variables. This approach provided crucial insights into how different input variables interact and impact predictions of patient readmission across various clinical contexts. Conclusions: The practical application of BERTopic technology in our hybrid model contributes to more efficient patient management and serves as a valuable tool for developing tailored treatment strategies and resource optimization. This study highlights the significance of integrating unstructured text data with traditional quantitative data to develop more accurate and interpretable predictive models in healthcare, emphasizing the importance of individualized care and cost-effective healthcare paradigms. Full article

Epilepsy is characterized by hypersynchronous neuronal discharges, which are associated with an increased cerebral metabolic rate of oxygen and ATP demand. Uncontrolled seizure activity (status epilepticus) results in mitochondrial exhaustion and ATP depletion, which potentially generate energy mismatch and neuronal loss. Many cells can adapt to increased energy demand by increasing metabolic capacities. However, acute metabolic adaptation during epileptic activity and its relationship to chronic epilepsy remains poorly understood. We elicited seizure-like events (SLEs) in an in vitro model of status epilepticus for eight hours. Electrophysiological recording and tissue oxygen partial pressure recordings were performed. After eight hours of ongoing SLEs, we used proteomics-based kinetic modeling to evaluate changes in metabolic capacities. We compared our findings regarding acute metabolic adaptation to published proteomic and transcriptomic data from chronic epilepsy patients. Epileptic tissue acutely responded to uninterrupted SLEs by upregulating ATP production capacity. This was achieved by a coordinated increase in the abundance of proteins from the respiratory chain and oxidative phosphorylation system. In contrast, chronic epileptic tissue shows a 25–40% decrease in ATP production capacity. In summary, our study reveals that epilepsy leads to dynamic metabolic changes. Acute epileptic activity boosts ATP production, while chronic epilepsy reduces it significantly. Full article