Status Classification Research Articles

Associations between discriminatory experiences and dementia in the Health and Retirement Study.

Dramatic racial and ethnic disparities in dementia necessitate research into potential risk factors and points of intervention. Using data from a large sample (n = 13,733) of older US residents participating in the Health and Retirement Study between 2006 and 2016, we investigated relationships between everyday and major discrimination and development of dementia. Data on self-reported everyday and major discrimination were collected via questionnaires. Algorithmic classification of probable dementia status was determined via a battery of cognitive tests. We used logistic regression models, and analyses were stratified by race and ethnicity and sex. We found that overall, more frequent experiences of everyday discrimination were associated with higher odds of developing dementia (odds ratio (OR) = 1.18; 95% confidence interval (CI): 1.10, 1.27; p < 0.001). Estimates stratified by race similarly suggested the positive association between everyday discrimination and odds of dementia onset was highest in non-Hispanic Black participants (OR: 1.30; 95% CI: 1.13, 1.51; p < 0.001). Our results reveal a link between frequency of everyday experiences of discrimination and dementia onset and highlight the role of psychosocial exposures in health and disease. This study underlines the impact that psychosocial stressors can have on cognitive health. Interventions addressing psychosocial risk factors experienced disproportionately by historically marginalized groups may be crucial in the goal to mitigate dementia disparities and achieve dementia equity.

Encoding-Based Machine Learning Approach for Health Status Classification and Remote Monitoring of Cardiac Patients

Encoding-Based Machine Learning Approach for Health Status Classification and Remote Monitoring of Cardiac Patients

Risk factors for the delayed discharge from anesthesia intensive care unit: a single-center retrospective study

BackgroundA single-center retrospective study was designed to investigate the risk factors associated with delayed discharge from the Anesthesia Intensive Care Unit (AICU).MethodsThis retrospective study involved patients admitted in the AICU from January 2017 to December 2022. Risk factors for the delayed discharge from the AICU were analyzed by the binary multivariate logistic regression analysis. Nomogram was constructed to predict the risk of delayed discharge from AICU. The performance of the nomogram was assessed using the receiver operating characteristic curve and calibration curve. A decision curve analysis was also performed to determine the net benefit threshold of prediction.ResultsA total of 14,338 patients admitted in the AICU were retrospectively recruited, involving 9,271 males and 5,067 females. The incidence of delayed discharge from the AICU in the cohort was 1.54% (221/14,338). Binary multivariate logistic regression analysis showed that younger than 18 years or older than 64 years, the American Society of Anesthesiologists physical status of class III-IV, body mass index of less than 18 kg/m2 or greater than 25 kg/m2, preoperative complications, emergency surgeries and intraoperative massive hemorrhage were risk factors for the delayed discharge from an AICU. We utilized nomograms to visually express data analysis results. Based on receiver operating characteristic analysis, calibration plots, and decision curve analysis, we concluded that the nomogram model exhibited excellent performance. Patients undergoing spine surgeries suffered from the highest proportion of delayed discharge from the AICU, followed by those receiving orthopedic and vascular surgeries. Postoperative hemorrhage was the major cause of delayed discharge from an AICU, followed by septic shock, hypoperfusion and pulmonary insufficiency.ConclusionThe incidence of delayed discharge from the AICU in a single-center tertiary hospital is 1.54%. It is influenced by various risk factors, including age, ASA physical status classification, BMI, preoperative complications, type of surgery and intraoperative blood loss. The nomogram model exhibits excellent performance.Trial registrationThe single-center retrospective study was approved by the Ethics Committee of Nanjing Drum Tower Hospital (No. 2021-563-01, Data: 22 November 2021) and registered on the Chinese Clinical Trial Registry (No. ChiCTR2300078251, Data: 01 December 2023).

Application of the 2018 Periodontal Status Classification to Epidemiological Survey Data (ACES) Framework to Estimate the Periodontitis Prevalence in the United States.

To compare periodontitis prevalence estimates based on the Application of the 2018 periodontal status Classification to Epidemiological Survey data (ACES) and the Centers for Disease Control and Prevention/American Academy of Periodontology (CDC/AAP) classification. National Health and Nutrition Examination Survey data for the years 2009/2010, 2011/2012 and 2013/2014 were survey-weighted and post-stratified to estimate the prevalence of periodontitis. Estimates based on ACES and CDC/AAP were cross-classified and stratified by age group. Prevalence estimates using different partial recording protocols were examined. Using the ACES framework, the prevalence of adults with periodontitis was 93.1% (95% CI: 91.9-94.2) (Stage I: 17.9%; Stage II: 46.2%; Stage III: 16.7%; Stage IV: 12.4%). Complexity factors did not alter Stage II prevalence. The CDC/AAP classification yielded a periodontitis prevalence of 38.9% (95% CI: 36.4-41.4) (Mild: 3.5%; Moderate: 28.1%; Severe: 7.3%). Partial recording protocols resulted in increased prevalence in the lower stages of periodontitis. The European Federation of Periodontology/American Academy of Periodontology Classification (using the ACES framework) overestimates periodontitis cases compared with the CDC/AAP classification. Including complexity factors in the ACES framework provides limited benefits in staging periodontitis. Partial-mouth recording protocols overestimate health and early disease stages while underestimating more severe disease.

Serum Irisin as a Predictor for Peripheral arterial disease: Insights from a Clinical Study

The purpose of this study was to investigate the correlation between serum irisin concentration and peripheral arterial disease (PAD), and to establish clinical prediction nomograms for PAD occurrence by comparing and analyzing clinical data from patients with PAD and healthy controls. A total of 112 patients with PAD and 90 healthy individuals were recruited for the study. Clinical data from both groups were collected and serum irisin concentration was measured using enzyme-linked immunosorbent assay (ELISA). Correlation analysis was conducted. Risk factors for PAD were identified through univariate and multivariate logistic regression. The clinical prediction nomograms were established and validated. A total of 202 patients were enrolled in this study, with an average age of 63.98±10.40years. Of these, 123 were male (60.9%) and 79 were female (39.1%). Hypertension was present in 104 patients (51.5%), diabetes in 59 patients (29.2%), dyslipidemia in 94 patients (46.5%), and 105 patients (52.0%) were smokers. Among them, 112 patients were assigned to the PAD group, which included 78 males (69.6%) and 34 females (30.4%), with an average age of 67.54±10.31years. In this group, 62 patients (55.4%) had hypertension, 53 (47.3%) had diabetes, 62 (55.4%) had dyslipidemia, and 78 (69.6%) were smokers. The Rutherford classification of these patients showed that 64 (57.1%) were at stage I, 25 (22.3%) at stage II, 16 (14.3%) at stage III, and 7 (6.3%) at stage IV. Serum irisin concentration in patients with PAD showed a significant positive correlation with serum high-density lipoprotein (HDL) (r=0.255) and a significant negative correlation with Rutherford classification (r=-0.374) and smoking status (r=-0.263). Univariate and multivariate logistic regression analyses identified irisin, age, diabetes, dyslipidemia, smoking, creatinine (CR), and neutrophil/lymphocyte ratio (NLR) as independent risk factors for the development of PAD (P<0.05). Based on these findings, a clinical prediction nomogram was established. Internal validation of the nomogram demonstrated strong discriminatory ability, with an area under the curve (AUC) of 0.942, indicating the model's excellent performance. Calibration curves and decision curve analyses further confirmed the model's robust calibration and clinical applicability. This study concluded that serum irisin concentrations were significantly lower in the PAD group compared to the healthy control group, and that serum irisin concentrations in the PAD group were significantly correlated with serum HDL, Rutherford classification, and smoking status. Additionally, Irisin level, age, diabetes, dyslipidemia, smoking, CR, and NLR were identified as independent risk factors for PAD development. The clinical prediction nomogram based on these factors may aid in accurately predicting the risk of PAD development.

Malnutrition and Associated Factors Among Patients With Cirrhosis at a Tertiary Care Center in Addis Ababa Ethiopia: An Ordinal Logistic Regression Analysis.

Cirrhosis is an irreversible stage of liver damage that decreases the ability of the liver to store and metabolize nutrients. Malnutrition is a common problem in patients with cirrhosis and increases the risk of mortality. This study aimed to assess malnutrition and associated factors among patients with cirrhosis at Tikur Anbessa Specialized Hospital, Addis Ababa, Ethiopia. A cross-sectional study was conducted at Tikur Anbessa Specialized Hospital. All patients with cirrhosis who were admitted to the hospital from August to November were included. Royal Free Hospital Global Assessment tool (RFH-GA) was used to assess nutritional status. Data were entered in Epi-data software version 4.6.0.2 and analyzed with STATA version 17/MP. Ordinal logistic regression analysis was fitted to determine factors associated with nutritional status. Statistical significance was declared at p value < 0.05. The prevalence of moderate malnutrition and severe malnutrition were 36.67% and 14.29%, respectively. Patients with ascites were five times at a higher risk of being severely malnourished (AOR = 5.08; 95% CI = 2.66-9.67). The odds of severe malnutrition decrease by 0.35 times for patients without a history of previous hospitalization (AOR = 0.35; 95% CI = 0.18-0.68). The odds of being in the higher category of nutritional status (severe malnutrition) are 10 times higher for patients with hepatic encephalopathy (AOR = 10.43; 95% CI = 4.66-23.31). As the level of creatinine blood urea nitrogen (Cr-BUN) increases, the risk of malnutrition increases by 2.57 times (AOR = 2.57; 95% CI = 1.02-5.78). Malnutrition is high among cirrhotic patients at Tikur Anbessa Specialized Hospital. Ascites, history of hospitalization, Cr-BUN, and hepatic encephalopathy are significant predictors of malnutrition.

Hospitalized Advanced HeartFailure With Preserved vs Reduced LeftVentricular Ejection Fraction: A Global Perspective.

Outcomes of hospitalized patients with heart failure (HF) and characteristics of advanced HF stage may vary across left ventricular ejection fraction (LVEF) and world regions. This study sought to analyze characteristics of hospitalized advanced HF patients across LVEF spectrum, world regions, and country income. Among 18,553 hospitalized patients with acute HF (7,902 new-onset HF and 10,651 decompensated chronic HF) enrolled in the global registry REPORT-HF (International Registry to Assess Medical Practice With Longitudinal Observation for Treatment of HeartFailure), the authors analyzed characteristics and outcomes of patients with advanced HF, defined as previously diagnosed HF; severe symptoms before current admission (NYHA functional class III/IV); and≥1 HF-related hospitalization in the preceding 12months, excluding the current. Differences among hospitalized advanced HF subgroups stratified by LVEF, world region, and country income were examined. Among 6,999 patients with decompensated chronic HF and available previous NYHA functional class and HF hospitalization status, 3,397 (48.5%; 18.3% of the total population) had advanced HF. Of these, 44.5% had severely reduced (≤30%), 34.9% mildly/moderately reduced (31%-49%), and 20.7% preserved (≥50%) LVEF. Patients from Eastern Europe had the lowest 1-year mortality (23%), whereas those from Southeast Asia had the highest (37%). Patients from lower-middle-income countries were younger, with shorter HF duration and lower comorbidity prevalence, received fewer beta-blockers and HF-devices, and had higher 1-year mortality (34%) than upper-middle-income (26%) or high-income countries (27%; P=0.018). Adjusted 1-year mortality risk did not differ among LVEF subgroups (all P > 0.05), nor did 1-year HF hospitalization rate (P=0.56). Hospitalized patients with advanced HF and preserved LVEF had similarly adverse outcomes as those with reduced LVEF. Patients from lower-middle-income countries had less implementation of HF therapies and higher 1-year mortality.

Bibliometric analysis of myelomeningocele management: National disease burden versus publication volume

Myelomeningocele (MMC) disproportionately affects low-resource areas and regions without mandatory folic acid fortification. No specific literature exists on the distribution of research output regarding neurosurgical management of myelomeningocele worldwide in relation to regional disease burden. We aimed to examine the country of origin and patient population of published papers on MMC and topics related to neurosurgical management of MMC, to determine whether these were proportionate to disease burden. A systematic literature search was conducted on neurosurgical aspects of MMC care. The geographic distribution of neurosurgical MMC research output was examined against the national burden of disease. Bibliometric analysis quantified author and patient country affiliations stratified by World Bank income group classification and folic acid fortification status, juxtaposed with disease burden. From 9692 titles, 1843 were included, representing 107,446 patients and 2650 authorship instances. High-income countries (HICs) constituted 3% of 2019's global neuraltube defect (NTD) births, 74% of authorships, and 83% of patients represented. Upper-middle-income countries (UMICs) represented 9% of NTD births, 16% of authorships, and 9% of published patients. Lower-middle-income countries (LMICs) represented 55% of NTD births but only 8.6% of authorships and 7% of patients. Low-income countries (LICs) shouldered 32% of NTD births and contributed 1.3% of authorships and 1.6% of patients. Countries with mandatory folic acid fortification represented 75% of patients and 54% of authorships. Postnatal repair, hydrocephalus, and postoperative complications were the most frequently studied topics. The global literature concerning neurosurgical management of myelomeningocele originates predominantly from HICs. Published experiences of myelomeningocele patients from LICs/LMICs are scarce, even though they constitute the majority of the affected population. Neurosurgeons and other health professionals must address this mismatch between disease burden and publication volume in order to inform practice, policy, and advocacy for MMC care worldwide.

Predicting abatacept retention using machine learning

BackgroundThe incorporation of machine learning is becoming more prevalent in the clinical setting. By predicting clinical outcomes, machine learning can provide clinicians with a valuable tool for refining precision medicine approaches and improving treatment outcomes.MethodsThis was a post hoc analysis of pooled patient-level data from the global, real-world ACTION and ASCORE trials in patients with rheumatoid arthritis (RA) initiating abatacept. Patient demographic and disease characteristics were input across 10 machine learning models used to predict 12-month treatment retention. Retention was defined as treatment for > 365 days or ≤ 365 days in patients who achieved remission or major clinical response (based on European Alliance of Associations for Rheumatology response criteria). The pooled dataset was split into a training/validation cohort for model development and a test cohort for an unbiased evaluation of performance. SHapley Additive exPlanation (SHAP) values determined the level of importance and directionality for key patient features predicting abatacept retention.ResultsThe pooled ACTION and ASCORE dataset included 5320 patients with RA (mean [standard deviation] age 57.7 [12.7] years; 79% female). The 12-month abatacept retention rate was 61% (n = 3236) with a discontinuation rate of 39% (n = 2037). In the training set (n = 4218), the gradient-boosting classifier model demonstrated the best performance (testing accuracy: 62%). This model had an area under the receiver operating characteristic curve (95% confidence interval) of 0.620 (0.586, 0.653) and F1 score of 0.659 (0.625, 0.689) in the test set of patients (n = 1055). Using this model, the five most important variables predicting 12-month abatacept retention were low body mass index (BMI), low American College of Rheumatology functional status class, anti-citrullinated protein antibody (ACPA) positivity, low Patient Global Assessment, and younger age.ConclusionsThe gradient-boosting classifier model identified key patient features predictive of abatacept retention from this large, real-world study population. The SHAP values conveyed the directionality and importance of BMI, functional status, ACPA serostatus, Patient Global Assessment, and age for abatacept retention. Findings are consistent with previous observations and help validate the machine learning approach for predictive modelling in RA treatment, and may help inform clinical decision making.Trial registrationNCT02109666 (ACTION), NCT02090556 (ASCORE).

Analysis of mental burden of students based on NASA-TLX at DAYAH DMA

One of the organizations in Aceh that deals with religious instruction and learning is Dayah DMA. Students who pursue higher education and are enrolled in religious education institutions are known as mahasantri, and they are thought to possess greater physical and psychological development than students in regular schools. No doubt learning in two distinct locations has different job demands, which could put more strain on Mahasantri's mind. This study aims to determine the causes of high mental load on mahasantri and investigate potential disparities in mental burden according to gender, status, and class levels. Purposive sampling is used in this study to handle primary data from 56 mahasantri respondents who completed questionnaires as part of a quantitative approach. According to the research that was done, 50% of mahasantri, or 28, report having a significant level of mental strain. Physical demand has the highest impact on mahasantri's mental burden, accounting for 18.35% of the total. Subsequently, an independent sample t-test conducted with SPSS version 26 was employed to statistically evaluate the average mental burden score to ascertain whether mental burden varied according to gender, status, and class level categories. The burden for gender and status categories did not differ, according to the results. But in terms of mental load, there was a notable variation for the class level category

Variety and results of the use of interventional oncoortopedic benefits for focal skeletal lesions

Introduction. The use of systemic drugs of special drug therapy in oncology is one of the key methods of treating patients including those with bone metastases. However, this does not always allow to eliminate the pain syndrome and avoid complications in the form of pathological fractures. Bone metastases often leave in the arsenal of oncologists’ mainly palliative agents, the main purpose of which is to reduce pain and improve the quality of life of patients.Aim. To analyze the results of minimally invasive interventions in the volume of percutaneous vertebroplasty, osteoplasty and radiofrequency thermoablation.Materials and methods. From 2015 to 2023, 488 patients on the basis of the Russian Scientific Center of Radioradiology underwent 716 interventional surgeries: 585 (81.7 %) percutaneous vertebroplastics, 103 (14.4 %) osteoplastics, 21 (2.9 %) radiofrequency thermoablasias, 7 (1 %) combined operations (radiofrequency thermoablasty + osteoplasty/vertebroplasty). Metastatic lesion was observed in 449 patients, benign tumors – in 38 (in 31 – hemangioma, in 7 – osteoid osteoma), borderline neoplasm (giant cell tumor) – in 1. Results were assessed by comparing measures of pain intensity in dependence on analgesic agents (by the visual analog scale (VAS) and Watkins scale), as well as motor activity levels (by the Eastern Cooperative Oncology Group (ECOG)) and neurological deficits (by the Frankel scale) before surgery, at the time of discharge and 3 months after surgery.Results. In patients with metastatic bone damage 3 months after surgery, a mean decrease in the intensity of pain syndrome according to VAS was noted from 5.8 to 3.2 points, on the Watkins scale - from 7.2 to 5.7 points; ECOG functional status increased from 2.5 to 1.5 points. In 67 % of patients with neurological deficiency (class D by the Frankel scale), an increase in neurological status (class E by the Frankel scale) was observed. In all patients treated for osteoid osteoma, pain relief and restoration of functional status (0 points by the VAS and ECOG scales) were noted by the 6th month of follow-up.Conclusion. According to the data obtained, the high effectiveness of the analgesic effect of interventional methods in patients with metastatic bone damage was noted. The use of vertebro- and osteoplasty allows to stabilize the affected segment of the skeleton (improve functional status and motor activity), and radiofrequency thermoablation – to achieve radicality of treatment in patients with osteoid osteoma.

Strabismus Surgery in Patients Aged Over 80 Years: Indications, Safety, and Outcomes.

Strabismus in the elderly can cause functional and psychological difficulties, particularly due to the impact of diplopia. Surgical intervention may alleviate diplopia and diminish psychosocial impact. However, the complexity of strabismus types, along with related ocular conditions and general health issues, pose unique challenges. This study explores the indications, safety, and outcomes of strabismus surgery in patients aged 80 years or more. Retrospective clinical cohort study. We reviewed patients aged 80 years and older who underwent strabismus surgery at Stein Eye Institute, University of California, Los Angeles, between 2014 and 2024. The study included 165 patients with a mean age of 83 ± 3 (standard deviation, range 80-94) years, of whom 52% were female. Diplopia was the primary complaint in 94% of patients, with 5 ± 9 years mean symptom duration. The most prevalent diagnosis was sagging eye syndrome, which accounted for 46% of cases. The most common pre-operative deviation was combined esotropia and hypertropia (30%). Surgery was performed in 48 patients under general anesthesia and 116 under topical anesthesia. The mean American Society of Anesthesiologists physical status classification score was 2.6 ± 0.5 (range 1-4). No complications occurred during anesthesia or surgery. Diplopia resolved in 124 patients (75%) after the initial surgery, increasing to 145 patients (87%) after one or two additional surgeries. Reoperation was required in 13% of patients overall. Strabismus surgery in patients over 80 years resolves diplopia and improves binocular alignment and stereopsis, without significant complications.

Machine Learning Modeling for American Society of Anesthesiologists Physical Status Classification Assignment in Children.

Machine Learning Modeling for American Society of Anesthesiologists Physical Status Classification Assignment in Children.

Prevalence and Factors Associated with Personal and Work-related Burnout among Primary Health Care Physicians in Tabuk, Saudi Arabia

Introduction: Physician burnout is a growing concern worldwide, including in Arab nations. Physicians working in primary health care settings are increasingly experiencing it. The study aimed to assess the status and determinants of burnout among primary health care physicians in the Tabuk Region, Saudi Arabia. Methods: A cross-sectional study was carried out using a Google Form questionnaire, based on the Copenhagen Burnout Inventory. The questionnaire was distributed among primary health care physicians through the Ministry of Health’s email and social media channels. The responses were collected using a five-point Likert scale, and the overall mean scores for personal and work-related burnout were calculated. Data analysis was performed using SPSS 16.0 and OpenEpi Version 3.01. Results: A total of 92 primary health care physicians responded to the survey. The overall mean scores for personal and work-related burnout were 38.99 and 41.41, respectively. The most common response category for both types of burnout was “Sometimes” or “Somewhat”. Physicians experienced personal burnout, characterized by emotional exhaustion (92.4%), feelings of being worn out (88%), tiredness (79.3%), and a sense of weakness and vulnerability to illness (69.6%). Similarly, they reported work-related burnout, manifested by feeling worn out after work (91.3%), feeling exhausted before work (83.7%), feeling burnt out by their work (82.6%), and feeling frustrated by their work (82.6%). Both personal and work-related burnout showed significant associations (p &lt; 0.05) with age group, gender, years of experience, marital status, and professional category. Moreover, nationality, hours of work per week, and duty schedule were significantly associated with work-related burnout (p &lt; 0.05). Conclusion: Physician burnout, both personal and work-related, is prevalent in primary healthcare settings in the Tabuk Region. It is significantly associated with various demographic and professional characteristics. Healthcare administrators and policymakers should develop and implement effective strategies to mitigate burnout and its detrimental effects on healthcare providers and the quality of care.

Natural language processing-based classification of early Alzheimer's disease from connected speech.

The automated analysis of connected speech using natural language processing (NLP) emerges as a possible biomarker for Alzheimer's disease (AD). However, it remains unclear which types of connected speech are most sensitive and specific for the detection of AD. We applied a language model to automatically transcribed connected speech from 114 Flemish-speaking individuals to first distinguish early AD patients from amyloid negative cognitively unimpaired (CU) and then amyloid negative from amyloid positive CU individuals using five different types of connected speech. The language model was able to distinguish between amyloid negative CU subjects and AD patients with up to 81.9% sensitivity and 81.8% specificity. Discrimination between amyloid positive and negative CU individuals was less accurate, with up to 82.7% sensitivity and 74.0% specificity. Moreover, autobiographical interviews consistently outperformed scene descriptions. Our findings highlight the value of autobiographical interviews for the automated analysis of connecting speech. This study compared five types of connected speech for the detection of early Alzheimer's disease (AD). Autobiographical interviews yielded a higher specificity than scene descriptions. A preceding clinical AD classification task can refine the performance of amyloid status classification in cognitively healthy individuals.

Multi task opinion enhanced hybrid BERT model for mental health analysis

Understanding the nuanced emotions and points of view included in user-generated content remains challenging, even though text data analysis for mental health is a crucial instrument for assessing emotional well-being. Most current models neglect the significance of integrating viewpoints in comprehending mental health in favor of single-task learning. To offer a more thorough knowledge of mental health, in this study, we present an Opinion-Enhanced Hybrid BERT Model (Opinion-BERT), built to handle multi-task learning for simultaneous sentiment and status categorization. With the help of TextBlob and SciPy, we extracted opinions and dynamically constructed new opinion embeddings to complement the pre-trained BERT model. Using a hybrid architecture, these embeddings are integrated with the contextual embeddings of BERT, whereby the CNN and BiGRU layers collected local and sequential characteristics. This combination helps our model to identify and categorize user status and attitudes from the text more accurately, which leads to more accurate mental health assessments. When we compared the performance of Opinion-BERT to some baseline models, including BERT, RoBERTa, and DistilBERT, we found that it performed much better. Opinion-enhanced embeddings are crucial for improving performance, as demonstrated by our multi-task learning framework’s 96.77% sentiment classification accuracy of 94.22% status classification accuracy. This work provides a more nuanced understanding of emotions and psychological states by demonstrating the potential of combining opinion and sentiment data for mental health analysis in a multi-task learning environment.

Moral Subjects in White Spaces: Impossible Solidarities

This article explores women of colour’s struggles against white spaces in anti-austerity, anti-fascist and migrants’ rights movements in Berlin, Brussels, Copenhagen, London, Madrid and Paris. We argue that solidarity is denied by white activists who resist women of colour’s practical demands to take race, class, gender, sexuality, disability and legal status seriously as an organising strategy. These demands are misinterpreted as emotional pleas for care and, crucially, as threats to the fantasies in which white activists place themselves as the eternal moral subjects and agents of their activism. Focusing on emotional expressions of solidarity can therefore fatally undermine the pragmatic work required to build solidarity. It is unclear how women of colour activists should pursue solidarity as a goal when their interests are misrepresented by their white comrades. Yet solidarity remains an impossible necessity in a cost-of-living crisis and far-right emergency.

Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach

We aimed to build a robust classifier for the MGMT methylation status of glioblastoma in multiparametric MRI. We focused on multi-habitat deep image descriptors as our basic focus. A subset of the BRATS 2021 MGMT methylation dataset containing both MGMT class labels and segmentation masks was used. A comprehensive mask fusion approach was developed to select relevant image crops of diseased tissue. These fusion masks, which were guided by multiple sequences, helped collect information from the regions that seem disease-free to radiologists in standard MRI sequences while harboring pathology. Integrating the information in different MRI sequences and leveraging the high entropic capacity of deep neural networks, we built a 3D ROI-based custom CNN classifier for the automatic prediction of MGMT methylation status of glioblastoma in multi-parametric MRI. Single sequence-based classifiers reached intermediate predictive performance with 0.65, 0.71, 0.77, and 0.82 accuracy for T1W, T2W, T1 contrast-enhanced, and FLAIR sequences, respectively. The multiparametric classifier using T1 contrast-enhanced and FLAIR images reached 0.88 accuracy. The accuracy of the four-input model that used all sequences was 0.81. The best model reached 0.90 ROC AUC value. Integrating human knowledge in the form of relevant target selection was a useful approach in MGMT methylation status prediction in MRI. Exploration of means to integrate radiology knowledge into the models and achieve human-machine collaboration may help to develop better models. MGMT methylation status of glioblastoma is an important prognostic marker and is also important for treatment decisions. The preoperative non-invasive predictive ability and the explanation tools of the developed model may help clinicians to better understand imaging phenotypes of MGMT methylation status of glial tumors.

An Intelligent Approach for Water Quality Status Classification Using Supervised Machine Learning Algorithms.

An Intelligent Approach for Water Quality Status Classification Using Supervised Machine Learning Algorithms.

Predictors of prolonged hospitalization among geriatric trauma patients using the modified 5-Item Frailty index in a Middle Eastern trauma center: an 11-year retrospective study

BackgroundUsing a validated tool, we explored the prevalence, risk factors, and predictors of longer hospitalization among hospitalized geriatric patients.MethodsRetrospective and comparative analyses of age groups (55–64 vs. ≥ 65 years), gender, survival status, and frailty index categories were performed. The Modified 5-Item Frailty Index was assessed, and multivariable logistic regression analysis was performed to predict prolonged hospitalization (> 7 days).ResultsThere were 17,600 trauma hospitalizations with a mean age of 32 ± 15 years between 2010 and 2021; of them, 9.2% were geriatrics at ≥ 55–64 years (n = 935) and ≥ 65 years (n = 691). The female/male ratio was 17.5%/82.5%, and the mean injury severity score was 13 ± 9. The injury rate for age ≥ 65 was 24 per 10,000 compared to 10 per 10,000 in the younger group age (≥ 55–64). 35% of injuries occurred at home due to falls. Overall mortality was 8%, with a higher rate among males than females (9% vs. 4%). The deceased were three years older at the time of death compared to the survivors. Higher frailty grades were associated with home-related falls and head injuries. Patients 65 years or older were likely to have higher frailty scores, as indicated by higher percentages in the mFI-5. Among the older group, 25% were moderately frail, and 18% severely frail. In the younger group, 50% were frail. Higher frailty scores correlated with increased acute kidney injury, pneumonia, urinary tract infections, and longer hospital stays. Severe frailty significantly predicted longer hospitalization (odds ratio 1.83, p = 0.007).ConclusionOne out of eleven trauma admissions was aged > 55. Head injury and bleeding were the leading causes of mortality in the study cohort. There was a significant decrease in the trend of geriatric trauma over the years. The modified FI-5 performs well as a predictive tool of prolonged hospitalizaion in trauma patients with different age groups.