Accurate prediction and grading of gliomas play a crucial role in evaluating brain tumor progression, assessing overall prognosis, and treatment planning. In addition to neuroimaging techniques, identifying molecular biomarkers that can guide the diagnosis, prognosis and prediction of the response to therapy has aroused the interest of researchers in their use together with machine learning and deep learning models. Most of the research in this field has been model-centric, meaning it has been based on finding better performing algorithms. However, in practice, improving data quality can result in a better model. This study investigates a data-centric machine learning approach to determine their potential benefits in predicting glioma grades. We report six performance metrics to provide a complete picture of model performance. Experimental results indicate that standardization and oversizing the minority class increase the prediction performance of four popular machine learning models and two classifier ensembles applied on a low-imbalanced data set consisting of clinical factors and molecular biomarkers. The experiments also show that the two classifier ensembles significantly outperform three of the four standard prediction models. Furthermore, we conduct a comprehensive descriptive analysis of the glioma data set to identify relevant statistical characteristics and discover the most informative attributes using four feature ranking algorithms.

Dental implant fractures pose a significant challenge to long-term treatment success. This systematic review aims to comprehensively examine the clinical factors influencing dental implant fractures (IFs). Furthermore, strategies to choose the right type of implant and prevent this complication are addressed. A systematic search was conducted across PubMed, Scopus, and Web of Science databases. Eligible studies included retrospective case-control, prospective cohort studies, and clinical trials. The initial search yielded 361 articles, of which 312 were excluded being these reviews, case reports, irrelevant, or written in languages other than English. This left 49 articles, with only 6 meeting the eligibility criteria for an in-depth review. These studies, all retrospective case-control, examine implant characteristics, patient demographics, surgical and prosthetic variables, biomechanical and functional factors, clinical and procedural variables, complications and maintenance issues. The risk of bias was assessed as low using the ROBINS-I tool. Key findings suggest a correlation between implant diameter and structural resistance, with wider implants demonstrating reduced fracture risk. Additionally, posterior regions, especially molars and premolars, exhibit higher susceptibility to IFs due to increased masticatory forces. Implant design and material may considerably influence fracture risk, with conical implants and screw-retained prostheses showing higher vulnerability. Biomechanical overload, particularly in patients with bruxism, emerges as a primary contributing factor to IFs. Prosthesis type significantly influences fracture incidence, with cantilever prostheses posing a higher risk due to increased stress. Peri-implant bone loss is strongly associated with IFs, emphasizing the need for meticulous preoperative assessments and individualized management strategies. Future research should prioritize larger and heterogeneous populations with long-term follow-up and standardized methodologies to enhance the generalizability and comparability of findings. Randomized controlled trials and biomechanical studies under controlled conditions are also essential to elucidate the complex interactions contributing to IFs and developing effective prevention strategies. Additionally, integrating patient-reported outcomes may offer a comprehensive understanding of the impact of IFs on quality of life.

BACKGROUND: Specific daily actions (eg, goal setting, meaningful activities) are associated with mental health. Performing specific daily actions at a higher frequency is associated with significantly lower baseline symptoms of depression and anxiety, as well as better psychological treatment outcomes for depression and anxiety.
OBJECTIVE: This study explored how the frequency of specific daily actions associated with mental health may differ prior to, during, and following treatment according to demographic and clinical characteristics.
METHODS: Using a sample of 448 patients from an Australian national digital psychology service, we examined baseline differences in daily action frequency and changes in daily action frequency during a digital psychological treatment according to demographic and clinical subgroups. A total of 5 specific types of daily actions were measured using the Things You Do Questionnaire: healthy thinking, meaningful activities, goals and plans, healthy habits, and social connections.
RESULTS: The frequency of daily actions differed according to employment status (largest P=.005) and educational level (largest P=.004). Daily action frequency was lower in those participants with more severe or chronic depression or anxiety symptoms (largest P=.004). Participants reported larger increases in how often they did these daily actions from baseline to midtreatment compared to mid- to posttreatment. Depression duration (P=.01) and severity (P<.001) were associated with differences in how daily action frequency changed during treatment.
CONCLUSIONS: The findings of this study support continued research exploring the relationship between daily actions and mental health, how this relationship might differ between individuals, and the clinical potential of supporting individuals to increase the frequency of daily actions to improve mental health.

OBJECTIVE: Our aims were to assess cognitive impairment in bipolar patients in remission compared with healthy controls, and to study its connection to clinical and therapeutic factors.
METHODS: This was a case-control study of patients with bipolar disorder (BD) in remission and matched healthy controls. It was carried out at the Hédi Chaker University Hospital in Sfax, Tunisia. The Screen for Cognitive Impairment in Psychiatry (SCIP) scale was used to assess cognitive function in patients and controls. This scale comprises subtests for verbal learning with immediate (VLT-I) and delayed (VLT-D) recall, working memory (WMT), verbal fluency (VFT) and information processing speed (PST).
RESULTS: We recruited 61 patients and 40 controls. Compared with controls, patients had significantly lower scores on the overall SCIP scale and on all SCIP subtests (p < 0.001 throughout) with moderate to high effects. In multivariate analysis, the presence of psychotic characteristics correlated with lower scores on the overall SCIP (p = 0.001), VLT-I (p = 0.001) and VLT-D (p = 0.007), WMT (p = 0.002) and PST (p = 0.008). Bipolar II correlated with lower LTV-I scores (p = 0.023). Age of onset and duration of the disorder were negatively correlated with PST scores (p < 10-3 and p = 0.007, respectively). Predominantly manic polarity correlated with lower VFT scores (p = 0.007).
CONCLUSIONS: Our study showed that bipolar patients in remission presented significantly more marked cognitive impairments, affecting various cognitive domains, than the controls. These cognitive impairments appear to be linked to clinical and therapeutic factors that are themselves considered to be factors of poor prognosis in BD.
OBJECTIVE: Nos objectifs étaient d’évaluer les troubles cognitifs chez des patients bipolaires en rémission comparativement à des témoins sains et d’étudier leur rapport avec les facteurs cliniques et thérapeutiques.
UNASSIGNED: Il s’agissait d’une étude cas-témoins, menée auprès de patients atteints de trouble bipolaire (TBP) en rémission et de témoins sains appariés. Elle a été réalisée au centre hospitalo-universitaire (CHU) Hédi Chaker de Sfax (Tunisie). L’échelle the Screen for cognitive impairment in psychiatry (SCIP) a été utilisée pour l’évaluation des fonctions cognitives chez les patients et les témoins. Cette échelle se compose des sous-échelles d’apprentissage verbal avec rappel immédiat (VLT-I) et différé (VLT-D), de la mémoire de travail (WMT), de la fluence verbale (VFT) et de la vitesse de traitement de l’information (PST).
UNASSIGNED: Nous avons recruté 61 patients et 40 témoins. Comparés aux témoins, les cas avaient des scores totaux du SCIP et de toutes les sous-échelles du SCIP significativement plus bas (p < 0,001 partout) avec des tailles d’effet modérées à élevées. Dans l’analyse multivariée, la présence de caractéristiques psychotiques était corrélée à l’abaissement des scores du SCIP total (p = 0,001), du VLT-I (p = 0,001) et VLT-D (p = 0,007), du WMT (p = 0,002), et du PST (p = 0,008). Le TBP de type 2 était corrélé à l’abaissement du score de VLT-I (p = 0,023). L’âge de début et la durée d’évolution du trouble étaient corrélés négativement au score PST (p < 10−3 et p = 0,007 respectivement). La polarité maniaque prédominante était corrélée à l’abaissement du score VFT (p = 0,007).
CONCLUSIONS: Notre étude a montré que les patients bipolaires en rémission présentaient des troubles cognitifs touchant différents domaines cognitifs, significativement plus marqués que chez les témoins. Ces troubles cognitifs semblent être liés à des facteurs cliniques et thérapeutiques considérés eux-mêmes comme des facteurs de mauvais pronostic de la maladie bipolaire.

UNASSIGNED: Suicidal behaviour is an established psychiatric complication of congestive cardiac failure (CCF), contributing significantly to morbidity and death by suicide. The magnitude and risk factors for suicidal behaviour among patients with CCF are yet to be unpacked, especially in developing nations such as Nigeria.
UNASSIGNED: To determine the prevalence of suicidal behaviour and the risk factors associated with suicidal behaviour, among patients with CCF in Nigeria.
UNASSIGNED: Cardiology outpatient clinic of Lagos State University Teaching Hospital, Lagos, Nigeria.
UNASSIGNED: A cross-sectional study was conducted among 98 randomly selected patients with a diagnosis of CCF. Participants were assessed with a socio-demographic and clinical factors questionnaire and Beck Scale of Suicidal Ideation. Chi-square test, t-test and logistic regression were used to analyse data.
UNASSIGNED: The prevalence of suicidal ideation and suicidal attempt among patients with CCF was 52% and 1%, respectively. No socio-demographic factor was significantly associated with suicidal ideation. Clinical factors associated with suicidal ideation were age at diagnosis (p = 0.042), aetiology of CCF (p = 0.001) and severity of CCF (p = 0.032). Only the severity of CCF (odds ratio [OR] = 20.557, p = 0.014) predicted suicidal ideation among patients with CCF.
UNASSIGNED: Suicidal behaviour constitutes a huge burden among the outpatient CCF population. The identification of clinical risk factors for suicidal ideation (age at diagnosis, aetiology and severity of CCF) further illuminates a pathway to mortality among patients with CCF.
UNASSIGNED: The findings lend a voice to the need for screening for suicidal behaviour, suicide prevention programmes, surveillance systems and government policies that support mental health for patients with CCF.

Equine melanomas are a common neoplasm in gray horses. However, scientific knowledge about their progression over time is quite scarce. Some owners and veterinarians still believe that early intervention is not necessary, stating that tumors evolve very slowly and intervention could worsen the animal\'s condition. This work aims to identify clinical and histological differences that may exist between equine melanomas with different excision intervals (time between tumor detection and surgical excision). A total of 42 tumors (13 benign and 29 malignant) from 34 horses were included in this study. There was a statistically significant association between excision interval and tumor size (p = 0.038), with tumors excised later being significantly larger than the ones excised sooner. The excision interval was also statistically associated with the number of tumors (p = 0.011), since the horses that carried a tumor for longer seemed to be prone to have multiple tumors. Furthermore, there was an association between excision interval and malignancy (p = 0.035), with tumor excised later being fives times more likely to be malignant. This study provides evidence of delayed excision\'s effect on the progression of equine melanomas. Additionally, it reinforces the importance of the early excision of these tumors.

BACKGROUND: This analysis of two Japanese clinical trials evaluated efficacy and safety after galcanezumab (GMB) discontinuation in patients with episodic migraine (EM) and chronic migraine (CM).
METHODS: Data were from a 6-month, randomized, double-blind, placebo [PBO]-controlled primary trial (patients with EM) and a 12-month open-label extension trial (patients with EM/CM). Patients received 6 months\' (primary) or 12/18 months\' (extension) treatment with GMB 120 mg (GMB120) plus 240-mg loading dose or 240 mg (GMB240) with 4 months\' post-treatment follow-up. Efficacy was assessed as number of monthly migraine headache days during post-treatment. Safety was assessed via post-treatment-emergent adverse events (PTEAEs).
RESULTS: The analysis population included 186 patients from the primary trial (PBO N = 93; GMB120 N = 45; GMB240 N = 48), 220 patients with EM from the extension trial (PBO/GMB120 N = 57; PBO/GMB240 N = 55; GMB120/GMB120 N = 55; GMB240/GMB240 N = 53), and 55 patients with CM (GMB120 N = 28; GMB240 N = 27). In patients with EM receiving 6 months\' GMB120, mean standard deviation (SD) monthly migraine headache days increased from 5.69 (4.64) at treatment end to 6.24 (4.37) at end of follow-up but did not return to pre-treatment levels (8.80 [2.96]). In the extension trial, mean monthly migraine headache days in patients with EM receiving GMB120 were 4.13 (3.85) after 12 months and 4.45 (3.78) at end of follow-up, and 3.59 (3.48) after 18 months and 3.91 (3.57) at end of follow-up. Monthly migraine headache days in patients with CM (12 months\' GMB120) were 10.71 (4.61) at treatment end and 11.17 (5.64) at end of follow-up (pre-treatment 20.15 [4.65]). Similar results were seen for patients receiving GMB240. The most observed PTEAE after GMB discontinuation was nasopharyngitis.
CONCLUSIONS: Galcanezumab exhibited post-treatment efficacy for up to 4 months in Japanese patients with EM and with CM. No unexpected safety signals were observed.
BACKGROUND: ClinicalTrials.gov, NCT02959177 and NCT02959190.

UNASSIGNED: Breast cancer is the leading cause of cancer-related fatalities among women worldwide. Conventional screening and risk prediction models primarily rely on demographic and patient clinical history to devise policies and estimate likelihood. However, recent advancements in artificial intelligence (AI) techniques, particularly deep learning (DL), have shown promise in the development of personalized risk models. These models leverage individual patient information obtained from medical imaging and associated reports. In this systematic review, we thoroughly investigated the existing literature on the application of DL to digital mammography, radiomics, genomics, and clinical information for breast cancer risk assessment. We critically analyzed these studies and discussed their findings, highlighting the promising prospects of DL techniques for breast cancer risk prediction. Additionally, we explored ongoing research initiatives and potential future applications of AI-driven approaches to further improve breast cancer risk prediction, thereby facilitating more effective screening and personalized risk management strategies.
UNASSIGNED: This study presents a comprehensive overview of imaging and non-imaging features used in breast cancer risk prediction using traditional and AI models. The features reviewed in this study included imaging, radiomics, genomics, and clinical features. Furthermore, this survey systematically presented DL methods developed for breast cancer risk prediction, aiming to be useful for both beginners and advanced-level researchers.
UNASSIGNED: A total of 600 articles were identified, 20 of which met the set criteria and were selected. Parallel benchmarking of DL models, along with natural language processing (NLP) applied to imaging and non-imaging features, could allow clinicians and researchers to gain greater awareness as they consider the clinical deployment or development of new models. This review provides a comprehensive guide for understanding the current status of breast cancer risk assessment using AI.
UNASSIGNED: This study offers investigators a different perspective on the use of AI for breast cancer risk prediction, incorporating numerous imaging and non-imaging features.

UNASSIGNED: Owing to individual heterogeneity, patients with idiopathic membranous nephropathy (IMN) exhibit varying sensitivities to immunotherapy. This study aimed to establish and validate a model incorporating pathological and clinical features using deep learning training to evaluate the response of patients with IMN to immunosuppressive therapy.
UNASSIGNED: The 291 patients were randomly categorized into training (n = 219) and validation (n = 72) cohorts. Patch-level convolutional neural network training in a weakly supervised manner was utilized to analyze whole-slide histopathological features. We developed a machine-learning model to assess the predictive value of pathological signatures compared to clinical factors. The performance levels of the models were evaluated using the area under the receiver operating characteristic curve (AUC) on the training and validation tests, and the prediction accuracies of the models for immunotherapy response were compared.
UNASSIGNED: Multivariate analysis indicated that diabetes and smoking were independent risk factors affecting the response to immunotherapy in IMN patients. The model integrating pathologic features had a favorable predictive value for determining the response to immunotherapy in IMN patients, with AUCs of 0.85 and 0.77 when employed in the training and test cohorts, respectively. However, when incorporating clinical features into the model, the predictive efficacy diminishes, as evidenced by lower AUC values of 0.75 and 0.62 on the training and testing cohorts, respectively.
UNASSIGNED: The model incorporating pathological signatures demonstrated a superior predictive ability for determining the response to immunosuppressive therapy in IMN patients compared to the integration of clinical factors.

OBJECTIVE: Survival analysis plays an essential role in the medical field for optimal treatment decision-making. Recently, survival analysis based on the deep learning (DL) approach has been proposed and is demonstrating promising results. However, developing an ideal prediction model requires integrating large datasets across multiple institutions, which poses challenges concerning medical data privacy.
METHODS: In this paper, we propose FedSurv, an asynchronous federated learning (FL) framework designed to predict survival time using clinical information and positron emission tomography (PET)-based features. This study used two datasets: a public radiogenic dataset of non-small cell lung cancer (NSCLC) from the Cancer Imaging Archive (RNSCLC), and an in-house dataset from the Chonnam National University Hwasun Hospital (CNUHH) in South Korea, consisting of clinical risk factors and F-18 fluorodeoxyglucose (FDG) PET images in NSCLC patients. Initially, each dataset was divided into multiple clients according to histological attributes, and each client was trained using the proposed DL model to predict individual survival time. The FL framework collected weights and parameters from the clients, which were then incorporated into the global model. Finally, the global model aggregated all weights and parameters and redistributed the updated model weights to each client. We evaluated different frameworks including single-client-based approach, centralized learning and FL.
RESULTS: We evaluated our method on two independent datasets. First, on the RNSCLC dataset, the mean absolute error (MAE) was 490.80±22.95 d and the C-Index was 0.69±0.01. Second, on the CNUHH dataset, the MAE was 494.25±40.16 d and the C-Index was 0.71±0.01. The FL approach achieved centralized method performance in PET-based survival time prediction and outperformed single-client-based approaches.
CONCLUSIONS: Our results demonstrated the feasibility and effectiveness of employing FL for individual survival prediction in NSCLC patients, using clinical information and PET-based features.