RESUMEN

Osteoporosis Canada 2023 clinical practice guidelines increase the number of individuals recommended or suggested for anti-osteoporosis pharmacotherapy by refining treatment guidance for those who fell within the 2010 guidelines' moderate-risk category. PURPOSE: In 2023, Osteoporosis Canada updated its 2010 clinical practice guidelines based upon consideration of fracture history, 10-year major osteoporotic fracture (MOF) risk, and BMD T-score in conjunction with age. The 2023 guidelines eliminated risk categories, including the moderate-risk group that did not provide clear treatment guidance. The current study was performed to appreciate the implications of the shift from 2010 risk categories to 2023 treatment guidance. METHODS: The study population consisted of 79,654 individuals age ≥ 50 years undergoing baseline DXA testing from January 1996 to March 2018. Each individual was assigned to mutually exclusive categories based on 2010 and 2023 guideline recommendations. Treatment qualification, 10-year predicted and 10-year observed MOF risk were compared. RESULTS: Treatment reclassification under the 2023 guidelines only affected 33.8% of individuals in the 2010 moderate-risk group, with 13.0% assigned to no treatment, 14.4% to suggest treatment, and 6.4% to recommend treatment. During the mean follow-up of 7.2 years, 6364 (8.0%) individuals experienced one or more incidents of MOF. The observed 10-year cumulative incidence of MOF in the study population was 10.5% versus the predicted 10.7% (observed to predicted mean calibration ratio 0.98, 95% CI 0.96-1.00). Individuals reclassified from 2010 moderate risk to 2023 recommend treatment were at greater MOF risk than those in the 2010 moderate-risk group assigned to 2023 suggest treatment or no treatment, but at lower risk than those in the 2010 high-risk group. CONCLUSIONS: Osteoporosis Canada 2023 clinical practice guidelines affect individuals within the 2010 moderate-risk category, increasing the number for whom anti-osteoporosis pharmacotherapy is recommended or suggested. Increased treatment could reduce the population burden of osteoporotic fractures, though moderate-risk individuals now qualifying for treatment have a lower predicted and observed fracture risk than high-risk individuals recommended for treatment under the 2010 guidelines.

Asunto(s)

RESUMEN

INTRODUCTION: Tower cranes are commonly employed in construction projects, despite presenting significant hazards to the workforce involved. METHOD: To address these safety concerns, a Knowledge-Based Decision-Support System for Safety Risk Assessment (KBDSS-SRA) has been developed. The system's capacity to thoroughly evaluate associated risks is illustrated through its utilization in various construction endeavors. RESULTS: The system accomplishes the following goals: (1) compiles essential risk factors specific to tower crane operations, (2) identifies critical safety risks that jeopardize worker well-being, (3) examines and assesses the identified safety risks, and (4) automates the labor-intensive and error-prone processes of safety risk assessment. The KBDSS-SRA assists safety management personnel in formulating well-grounded decisions and implementing effective measures to enhance the safety of tower crane operations. PRACTICAL APPLICATIONS: This is facilitated by an advanced computerized tool that underscores the paramount significance of safety risks and suggests strategies for their future mitigation.

Asunto(s)

RESUMEN

Pyroptosis-related genes have great potential for prognosis, an accurate prognostic model based on pyroptosis genes has not been seen in Colorectal adenocarcinoma (COAD). Furthermore, understanding the mechanisms of gene expression characteristics and the Tumor Immune Microenvironment associated with the prognosis of COAD is still largely unknown. Constructing a prognostic model based on pyroptosis-related genes, and revealing prognosis-related mechanisms associated with the gene expression characteristics and tumor microenvironment. 59 pyroptosis-related genes were collected. The gene expression data and clinical data of COAD were downloaded from The Cancer Genome Atlas. External validation datasets were downloaded from the Gene Expression Omnibus database. 10 characteristic genes with prognostic values were obtained using univariate and LASSO Cox. 10-gene Riskscore prognostic model was constructed. Both gene set enrichment analysis and network propagation methods were used to find pathways and key genes leading to different prognostic risks. The area under the ROC curves were used to evaluate the performance of the model to distinguish between high-risk and low-risk patients, the results were 0.718, 0.672, and 0.669 for 1-, 3-, and 5-year survival times. A nomogram based on Riskscore and clinical characteristics showed the probability of survival at 1, 3, and 5 years, and the calibration curves showed good agreement between the predicted and actual observations, its C-index is 0.793. The decision curves showed that the net benefit of the nomogram was significantly superior to that of the other single variables. Four key pathways leading to different prognostic risks were obtained. Six key genes with prognostic value, significant expression differences (P < .05) and significant survival differences (P < .05) between high/low risk groups were obtained from the gene set of all 4 key pathways. This study constructed a prognostic model for COAD using 10 pyroptosis-related genes with prognostic value. This study also revealed significant differences in specific pathways and the tumor immune microenvironment (TME) between the high-risk group and the low-risk group, highlighted the roles of ALDH5A1 and Wnt signaling in promoting COAD and the suppressive effects of the IL-4/IL-13 pathway and RORC on COAD. The study will be helpful for precision therapy.

Asunto(s)

RESUMEN

Uveal melanoma (UM) is a common health challenge worldwide as a prevalent intraocular malignancy because of its high mortality rate. However, clinical workers do not have an accurate prognostic tool now. Immune function is closely related to tumor development. Interestingly, researchers have identified that long noncoding RNAs (lncRNAs) are tightly associated with biological processes at the cellular level, particularly their involvements in immune response and its regulation of the growth of tumor cells. Hence, lncRNAs may be involved in the progression of uveal melanoma. UM patients' RNA expression matrices were extracted from TCGA database. The targeted immune genes were filtered by weighted correlation network analysis and the immune-related lncRNAs with a high prognostic relevance were obtained by Cox regression analysis and least absolute shrinkage and selection operator regression analysis. Each sample was scored according to those lncRNA expression and divided into high-risk and low-risk group. We confirmed the sensitivity and independence of our risk model compared to the tumor mutation burden score. Finally, we demonstrated the clinical relevance of our model by examining its sensitivity to different drugs. The risk score based on our risk model was significantly independent of other clinical parameters in either univariate (hazard ratio = 109.852 [15.738-766.749], P value < .001) or multivariate (hazard ratio = 114.075 [15.207-855.735], P value < .001) analyses. The ROC curves of this model imply high predictive accuracy for 1-year, 3-year, and 5-year survival (1-year area under the curve [AUC] = 0.849, 3-years AUC = 0.848, and 5-years AUC = 0.761). Our study revealed that immune-related lncRNAs are significant in the clinical diagnosis, treatment and prognosis of UM patients. We successfully constructed a lncRNA-based prognostic risk model which may serve as a future reference for the diagnosis and prognosis of UM. Based on this model we also validated the sensitivity of some cancer drugs, which has implications for the future immunotherapy and drug development.

Asunto(s)

Asunto(s)

RESUMEN

Rhegmatogenous retinal detachment (RRD) is a severe disease of the visual organ that is one of the leading causes of blindness worldwide. Without surgical treatment, RRD almost always leads to vision loss and blindness. Surgical treatment in the early stages of the disease reduces the risk of blindness. This article analyzes scientific publications reflecting the issues of prognosis and prevention of RRD. Literature analysis showed that there are few prognostic matrices in ophthalmology in general, and specifically related to RRD. Most prognostic matrices for RRD are aimed at preventing its recurrence and predicting the development or progression of peripheral vitreochorioretinal dystrophy in the operated or fellow eye. Building a prognostic matrix for the risk of occurrence and development of such a serious disease as RRD in adults will allow early prediction, enabling surgical treatment in the shortest possible time and positively influencing the functional outcome of treatment.

Asunto(s)

RESUMEN

Percutaneous coronary and structural heart interventions are increasingly preferred over cardiac surgery due to reduced rates of periprocedural complications and faster recovery but often require postprocedural antithrombotic therapy for the prevention of local thrombotic events. Antithrombotic therapy is inevitably associated with increased bleeding, the extent of which is proportional to the number, duration, and potency of the antithrombotic agents used. Bleeding complications have important clinical implications, which may outweigh the expected benefit of reducing thrombotic events. Herein, we provide a comprehensive description of the classification and clinical relevance of high bleeding risk in patients undergoing coronary and structural heart interventions.

Asunto(s)

RESUMEN

Pancreatic ductal adenocarcinoma (PDAC) continues to remain one of the leading causes of cancer-related death. Unlike other malignancies where universal screening is recommended, the same cannot be said for PDAC. The purpose of this study is to review which patients are at high risk of developing PDAC and therefore candidates for screening, methods/frequency of screening, and risk for these groups of patients.

Asunto(s)

RESUMEN

OBJECTIVE: To construct Risk factor assessment table for hyperoxemia in patients after cardiopulmonary bypass heart surgery based on Delphi method, providing a basis for early prediction and assessment of the risk of hyperoxemia in patients after cardiac surgery. METHODS: A research team was established. Based on the characteristics of extracorporeal circulation cardiac surgery, the Chinese and English literature published by each database until October 2022 was retrieved and the opinions of relevant professional clinicians were combined to screen the risk factors of hyperoxemia in patients after cardiopulmonary bypass heart surgery, and the preliminary draft of the Risk factor assessment table for hyperoxemia in patients after cardiopulmonary bypass heart surgery was drawn up. The Delphi method was used to conduct two rounds of expert letter consultation to supplement and improve the initial draft and finally established the final draft of the Risk factor assessment table for hyperoxemia in patients after cardiopulmonary bypass heart surgery. RESULTS: The preliminary draft of the Risk factor assessment table for hyperoxemia in patients after cardiopulmonary bypass heart surgery was constructed according to the literature review and the opinions of relevant professional clinicians, which contained 4 dimensions and 21 items. A total of 14 experts were consulted by letter, including 5 senior titles and 9 associate senior titles. Six of them major in critical care and the other eight major in cardiovascular surgery. The effective response rates for the two rounds of questionnaire surveys were 100% and 85.71%, expert familiarity levels were 0.81 and 0.80, judgment coefficients were 0.94 and 0.92, respectively. Expert authority coefficients were both 0.86. Coefficients of variation for the importance and feasibility items in the two rounds ranged from 0.13 to 0.32 and 0.11 to 0.32, 0.06 to 0.26 and 0.06 to 0.35, respectively. The Kendall's W for importance and feasibility in the two rounds were 0.264 and 0.162, and 0.258 and 0.144 respectively, indicating statistically significant (all P < 0.05). After two rounds of expert consultations, a comprehensive evaluation and selection process resulted in the final establishment of the Risk factor assessment table for hyperoxemia in patients after cardiopulmonary bypass heart surgery, consisting of 4 dimensions and 23 items, which included general data, past history, operation-related data and postoperative data. CONCLUSIONS: The Risk factor assessment table for hyperoxemia in patients after cardiopulmonary bypass heart surgery based on the Delphi method is highly scientific and feasible, which can provide reference for clinical assessments of the risk of hyperoxemia in such patients.

Asunto(s)

RESUMEN

BACKGROUND: While left ventricular ejection fraction (LVEF) is the primary variable utilized for prognosis following myocardial infarction (MI), it is relatively indiscriminate for survival in patients with mildly reduced (> 40%) or preserved LVEF (> 50%). Improving risk stratification in patients with mildly reduced or preserved LVEF remains an unmet need, and could be achieved by using a combination approach using prognostically validated measures of left-ventricular (LV) size, geometry, and function. AIMS: The aim of this study was to compare the prognostic utility of a Combined Echo-Score for predicting all-cause (ACM) and cardiac mortality (CM) following MI to LVEF alone, including the sub-groups with LVEF > 40% and LVEF > 50%. METHODS: Retrospective data on 3094 consecutive patients with MI from 2013 to 2021 who had inpatient echocardiography were included, including both patients with ST-elevation MI (n = 869 [28.1%]) and non-ST-elevation MI (n = 2225 [71.9%]). Echo-Score consisted of LVEF < 40% (2 points) or LVEF < 50% (1 point), and 1 point each for left atrial volume index > 34 mL/m2, septal E/e' > 15, abnormal LV mass-index, tricuspid regurgitation velocity > 2.8 m/s, and abnormal LV end-systolic volume-index. Simple addition was used to derive a score out of 7. RESULTS: At a median follow-up of 4.5 years there were 445 deaths (130 cardiac deaths). On Cox proportional-hazards multivariable analysis incorporating significant clinical and echocardiographic predictors, Echo-Score was an independent predictor of both ACM (HR 1.34, p < .001) and CM (HR 1.59, p < .001). Inter-model comparisons of model 𝛘2, Harrel's C and Somer's D, and Receiver operating curves confirmed the superior prognostic value of Echo-Score for both endpoints compared to LVEF. In the subgroups with LVEF > 40% and LVEF > 50%, Echo-Score was similarly superior to LVEF for predicting ACM and CM. CONCLUSIONS: An Echo-Score composed of prognostically validated LV parameters is superior to LVEF alone for predicting survival in patients with MI, including the subgroups with mildly reduced and preserved LVEF. This could lead to improved patient risk stratification, better-targeted therapies, and potentially more efficient use of device therapies. Further studies should be considered to define the benefit of further investigation and treatment in high-risk subgroups.

Asunto(s)

RESUMEN

During patient follow-up in a randomized trial, some deaths may occur. Where death (or noncardiovascular death) is not part of an outcome of interest it is termed a competing risk. Conventional analyses (eg, Cox proportional hazards model) handle death similarly to other censored follow-up. Patients still alive are unrealistically assumed to be representative of those who died. The Fine and Gray model has been used to handle competing risks, but is often used inappropriately and can be misleading. We propose an alternative multiple imputation approach that plausibly accounts for the fact that patients who die tend also to be at high risk for the (unobserved) outcome of interest. This provides a logical framework for exploring the impact of a competing risk, recognizing that there is no unique solution. We illustrate these issues in 3 cardiovascular trials and in simulation studies. We conclude with practical recommendations for handling competing risks in future trials.

Asunto(s)

RESUMEN

BACKGROUND: The ability of a 1-time measurement of non-high-density lipoprotein cholesterol (non-HDL-C) or low-density lipoprotein cholesterol (LDL-C) to predict the cumulative exposure to these lipids during early adulthood (age 18-40 years) and the associated atherosclerotic cardiovascular disease (ASCVD) risk after age 40 years is not clear. OBJECTIVES: The objectives of this study were to evaluate whether a 1-time measurement of non-HDL-C or LDL-C in a young adult can predict cumulative exposure to these lipids during early adulthood, and to quantify the association between cumulative exposure to non-HDL-C or LDL-C during early adulthood and the risk of ASCVD after age 40 years. METHODS: We included CARDIA (Coronary Artery Risk Development in Young Adults Study) participants who were free of cardiovascular disease before age 40 years, were not taking lipid-lowering medications, and had ≥3 measurements of LDL-C and non-HDL-C before age 40 years. First, we assessed the ability of a 1-time measurement of LDL-C or non-HDL-C obtained between age 18 and 30 years to predict the quartile of cumulative lipid exposure from ages 18 to 40 years. Second, we assessed the associations between quartiles of cumulative lipid exposure from ages 18 to 40 years with ASCVD events (fatal and nonfatal myocardial infarction and stroke) after age 40 years. RESULTS: Of 4,104 CARDIA participants who had multiple lipid measurements before and after age 30 years, 3,995 participants met our inclusion criteria and were in the final analysis set. A 1-time measure of non-HDL-C and LDL-C had excellent discrimination for predicting membership in the top or bottom quartiles of cumulative exposure (AUC: 0.93 for the 4 models). The absolute values of non-HDL-C and LDL-C that predicted membership in the top quartiles with the highest simultaneous sensitivity and specificity (highest Youden's Index) were >135 mg/dL for non-HDL-C and >118 mg/dL for LDL-C; the values that predicted membership in the bottom quartiles were <107 mg/dL for non-HDL-C and <96 mg/dL for LDL-C. Individuals in the top quartile of non-HDL-C and LDL-C exposure had demographic-adjusted HRs of 4.6 (95% CI: 2.84-7.29) and 4.0 (95% CI: 2.50-6.33) for ASCVD events after age 40 years, respectively, when compared with each bottom quartile. CONCLUSIONS: Single measures of non-HDL-C and LDL-C obtained between ages 18 and 30 years are highly predictive of cumulative exposure before age 40 years, which in turn strongly predicts later-life ASCVD events.

Asunto(s)

RESUMEN

Recurrent epidemics of respiratory infections have drawn attention from the academic community and the general public in recent years. Aircraft plays a pivotal role in facilitating the cross-regional transmission of pathogens. In this study, we initially utilized an Airbus A320 model for computational fluid dynamics (CFD) simulations, subsequently validating the model's efficacy in characterizing cabin airflow patterns through comparison with empirical data. Building upon this validated framework, we investigate the transport dynamics of droplets of varying sizes under three air supply velocities. The Euler-Lagrangian method is employed to meticulously track key parameters associated with droplet transport, enabling a comprehensive analysis of particle behavior within the cabin environment. This study integrates acquired data into a novel PCR (Personal Contamination Rate) equation to assess individual contamination rates. Numerical simulations demonstrate that increasing air supply velocity leads to enhanced stability in the movement of larger particles compared to smaller ones. Results show that the number of potential infections in the cabin decreases by 51.8% at the highest air supply velocity compared to the base air supply velocity, and the total exposure risk rate reduced by 26.4%. Thus, optimizing air supply velocity within a specific range effectively reduces the potential infection area. In contrast to previous research, this study provides a more comprehensive analysis of droplet movement dynamics across various particle sizes. We introduce an improved method for calculating the breathing zone, thereby enhancing droplet counting accuracy. These findings have significant implications for improving non-pharmacological public health interventions and optimizing cabin ventilation system design.

Asunto(s)

RESUMEN

Accurate prediction of coronary artery disease (CAD) is crucial for enabling early clinical diagnosis and tailoring personalized treatment options. This study attempts to construct a machine learning (ML) model for predicting CAD risk and further elucidate the complex nonlinear interactions between the disease and its risk factors. Employing the Z-Alizadeh Sani dataset, which includes records of 303 patients, univariate analysis and the Boruta algorithm were applied for feature selection, and nine different ML techniques were subsequently deployed to produce predictive models. To elucidate the intricate pathogenesis of CAD, this study harnessed the analytical capabilities of Shapley values, alongside the use of generalized additive models for curve fitting, to probe into the nonlinear interactions between the disease and its associated risk factors. Furthermore, we implemented a piecewise linear regression model to precisely pinpoint inflection points within these complex nonlinear dynamics. The findings of this investigation reveal that logistic regression (LR) stands out as the preeminent predictive model, demonstrating remarkable efficacy, it achieved an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.981 (95% CI: 0.952-1), and an Area Under the Precision-Recall Curve (AUPRC) of 0.993. The utilization of the 14 most pivotal features in constructing a dynamic nomogram. Analysis of the Shapley smoothing curves uncovered distinctive "S"-shaped and "C"-shaped relationships linking age and triglycerides to CAD, respectively. In summary, machine learning models could provide valuable insights for the early diagnosis of CAD. The SHAP method may provide a personalized risk assessment of the relationship between CAD and its risk factors.

Asunto(s)

RESUMEN

INTRODUCTION: Patients with multiple myeloma (MM) face heightened infection susceptibility, particularly severe risks from COVID-19. This study, the first systematic review in its domain, seeks to assess the impacts of COVID-19 on MM patients. METHOD: Adhering to PRISMA guidelines and PROSPERO registration (ID: CRD42023407784), this study conducted an exhaustive literature search from January 1, 2020, to April 12, 2024, using specified search terms in major databases (PubMed, EMBASE, and Web of Science). Quality assessment utilized the JBI Critical checklist, while publication bias was assessed using Egger's test and funnel plot. The leave-one-out sensitivity analyses were performed to assess the robustness of the results by excluding one study at a time to identify studies with a high risk of bias or those that significantly influenced the overall effect size. Data synthesis involved fitting a random-effects model and estimating meta-regression coefficients. RESULTS: A total of 14 studies, encompassing a sample size of 3214 yielded pooled estimates indicating a hospitalization rate of 53% (95% CI: 40.81, 65.93) with considerable heterogeneity across studies (I2 = 99%). The ICU admission rate was 17% (95% CI: 11.74, 21.37), also with significant heterogeneity (I2 = 94%). The pooled mortality rate was 22% (95% CI: 15.33, 28.93), showing high heterogeneity (I2 = 97%). The pooled survival rate stood at 78% (95% CI: 71.07, 84.67), again exhibiting substantial heterogeneity (I2 = 97%). Subgroup analysis and meta-regression highlighted that study types, demographic factors, and patient comorbidities significantly contributed to the observed outcome heterogeneity, revealing distinct patterns. Mortality rates increased by 15% for participants with a median age above 67 years. ICU admission rates were positively correlated with obesity, with a 20% increase for groups with at least 19% obesity. Mortality rates rose by 33% for the group of patients with at least 19% obesity, while survival rates decreased by 33% in the same group. CONCLUSION: Our meta-analysis sheds light on diverse COVID-19 outcomes in multiple myeloma. Heterogeneity underscores complexities, and study types, demographics, and co-morbidities significantly influence results, emphasizing the nuanced interplay of factors.

Asunto(s)

RESUMEN

INTRODUCTION: Risk prediction models, such as The Society of Thoracic Surgeons (STS) risk score and the European System for Cardiac Operative Risk Evaluation II (EuroSCORE II), are recommended for assessing operative mortality in coronary artery bypass grafting (CABG). However, their performance is questionable in Brazil. OBJECTIVE: To assess the performance of the STS score and EuroSCORE II in isolated CABG at a Brazilian reference center. METHODS: Observationaland prospective study including 438 patients undergoing isolated CABG from May 2022-May 2023 at the Instituto Dante Pazzanese de Cardiologia. Observed mortality was compared with predicted mortality (STS score and EuroSCORE II) by discrimination (area under the curve [AUC]) and calibration (observed/expected ratio [O/E]) in the total sample and subgroups of stable coronary artery disease (CAD) and acute coronary syndrome (ACS). RESULTS: Observed mortality was 4.3% (n=19) and estimated at 1.21% and 2.74% by STS and EuroSCORE II, respectively. STS (AUC=0.646; 95% confidence interva [CI] 0.760-0.532) and EuroSCORE II (AUC=0.697; 95% CI 0.802-0.593) presented poor discrimination. Calibration was absent for the North American mode (P<0.05) and reasonable for the European model (O/E=1.59, P=0.056). In the subgroups, EuroSCORE II had AUC of 0.616 (95% CI 0.752-0.480) and 0.826 (95% CI 0.991-0.661), while STS had AUC of 0.467 (95% CI 0.622-0.312) and 0.855 (95% CI 1.0-0.706) in ACS and CAD patients, respectively, demonstrating good score performance in stable patients. CONCLUSION: The predictive models did not perform optimally in the total sample, but the EuroSCORE was superior, especially in elective stable patients, where accuracy was satisfactory.

Asunto(s)

RESUMEN

BACKGROUND: The role of the geriatric nutritional risk index (GNRI) as a prognostic factor in intensive care unit (ICU) patients with acute kidney injury (AKI) remains uncertain. OBJECTIVES: The aim of this study was to investigate the impact of the GNRI on mortality outcomes in critically ill patients with AKI. METHODS: For this retrospective study, we included 12,058 patients who were diagnosed with AKI based on ICD-9 codes from the eICU Collaborative Research Database. Based on the values of GNRI, nutrition-related risks were categorized into four groups: major risk (GNRI < 82), moderate risk (82 ≤ GNRI < 92), low risk (92 ≤ GNRI < 98), and no risk (GNRI ≥ 98). Multivariate analysis was used to evaluate the relationship between GNRI and outcomes. RESULTS: Patients with higher nutrition-related risk tended to be older, female, had lower blood pressure, lower body mass index, and more comorbidities. Multivariate analysis showed GNRI scores were associated with in-hospital mortality. (Major risk vs. No risk: OR, 95% CI: 1.90, 1.54-2.33, P < 0.001, P for trend < 0.001). Moreover, increased nutrition-related risk was negatively associated with the length of hospital stay (Coefficient: -0.033; P < 0.001) and the length of ICU stay (Coefficient: -0.108; P < 0.001). The association between GNRI scores and the risks of in-hospital mortality was consistent in all subgroups. CONCLUSIONS: GNRI serves as a significant nutrition assessment tool that is pivotal to predicting the prognosis of critically ill patients with AKI.

Asunto(s)

RESUMEN

Over 700,000 people die by suicide annually. Collecting longitudinal fine-grained data about at-risk individuals, as they occur in the real world, can enhance our understanding of the temporal dynamics of suicide risk, leading to better identification of those in need of immediate intervention. Self-assessment questionnaires were collected over time from 89 at-risk individuals using the EMMA smartphone application. An artificial intelligence (AI) model was trained to assess current level of suicidal ideation (SI), an early indicator of the suicide risk, and to predict its progression in the following days. A key challenge was the unevenly spaced and incomplete nature of the time series data. To address this, the AI was built on a missing value imputation algorithm. The AI successfully distinguished high SI levels from low SI levels both on the current day (AUC = 0.804, F1 = 0.625, MCC = 0.459) and three days in advance (AUC = 0.769, F1 = 0.576, MCC = 0.386). Besides past SI levels, the most significant questions were related to psychological pain, well-being, agitation, emotional tension, and protective factors such as contacts with relatives and leisure activities. This represents a promising step towards early AI-based suicide risk prediction using a smartphone application.

Asunto(s)

RESUMEN

Melanoma of the skin is the 17th most common cancer worldwide. Early detection of suspicious skin lesions (melanoma) can increase 5-year survival rates by 20%. The 7-point checklist (7PCL) has been extensively used to suggest urgent referrals for patients with a possible melanoma. However, the 7PCL method only considers seven meta-features to calculate a risk score and is only relevant for patients with suspected melanoma. There are limited studies on the extensive use of patient metadata for the detection of all skin cancer subtypes. This study investigates artificial intelligence (AI) models that utilise patient metadata consisting of 23 attributes for suspicious skin lesion detection. We have identified a new set of most important risk factors, namely "C4C risk factors", which is not just for melanoma, but for all types of skin cancer. The performance of the C4C risk factors for suspicious skin lesion detection is compared to that of the 7PCL and the Williams risk factors that predict the lifetime risk of melanoma. Our proposed AI framework ensembles five machine learning models and identifies seven new skin cancer risk factors: lesion pink, lesion size, lesion colour, lesion inflamed, lesion shape, lesion age, and natural hair colour, which achieved a sensitivity of 80.46 ± 2.50 % and a specificity of 62.09 ± 1.90 % in detecting suspicious skin lesions when evaluated using the metadata of 53,601 skin lesions collected from different skin cancer diagnostic clinics across the UK, significantly outperforming the 7PCL-based method (sensitivity 68.09 ± 2.10 % , specificity 61.07 ± 0.90 % ) and the Williams risk factors (sensitivity 66.32 ± 1.90 % , specificity 61.71 ± 0.6 % ). Furthermore, through weighting the seven new risk factors we came up with a new risk score, namely "C4C risk score", which alone achieved a sensitivity of 76.09 ± 1.20 % and a specificity of 61.71 ± 0.50 % , significantly outperforming the 7PCL-based risk score (sensitivity 73.91 ± 1.10 % , specificity 49.49 ± 0.50 % ) and the Williams risk score (sensitivity 60.68 ± 1.30 % , specificity 60.87 ± 0.80 % ). Finally, fusing the C4C risk factors with the 7PCL and Williams risk factors achieved the best performance, with a sensitivity of 85.24 ± 2.20 % and a specificity of 61.12 ± 0.90 % . We believe that fusing these newly found risk factors and new risk score with image data will further boost the AI model performance for suspicious skin lesion detection. Hence, the new set of skin cancer risk factors has the potential to be used to modify current skin cancer referral guidelines for all skin cancer subtypes, including melanoma.

Asunto(s)

RESUMEN

In intensive care unit (ICU) patients undergoing mechanical ventilation (MV), the occurrence of difficult weaning contributes to increased ventilator-related complications, prolonged hospitalization duration, and a significant rise in healthcare costs. Therefore, early identification of influencing factors and prediction of patients at risk of difficult weaning can facilitate early intervention and preventive measures. This study aimed to strengthen airway management for ICU patients by constructing a risk prediction model with comprehensive and individualized offline programs based on machine learning techniques. This study involved the collection of data from 487 patients undergoing MV in the ICU, with a total of 36 variables recorded. The dataset was divided into a training set (70% of the data) and a test set (30% of the data). Five machine learning models, namely logistic regression, random forest, support vector machine, light gradient boosting machine, and extreme gradient boosting, were compared to predict the risk of difficult weaning in ICU patients with MV. Significant influencing factors were identified based on the results of these models, and a risk prediction model for ICU patients with MV was established. When evaluating the models using AUC (Area under the Curve of ROC) and Accuracy as performance metrics, the Random Forest algorithm exhibited the best performance among the five machine learning algorithms. The area under the operating characteristic curve for the subjects was 0.805, with an accuracy of 0.748, recall (0.888), specificity (0.767) and F1 score (0.825). This study successfully developed a risk prediction model for ICU patients with MV using a machine learning algorithm. The Random Forest algorithm demonstrated the highest prediction performance. These findings can assist clinicians in accurately assessing the risk of difficult weaning in patients and formulating effective individualized treatment plans. Ultimately, this can help reduce the risk of difficult weaning and improve the quality of life for patients.

Asunto(s)