Left atrial function in patients with rheumatic mitral stenosis: addressing prognostic insights beyond atrial fibrillation prediction.

Aims: Rheumatic mitral stenosis (MS) frequently leads to impaired left atrial (LA) function because of pressure overload, highlighting the underlying atrial pathology. Two-dimensional speckle tracking echocardiography (2D-STE) offers early detection of LA dysfunction, potentially improving risk assessment in patients with MS. This study aims to evaluate the predictive value of LA function assessed by 2D-STE for clinical outcomes in patients with MS. Methods and results: Between 2011 and 2021, patients with MS underwent LA function assessment using 2D-STE, with focus on the reservoir phase (LASr). Atrial fibrillation (AF) development constituted the primary outcome, with death or valve replacement as the secondary outcome. Conditional inference trees were employed for analysis, validated through sample splitting. The study included 493 patients with MS (mean valve area 1.1 ± 0.4 cm2, 84% female). At baseline, 166 patients (34%) had AF, with 62 patients (19%) developing AF during follow-up. LASr emerged as the primary predictor for new-onset AF, with a threshold of 17.9%. Over a mean 3.8-year follow-up, 125 patients (25%) underwent mitral valve replacement, and 32 patients (6.5%) died. A decision tree analysis identified key predictors such as age, LASr, severity of tricuspid regurgitation (TR), net atrioventricular compliance (C n), and early percutaneous mitral valvuloplasty, especially in patients aged ≤49 years, where LASr, with a threshold of 12.8%, significantly predicted adverse outcomes. Conclusion: LASr emerged as a significant predictor of cardiovascular events in this MS cohort, validated through a decision tree analysis. Patients were stratified into low- or high-risk categories for adverse outcomes, taking into account LASr, age, TR severity, and C n.

Development and validation of interpretable machine learning models to predict glomerular filtration rate in chronic kidney disease Colombian patients.

BACKGROUND: ML predictive models have shown their capability to improve risk prediction and assist medical decision-making, nevertheless, there is a lack of accuracy systems to early identify future rapid CKD progressors in Colombia and even in South America. OBJECTIVE: The purpose of this study was to develop a series of interpretable machine learning models that predict GFR at 6-months, 9-months, and 12-months. STUDY DESIGN AND SETTING: Over 29,000 CKD patients stage 1 to 3b (estimated GFR, <60 mL/min/1.73 m2) with an average of 3-year follow-up data were included. We used the machine learning extreme gradient boosting (XGBoost) to build three models to predict the next eGFR. Models were internally and externally validated. In addition, we included SHapley Additive exPlanation (SHAP) values to offer interpretable global and local prediction models. RESULTS: All models showed a good performance in development and external validation. However, the 6-months XGBoost prediction model showed the best performance in internal (MAE average = 6.07; RSME = 78.87), and in external validation (MAE average = 6.45, RSME = 18.94). The top 3 most influential features that pushed the predicted eGFR value to lower values were the interpolated values for eGFR and creatinine, and eGFR at baseline. CONCLUSION: In the current study we have developed and validated machine learning models to predict the next eGFR value at different intervals. Furthermore, we attempted to approach the need for prediction explanation by offering transparent predictions.

Non-Invasive Prediction of Choledocholithiasis Using 1D Convolutional Neural Networks and Clinical Data.

This paper introduces a novel one-dimensional convolutional neural network that utilizes clinical data to accurately detect choledocholithiasis, where gallstones obstruct the common bile duct. Swift and precise detection of this condition is critical to preventing severe complications, such as biliary colic, jaundice, and pancreatitis. This cutting-edge model was rigorously compared with other machine learning methods commonly used in similar problems, such as logistic regression, linear discriminant analysis, and a state-of-the-art random forest, using a dataset derived from endoscopic retrograde cholangiopancreatography scans performed at Olive View-University of California, Los Angeles Medical Center. The one-dimensional convolutional neural network model demonstrated exceptional performance, achieving 90.77% accuracy and 92.86% specificity, with an area under the curve of 0.9270. While the paper acknowledges potential areas for improvement, it emphasizes the effectiveness of the one-dimensional convolutional neural network architecture. The results suggest that this one-dimensional convolutional neural network approach could serve as a plausible alternative to endoscopic retrograde cholangiopancreatography, considering its disadvantages, such as the need for specialized equipment and skilled personnel and the risk of postoperative complications. The potential of the one-dimensional convolutional neural network model to significantly advance the clinical diagnosis of this gallstone-related condition is notable, offering a less invasive, potentially safer, and more accessible alternative.

Community-acquired acute kidney injury in Southeast Brazil and independent risk predictors: a prospective cohort study.

BACKGROUND: The prevalence and risk factors for community-acquired acute kidney injury (CA-AKI) are unknown. This study aimed to explore the incidence of CA-AKI in a tertiary care center and to depict the main clinical characteristics related to this condition. METHODS: This was a prospective cohort study involving patients admitted to the emergency department (Hospital de Clínicas, UNICAMP, Campinas, Brazil) between January 2019 and September 2021. Adults (≥ 18 yrs) who presented to the emergency room with symptoms potentially associated with an increased risk of AKI were included. Individuals with a prior diagnosis of stage 5 chronic kidney disease or with a confirmed COVID-19 infection were excluded. A score based on clinical signs and symptoms was assigned to predict the risk of severe AKI. RESULTS: Of the 261 patients enrolled, CA-AKI was diagnosed in 65 (25%). The CA-AKI group was older [57(± 14) vs. 51(± 18) years, p = 0.02] and had a lower baseline estimated glomerular filtration rate [103 (88-113) vs. 109 (97-121) mL/min/1.73 m2; p = 0.01]. Logistic regression showed that scores ≥ 7 points [odds ratio (OR) 2.8 (1.281-6.133), 95% confidence interval (CI), p = 0.01], age [OR 1.02 (1.007-1.044), 95% CI, p = 0.008] and liver disease [OR 2.6 (1.063-6.379), 95% CI, p = 0.03] were independently related to CA-AKI. CONCLUSION: The incidence of CA-AKI was not negligible among patients admitted to a tertiary care center; CA-AKI can be suspected on a clinical basis and confirmed by serum creatinine. Age, liver disease and higher scores in risk prediction tools were related to an increased incidence of CA-AKI.

Breast cancer risk prediction using machine learning: a systematic review.

Background: 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. Objective and methods: 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. Results: 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. Conclusion: This study offers investigators a different perspective on the use of AI for breast cancer risk prediction, incorporating numerous imaging and non-imaging features.

The usefulness of SAGE score in predicting high pulse wave velocity in hypertensive patients: a retrospective cohort study.

Introduction: Aortic stiffness assessed by pulse wave velocity (PWV) is an important predictor to evaluate the risk of hypertensive patients. However, it is underutilized in clinical practice. We aimed to identify the optimal cutoff SAGE score that would indicate a risk PWV ≥ 10 m/s in Brazilian ambulatory hypertensive patients. Materials and methods: A retrospective cohort study. Patients underwent central blood pressure measurement using a validated oscillometric device from August 2020 to December 2021. A ROC curve was constructed using the Youden statistic to define the best score to identify those at high risk for PWV ≥ 10 m/s. Results: A total of 212 hypertensive individuals were selected. The mean age was 64.0 ± 12.4 years and 57.5% were female. The following comorbidities were present: overweight (47.6%), obesity (34.3%), and diabetes (25.0%). Most of the sample (68.9%) had PWV < 10 m/s. According to Youden's statistic, a cutoff point of 6 provided the optimal combination of sensitivity and specificity for identifying patients with a PWV ≥ 10 m/s. This cutoff achieved sensitivity of 97.0%, and specificity of 82.9%. In clinical practice, however, a cutoff point of 7 (where score values of at least 7 were considered to indicate high risk) had a positive likelihood ratio of 8.2 and a negative likelihood ration of 0.346, making this the ideal choice by accurately excluding patients who are less likely to have PWV ≥ 10 m/s. Conclusion: A SAGE score ≥7 identified Brazilian hypertensive patients with a high risk of PWV ≥ 10 m/s.

Clinical risk prediction model and external validation of positive surgical margin in laparoscopic radical prostatectomy based on MRI lesion location.

OBJECTIVE: To clarify the composition of lesions in different magnetic resonance imaging (MRI) partitions of positive surgical margins (PSM) after laparoscopic radical prostatectomy, explore the influence of lesion location on PSM, and construct a clinical prediction model to predict the risk of PSM. MATERIALS AND METHODS: This retrospective cohort study included 309 patients who underwent laparoscopic radical prostatectomy from 2018 to 2021 in our center was performed. 129 patients who met the same criteria from January to September 2022 were external validation cohorts. RESULTS: The incidence of PSM in transition zone (TZ) lesions was higher than that in peripheral zone (PZ) lesions. The incidence of PSM in the middle PZ was lower than that in other regions. Prostate specific antigen (PSA), clinical T-stage, the number of positive cores, international society of urological pathology (ISUP) grade (biopsy), MRI lesion location, extracapsular extension, seminal vesicle invasion (SVI), pseudo-capsule invasion (PCI), long diameter of lesions, lesion volume, lesion volume ratio, PSA density were related to PSM. MRI lesion location and PCI were independent risk factors for PSM. Least absolute shrinkage and selection operator (LASSO) regression was used to construct a clinical prediction model for PSM, including five variables: the number of positive cores, SVI, MRI lesion location, long diameter of lesions, and PSA. CONCLUSION: The positive rate of surgical margin in middle PZ was significantly lower than that in other regions, and MRI lesion location was an independent risk factor for PSM.

Predicting the Need for Blood Transfusions in Cardiac Surgery: A Comparison between Machine Learning Algorithms and Established Risk Scores in the Brazilian Population.

INTRODUCTION: Blood transfusion is a common practice in cardiac surgery, despite its well-known negative effects. To mitigate blood transfusion-associated risks, identifying patients who are at higher risk of needing this procedure is crucial. Widely used risk scores to predict the need for blood transfusions have yielded unsatisfactory results when validated for the Brazilian population. METHODS: In this retrospective study, machine learning (ML) algorithms were compared to predict the need for blood transfusions in a cohort of 495 cardiac surgery patients treated at a Brazilian reference service between 2019 and 2021. The performance of the models was evaluated using various metrics, including the area under the curve (AUC), and compared to the commonly used Transfusion Risk and Clinical Knowledge (TRACK) and Transfusion Risk Understanding Scoring Tool (TRUST) scoring systems. RESULTS: The study found that the model had the highest performance, achieving an AUC of 0.7350 (confidence interval [CI]: 0.7203 to 0.7497). Importantly, all ML algorithms performed significantly better than the commonly used TRACK and TRUST scoring systems. TRACK had an AUC of 0.6757 (CI: 0.6609 to 0.6906), while TRUST had an AUC of 0.6622 (CI: 0.6473 to 0.6906). CONCLUSION: The findings of this study suggest that ML algorithms may offer a more accurate prediction of the need for blood transfusions than the traditional scoring systems and could enhance the accuracy of predicting blood transfusion requirements in cardiac surgery patients. Further research could focus on optimizing and refining ML algorithms to improve their accuracy and make them more suitable for clinical use.

Predicting the Need for Blood Transfusions in Cardiac Surgery: A Comparison between Machine Learning Algorithms and Established Risk Scores in the Brazilian Population

ABSTRACT Introduction: Blood transfusion is a common practice in cardiac surgery, despite its well-known negative effects. To mitigate blood transfusion-associated risks, identifying patients who are at higher risk of needing this procedure is crucial. Widely used risk scores to predict the need for blood transfusions have yielded unsatisfactory results when validated for the Brazilian population. Methods: In this retrospective study, machine learning (ML) algorithms were compared to predict the need for blood transfusions in a cohort of 495 cardiac surgery patients treated at a Brazilian reference service between 2019 and 2021. The performance of the models was evaluated using various metrics, including the area under the curve (AUC), and compared to the commonly used Transfusion Risk and Clinical Knowledge (TRACK) and Transfusion Risk Understanding Scoring Tool (TRUST) scoring systems. Results: The study found that the model had the highest performance, achieving an AUC of 0.7350 (confidence interval [CI]: 0.7203 to 0.7497). Importantly, all ML algorithms performed significantly better than the commonly used TRACK and TRUST scoring systems. TRACK had an AUC of 0.6757 (CI: 0.6609 to 0.6906), while TRUST had an AUC of 0.6622 (CI: 0.6473 to 0.6906). Conclusion: The findings of this study suggest that ML algorithms may offer a more accurate prediction of the need for blood transfusions than the traditional scoring systems and could enhance the accuracy of predicting blood transfusion requirements in cardiac surgery patients. Further research could focus on optimizing and refining ML algorithms to improve their accuracy and make them more suitable for clinical use.

Application of colon leakage score in the left-sided colorectal surgery.

Background: Colon leakage score (CLS) was developed for risk prediction of anastomotic leak (AL) in the left-sided colorectal surgery. Although the risk factors for leakage are well known and accepted by the surgical community, an accurate forecast of AL is still a difficult task. Objective: The study aims to apply the CLS in patients undergoing left-sided colorectal surgery. Methods: Retrospective study in patients with the left-sided colorectal surgery and primary anastomosis without diverting stoma. CLS was calculated in patients, who were classified in AL and NO-AL groups. Predictive value of CLS was evaluated by receiver operator characteristic. Correlation between CLS and AL was determined. 208 patients (55% male, mean age 59 years) were included in the study. Results: Overall, AL was 7.2%. Mean CLS of all patients was 7.2 ± 3.2 (0-17). Patients with AL had a higher CLS (11.8 ± 2.3) than NO-AL patients (6.8 ± 3) (p = 0.0001). The area under the curve for the prediction of AL by CLS was 0.898 ([CI] 0.829-0.968, p = 0.0001). A CLS of 8.5 had 93% sensitivity and 72% specificity. There was a statistically significant odds ratio for CLS and AL (0.58: [CI] 0.46-0.73, p = 0.0001). Conclusion: CLS is a useful tool to predict AL in the left-sided colorectal surgery.

Antecedentes: La puntuación de fugas de colon (CLS) se desarrolló para la predicción del riesgo de fuga anastomótica (AL) en la cirugía colorrectal del lado izquierdo, con la finalidad de obtener un pronóstico preciso. Objetivo: Este estudio tiene el objetivo de aplicar el CLS en pacientes con cirugía colorrectal de lado izquierdo. Método: Estudio retrospectivo en pacientes con cirugía colorrectal izquierda y anastomosis primaria sin estoma de derivación. Se calculó el CLS en los pacientes, los cuales fueron clasificados en los grupos con AL y sin AL. Resultados: La media del CLS de todos los pacientes fue de 7.2 ± 3.2 (0-17). Los pacientes con AL tenían un CLS más alto (11.8 ± 2.3) que los pacientes sin AL (6.8 ± 3) (p = 0.0001). El área bajo la curva para la predicción de la AL mediante el CLS fue de 0.898 (intervalo de confianza (CI) 0.829-0.968; p = 0.0001). Un CLS de 8.5 tuvo una sensibilidad del 93% y una especificidad del 72%. Además, se obtuvo un Odds Ratio con una diferencia estadísticamente significativa para el CLS y AL (0.58; CI 0.46-0.73; p = 0.0001). Conclusión: La CLS es una herramienta útil para predecir la AL en la cirugía colorrectal del lado izquierdo.

Temporal validation of the MMCD score to predict kidney replacement therapy and in-hospital mortality in COVID-19 patients.

BACKGROUND: Acute kidney injury has been described as a common complication in patients hospitalized with COVID-19, which may lead to the need for kidney replacement therapy (KRT) in its most severe forms. Our group developed and validated the MMCD score in Brazilian COVID-19 patients to predict KRT, which showed excellent performance using data from 2020. This study aimed to validate the MMCD score in a large cohort of patients hospitalized with COVID-19 in a different pandemic phase and assess its performance to predict in-hospital mortality. METHODS: This study is part of the "Brazilian COVID-19 Registry", a retrospective observational cohort of consecutive patients hospitalized for laboratory-confirmed COVID-19 in 25 Brazilian hospitals between March 2021 and August 2022. The primary outcome was KRT during hospitalization and the secondary was in-hospital mortality. We also searched literature for other prediction models for KRT, to assess the results in our database. Performance was assessed using area under the receiving operator characteristic curve (AUROC) and the Brier score. RESULTS: A total of 9422 patients were included, 53.8% were men, with a median age of 59 (IQR 48-70) years old. The incidence of KRT was 8.8% and in-hospital mortality was 18.1%. The MMCD score had excellent discrimination and overall performance to predict KRT (AUROC: 0.916 [95% CI 0.909-0.924]; Brier score = 0.057). Despite the excellent discrimination and overall performance (AUROC: 0.922 [95% CI 0.914-0.929]; Brier score = 0.100), the calibration was not satisfactory concerning in-hospital mortality. A random forest model was applied in the database, with inferior performance to predict KRT requirement (AUROC: 0.71 [95% CI 0.69-0.73]). CONCLUSION: The MMCD score is not appropriate for in-hospital mortality but demonstrates an excellent predictive ability to predict KRT in COVID-19 patients. The instrument is low cost, objective, fast and accurate, and can contribute to supporting clinical decisions in the efficient allocation of assistance resources in patients with COVID-19.

Risk prediction in patients with classical low-flow, low-gradient aortic stenosis undergoing surgical intervention.

Introduction: Classical low-flow, low-gradient aortic stenosis (LFLG-AS) is an advanced stage of aortic stenosis, which has a poor prognosis with medical treatment and a high operative mortality after surgical aortic valve replacement (SAVR). There is currently a paucity of information regarding the current prognosis of classical LFLG-AS patients undergoing SAVR and the lack of a reliable risk assessment tool for this particular subset of AS patients. The present study aims to assess mortality predictors in a population of classical LFLG-AS patients undergoing SAVR. Methods: This is a prospective study including 41 consecutive classical LFLG-AS patients (aortic valve area ≤1.0 cm2, mean transaortic gradient <40 mmHg, left ventricular ejection fraction <50%). All patients underwent dobutamine stress echocardiography (DSE), 3D echocardiography, and T1 mapping cardiac magnetic resonance (CMR). Patients with pseudo-severe aortic stenosis were excluded. Patients were divided into groups according to the median value of the mean transaortic gradient (≤25 and >25 mmHg). All-cause, intraprocedural, 30-day, and 1-year mortality rates were evaluated. Results: All of the patients had degenerative aortic stenosis, with a median age of 66 (60-73) years; most of the patients were men (83%). The median EuroSCORE II was 2.19% (1.5%-4.78%), and the median STS was 2.19% (1.6%-3.99%). On DSE, 73.2% had flow reserve (FR), i.e., an increase in stroke volume ≥20% during DSE, with no significant differences between groups. On CMR, late gadolinium enhancement mass was lower in the group with mean transaortic gradient >25 mmHg [2.0 (0.0-8.9) g vs. 8.5 (2.3-15.0) g; p = 0.034), and myocardium extracellular volume (ECV) and indexed ECV were similar between groups. The 30-day and 1-year mortality rates were 14.6% and 43.8%, respectively. The median follow-up was 4.1 (0.3-5.1) years. By multivariate analysis adjusted for FR, only the mean transaortic gradient was an independent predictor of mortality (hazard ratio: 0.923, 95% confidence interval: 0.864-0.986, p = 0.019). A mean transaortic gradient ≤25 mmHg was associated with higher all-cause mortality rates (log-rank p = 0.038), while there was no difference in mortality regarding FR status (log-rank p = 0.114). Conclusions: In patients with classical LFLG-AS undergoing SAVR, the mean transaortic gradient was the only independent mortality predictor in patients with LFLG-AS, especially if ≤25 mmHg. The absence of left ventricular FR had no prognostic impact on long-term outcomes.

Development of machine learning models to predict gestational diabetes risk in the first half of pregnancy.

BACKGROUND: Early prediction of Gestational Diabetes Mellitus (GDM) risk is of particular importance as it may enable more efficacious interventions and reduce cumulative injury to mother and fetus. The aim of this study is to develop machine learning (ML) models, for the early prediction of GDM using widely available variables, facilitating early intervention, and making possible to apply the prediction models in places where there is no access to more complex examinations. METHODS: The dataset used in this study includes registries from 1,611 pregnancies. Twelve different ML models and their hyperparameters were optimized to achieve early and high prediction performance of GDM. A data augmentation method was used in training to improve prediction results. Three methods were used to select the most relevant variables for GDM prediction. After training, the models ranked with the highest Area under the Receiver Operating Characteristic Curve (AUCROC), were assessed on the validation set. Models with the best results were assessed in the test set as a measure of generalization performance. RESULTS: Our method allows identifying many possible models for various levels of sensitivity and specificity. Four models achieved a high sensitivity of 0.82, a specificity in the range 0.72-0.74, accuracy between 0.73-0.75, and AUCROC of 0.81. These models required between 7 and 12 input variables. Another possible choice could be a model with sensitivity of 0.89 that requires just 5 variables reaching an accuracy of 0.65, a specificity of 0.62, and AUCROC of 0.82. CONCLUSIONS: The principal findings of our study are: Early prediction of GDM within early stages of pregnancy using regular examinations/exams; the development and optimization of twelve different ML models and their hyperparameters to achieve the highest prediction performance; a novel data augmentation method is proposed to allow reaching excellent GDM prediction results with various models.

Copula modeling for the estimation of measures of marker classification and predictiveness performance with survival outcomes.

The discriminative and predictive power of a continuous-valued marker for survival outcomes can be summarized using the receiver operating characteristic and predictiveness curves, respectively. In this paper, fully parametric and semi-parametric copula-based constructions of the joint model of the marker and the survival time are developed for characterizing, plotting, and analyzing both curves along with other underlying performance measures. The formulations require a copula function, a parametric specification for the margin of the marker, and either a parametric distribution or a non-parametric estimator for the margin of the time to event, to respectively characterize the fully parametric and semi-parametric joint models. Estimation is carried out using maximum likelihood and a two-stage procedure for the parametric and semi-parametric models, respectively. Resampling-based methods are used for computing standard errors and confidence bounds for the various parameters, curves, and associated measures. Graphical inspection of residuals from each conditional distribution is employed as a guide for choosing a copula from a set of candidates. The performance of the estimators of various classification and predictiveness measures is assessed in simulation studies, assuming different copula and censoring scenarios. The methods are illustrated with the analysis of two markers using the familiar primary biliary cirrhosis data set.

Proposing an integrative, dynamic and transdiagnostic model for addictions: dysregulation phenomena of the three main modes of the predostatic mind.

Several theories have been proposed to explain the complex diagnostic aspects related to addiction disorders and their development. Recent frameworks tend to focus on dimensional perspectives of symptoms rather than categorical systems, since substance use disorders are frequently comorbid with other psychiatric and especially personality disorders. However, useful transdiagnostic models that could integrate clinical evaluation derived from neuroscientific theories are lacking. In the present manuscript, the authors propose a model based on a new paradigm, in an attempt to better explain this complex, multifaceted phenomenon. The new paradigm presupposes that emotions and behavior are a response to risk prediction. Individuals make choices and engage in actions to manage potential risks/rewards in order to seek or maintain homeostasis in their internal and external environments - a mechanism that the authors call predostatic (predictive mechanism with homeostatic purpose). The model considers three main modes of the predostatic mind: (1) Alarm Mode, activated by high and/or imminent risk prediction; (2) Seek Mode, activated by long-term risk or reward prediction; and (3) Balance Mode, a self-regulating state of mind related to low risk prediction, a soothing system and a calm state. Addiction is seen as a chronic dysregulation of organism systems leading to internalizing or externalizing phenomena mainly related to the Seek and Alarm Modes, which are persistently activated by reward and risk prediction, respectively, thus hindering Balance. Addiction neuroscience research has shown that chronic drug use or engagement in addictive behaviors can lead to neuroadaptations in the brain reward circuitry, disrupting normal balance and the regulation of reward processes. This dysregulation can contribute to persistent drug-seeking/addictive behaviors despite negative consequences. This newly proposed dynamic and integrative model, named dysregulation based on externalizing and internalizing phenomena of the three main modes of the predostatic mind (DREXI3), proposes six dysregulation dimensions with basic emotional and behavioral symptoms, such as neurophysiological alterations, impulsivity, compulsion, cognitive impairment/psychosis, mood, and anxiety/anger. In this paper, the authors explain the rationale behind DREXI3 and present some hypothetical clinical examples to better illustrate the use of the model in clinical practice. The development of this innovative model could possibly guide tailored treatment interventions in the addiction field.

Machine learning for atrial fibrillation risk prediction in patients with sleep apnea and coronary artery disease.

Background: Patients with sleep apnea (SA) and coronary artery disease (CAD) are at higher risk of atrial fibrillation (AF) than the general population. Our objectives were: to evaluate the role of CAD and SA in determining AF risk through cluster and survival analysis, and to develop a risk model for predicting AF. Methods: Electronic medical record (EMR) database from 22,302 individuals including 10,202 individuals with AF, CAD, and SA, and 12,100 individuals without these diseases were analyzed using K-means clustering technique; k-nearest neighbor (kNN) algorithm and survival analysis. Age, sex, and diseases developed for each individual during 9 years were used for cluster and survival analysis. Results: The risk models for AF, CAD, and SA were identified with high accuracy and sensitivity (0.98). Cluster analysis showed that CAD and high blood pressure (HBP) are the most prevalent diseases in the AF group, HBP is the most prevalent disease in CAD; and HBP and CAD are the most prevalent diseases in the SA group. Survival analysis demonstrated that individuals with HBP, CAD, and SA had a 1.5-fold increased risk of developing AF [hazard ratio (HR): 1.49, 95% CI: 1.18-1.87, p = 0.0041; HR: 1.46, 95% CI: 1.09-1.96, p = 0.01; HR: 1.54, 95% CI: 1.22-1.94, p = 0.0039, respectively] and individuals with chronic kidney disease (CKD) developed AF approximately 50% earlier than patients without these comorbidities in a period of 7 years (HR: 3.36, 95% CI: 1.46-7.73, p = 0.0023). Comorbidities that contributed to develop AF earlier in females compared to males in the group of 50-64 years were HBP (HR: 3.75 95% CI: 1.08-13, p = 0.04) CAD and SA in the group of 60-75 years were (HR: 2.4 95% CI: 1.18-4.86, p = 0.02; HR: 2.51, 95% CI: 1.14-5.52, p = 0.02, respectively). Conclusion: Machine learning based algorithms demonstrated that CAD, SA, HBP, and CKD are significant risk factors for developing AF in a Latin-American population.

Diagnóstico y tratamiento de la embolia pulmonar aguda durante el embarazo

Introducción: La embolia pulmonar aguda es una de las causas más frecuentes de mortalidad y morbilidad grave durante el embarazo, sin embargo, no existe un consenso para su diagnóstico definitivo. Objetivo: Exponer las consideraciones más importantes para el diagnóstico y tratamiento de gestantes con sospecha de embolia pulmonar. Material y Métodos: Revisión de la literatura sobre el tema, publicada desde 2012 y hasta la actualidad que incluyó las bases de datos PubMed/MEDLINE, EMBASE, Lilacs y SciELO. Desarrollo: Las guías actuales muestran controversias en relación con el uso de reglas de predicción de riesgo, la cuantificación del dímero D y la indicación de estudios de imagen. La evaluación clínica continúa siendo el principal sustrato diagnóstico, pero se ha señalado que tanto una gammagrafía de ventilación-perfusión normal como una angio TC negativa excluyen con precisión la embolia pulmonar durante el embarazo. El uso de heparinas es el tratamiento de elección, mientras que los nuevos anticoagulantes orales no están recomendados en el embarazo a falta de estudios que avalen su seguridad. La fibrinólisis se puede considerar ante gestantes de alto riesgo (hipotensión grave, shock o parada cardiorespiratoria). Conclusiones: El manejo de las pacientes debe ser por un equipo multidisciplinario, lo que permitirá obtener mejores resultados maternos y perinatales.

Introduction: Acute pulmonary embolism is one of the most frequent causes of mortality and serious morbidity during pregnancy; however, there is no consensus on its definitive diagnosis. Objective: To expose the most important considerations for the diagnosis and treatment of pregnant women with suspected pulmonary embolism. Material and Methods: Literature review on the subject, published from 2012 to the present, which included the PubMed/MEDLINE, EMBASE, Lilacs and SciELO databases. Development: The current guidelines show controversies in relation to the use of risk prediction rules, the quantification of D-dimer and the indication of imaging studies. Clinical evaluation continues to be the main diagnostic substrate, but it has been pointed out that both a normal ventilation-perfusion scintigraphy and a negative CT angiography accurately exclude pulmonary embolism during pregnancy. The use of heparins is the treatment of choice, while the new oral anticoagulants are not recommended in pregnancy due to the lack of studies that support their safety. Fibrinolysis can be considered in high-risk pregnant women (severe hypotension, shock, or cardiorespiratory arrest). Conclusions: The management of these patients should be undertaken by a multidisciplinary team, which will allow better maternal and perinatal results.

Forecasting Weekly Dengue Cases by Integrating Google Earth Engine-Based Risk Predictor Generation and Google Colab-Based Deep Learning Modeling in Fortaleza and the Federal District, Brazil.

Efficient and accurate dengue risk prediction is an important basis for dengue prevention and control, which faces challenges, such as downloading and processing multi-source data to generate risk predictors and consuming significant time and computational resources to train and validate models locally. In this context, this study proposed a framework for dengue risk prediction by integrating big geospatial data cloud computing based on Google Earth Engine (GEE) platform and artificial intelligence modeling on the Google Colab platform. It enables defining the epidemiological calendar, delineating the predominant area of dengue transmission in cities, generating the data of risk predictors, and defining multi-date ahead prediction scenarios. We implemented the experiments based on weekly dengue cases during 2013-2020 in the Federal District and Fortaleza, Brazil to evaluate the performance of the proposed framework. Four predictors were considered, including total rainfall (Rsum), mean temperature (Tmean), mean relative humidity (RHmean), and mean normalized difference vegetation index (NDVImean). Three models (i.e., random forest (RF), long-short term memory (LSTM), and LSTM with attention mechanism (LSTM-ATT)), and two modeling scenarios (i.e., modeling with or without dengue cases) were set to implement 1- to 4-week ahead predictions. A total of 24 models were built, and the results showed in general that LSTM and LSTM-ATT models outperformed RF models; modeling could benefit from using historical dengue cases as one of the predictors, and it makes the predicted curve fluctuation more stable compared with that only using climate and environmental factors; attention mechanism could further improve the performance of LSTM models. This study provides implications for future dengue risk prediction in terms of the effectiveness of GEE-based big geospatial data processing for risk predictor generation and Google Colab-based risk modeling and presents the benefits of using historical dengue data as one of the input features and the attention mechanism for LSTM modeling.

The predictive capability of aortic stiffness index for aortic dissection among dilated ascending aortas.

OBJECTIVE: We created a finite element model to predict the probability of dissection based on imaging-derived aortic stiffness and investigated the link between stiffness and wall tensile stress using our model. METHODS: Transthoracic echocardiogram measurements were used to calculate aortic diameter change over the cardiac cycle. Aortic stiffness index was subsequently calculated based on diameter change and blood pressure. A series of logistic models were developed to predict the binary outcome of aortic dissection using 1 or more series of predictor parameters such as aortic stiffness index or patient characteristics. Finite element analysis was performed on a subset of diameter-matched patients exhibiting patient-specific material properties. RESULTS: Transthoracic echocardiogram scans of patients with type A aortic dissection (n = 22) exhibited elevated baseline aortic stiffness index when compared with aneurysmal patients' scans with tricuspid aortic valve (n = 83, P < .001) and bicuspid aortic valve (n = 80, P < .001). Aortic stiffness index proved an excellent discriminator for a future dissection event (area under the curve, 0.9337, odds ratio, 2.896). From the parametric finite element study, we found a correlation between peak longitudinal wall tensile stress and stiffness index (ρ = .6268, P < .001, n = 28 pooled). CONCLUSIONS: Noninvasive transthoracic echocardiogram-derived aortic stiffness measurements may serve as an impactful metric toward predicting aortic dissection or quantifying dissection risk. A correlation between longitudinal stress and stiffness establishes an evidence-based link between a noninvasive stiffness parameter and stress state of the aorta with clinically apparent dissection events.