Origin, pathogenicity, and transmissibility of a human isolated influenza A(H10N3) virus from China

Subtype H10 viruses are known to infect humans in Africa, Oceania, and Asia. In 2021, 2022, and recently in April 2024, a novel H10N3 subtype avian influenza virus was found cause human infection with severe pneumonia. Herein, we comprehensively studied the phylogenetic evolution and biological characteristics of the newly emerged influenza A(H10N3) virus. We found that the human isolated H10N3 virus was generated in early 2019 in domestic poultry. The viruses bound to salic acid α2, 3 receptors, indicating their insufficient ability to infect humans. Although a low pathogenic avian influenza virus, the human isolated H10N3 virus exhibited robust pathogenicity in both BALB/c and C57BL/6 mice, with MLD50 1000 times higher than a homologous environmental isolate. The human isolated H10N3 also showed respiratory droplet transmissibility in ferrets. Considering the continuous circulation in avian populations and repeated transmission to humans, strengthened surveillance of H10 subtype viruses in poultry should be put into effect.

Association between renal mean perfusion pressure and prognosis in patients with sepsis-associated acute kidney injury: insights from the MIMIC IV database

OBJECTIVE

To investigate the association between renal mean perfusion pressure (MPP) and prognosis in sepsis-associated acute kidney injury (SA-AKI).

METHODS

Data were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Group-based trajectory modeling (GBTM) was applied to identify dynamic MPP patterns, while restricted cubic spline (RCS) curves were utilized to confirm the non-linear relationship between MPP and mortality. Cox regression analysis assessed the risk of mortality across different MPP levels, adjusting for potential confounders. Subgroup analyses and sensitivity analyses were conducted to ensure the robustness of the findings.

RESULTS

A total of 2318 patients with SA-AKI were stratified into five MPP trajectories by GBTM. Patients in Traj-1 and Traj-2, characterized by consistently low MPP (<60 mmHg), demonstrated markedly higher 90-d mortality (62.86% and 26.98%). RCS curves revealed a non-linear inverse relationship between MPP and 90-d mortality, identifying 60 mmHg as the optimal threshold. Patients with MPP ≤ 60 mmHg exhibited significantly elevated 90-d mortality compared to those with MPP > 60 mmHg (29.81% vs. 20.88%). Cox regression analysis established Traj-1 and Traj-2 as independent risk factors for increased mortality relative to Traj-3 (60-70 mmHg), with hazard ratios (HRs) of 4.67 (95%-CI 3.28-6.67) and 1.45 (95%-CI 1.20-1.76). MPP > 60 mmHg was significantly associated with reduced 90-d mortality (HR 0.65, 95%-CI 0.55-0.77). Subgroup and PSM analyses supported these findings.

CONCLUSIONS

Dynamic MPP trajectory serves as a valuable prognostic biomarker for SA-AKI. Early monitoring of MPP trends offers critical insights into renal perfusion management, potentially improving outcomes in SA-AKI.

Psychometric validation of the Chinese version of the Edmonton-33 scale in patients with head and neck cancer

Objective

This study aimed to translate the Edmonton-33 scale (E-33) into Chinese and evaluate its reliability and validity in patients with head and neck cancer (HNC).

Methods

In Phase 1, the E-33 was translated from English to Chinese using the Brislin double-back translation method. Content validity was evaluated by a panel of experts, and a pilot test was conducted with a small sample of HNC patients. In Phase 2, a cohort of 510 patients from Henan and Hubei provinces was recruited. Psychometric properties were assessed through item analysis; and reliability testing (including Cronbach's alpha, test-retest reliability, and split-half reliability), as well as construct validity (using exploratory and confirmatory factor analysis).

Results

The item-level content validity index (I-CVI) ranged from 0.833 to 1.000, and the scale-level content validity index (S-CVI/Ave) was 0.965. The Cronbach's alpha, the test-retest reliability coefficient, and the split-half reliability values were 0.922, 0.973, and 0.971, respectively. Four main factors were identified using exploratory factor analysis, explaining 77.07% of the total variance. Confirmatory factor analysis showed good fit indices: χ2/df ​= ​1.626, RMSEA ​= ​0.048, NFI ​= ​0.936, RFI ​= ​0.930, IFI ​= ​0.974, TLI ​= ​0.972, and CFI ​= ​0.974.

Conclusions

The Chinese version of the Edmonton-33 scale (CE-33) demonstrated high reliability and validity, suggesting its potential as a valuable self-report tool for assessing functional outcomes in Chinese-speaking HNC patients.

Utilization of lactate trajectory models for predicting acute kidney injury and mortality in patients with hyperlactatemia: insights across three independent cohorts

This study aims to investigate the association between lactate trajectories and the risk of acute kidney injury (AKI) and hospital mortality in patients with hyperlactatemia. We conducted a multicenter retrospective study using data from three independent cohorts. By the lactate levels during the first 48 h of ICU admission, patients were classified into distinct lactate trajectories using group-based trajectory modeling (GBTM) method. The primary outcomes were AKI incidence and hospital mortality. Logistic regression analysis assessed the association between lactate trajectories and clinical outcomes, with adjusting potential confounders. Patients were divided into three trajectories: mild hyperlactatemia with rapid recovery (Traj-1), severe hyperlactatemia with gradual recovery (Traj-2), and severe hyperlactatemia with persistence (Traj-3). Traj-3 was an independent risk factor of both hospital mortality (all p < 0.001) and AKI development (all p < 0.001). Notably, Traj-2 was also associated with increased risk of mortality and AKI development (all p < 0.05) using Traj-1 as reference, except for the result in the Tianjin Medical University General Hospital (TMUGH) cohort for mortality in adjusted model (p = 0.123). Our finding was still robust in subgroup and sensitivity analysis. In the combination cohort, both Traj-2 and Traj-3 were considered as independent risk factor for hospital mortality and AKI development (all p < 0.001). When compared with the Traj-3, Traj-2 was only significantly associated with the decreased risk of hospital mortality (OR 0.17, 95% CI 0.14-0.20, p < 0.001), but no with the likelihood of AKI development (OR 0.90, 95% CI 0.77-1.05, p = 0.172). Lactate trajectories provide valuable information for predicting AKI and mortality in critically ill patients.

Impact of 30 mL/kg fluid resuscitation completed within one hour on elderly septic shock patient

OBJECTIVE

This study aimed to investigate the prognostic impact of completing 30 mL/kg fluid resuscitation within 1 h in elderly septic shock patients.

METHODS

This was a multicenter prospective observational cohort study. We applied logistic regression to assess the impact of completing 30 mL/kg fluid resuscitation within 1 h on respiratory support escalation including new-onset mechanical ventilation, bilevel positive airway pressure (BiPAP), and high-flow nasal cannula (HFNC) as well as heart failure (HF). We plotted Kaplan-Meier (K-M) curves to evaluate survival in patients completing 30 mL/kg fluid resuscitation within 1 h. We performed mediation analyses to determine the influence of HF on mortality associated with completing 30 mL/kg fluid resuscitation within 1 h.

RESULTS

Completing 30 mL/kg fluid resuscitation within 1 h increased the odds ratios of new-onset BiPAP (adjusted OR = 3.411; 95% confidence interval (CI) = [1.526, 7.620]) and HFNC (adjusted OR = 2.576; 95% CI = [1.252, 5.297]) within 24 h as well as the odds ratio of HF (adjusted OR = 2.291; 95% CI = [1.266, 4.149]). The adjusted K-M curve showed that patients completing 30 mL/kg fluid resuscitation within 1 h had higher 30-d mortality than those completing it over longer periods. The mediation effect suggested that completing 30 mL/kg fluid resuscitation within 1 h could be fatal primarily because it increased the risk of HF.

CONCLUSION

For elderly patients with septic shock, completing 30 ml/kg of fluid resuscitation within 1 h ought to be more cautious, particularly considering the patient's cardiac function and overall clinical status.

Investigation of the connection between triglyceride-glucose (TyG) index and the risk of acute kidney injury in septic patients - a retrospective analysis utilizing the MIMIC-IV database

The TyG index serves as a valuable tool for evaluating insulin resistance. An elevated TyG has shown a strong association with the occurrence of acute kidney injury (AKI). Nevertheless, existing literature does not address the relationship between the TyG index and acute kidney injury in patients with sepsis. Sepsis patients were identified from the MIMIC-IV database and categorized into four groups according to quadrilles of their TyG index values. The primary outcome of this study was the incidence of AKI. The relationship between the TyG index and the risk of AKI in septic patients was evaluated using Cox proportional hazards and restricted cubic spline models. Subgroup analyses were conducted to investigate the prognostic value of the TyG index in different subgroups. A total of 2,616 patients with sepsis (57% of whom were male) were included in this study. The incidence of AKI was found to be 78%. Cox proportional hazards analysis revealed a significant correlation between the TyG index and the occurrence of AKI in septic patients. Furthermore, a restricted cubic spline model revealed an approximately linear relationship between a higher TyG index and an elevated risk of AKI in septic patients. The trend of the hazard ratio (HR) remained consistent across various subgroups. These findings emphasize the reliability of the TyG index as an independent predictor for the occurrence of AKI and unfavorable renal outcomes in sepsis patients. Nevertheless, establishing a causal relationship between the two requires demonstration through larger prospective studies.

Applying machine learning to predict bowel preparation adequacy in elderly patients for colonoscopy: development and validation of a web-based prediction tool

BACKGROUND

Adequate bowel preparation is crucial for effective colonoscopy, especially in elderly patients who face a high risk of inadequate preparation. This study develops and validates a machine learning model to predict bowel preparation adequacy in elderly patients before colonoscopy.

METHODS

The study adhered to the TRIPOD AI guidelines. Clinical data from 471 elderly patients collected between February and December 2023 were utilized for developing and internally validating the model, while 221 patients' data from March to June 2024 were used for external validation. The Boruta algorithm was applied for feature selection. Models including logistic regression, light gradient boosting machines, support vector machines (SVM), decision trees, random forests, and extreme gradient boosting were evaluated using metrics such as AUC, accuracy, sensitivity, and specificity. The SHAP algorithm helped rank feature importance. A web-based application was developed using the Streamlit framework to enhance clinical usability.

RESULTS

The Boruta algorithm identified 7 key features. The SVM model excelled with an AUC of 0.895 (95% CI: 0.822-0.969), and high accuracy, sensitivity, and specificity. In external validation, the SVM model maintained robust performance with an AUC of 0.889. The SHAP algorithm further explained the contribution of each feature to model predictions.

CONCLUSION

The study developed an interpretable and practical machine learning model for predicting bowel preparation adequacy in elderly patients, facilitating early interventions to improve outcomes and reduce resource wastage.

Lipocalin 2 mediates kidney function abnormalities induced by ischemic stroke in mice: Involvement of neural pathways

BACKGROUND

Kidney function abnormalities is a common complication following ischemic stroke. Lipocalin 2 (LCN2) is currently a well-recognized specific biomarker of tubular injury. However, the role of LCN2 in kidney function abnormalities following stroke remains elusive. The sympathetic nervous system plays a crucial role in linking the brain and kidney. However, whether the kidney sympathetic nervous system regulates the expression of LCN2 following ischemic stroke has not been identified.

METHODS

In this study, we established a middle cerebral artery occlusion (MCAO) model to induce ischemic stroke in mice. Renal function was assessed 24 h after cerebral ischemia-reperfusion injury. Transcriptomic sequencing of kidney tissue was performed to identify potential pathological mechanisms. The role of LCN2 in post-stroke renal injury was investigated using renal tubule-specific LCN2 knockout mice and a combination of qPCR, western blotting, immunofluorescence, and transmission electron microscopy. In addition, renal denervation (RDN) was used to explore the relationship between sympathetic nerves and the expression of renal LCN2.

RESULTS

Ischemic stroke significantly exhibits renal functional impairment 24 h after reperfusion. Notably, RNA sequencing and Western blotting revealed a markedly increased expression of renal LCN2 following ischemic stroke. Renal tubular Lcn2-specific knockout significantly ameliorated the occurrence of kidney function abnormalities after stroke. Subsequently, we observed that the activation of renal sympathetic nerves upregulates LCN2 and induces kidney function abnormalities after stroke.

CONCLUSIONS

These findings reveal a neural pathway in which the sympathetic nervous system upregulates LCN2, providing potential therapeutic strategies for renal protection following ischemic stroke.

Development and validation of explainable machine learning models for female hip osteoporosis using electronic health records

BACKGROUND

Hip fractures are associated with reduced mobility, and higher morbidity, mortality, and healthcare costs. Approximately 90% of hip fractures in the elderly are associated with osteoporosis, making it particularly important to screen the population for hip osteoporosis and intervene early. Dual-energy X-ray absorptiometry (DXA) has limited accessibility, so predictive models for hip osteoporosis that do not use bone mineral density (BMD) data are essential. We aimed to develop and validate prediction models for female hip osteoporosis using electronic health records without BMD data.

METHODS

This retrospective study used anonymized medical electronic records, from September 2013 to November 2023, from the Health Management Center of the Second Xiangya Hospital. A total of 8039 women were included in the derivation dataset. The set was then randomized into a 75% training dataset and a 25% testing dataset. Four algorithms for feature selection were used to identify predictors of osteoporosis. The identified predictors were then used to train and optimize eight machine learning models. The models were tuned using 5-fold cross-validation to assess model performance in the testing dataset and the independent validation dataset from the National Health and Nutrition Examination Surveys (NHANES). The SHapley Additive explanation (SHAP) method was used to rank feature importance and explain the final model.

RESULTS

A combination of the Boruta, LASSO, varSelRF, and RFE methods identified systolic blood pressure, red blood cell count, glycohemoglobin, alanine aminotransferase, aspartate aminotransferase, uric acid, age, and body mass index as the most important predictors of osteoporosis in women. The XGBoost model outperformed the other models, with an Area Under the Curve (AUC) of 0.805 (95%CI: 0.779-0.831), and a moderate sensitivity of 0.706. The externally validated XGBoost model had an AUC of 0.811 (95% CI: 0.793-0.828), with a moderate sensitivity of 0.775.

CONCLUSIONS

The XGBoost model demonstrates high identification performance even without questionnaire data, out-performing both the traditional the logistic regression model and the OSTA model. It can be integrated into routine clinical workflows to identify females at high risk for osteoporosis.

Quality of life in caregivers of toddlers with autism features

Understanding factors that contribute to the quality of life (QoL) of primary caregivers of young autistic children can help researchers and clinicians provide high-quality support to caregivers and families. This study examined whether family demographic factors, parenting stress, and caregivers' perceptions of family-centered healthcare experiences uniquely predict caregivers' QoL. Participants were caregivers of toddlers with: features of autism (n = 119), other developmental delays (n = 101), and no developmental concerns (n = 264). We hypothesized that higher levels of perceived family-centered care would moderate (ameliorate) the relation between parenting stress and QoL. Higher levels of perceived family-centered care were associated with higher QoL for all groups but did not moderate the negative relation between parenting stress and QoL. Negative effects of parenting stress on QoL were stronger for caregivers of children with autism features compared to other groups. Future research is needed to determine how to provide additional support to caregivers with lower QoL, particularly caregivers who are experiencing income- or parenting-related stress and lower levels of family-centered care. Caregiver QoL is especially important to support across service settings (e.g., primary care, early intervention) during the birth-to-three period, when the process of accessing autism services can be challenging for caregivers.

Inter-atrial block as a predictor of adverse outcomes in patients with HFpEF

AIMS

Inter-atrial block (IAB), a marker of electrical atrial dysfunction, is associated with an increased risk of atrial fibrillation (AF) and adverse events in various populations. The prognostic impact of IAB in heart failure (HF) with preserved ejection fraction (HFpEF) remains unknown. The aim of this study is to determine the prevalence of IAB and the association of IAB and AF with adverse events in HFpEF across different healthcare settings.

METHODS AND RESULTS

To identify electrical atrial dysfunction, baseline ECG's and medical history were analysed in HFpEF patients in an ambulatory setting and after recent HF hospitalisation. Patients were categorised into (i) HFpEFNo IAB, (ii) HFpEFIAB, or (iii) HFpEFAF. Adverse events included HF hospitalisation, cardiac/sudden death and a composite of both. The ambulatory cohort included 372 patients [mean age 75 ± 7 years, 252 (68%) females]. The recently hospitalised cohort included 132 patients [mean age 81 ± 10 years, 80 (61%) females]. Ambulatory patients included 17 (4%) HFpEFnoIAB, 114 (31%) HFpEFIAB and 241 (65%) HFpEFAF, while recently hospitalised patients included 31 (23%), 73 (55%) and 28 (21%), respectively. After 33 months of follow-up of ambulatory patients, composite endpoints occurred in 0 (0%) HFpEFnoIAB, 12 (11%) HFpEFIAB [HR 4.1 (95% CI 0.5-522.6)] and 59 (24%) HFpEFAF patients [HR 10.1 (95% CI 1.5-1270.4), P < 0.001]. Recently hospitalised patients showed a similar trend, with composite endpoints in 10 (32%) HFpEFnoIAB, 31 (42%) HFpEFIAB (HR 1.5 [95% CI 0.7-3.1]) and 22 (79%) HFpEFAF (HR 3.8 [95% CI 1.8-8.1], P < 0.001).

CONCLUSIONS

Progressive stages of electrical atrial dysfunction appeared to be prognostic markers of adverse outcomes in ambulatory and recently hospitalised patients with HFpEF. Ambulatory patients with HFpEF and no early stages of electrical atrial dysfunction showed to be at very low risk for adverse outcomes. Whether such patients benefit less strict management remains to be investigated.

The relationship between leisure time activities and chronic musculoskeletal pain in schoolteachers

BACKGROUND

Leisure activities (LAs) have a positive effect on well-being, healthy aging, cognitive functions, physical function, and mental health.

PURPOSE

To determine the prevalence of chronic musculoskeletal pain (CMSP) in schoolteachers and evaluate the relationship between different types of LAs and CMSP.

METHODS

A total of 433 in-service schoolteachers (303 female, 130 male) participated in this cross-sectional study between January 2023 and March 2023 using an online survey. Common LAs in Turkey, including reading books/magazines/newspapers or writing stories/letters, leisure physical activities (PAs), computer-based LAs, television viewing, LAs on smartphones, music listening, going to the cinema/theatre/opera/ballet/concert, gardening, cooking meal/pastry, meeting with friends, and painting/marbling/ceramic/knitting, and their durations were recorded.

RESULTS

The median age of the participants was 38.0 (IQR, 35.0-45.0) years. The prevalence of CMSP was 44.8%. Multiple logistic regression analysis including age, sex, body mass index, comorbidities, weekly standing duration at work, and LAs showed that there was an inverse relationship between CMSP and PAs (OR = 0.564, 95% CI: 0.357-0.890) and listening to music (OR = 0.555, 95% CI: 0.317-0.973). Moreover, LAs on smartphones (OR = 4.318, 95% CI: 2.004-9.308), gardening (OR = 1.827, 95% CI: 1.097-3.043), and having a thyroid disorder (OR = 2.212, 95% CI: 1.045-4.684) were predictive variables for CMSP.

CONCLUSIONS

Considering that PAs and music listening are inversely associated with CMSP, it may be beneficial to make them a part of the lifestyle of both healthy individuals and individuals with CMSP. Physicians should also be aware that LAs on smartphones carry a greater risk for CMSP.

Current applications and research trends of ultrasound examination in acute kidney injury assessment: a bibliometric analysis

BACKGROUND

Acute kidney injury (AKI) is a significant clinical condition, and ultrasound examination has emerged as a crucial non-invasive imaging method for assessing kidney status, especially in its diagnosis and management. This study aims to perform a bibliometric analysis to clarify current research trends in ultrasound assessment of AKI.

METHODS

We conducted a literature search in the Web of Science database using keywords related to ultrasound examinations of acute kidney injury, up to November 15, 2023. The results were analyzed using the bibliometric software package in R. Relevant literature information was analyzed.

RESULTS

A total of 1109 articles were included in the study. Research papers published between 2019 and 2024 demonstrated a significant upward trend. The United States, China, and Italy ranked as the top three countries in terms of publication volume. Among the top 10 research institutions with the highest number of publications, 6 are in the United States, with Université de Montréal being the institution with the most publications. Keyword trends focused on: resistive index, risk factors, therapy, glomerular filtration rate, survival, etc. CONCLUSION: This bibliometric study highlights the advancements in ultrasound examination for AKI and underscores the importance of such analyses in determining research trends. Future research should emphasize the integration of various imaging techniques to improve diagnostic accuracy and clinical management of AKI.

Honeybee colony soundscapes: Decoding distance-based cues and environmental stressors

Honey bees play a crucial role in agricultural productivity and ecological stability, yet their interactions with environmental stressors, particularly volatile organic compounds (VOCs) and pollutants, pose significant challenges to their cognitive functions and behavior. This study investigates the effects of VOCs on the acoustic communication within honeybee colonies and foraging behavior, specifically focusing on how these compounds influence distance-related cues conveyed through colony sounds. Using OpenL3 embeddings and machine learning models, the study achieved accurate classification of food source distances based on acoustic features, with the K-Nearest Neighbors (KNN) model demonstrating superior performance. The introduction of ethyl acetate and acetone caused minor reductions in classification accuracy but had divergent impacts on foraging dynamics: ethyl acetate enhanced landing efficiency, whereas acetone disrupted foraging activity. These findings highlight the utility of acoustic analysis for studying honey bee behavior and underscore the importance of mitigating environmental stressors to sustain pollinator populations.

Modeling the hospitalization time of stroke patients at Abdul Wahab Sjahranie Hospital Samarinda using the Weibull Regression Model

The Weibull regression model is a regression model derived from the Weibull distribution, where the Weibull distribution is influenced by covariates. In this study, parameter estimation for the Weibull regression model was conducted using the Maximum Likelihood (ML) estimation. The aim of the study is to develop a Weibull regression model based on the hospitalization time of stroke patients at Abdul Wahab Sjahranie Hospital, Samarinda, during the period of 2021-2022, and to identify the factors affecting it. The event of interest in this study is patient recovery. The results indicate that the ML estimator of the Weibull regression model was obtained numerically using the Newton-Raphson iterative. The factors influencing the Weibull regression model include age, body mass index (BMI), and a history of diabetes mellitus. An increase in patient age and a history of diabetes mellitus are associated with an increase in the probability of the patient not recovering, a decrease in the likelihood of recovery, a lower recovery rate, and a longer recovery time. In contrast, an increase in BMI is associated with a decrease in the probability of the patient not recovering, an increase in the likelihood of recovery, a higher recovery rate, and a shorter recovery time. Some highlights in this article, the proposed method are:•We present The Weibull distribution influenced by covariates is called the Weibull regression model•The potential recovery of stroke disease and the factors that influence it can be analyzed through Weibull regression modeling.•The chance of a patient not recovering is modeled through a Weibull survival regression model, the chance of a patient recovering is modeled through a Weibull cumulative distribution regression model, the patient's recovery rate is modeled through a Weibull hazard regression model, and the average patient hospitalization time is modeled through a Weibull mean regression model.

Impact of nutrition-related laboratory tests on mortality of patients who are critically ill using artificial intelligence: A focus on trace elements, vitamins, and cholesterol

BACKGROUND

This study aimed to understand the collective impact of trace elements, vitamins, cholesterol, and prealbumin on patient outcomes in the intensive care unit (ICU) using an advanced artificial intelligence (AI) model for mortality prediction.

METHODS

Data from ICU patients (December 2016 to December 2021), including serum levels of trace elements, vitamins, cholesterol, and prealbumin, were retrospectively analyzed using AI models. Models employed included category boosting (CatBoost), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and multilayer perceptron (MLP). Performance was evaluated using area under the receiver operating characteristic curve (AUROC), accuracy, precision, recall, and F1-score. The performance was evaluated using 10-fold crossvalidation. The SHapley Additive exPlanations (SHAP) method provided interpretability.

RESULTS

CatBoost emerged as the top-performing individual AI model with an AUROC of 0.756, closely followed by LGBM, MLP, and XGBoost. Furthermore, the ensemble model combining these four models achieved the highest AUROC of 0.776 and more balanced metrics, outperforming all models. SHAP analysis indicated significant influences of prealbumin, Acute Physiology and Chronic Health Evaluation II score, and age on predictions. Notably, the ratios of selenium to age and low-density lipoprotein to total cholesterol also had a notable impact on the models' output.

CONCLUSION

The study underscores the critical role of nutrition-related parameters in ICU patient outcomes. Advanced AI models, particularly in an ensemble approach, demonstrated improved predictive accuracy. SHAP analysis offered insights into specific factors influencing patient survival, highlighting the need for broader consideration of these biomarkers in critical care management.

ACCREDIT: Validation of clinical score for progression of COVID-19 while hospitalized

COVID-19 is no longer a global health emergency, but it remains challenging to predict its prognosis.

Objective

To develop and validate an instrument to predict COVID-19 progression for critically ill hospitalized patients in a Brazilian population.

Methodology

Observational study with retrospective follow-up. Participants were consecutively enrolled for treatment in non-critical units between January 1, 2021, to February 28, 2022. They were included if they were adults, with a positive RT-PCR result, history of exposure, or clinical or radiological image findings compatible with COVID-19. The outcome was characterized as either transfer to critical care or death. Predictors such as demographic, clinical, comorbidities, laboratory, and imaging data were collected at hospitalization. A logistic model with lasso or elastic net regularization, a random forest classification model, and a random forest regression model were developed and validated to estimate the risk of disease progression.

Results

Out of 301 individuals, the outcome was 41.8 %. The majority of the patients in the study lacked a COVID-19 vaccination. Diabetes mellitus and systemic arterial hypertension were the most common comorbidities. After model development and cross-validation, the Random Forest regression was considered the best approach, and the following eight predictors were retained: D-dimer, Urea, Charlson comorbidity index, pulse oximetry, respiratory frequency, Lactic Dehydrogenase, RDW, and Radiologic RALE score. The model's bias-corrected intercept and slope were - 0.0004 and 1.079 respectively, the average prediction error was 0.028. The ROC AUC curve was 0.795, and the variance explained was 0.289.

Conclusion

The prognostic model was considered good enough to be recommended for clinical use in patients during hospitalization (https://pedrobrasil.shinyapps.io/INDWELL/). The clinical benefit and the performance in different scenarios are yet to be known.

Explore poverty with statistical modeling: The bivariate polynomial binary logit regression (BPBLR)

Logit regression (or logistic regression) is a statistical analysis of categorical data. The binary responses have two categories. We present the Bivariate Polynomial Binary Logit Regression (BPBLR), which extends logit regression by modeling two correlated binary response variables. This model uses a polynomial pattern to capture the association between the logit and predictor variables. The maximum likelihood estimation (MLE) method is used for parameter estimation, and the maximum likelihood ratio test (MLRT) method is used for the statistical testing of the proposed model. The distribution of the test statistics asymptotically is the Chi-square distribution. Selection of the optimal polynomial degree and the best model is based on the minimum Deviance value. Some highlights of the proposed method are:•Statistical modeling innovation on categorical data with two correlated binary response variables, namely Bivariate Polynomial Binary Logit Regression (BPBLR).•The statistical test is obtained using MLRT method.•The BPBLR model is applied to actual datasets regarding the depth and severity of poverty to capture poverty problems SDGs 1.

Risk factors and predictive models for post-operative moderate-to-severe mitral regurgitation following transcatheter aortic valve replacement: a machine learning approach

BACKGROUND

Post-operative moderate-to-severe mitral regurgitation (MR) following transcatheter aortic valve replacement (TAVR) is associated with poor outcomes, yet the factors contributing to this complication are not well understood. This study aimed to identify risk factors and develop predictive models for post-operative MR following TAVR using machine learning (ML) techniques to enhance early detection and intervention.

METHODS

We retrospectively analyzed data from patients who underwent TAVR at our center between August 2014 and August 2023. Patients were classified into post-operative and nonpost-operative MR groups based on postprocedural MR severity. Various ML models were evaluated for predictive performance using metrics such as accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC). Shapley Additive Explanation (SHAP) values were used to interpret predictive patterns and develop a clinically relevant model.

RESULTS

Among the evaluated models, the random forest model exhibited the highest predictive performance for post-operative moderate-to-severe MR after TAVR. Key predictors, which were confirmed by the SHAP analysis as important in the predictive framework, included echocardiographic parameters, blood test results, patient age, and body mass index.

CONCLUSIONS

ML models show promise in predicting post-operative moderate-to-severe MR after TAVR by integrating clinical indicators to enhance predictive accuracy.

CLINICAL TRIAL NUMBER

Not applicable.

Predictive accuracy of changes in the inferior vena cava diameter for predicting fluid responsiveness in patients with sepsis: A systematic review and meta-analysis

BACKGROUND

Existing guidelines emphasize the importance of initial fluid resuscitation therapy in sepsis management. However, in previous meta-analyses, there have been inconsistencies in differentiating between spontaneously breathing and mechanically ventilated septic patients.

OBJECTIVE

To consolidate the literature on the predictive accuracy of changes in the inferior vena cava diameter (∆IVC) for fluid responsiveness in septic patients.

METHODS

The Embase, Web of Science, Cochrane Library, MEDLINE, PubMed, Wanfang, China National Knowledge Infrastructure (CNKI), Chinese Biomedical (CBM) and VIP (Weipu) databases were comprehensively searched. Statistical analyses were performed with Stata 15.0 software and Meta-DiSc 1.4.

RESULTS

Twenty-one research studies were deemed suitable for inclusion. The sensitivity and specificity of ∆ IVC were 0.84 (95% CI 0.76, 0.90) and 0.87 (95% CI 0.80, 0.91), respectively. With respect to the distensibility of the inferior vena cava (dIVC), the sensitivity was 0.79 (95% CI 0.68, 0.86), and the specificity was 0.82 (95% CI 0.73, 0.89). For collapsibility of the inferior vena cava (cIVC), the sensitivity and specificity values were 0.92 (95% CI 0.83, 0.96) and 0.93 (95% CI 0.86, 0.97), respectively.

CONCLUSION

The results indicated that ∆IVC is as a dependable marker for fluid responsiveness in sepsis patients. dIVC and cIVC also exhibited high levels of accuracy in predicting fluid responsiveness in septic patients.

An overview of reviews on digital health interventions during COVID- 19 era: insights and lessons for future pandemics

BACKGROUND

The COVID- 19 pandemic has significantly impacted global health, underscoring the crucial role of digital health solutions. The World Health Organization's Classification of Digital Interventions, Services, and Applications in Health (CDISAH) provides a framework for categorizing these technologies. This study aims to analyze the adoption and trends of digital health interventions during the COVID- 19 pandemic, mapping them to the CDISAH framework to identify the most and least utilized interventions and technologies.

METHODS

This overview-of-reviews study was conducted from 1 st January 2020 to 30 th December 2023, focusing on systematic reviews and meta-analyses retrieved from the Cochrane Database of Systematic Reviews, PubMed, Scopus, Web of Science, IEEE Xplore, and ProQuest. Additionally, gray literature was identified through searches on the Google Scholar platform and reviewing the citations and reference lists of the included studies. The findings were qualitatively mapped to the CDISAH framework.

RESULTS

A total of 64 review articles were analyzed. A content analysis of the included studies identified 292 codes related to healthcare providers, 257 codes related to data services, 88 codes related to individuals, and 43 codes related to health management and support personnel. The results revealed that the most frequent interventions were associated with telemedicine and data management subcategories, while gaps were identified in areas such as individual-based data reporting during the pandemic, highlighting the need for individuals to take a more active role in managing their own health in preparation for future crises.

CONCLUSIONS

This study identifies both the strengths and weaknesses of the current digital health landscape. It emphasizes the transformative impact of digital health technologies during the COVID- 19 pandemic and provides a roadmap for future improvements in digital health interventions. By providing a comprehensive overview of digital health during this period, the study underscores the importance of implementing robust digital health strategies within the healthcare system to address existing gaps, leverage strengths, and enhance preparedness and resilience in future public health crises.

Association between neutrophil-platelet ratio and 28-day mortality in patients with sepsis: a retrospective analysis based on MIMIC-IV database

BACKGROUND

The immune system and inflammation are intimately linked to the pathophysiology of sepsis. The neutrophil‒platelet ratio (NPR), associated with inflammation and immunology, may be useful in predicting sepsis outcomes. According to earlier research, the NPR is linked to the prognosis of several diseases. This study aimed to investigate the connection between the NPR and unfavorable outcomes in patients with sepsis.

METHODS

We retrieved patient clinical data from the Medical Information Mart for Intensive Care IV database (MIMIC-IV 2.2) based on the inclusion and exclusion criteria. The NPR quartile was used to divide the population into four groups. 28-day mortality was the main result, whereas 90-day mortality was the secondary result. The Cox regression model, Kaplan‒Meier survival curve, and limited cubic spline were used to examine the associations between the NPR and the negative outcomes of sepsis. Subgroup analysis was also conducted. At the same time, we used Latent Class Trajectory Model (LCTM) to assess the trajectory of NPR within six days of ICU admission, and to assess the relationship between NPR trajectory and mortality at 28 and 90 days.

RESULTS

This study included 3339 patients. Quartile 4 had the greatest 28-day and 90-day mortality rates, according to the Cox regression model and Kaplan‒Meier survival curve. A J-shaped relationship between the NPR and mortality was found in restricted cubic spline investigations. This means higher and lower NPRs were linked to higher mortality, with NPR = 3.81 as the tipping point. A total of 434 patients were included in the trajectory analysis, and three trajectory patterns were identified. Patients with sepsis had an increased mortality rate in the slow-decline group compared with the stable development group.

CONCLUSION

The NPR has prognostic value for patients with sepsis, and there is a J-shaped relationship between the two variables. Patients with sepsis who have a slowly declining NPR have an increased mortality rate.

CLINICAL TRIAL

Not applicable.

CpG island methylator phenotype classification improves risk assessment in pediatric T-cell acute lymphoblastic leukemia

ABSTRACT

Current intensive treatment of pediatric T-cell acute lymphoblastic leukemia (T-ALL) has substantial side effects, highlighting a need for novel biomarkers to improve risk stratification. Canonical biomarkers, such as genetics and immunophenotype, are largely not used in pediatric T-ALL stratification. This study aimed to validate the prognostic relevance of DNA methylation CpG island methylator phenotype (CIMP) risk stratification in 2 pediatric T-ALL patient cohorts: the Nordic Society of Paediatric Haematology (NOPHO) ALL2008 T-ALL study cohort (n = 192) and the Dutch Childhood Oncology Group (DCOG) ALL-10/ALL-11 validation cohorts (n = 156). Both cohorts revealed that combining CIMP classification at diagnosis with measurable residual disease (MRD) at treatment day 29 (D29) or 33 (D33) significantly improved outcome prediction. The poor prognosis subgroup, characterized by CIMP low/D29 or D33 MRD ≥ 0.1%, had a cumulative incidence of relapse (pCIR5yr) of 29% and 23% and overall survival (pOS5yr) of 59.7% and 65.4%, in NOPHO and DCOG, respectively. Conversely, a good prognosis subgroup was also identified representing CIMP high/D29 or D33 MRD < 0.1% with pCIR5yr of 0% and 3.4% and pOS5yr of 98.2% and 94.8%, in NOPHO and DCOG, respectively. For NOPHO, MRD was also evaluated on D15, and the relapse prediction accuracy of CIMP/D29 MRD (0.79) and CIMP/D15 MRD (0.75) classification was comparable, indicating potential for earlier stratification. The evaluation of the biology behind the CIMP subgroups revealed associations with transcriptome profiles, genomic aberrations, and mitotic history, suggesting distinct routes for leukemia development. In conclusion, integrating MRD assessment with the novel CIMP biomarker has the potential to improve risk stratification in pediatric T-ALL and guide future therapeutic decisions.

Advancements and implications of artificial intelligence for early detection, diagnosis and tailored treatment of cancer

The complexity and heterogeneity of cancer makes early detection and effective treatment crucial to enhance patient survival and quality of life. The intrinsic creative ability of artificial intelligence (AI) offers improvements in patient screening, diagnosis, and individualized care. Advanced technologies, like computer vision, machine learning, deep learning, and natural language processing, can analyze large datasets and identify patterns that permit early cancer detection, diagnosis, management and incorporation of conclusive treatment plans, ensuring improved quality of life for patients by personalizing care and minimizing unnecessary interventions. Genomics, transcriptomics and proteomics data can be combined with AI algorithms to unveil an extensive overview of cancer biology, assisting in its detailed understanding and will help in identifying new drug targets and developing effective therapies. This can also help to identify personalized molecular signatures which can facilitate tailored interventions addressing the unique aspects of each patient. AI-driven transcriptomics, proteomics, and genomes represents a revolutionary strategy to improve patient outcome by offering precise diagnosis and tailored therapy. The inclusion of AI in oncology may boost efficiency, reduce errors, and save costs, but it cannot take the role of medical professionals. While clinicians and doctors have the final say in all matters, it might serve as their faithful assistant.

Interpretable machine learning models to predict decline in intrinsic capacity among older adults in China: a prospective cohort study

BACKGROUND

Monitoring intrinsic capacity and implementing appropriate interventions can support healthy aging. There are, though, few tools available for predicting decline in intrinsic capacity among older adults. This study aimed to develop and validate an interpretable machine learning model designed to identify populations at elevated risk of a decline in intrinsic capacity.

METHODS

Using data from the China Health and Retirement Longitudinal Study baseline (2011) and 4-year follow-up (2015), a total of 822 participants were randomly allocated to a training set and a testing set at a 7:3 ratio. Five machine learning methods were employed to train the model and assess its performance through various metrics. The SHapley Additive exPlanation method was subsequently used to interpret the optimal model.

RESULTS

The 4-year incidence of decline in intrinsic capacity among the older adults in the sample was 44.6 % (n = 367). Nine variables were screened for model construction, among which eXtreme gradient boosting demonstrated the best predictive performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.715 (95 % CI 0.651-0.780) in the testing set. The SHapley Additive exPlanation method identified educational level, smoking, handgrip strength, self-rated health, and residence as the top five significant predictors.

CONCLUSIONS

The developed model can serve as a highly effective tool for primary care teams to identify older adults with early signs of decline in intrinsic capacity, facilitating the provision of subsequent screening and tailored interventions for intrinsic capacity.

Hierarchical clustering analysis to inform classification of congenital malformations for surveillance of medication safety in pregnancy

There is growing interest in the secondary use of health care data to evaluate medication safety in pregnancy. Tree-based scan statistics (TBSS) offer an innovative approach to help identify potential safety signals; they use hierarchically organized outcomes, generally based on existing clinical coding systems that group outcomes by organ system. When assessing teratogenicity, such groupings often lack a sound embryologic basis, given the etiologic heterogeneity of congenital malformations. The study objective was to enhance the grouping of congenital malformations to be used in scanning approaches through implementation of hierarchical clustering analysis (HCA) and to pilot test an HCA-enhanced TBSS approach for medication safety surveillance in pregnancy in 2 test cases using > 4.2 million mother-child dyads from 2 US-nationwide databases. Hierarchical clustering analysis identified (1) malformation combinations belonging to the same organ system already grouped in existing classifications, (2) known combinations across different organ systems not previously grouped, (3) unknown combinations not previously grouped, and (4) malformations seemingly standing on their own. Testing the approach with valproate and topiramate identified expected signals and a signal for an HCA-cluster missed by traditional classification. Augmenting existing classifications with clusters identified through large data exploration may be promising when defining phenotypes for surveillance and causal inference studies.

Comparison of different AI systems for diagnosing sepsis, septic shock, and cardiogenic shock: a retrospective study

Sepsis, septic shock, and cardiogenic shock are life-threatening conditions associated with high mortality rates, but differentiating them is complex because they share certain symptoms. Using the Medical Information Mart for Intensive Care (MIMIC)-III database and artificial intelligence (AI), we aimed to increase diagnostic precision, focusing on Bayesian network classifiers (BNCs) and comparing them with other AI methods. Data from 5970 adults, including 950 patients with cardiogenic shock, 1946 patients with septic shock, and 3074 patients with sepsis, were extracted for this study. Of the original 51 variables included in the data records, 12 were selected for constructing the predictive model. The data were divided into training and validation sets at an 80:20 ratio, and the performance of the BNCs was evaluated and compared with that of other AI models, such as the one rule classifier (OneR), classification and regression tree (CART), and an artificial neural network (ANN), in terms of accuracy, sensitivity, specificity, precision, and F1-score. The BNCs exhibited an accuracy of 87.6% to 91.5%. The CART model demonstrated a notable 91.6% accuracy when only three decision levels were used, whereas the intricate ANN model reached 90.5% accuracy. Both the BNCs and the CART model allowed clear interpretation of the predictions. BNCs have the potential to be valuable tools in diagnostic tasks, with an accuracy, sensitivity, and precision comparable, in some cases, to those of ANNs while demonstrating superior interpretability.

Platelet indices at admission and their performance associated with predicting all-cause mortality in the ICU: a large cross-sectional cohort study

Platelet indices at admission offer the most opportune time for clinical decision-making, as they provide earliest insights, unlike later assessments during the intensive care unit (ICU) stay. There is emerging evidence suggesting the utility of platelet indices in predicting mortality. The objective of this study was, for the first time as far as the literature indicates, to elucidate the utility of seven platelet indices at admission in a large ICU cohort using Sysmex XN-series analysers. This cross-sectional study enrolled 592 ICU patients. The association of platelet indices at admission with the in-ICU and 90-day mortality was evaluated using logistic regression and receiver operating characteristic curve analysis. Of the platelet indices studied, absolute-immature platelet fraction (A-IPF), and mean platelet volume (MPV) and percentage-immature platelet fraction (%-IPF) were shown to be independently associated with predicting the in-ICU and 90-day mortality, respectively. The A-IPF cut-off value for predicting the in-ICU mortality was >6.4 × 109/L (adjusted area under the curve (aAUC) 0.736, and adjusted Odds Ratio (aOR) 1.04), and the MPV and %-IPF cut-off values for predicting the 90-day mortality were >9.5 fL (aAUC 0.759, and aOR 1.26) and >6.3% (aAUC 0.762, and aOD 1.06), respectively (all p < 0.05). Admission A-IPF was the best predictor of in-ICU mortality, while admission MPV and %-IPF were the best predictors of 90-day mortality. These indices, all measured at admission, provide the earliest possible data relevant to mortality prediction. These are routinely available indices which deserve to be considered for new future ICU scoring systems.

Impact of KIT mutation on efficacy of venetoclax and hypomethylating agents in newly diagnosed acute myeloid leukemia

BACKGROUND

The combination of venetoclax (VEN) with hypomethylating agents (HMAs) has emerged as a new standard treatment for older or unfit patients with acute myeloid leukemia (AML). However, the predictive factors for VEN/HMA efficacy remain unclear. In our study, we performed the first analysis of the impact of KIT mutations on therapeutic outcomes in newly diagnosed AML patients undergoing VEN/HMA regimens.

METHODS

In this retrospective study, we included 16 KIT-mutant AML patients receiving VEN/HMA (Cohort A), 141 KIT-wild-type AML patients receiving VEN/HMA (Cohort B), and 69 KIT-mutant AML patients receiving intensive chemotherapy (IC) (Cohort C). We compared the differences in therapeutic efficacy among the different cohorts. Furthermore, we conducted multivariate analyses in patients receiving VEN/HMA to identify factors influencing therapeutic outcomes.

RESULTS

Compared to Cohort B, Cohort A exhibited significantly lower overall response rate (ORR) (18.8% vs. 72.3%, p < 0.001) and measurable residual disease (MRD) negativity rate (18.8% vs. 68.1%, p < 0.001), with a shorter median event-free survival (EFS) (1.9 months vs. 7.8 months, p < 0.001). No significant difference in overall survival (OS) was observed. Among KIT-mutant patients, IC showed superior ORR (78.3% vs. 18.8%, p < 0.001), MRD negativity rate (75.4% vs. 18.8%, p < 0.001), and EFS (12.2 months vs. 1.9 months, p < 0.001) compared to VEN/HMA. No significant difference in OS was observed between the two cohorts. Multivariate analysis confirmed KIT mutations as an independent predictor of lower ORR (OR 0.020, 95% CI 0.002-0.211, p = 0.001) and shorter EFS (HR 6.318, 95% CI 2.659-15.012, p < 0.001).

CONCLUSIONS

Our findings suggest that KIT mutations are associated with poor response and shorter EFS in AML patients treated with VEN/HMA, highlighting the importance of KIT mutation status in risk stratification and treatment selection.

Data-driven machine learning algorithm model for pneumonia prediction and determinant factor stratification among children aged 6-23 months in Ethiopia

INTRODUCTION

Pneumonia is the leading cause of child morbidity and mortality and accounts for 5.6 million under-five child deaths. Pneumonia has a significant impact on the quality of life, the country's economy, and the survival of children. Therefore, this study aimed to develop data-driven predictive model using machine learning algorithms to predict pneumonia and stratify the determinant factors among children aged 6-23 months in Ethiopia.

METHODS

A total of 2035 samples of children were used from the 2016 Ethiopian Demographic and Health Survey dataset. Jupyter Notebook from Anaconda Navigators was used for data management and analysis. Important libraries such as Pandas, Seaborn, and Numpy were imported from Python. The data was pre-processed into a training and testing dataset with a 4:1 ratio, and tenfold cross-validation was used to reduce bias and enhance the models' performance. Six machine learning algorithms were used for model building and comparison, and confusion matrix elements were used to evaluate the performance of each algorithm. Principal component analysis and heatmap function were used for correlation detection between features. Feature importance score was used to identify and stratify the most important predictors of pneumonia.

RESULTS

From 2035 total samples, 16.6%, 20.1%, and 24.2% of children had short rapid breath, fever, and cough respectively. The overall magnitude of pneumonia among children aged 6-23 months was 31.3% based on the 2016 EDHS report. A random forest algorithm is the relatively best performance model to predict pneumonia and stratify its determinates with 91.3% accuracy. The health facility visits, child sex, initiation of breastfeeding, birth interval, birth weight, husbands' education, women's age, and region, are the top eight important predictors of pneumonia among children with important scores of more than 5% to 20% respectively.

CONCLUSIONS

Random forest is the best model to predict pneumonia and stratify its determinant factors. The implications of this study are profound for advanced research methodology, tailored to promote effective health interventions such as lifestyle modification and behavioral intervention, based on individuals' unique features, specifically for stakeholders to take proactive childcare interventions. The study would serve as pioneering evidence for future research, and researchers are recommended to use deep learning algorithms to enhance prediction accuracy.

The urea-to-creatinine ratio as an emerging biomarker in critical care: a scoping review and meta-analysis

BACKGROUND

Severe protein catabolism is a major aspect of critical illness and leads to pronounced muscle wasting and, consequently, extended intensive care unit (ICU) stay and increased mortality. The urea-to-creatinine ratio (UCR) has emerged as a promising biomarker for assessing protein catabolism in critical illness, which is currently lacking. This review aims to elucidate the role of UCR in the context of critical illness.

METHODS

This scoping review adhered to the PRISMA Extension for Scoping Reviews guidelines. A comprehensive literature search was conducted on the 3rd of September 2024, across Embase, PubMed, ScienceDirect, and Cochrane Library to identify studies related to (1) critically ill adult patients and (2) reporting at least a single UCR value. A meta-analysis was conducted for ≥ 5 studies with identical outcome parameters.

RESULTS

Out of 1,450 studies retrieved, 47 were included in this review, focusing on UCR's relation to protein catabolism and persistent critical illness (10 studies), mortality (16 studies), dietary protein interventions (2 studies), and other outcomes (19 studies), such as delirium, and neurological and cardiac adverse events. UCR is inversely correlated to muscle cross-sectional area over time and associated to length of ICU stay, emphasising its potential role in identifying patients with ongoing protein catabolism. A UCR (BUN-to-creatinine in mg/dL) of ≥ 20 (equivalent to a urea-to-creatinine in mmol/L of approximately 80) upon ICU admission, in comparison with a value < 20, was associated with a relative risk of 1.60 (95% CI 1.27-2.00) and an adjusted hazard ratio of 1.29 (95% CI 0.89-1.86) for in-hospital mortality.

DISCUSSION

UCR elevations during critical illness potentially indicate muscle protein catabolism and the progression to persistent critical illness, and high levels at ICU admission could be associated with mortality. UCR increments during ICU stay may also indicate excessive exogenous dietary protein intake, overwhelming the body's ability to use it for whole-body or muscle protein synthesis. Dehydration, gastrointestinal bleeding, kidney and liver dysfunction, and renal replacement therapy may also influence UCR and are considered potential pitfalls when assessing catabolic phases of critical illness by UCR. Patient group-specific cut-off values are warranted to ensure its validity and application in clinical practice.

A comprehensive review of neurotransmitter modulation via artificial intelligence: A new frontier in personalized neurobiochemistry

The deployment of artificial intelligence (AI) is revolutionizing neuropharmacology and drug development, allowing the modulation of neurotransmitter systems at the personal level. This review focuses on the neuropharmacology and regulation of neurotransmitters using predictive modeling, closed-loop neuromodulation, and precision drug design. The fusion of AI with applications such as machine learning, deep-learning, and even computational modeling allows for the real-time tracking and enhancement of biological processes within the body. An exemplary application of AI is the use of DeepMind's AlphaFold to design new GABA reuptake inhibitors for epilepsy and anxiety. Likewise, Benevolent AI and IBM Watson have fast-tracked drug repositioning for neurodegenerative conditions. Furthermore, we identified new serotonin reuptake inhibitors for depression through AI screening. In addition, the application of Deep Brain Stimulation (DBS) settings using AI for patients with Parkinson's disease and for patients with major depressive disorder (MDD) using reinforcement learning-based transcranial magnetic stimulation (TMS) leads to better treatment. This review highlights other challenges including algorithm bias, ethical concerns, and limited clinical validation. Their proposal to incorporate AI with optogenetics, CRISPR, neuroprosthesis, and other advanced technologies fosters further exploration and refinement of precision neurotherapeutic approaches. By bridging computational neuroscience with clinical applications, AI has the potential to revolutionize neuropharmacology and improve patient-specific treatment strategies. We addressed critical challenges, such as algorithmic bias and ethical concerns, by proposing bias auditing, diverse datasets, explainable AI, and regulatory frameworks as practical solutions to ensure equitable and transparent AI applications in neurotransmitter modulation.

Age-related loss of large dendritic spines in the precuneus is statistically mediated by proteins which are predicted targets of existing drugs

Preservation of dendritic spines is a putative mechanism of protection against cognitive impairment despite development of Alzheimer Disease (AD)-related pathologies. Aging, the chief late-onset AD risk factor, is associated with dendritic spine loss in select brain areas. However, no study to our knowledge has observed this effect in precuneus, an area selectively vulnerable to early accumulation of AD-related pathology. We therefore quantified dendritic spine density in precuneus from 98 subjects without evidence of neurocognitive decline, spanning ages 20-96, and found a significant negative correlation between age and large dendritic spine density. In these same subjects, we conducted liquid chromatography-tandem mass spectrometry of >5000 proteins and identified 203 proteins which statistically mediate the effect of age on large dendritic spine density. Using computational pharmacology, we identified ten drugs which are predicted to target these mediators, informing future studies designed to test their effects on age-related dendritic spine loss and cognitive decline.

Artificial Intelligence for the Detection of Patient-Ventilator Asynchrony

Patient-ventilator asynchrony (PVA) is a challenge to invasive mechanical ventilation characterized by misalignment of ventilatory support and patient respiratory effort. PVA is highly prevalent and associated with adverse clinical outcomes, including increased work of breathing, oxygen consumption, and risk of barotrauma. Artificial intelligence (AI) is a potentially transformative solution offering capabilities for automated detection of PVA. This narrative review characterizes the landscape of AI models designed for PVA detection and quantification. A comprehensive literature search identified 13 studies, spanning diverse settings and patient populations. Machine learning (ML) techniques, derivation datasets, types of asynchronies detected, and performance metrics were assessed to provide a contemporary view of AI in this domain. We reviewed 166 articles published between 1989 and April 2024, of which 13 were included, encompassing 332 participants and analyzing >5.8 million breaths. Patient counts ranged between 8 and 107 and breath data ranged between 1,375 and 4.2 M. The reason for invasive mechanical ventilation use was given as ARDS in three articles, whereas the remainder had different invasive mechanical ventilation indications. Various ML methods as well as newer deep learning techniques were used to address PVA types. Sensitivity and specificity of 10 of the 13 models were >0.9, and 8 models reported accuracy of >0.9. AI models have significant potential to address PVA in invasive mechanical ventilation, displaying high accuracy across various populations and asynchrony types. This showcases their potential to accurately detect and quantify PVA. Future work should focus on model validation in diverse clinical settings and patient populations.

Convolutional long short-term memory neural network integrated with classifier in classifying type of asynchrony breathing in mechanically ventilated patients

BACKGROUND AND OBJECTIVE

Asynchronous breathing (AB) occurs when a mechanically ventilated patient's breathing does not align with the mechanical ventilator (MV). Asynchrony can negatively impact recovery and outcome, and/or hinder MV management. A model-based method to accurately classify different AB types could automate detection and have a measurable clinical impact.

METHODS

This study presents an approach using a 1-dimensional (1D) of airway pressure data as an input to the convolutional long short-term memory neural network (CNN-LSTM) with a classifier method to classify AB types into three categories: 1) reverse Triggering (RT); 2) premature cycling (PC); and 3) normal breathing (NB), which cover normal breathing and 2 primary forms of AB. Three types of classifier are integrated with the CNN-LSTM model which are random forest (RF), support vector machine (SVM) and logistic regression (LR). Clinical data inputs include measured airway pressure from 7 MV patients in IIUM Hospital ICU under informed consent with a total of 4500 breaths. Model performance is first assessed in a k-fold cross-validation assessing accuracy in comparison to the proposed CNN-LSTM integrated with each type of classifier. Then, confusion matrices are used to summarize classification performance for the CNN without classifier, CNN-LSTM without classifier, and CNN-LSTM with each of the 3 classifiers (RF, SVM, LR).

RESULTS AND DISCUSSION

The 1D CNN-LSTM with classifier method achieves 100 % accuracy using 5-fold cross validation. The confusion matrix results showed that the combined CNN-LSTM model with classifier performed better, demostrating higher accuracy, sensitivity, specificity, and F1 score, all exceeding 83.5 % across all three breathing categories. The CNN model without classifier and CNN-LSTM model without classifier displayed comparatively lower performance, with average values of F1 score below 71.8 % for all three breathing categories.

CONCLUSION

The results validate the effectiveness of the CNN-LSTM neural network model with classifier in accurately detecting and classifying the different categories of AB and NB. Overall, this model-based approach has the potential to precisely classify the type of AB and differentiate normal breathing. With this developed model, a better MV management can be provided at the bedside, and these results justify prospective clinical testing.

An explainable non-invasive hybrid machine learning framework for accurate prediction of thyroid-stimulating hormone levels

Machine learning models, including thyroid biomarkers, are increasingly utilized in healthcare for biomarker prediction. These models offer the potential to enhance disease diagnosis through data-driven approaches relying on non-invasive techniques. However, no studies have explored the application of fully non-invasive methods for predicting thyroid-stimulating hormone (TSH) levels. Consequently, this study introduces a novel, fully non-invasive framework for predicting TSH levels by developing an innovative hybrid machine learning model that balances performance, complexity, and interpretability. Seven ML models were evaluated, and the best-performing models were integrated into a hybrid approach to balance performance, complexity, and interpretability. A dataset of 6190 instances from Jordan was used for model development. Four-dimensional non-invasive factors, including demographics, symptoms, family history, and newly engineered symptom scores, were incorporated into the model. The hybrid model achieved an R2 of 94.2 % and RMSE of 0.015, demonstrating superior predictive performance. Model interpretability was ensured using LIME and SHAP explainers, confirming aggregated symptom scores' critical role in enhancing prediction accuracy. A robust feature selection technique was implemented, reducing model complexity and enhancing performance. Among the top ten features for predicting TSH levels were hypothyroidism and hyperthyroidism symptom scores, family history, cold intolerance, itchy-dry skin, sweating, hand tremors, and palpitations. The model can be employed to develop cost-effective diagnostic tools for thyroid disorders. It also offers a robust framework that can be generalized to predict other biomarkers and applied in diverse contexts.

Machine-learning approaches for risk prediction in transcatheter aortic valve implantation: Systematic review and meta-analysis

OBJECTIVES

With the expanding integration of artificial intelligence (AI) and machine learning (ML) into the structural heart domain, numerous ML models have emerged for the prediction of adverse outcomes after transcatheter aortic valve implantation (TAVI). We aim to identify, describe, and critically appraise ML prediction models for adverse outcomes after TAVI. Key objectives consisted in summarizing model performance, evaluating adherence to reporting guidelines, and transparency.

METHODS

We searched PubMed, SCOPUS, and Embase through August 2023. We selected published machine learning models predicting TAVI outcomes. Two reviewers independently screened articles, extracted data, and assessed the study quality according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Outcomes included summary C-statistics and model risk of bias assessed with the Prediction Model Risk of Bias Assessment Tool. C-statistics were pooled using a random-effects model.

RESULTS

Twenty-one studies (118,153 patients) employing various ML algorithms (76 models) were included in the systematic review. Predictive ability of models varied: 11.8% inadequate (C-statistic <0.60), 26.3% adequate (C-statistic 0.60-0.70), 31.6% acceptable (C-statistic 0.70-0.80), and 30.3% demonstrated excellent (C-statistic >0.80) performance. Meta-analyses revealed excellent predictive performance for early mortality (C-statistic: 0.81; 95% confidence interval [CI], 0.65-0.91), acceptable performance for 1-year mortality (C-statistic: 0.76; 95% CI, 0.67-0.84), and acceptable performance for predicting permanent pacemaker implantation (C-statistic: 0.75; 95% CI, 0.51-0.90).

CONCLUSIONS

ML models for TAVI outcomes exhibit adequate-to-excellent performance, suggesting potential clinical utility. We identified concerns in methodology and transparency, emphasizing the need for improved scientific reporting standards.

Determinants of Prolonged Hospitalization in Children and Adolescents: A Retrospective Observational Study

INTRODUCTION

Ensuring an appropriate length of stay (LOS) is a primary goal for hospitals, as prolonged LOS poses clinical risks and organizational challenges. Children and adolescents are particularly susceptible to prolonged LOS due to frequent hospitalizations and unique vulnerabilities, including developmental disabilities that may necessitate additional care and monitoring. This study aims to describe the LOS of children and adolescent patients and identify the sociodemographic, organizational, clinical, and nursing care factors contributing to prolonged LOS in this population.

DESIGN

Observational, retrospective, monocentric study.

METHODS

A sequential sampling approach was used to select the clinical records of 1538 children and adolescent patients admitted to an Italian university hospital in 2022. The study included all children and adolescents aged 3-18 who were hospitalized for a minimum of 2 days. Patients from outpatient units and those with LOS shorter than 2 days were excluded. The Neonatal Pediatric Professional Assessment Instrument (PAIped) and the Hospital Discharge Register were used to collect sociodemographic, organizational, clinical, and nursing care patient data, including nursing diagnoses (NDs) and nursing actions (NAs). A forward stepwise regression approach was used to identify predictors of LOS among the selected variables. A mediation analysis was conducted to explore the role of nursing predictors, identified in the stepwise regression, as mediators between the number of medical diagnoses and LOS.

RESULTS

Positive correlations between the number of medical diagnoses, NDs, NAs, and LOS were discovered (rs = 0.262, p = < 0.001; rs = 0.114, p = < 0.001; rs = 0.384, p = < 0.001, respectively). Longer hospital stays were associated with an increased number of medical diagnoses, NDs, and NAs. The number of NAs emerged as an independent predictor of LOS (β = 0.516; p < 0.001). Other significant determinants of LOS included a higher number of NAs and medical diagnoses, the presence of a medical DRG category, increased DRG weight, emergency admissions, residency in rural areas, and older age (F = 122.222, p < 0.001, R2 = 0.361, adjusted R2 = 0.358). The mediation analysis showed that the number of medical diagnoses positively predicted the number of NAs (β = 2.774, p < 0.001), which, in turn, positively affected LOS (β = 0.162, p < 0.001). A significant indirect effect of the number of medical diagnoses on LOS through NAs was observed (β = 0.448, 95% CI [0.34, 0.55]), along with a significant direct effect of medical diagnoses on LOS, even with the mediator in the model (β = 0.633, p < 0.001), indicating partial mediation (F = 321.6892; R2 = 0.295; p < 0.001). These results highlight the influence of medical diagnoses on LOS through the mediating role of NAs.

CONCLUSIONS

Our study highlights the significant interplay between determinants of LOS in children and adolescent patients, emphasizing the need for targeted interventions, resource planning, and the integration of clinical nursing information systems to enhance care quality and support evidence-based practices.

CLINICAL RELEVANCE

Optimizing resource distribution and implementing specific interventions for patients at risk of prolonged LOS could help mitigate this negative outcome and enhance the quality of care. Incorporating nursing data into DRG systems could improve reimbursement accuracy and benefit the nursing profession, which may result in better patient outcomes and lower hospital expanses.

Predicting Agitation Events in the Emergency Department Through Artificial Intelligence

Importance

Agitation events are increasing in emergency departments (EDs), exacerbating safety risks for patients and clinicians. A wide range of clinical etiologies and behavioral patterns in the emergency setting make agitation prediction difficult in this setting.

Objective

To develop, train, and validate an agitation-specific prediction model based on a large, diverse set of past ED visit data.

Design, Setting, and Participants

This cohort study included electronic health record data collected from 9 ED sites within a large, urban health system in the Northeast US. All ED visits featuring patients aged 18 years or older from January 1, 2015, to December 31, 2022, were included in the analysis and modeling. Data analysis occurred between May 2023 and September 2024.

Exposures

Variables that served as potential exposures of interest, encompassing demographic information, patient history, initial vital signs, visit information, mode of arrival, and health services utilization.

Main Outcomes and Measures

The primary outcome of agitation was defined as the presence of an intramuscular chemical sedation and/or violent physical restraint order during an ED visit. A clinical model was developed to identify risk factors that predict agitation development during an ED visit prior to symptom onset. Model performance was measured using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (PR-AUC).

Results

The final cohort comprised 3 048 780 visits. The cohort had a mean (SD) age of 50.2 (20.4) years, with 54.7% visits among female patients. The final artificial intelligence model used 50 predictors for the primary outcome of predicting agitation events. The model achieved an AUROC of 0.94 (95% CI, 0.93-0.94) and a PR-AUC of 0.41 (95% CI, 0.40-0.42) in cross-validation, indicating good discriminative ability. Calibration of the model was evaluated and demonstrated robustness across the range of predicted probabilities. The top predictors in the final model included factors such as number of past ED visits, initial vital signs, medical history, chief concern, and number of previous sedation and restraint events.

Conclusions and Relevance

Using a cross-sectional cohort of ED visits across 9 hospitals, the prediction model included factors for detecting risk of agitation that demonstrated high accuracy and applicability across diverse patient populations. These results suggest that clinical application of the model may enhance patient-centered care through preemptive deescalation and prevention of agitation.

An overview of patient-ventilator asynchrony in children

INTRODUCTION

Mechanically ventilated children often have patient-ventilator asynchrony (PVA). When a ventilated patient has spontaneous effort, the ventilator attempts to synchronize with the patient, but PVA represents a mismatch between patient respiratory effort and ventilator delivered breaths.

AREAS COVERED

This review will focus on subtypes of patient ventilator asynchrony, methods to detect or measure PVA, risk factors for and characteristics of patients with PVA subtypes, potential clinical implications, treatment or prevention strategies, and future areas for research. Throughout this review, we will provide pediatric specific considerations.

EXPERT OPINION

PVA in pediatric patients supported by mechanical ventilation occurs frequently and is understudied. Pediatric patients have unique physiologic and pathophysiologic characteristics which affect PVA. While recognition of PVA and its subtypes is important for bedside clinicians, the clinical implications and risks versus benefits of treatment targeted at reducing PVA remain unknown. Future research should focus on harmonizing PVA terminology, refinement of automated detection technologies, determining which forms of PVA are harmful, and development of PVA-specific ventilator interventions.

What influences interruption of continuous renal replacement therapy in intensive care unit patients: A review with meta-analysis on outcome variables

BACKGROUND

Evidence suggests that 8%-10% of ICU patients receive renal replacement therapy. However, there is a high rate of unplanned CRRT interruption, ranging between 17% and 74%. Studies on unplanned interruption of CRRT mainly focused on the retrospective investigation of related risk factors and conclusions have been diverse.

AIM

This article aims to clarify the main influencing factors related to unplanned interruption of continuous renal replacement therapy (CRRT) in adult patients in intensive care units (ICUs).

STUDY DESIGN

A literature review and meta-analysis were undertaken. Following the application of the Newcastle-Ottawa Scale (NOS), a total of 15 articles were included in a total of 2132 patients who underwent 3690 CRRT procedures and 2181 unplanned interruption times. The methodological guideline of a scoping review was applied for the evidence synthesis while applying the meta-analysis quantitative methodological guideline to identify and clarify main influencing factors related to unplanned interruption of CRRT. The reporting Prisma Protocol was followed.

RESULTS

Longer filter life and prothrombin activation time, higher red blood cell count, greater transmembrane pressure, faster blood flow rate, intermittent saline irrigation, lower creatinine level, low prothrombin activity and pre-dilution are factors identified to potentially affect unplanned CRRT in ICU patients.

CONCLUSIONS

Available evidence suggests four clinical challenges associated with unplanned CRRT interruption, namely: (a) effects of red blood cell count, filter life, cross-mode pressure, blood flow velocity, prothrombin activity and activated partial thrombin time on unplanned interruption; (b) influence of dilution mode on unplanned interruption; (c) influence of intermittent saline irrigation on unplanned interruption; (d) influence of Scr level on unplanned interruption.

RELEVANCE TO CLINICAL PRACTICE

The potential to increase the ability to better manage unplanned CRRT in ICUs has been identified in this article and constitutes a relevant potential health care management contribution that can be implemented by nurses.

Platelet count trajectory patterns and prognosis in critically ill patients with thrombocytopenia: Based on latent growth mixture model analysis

BACKGROUND

The role of longitudinal platelet count trajectories in critically ill patients with thrombocytopenia is unclear. This study aimed to identify the association between trajectory patterns and prognosis and assess whether these patterns could enhance the predictive capability of Acute Physiology and Chronic Health Evaluation (APACHE) IV or Sequential Organ Failure Assessment (SOFA) scores for mortality.

METHODS

This retrospective cohort study employed latent growth mixture modeling (LGMM) to identify platelet count trajectory patterns. Cox proportional hazards model was used to evaluate the association between the patterns and mortality. Receiver Operating Characteristic (ROC) curves were plotted, and the areas under the curves (AUCs) were compared between models using the APACHE IV or SOFA score alone and those incorporating trajectory patterns.

RESULTS

A total of 1683 patients from the eICU Collaborative Research Database (eICU-CRD) and 931 patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were included. Two trajectory patterns were identified: Class 1, characterized by "Gradual increase," and Class 2, with "Persistent low." Patients in Class 2 had higher ICU mortality (eICU-CRD: 2.273[1.457-3.546]; MIMIC-IV database: 1.991[1.162-3.412]). Incorporating trajectory patterns into the APACHE IV or SOFA scores substantially enhanced the AUC of these scoring systems alone in predicting ICU mortality (eICU-CRD: P < 0.001; MIMIC-IV database: P = 0.0018).

CONCLUSION

The longitudinal platelet count trajectory patterns are complementary predictors of survival in critically ill patients with thrombocytopenia. Persistently low platelet counts are significantly associated with unfavorable clinical outcomes.

Advancing harmful algal bloom predictions using chlorophyll-a as an Indicator: Combining deep learning and EnKF data assimilation method

The use of data driven deep learning models to predict and monitor Harmful Algal Blooms (HABs) has evolved over the years due to increasing technologies, availability of high frequency data, and statistical prowess. Despite the prowess of these data driven models, they are limited by inherent model structure and uncertainty in the generating process. To overcome the limitations of data driven models, in this research, we introduced the concept of data assimilation (DA) to account for model errors and incorporate new observations into the data driven deep learning HABs prediction model. Data assimilation is a computational method that enhances the precision of predictions in dynamic systems by combining real-time observations with model forecasts. In this study, we developed 100 Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) to make one-day ahead prediction of chlorophyll-a, an indicator of HABs, using high-frequency pH, temperature, specific conductivity, turbidity, dissolved oxygen, saturated dissolved oxygen, and oxidation-reduction potential (ORP) data. We used an Ensemble Kalman Filter (EnKF) approach to assimilate chlorophyll-a observations of greater confidence into the HABs prediction model. We explored different assimilation frequencies to observe the appropriate timesteps required for introducing new information into the modeling system. The results showed improved chlorophyll-a prediction, as forecasted by the system when DA is applied. We found that increasing assimilation frequency tends to provide improved chlorophyll-a prediction, with daily assimilation having RMSE of 0.03 μg/l for GRU and 0.02 μg/l for LSTM, while monthly assimilation resulted in RMSE of 3.63 μg/l for GRU and 3.59 μg/l for LSTM. The study revealed the potential application of DA strategy to enhance the accuracy and reliability of deep learning models for HABs monitoring. In the presence of new chlorophyll-a observations, findings from this research inform on the appropriate frequency to which such information can be incorporated into a HABs prediction model framework. This process ensures that the model provides timely and accurate predictions to support effective HABs management and decision-making efforts.

Bathing with 2% chlorhexidine gluconate versus routine care for preventing surgical site infections after pancreatic surgery: a single-centre randomized controlled trial

OBJECTIVES

The study aims to investigate whether bathing with 2% chlorhexidine gluconate (CHG) reduces the incidence of surgical site infection (SSI) in patients undergoing routine pancreatic surgery.

METHODS

A randomized controlled trial was conducted at a large-volume pancreatic centre between 1 January 2021 and 31 December 2022. Patients undergoing clean-contaminated pancreatic surgery were enrolled and randomized into an intervention arm (bathing with a 2% CHG wipe) and a control arm (routine care, soap, and water). The primary outcome was the incidence of SSI after pancreatic surgery within 30 days.

RESULTS

Overall, 614 patients (intervention arm, 311; control arm, 303) were included in intention-to-treat analysis. In total, 8.8% (54/614) patients developed SSI. The incidence of SSI in the intervention arm was 6.8% (21/311) and 10.9% (33/303) in control arm, and the difference did not reach the level of statistical significance (p 0.070). The time to SSI was significantly extended when patients were in the intervention arm (log-rank test, p 0.047). The intervention did not significantly reduce the incidence of healthcare-associated infection, hospital-acquired pneumonia, and bloodstream infection. No adverse events were observed. However, in the per-protocol analysis among 519 patients, the intervention arm showed a significantly lower incidence of overall SSI than that of those in the control arm (21/272, 7.7% vs. 33/242, 13.4%, p 0.036).

DISCUSSION

Bathing with 2% CHG could potentially reduce the incidence of SSI for the patients scheduled to undergo pancreatic surgery for which further well-designed clinical trials are warranted.

Current Management of Uncomplicated Type B Aortic Dissection

Aortic dissection is the most common thoracic aortic emergency and is associated with significant morbidity and mortality. Initial complications are dependent on reduction of sheer stress against the aortic wall to protect against rupture and minimize progression of the aortic wall injury. In patients with dissection starting at or distal to the left subclavian artery (Stanford type B), initial management includes strict blood pressure and heart rate control with monitoring for any complications such as malperfusion, rupture, or hemodynamic instability. Following the acute dissection event, survivors are faced with the lifelong need for blood pressure control and surveillance imaging to monitor for potential aortic deterioration leading to rupture or aneurysm formation. This review will discuss the latest recommendations for current management of uncomplicated type B aortic dissection including the evolving role of endovascular therapies.

Genetic risk, lifestyle adherence, and risk of developing hyperuricaemia in a Japanese population

OBJECTIVE

The objective of this study was to investigate the inter-relationships among genetic risk, adherence to a healthy lifestyle, and susceptibility to hyperuricaemia.

METHODS

This prospective cohort study was conducted with 7241 hyperuricaemia-free individuals aged ≥20 years from the Tohoku Medical Megabank Community-based cohort study. A comprehensive lifestyle score included assessment of BMI, smoking, drinking, and physical activity, and a polygenic risk score (PRS) was constructed based on uric acid loci from a previous genome-wide association study meta-analysis. A multiple logistic regression model was used to estimate the association between genetic risk, adherence to a healthy lifestyle, and hyperuricaemia incidence and to calculate the area under the receiver operating characteristic curve (AUROC). Hyperuricaemia was defined as a uric acid level of ≥7.0 mg/dL or a self-reported history of hyperuricaemia.

RESULTS

Of the 7241 adults [80.7% females; mean (±s.d.) age: 57.7 (12.6) years], 217 (3.0%) developed hyperuricaemia during 3.5 years of follow-up period. Genetic risk was correlated with hyperuricaemia development (P for interaction = 0.287), and lifestyle risks were independently associated. Participants with a high genetic risk and poor lifestyle had the highest risk (odds ratio: 5.34; 95% CI: 2.61-12.10). Although not statistically significant, adding the PRS in the model with lifestyle information improved predictive ability (AUROC = 0.771, 95% CI: 0.736-0.806 for lifestyle; AUROC = 0.785, 95% CI: 0.751-0.819 for lifestyle and PRS; P= 0.07).

CONCLUSION

A healthy lifestyle to prevent hyperuricaemia, irrespective of genetic risk, may mitigate the genetic risk. Genetic risk may complement lifestyle factors in identifying individuals at a heightened hyperuricaemia risk.

Machine learning for predicting outcomes of transcatheter aortic valve implantation: A systematic review

BACKGROUND

Transcatheter aortic valve implantation (TAVI) therapy has demonstrated its clear benefits such as low invasiveness, to treat aortic stenosis. Despite associated benefits, still post-procedural complications might occur. The severity of these complications depends on pre-existing clinical conditions and patient specific complex anatomical features. Accurate prediction of TAVI outcomes will assist in the precise risk assessment for patients undergoing TAVI. Throughout the past decade, different machine learning (ML) approaches have been utilized to predict outcomes of TAVI. This systematic review aims to assess the application of ML in TAVI for the purpose of outcome prediction.

METHODS

Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline was adapted for searching the PubMed and Scopus databases on ML use in TAVI outcomes prediction. Once the studies that meet the inclusion criteria were identified, data from these studies were retrieved and were further examined. 17 parameters relevant to TAVI outcomes were carefully identified for assessing the quality of the included studies.

RESULTS

Following the search of the mentioned databases, 78 studies were initially retrieved, and 17 of these studies were included for further assessment. Most of the included studies focused on mortality prediction, utilizing datasets of varying sizes and diverse ML algorithms. The most employed ML algorithms were random forest, logistics regression, and gradient boosting. Among the studied parameters, serum creatinine, age, BMI, hemoglobin, and aortic valve mean gradient were identified as key predictors for TAVI outcomes. These predictors were found to be well aligned with established associations in current literature.

CONCLUSION

ML presents a promising opportunity for improving the success and safety of TAVI and enhancing patient-centered care. While currently retrospective studies with low generalizability and heterogeneity form the basis of ML TAVI research, future prospective investigations with highly heterogeneous patient TAVI cohorts will be critically important for firmly establishing the applicability of ML in predicting TAVI outcomes.

Predictive power of ALBI score-based nomogram for 30-day mortality following transcatheter aortic valve implantation

AIM

This retrospective, multi-center study evaluates the relationships between novel liver function scoring systems - Albumin-Bilirubin (ALBI) score, EZ-ALBI, PALBI, and MELD-XI - and outcomes in patients undergoing transcatheter aortic valve implantation (TAVI). Feature importance was assessed with SHAP-values via the XGBoost-algorithm.

RESULTS

The ALBI score exhibited the strongest association with 30-day mortality after TAVI (AUC = 0.723, p < 0.001), outperforming other scores in this regard and consistently demonstrating predictive power across various subgroup populations. Higher 30-day mortality rates were observed in the higher tertiles of the ALBI score compared to the lower tertiles (log-rank p-value = 0.004). The ALBI-based nomogram (C-index = 0.81, 95% CI:0.73-0.86, p = 0 < 001) demonstrated superior predictive power for 30-day mortality post-TAVI compared to the STS (C-index = 0.71, 95% CI :0.64-0.77, p = 0 < 001). In addition, the nomogram showed a significant improvement in reclassification (69.3%, p < 0.001) and a stronger discrimination 15.2%, p < 0.001) compared to the STS. It integrates nine variables, first ALBI score (SHAP:1.165), including NYHA class (0.594), body mass index (0.510), glomerular filtration rate, creatinine, hemoglobin, gender, predilatation requirement, presence of chronic kidney disease, and providing a comprehensive risk assessment tool.

CONCLUSION

This study exhibits the significance of liver dysfunction with AS patients and suggests incorporating liver function parameters in pre-operative risk assessments for better clinical outcomes in TAVI procedures.

Development and evaluation of prediction models to improve the hospital appointments overbooking strategy at a large tertiary care hospital in the Sultanate of Oman: a retrospective analysis

OBJECTIVE

Missed hospital appointments are common among outpatients and have significant clinical and economic consequences. The purpose of this study is to develop a predictive model of missed hospital appointments and to evaluate different overbooking strategies.

STUDY DESIGN

Retrospective cross-sectional analysis.

SETTING

Outpatient clinics of the Royal Hospital in Muscat, Oman.

PARTICIPANTS

All outpatient clinic appointments scheduled between January 2014 and February 2021 (n=947 364).

PRIMARY AND SECONDARY OUTCOME MEASURES

Predictive models were created using logistic regression for the entire cohort and individual practices to predict missed hospital appointments. The performance of the models was evaluated using a holdout set. Simulations were performed to compare the effectiveness of predictive model-based overbooking and organisational overbooking in optimising appointment utilisation.

RESULTS

Of the 947 364 outpatient appointments booked, 201 877 (21.3%) were missed. The proportion of missed appointments varied by clinic, ranging from 13.8% in oncology to 28.3% in urology. The area under the receiver operating characteristic curve (AUC) for the overall predictive model was 0.771 (95% CI: 0.768 to 0.775), while the AUC for the clinic-specific predictive model was 0.845 (95% CI: 0.836 to 0.855) for oncology and 0.738 (95% CI: 0.732 to 0.744) for paediatrics. The overbooking strategy based on the predictive model outperformed systematic overbooking, with shortages of available appointments at 10.4% in oncology and 25.0% in gastroenterology.

CONCLUSIONS

Predictive models can effectively estimate the probability of missing a hospital appointment with high accuracy. Using these models to guide overbooking strategies can enable better appointment scheduling without burdening clinics and reduce the impact of missed appointments.

Identification and external validation of tumor DNA methylation panel for the recurrence risk stratification of stage II colon cancer

BACKGROUND

Tailoring surveillance and treatment strategies for stage II colon cancer (CC) after curative surgery remains challenging, and personalized approaches are lacking. We aimed to identify a gene methylation panel capable of stratifying high-risk stage II CC patients for recurrence beyond traditional clinical variables.

METHODS

Genome-wide tumor tissue DNA methylation data were analyzed from 562 stage II CC patients who underwent surgery in Germany (DACHS study). The cohort was divided into a training set (N = 395) and an internal validation set (N = 131), with external validation performed on 97 stage II CC patients from Spain. DNA methylation markers were primarily selected using the Elastic Net Cox model. The resulting prognostic index (PI), a combination of clinical factors and selected methylation markers, was compared to baseline models using clinical variables or microsatellite instability (MSI), with discrimination and prediction accuracy assessed through time-dependent receiver operating characteristic curves (AUC) and Brier scores.

RESULTS

The final PI incorporated age, sex, tumor stage, location, and 27 DNA methylation markers. The PI consistently outperformed the baseline model including age, sex, and tumor stage in time-dependent AUC across validation cohorts (e.g., 1-year AUC and 95 % confidence interval: internal validation set, PI: 0.66, baseline model: 0.52; external validation set, PI: 0.72, baseline model: 0.64). In internal validation, the PI also showed a consistently improved time-dependent AUC compared with a combination of MSI and tumor stage only. Nevertheless, the PI did not improve the prediction accuracy of CC recurrence compared to the baseline model.

CONCLUSIONS

This study identified 27 tumor tissue DNA methylation biomarkers that improved the discriminative power in classifying recurrence risk among stage II colon cancer patients. While this methylation panel alone lacks sufficient prediction accuracy for clinical application, its discriminative improvement suggests potential value as part of a multimodal risk-stratification tool.