Early Identification Of Patients Research Articles

The PREVSAM model, “prevention of sickness absence through early identification and rehabilitation of at-risk patients with musculoskeletal disorders”, is seen as beneficial for patients risking persistent musculoskeletal disorders but may be difficult to implement – a focus group study

Purpose The rehabilitation model “Prevention of sickness absence through early identification and rehabilitation of at-risk patients with musculoskeletal disorders” (PREVSAM) was tested in a randomised controlled trial. This study aimed to explore participating healthcare professionals’ experiences of working according to the PREVSAM model, and their perceptions of its clinical benefit and feasibility in primary care rehabilitation. Methods A focus group study including 12 healthcare professionals from five primary care rehabilitation clinics was analysed according to the focus group methodology described by Krueger and Casey. Results Four themes were identified. A clear framework describes how PREVSAM facilitates person-centred teamwork. The value of teamwork highlights benefits and challenges with teamwork. Through thick and thin discusses perceived patient benefits. In the ideal world focusses on feasibility of implementing the model. Conclusions The participants experienced that the PREVSAM model may be beneficial for the patients, for their own work situation and workplace, and for society. Identifying psychological risk factors was perceived as helpful, but not enough to capture patients in need of team-based rehabilitation. While considered feasible, barriers for implementing the model were identified. Managers and healthcare policy makers must prioritise and create appropriate conditions for team-based musculoskeletal rehabilitation in primary care.

Usefulness of risk assessment tools in predicting hemodynamic outcome after balloon pulmonary angioplasty: a comparative analysis

ABSTRACT Objectives Several parameters of widely used risk assessment tools for pulmonary arterial hypertension (PAH) have been linked to hemodynamic outcomes of balloon pulmonary angioplasty (BPA). Therefore, we aimed to determine whether these risk assessment tools could be used to predict hemodynamic outcomes following BPA. Methods In this retrospective study, we included 139 patients with chronic thromboembolic pulmonary hypertension who had undergone BPA. We compared the accuracies of seven well-validated risk assessment tools for predicting hemodynamic outcomes following BPA. A favorable hemodynamic outcome was defined as a mean pulmonary arterial pressure <30 mmHg at follow-up. Results The baseline risk profiles varied significantly among the risk assessment tools. The US Registry to Evaluate Early and Long-Term PAH Disease Management risk scales and the French risk assessment tools rated most patients as high-risk, while the Comparative, Prospective Registry of Newly Initiated Therapies for Pulmonary Hypertension (COMPERA) series and laboratory examination-based risk scales categorized most patients as having intermediate-risk. COMPERA 2.0 (4-strata) exhibited the highest predictive power among all risk stratifications. Noninvasive risk stratification (COMPERA 2.0 [3-strata]) showed a comparable predictive ability to that of invasive risk stratification (COMPERA 1.0) (area under the curve 0.649 vs. 0.648). Moreover, incorporating diffusing capacity of the lungs for carbon monoxide and tricuspid regurgitation velocity into COMPERA 2.0 (4-strata) further enhanced its predictive power (net reclassification index 0.153, 95% confidence interval 0.009–0.298, p = 0.038). Additionally, this refined COMPERA version had a high calibration accuracy (slope 0.96). Conclusion Although the risk strata distribution varied among different risk assessment tools, the proportion of patients achieving favorable hemodynamics decreased with the escalation of risk stratification in most models. The well-validated risk assessment tools for PAH could also predict hemodynamic outcomes following BPA, and the refined COMPERA 2.0 model exhibited the highest predictive ability among these. Applying risk assessment tools before BPA can facilitate early identification of patients in need of closer monitoring and more intensive interventions, contributing to a better prognosis after BPA.

A novel predictive model for differentiating cardiac and non-cardiac syncope in syncope-admitted patients

Abstract Background Syncope due to cardiac causes presents a higher risk for mortality or other adverse events compared to those with non-cardiac causes. Thus, a critical focus in syncope management must be the early identification of these patients. Purpose This study sought to explore the predictive role of readily available clinical features for cardiac syncope and develop a diagnostic nomogram to facilitate its adoption in practice. Methods 877 patients who were hospitalized with syncope and had a confirmed cause were included in this retrospective study at a tertiary heart center. They were randomly divided into the training set and validation set and were categorized into two groups based on their underlying cause: cardiac syncope and non-cardiac syncope. A wide range of clinical features were analyzed and selected using LASSO regression. Subsequently, we utilized multivariable logistic regression analysis to identify independent predictors and construct a nomogram. The receiver operating characteristic (ROC) curves and the area under the curves (AUCs) were used to assess the predictive accuracy of the predictive model. Furthermore, calibration curves were used to measure the alignment between the predicted and actual observed probability, and decision curve analysis (DCA) was used to evaluate the clinical benefit of the nomogram. Results Within the entire cohort, 521 patients were diagnosed with cardiac syncope and 356 patients were diagnosed with non-cardiac syncope. Among 36 candidate variables, five independent predictors for cardiac syncope were selected using the LASSO logistic regression analysis, including BMI (OR 1.088; 95%CI 1.022-1.158), LVEF (OR 0.940; 95%CI 0.908-0.973), logarithmic NT-proBNP (OR 1.463; 95%CI 1.240-1.727), chest symptoms preceding syncope (OR 5.251; 95%CI 3.326-8.288), and abnormal electrocardiogram (OR 6.171; 95%CI 3.966-9.600). Subsequently, a nomogram based on the five independent predictors was developed, yielding AUC of 0.873 (95% CI 0.845–0.902) and 0.856 (95%CI 0.809-0.903) in the training set and the validation set, respectively. The calibration curves showcased the nomogram's strong calibration, and DCA curves revealed its potential as a highly effective tool in clinical practice. Conclusions This study has successfully developed and internally validated a novel predictive nomogram for distinguishing between cardiac and non-cardiac syncope, which holds a promise to serve as an effective tool to help facilitate early identification of such patients in clinical practice.ROC curves of the training and test setThe nomogram and web-based calculator

#2919 Renal functional reserve assessment in patients with coronary microvascular dysfunction and preserved renal function—experience of a center

Abstract Background and Aims Renal Functional Reserve (RFR) is a field of scientific debate and may be a valuable diagnostic tool for the early detection of subclinical renal disease. According to literature, chronic kidney disease is related to cardiovascular disease (CVD), however the available data on the association of early renal dysfunction and CVD are sparse. The aim of the present study is to evaluate RFR in patients with coronary microvascular dysfunction (CMD) and preserved renal function [eGFR≥ 60 ml/min/1.73 m2 (CKD-EPI) and proteinuria&amp;lt; 400 mg/24 h]. Method This is a single-center, prospective study enrolling patients with INOCA. We are presenting preliminary results. In the absence of significant coronary artery stenosis, functional coronary circulation assessment was performed for all patients and we estimated coronary flow reserve (CFR) and index of microvascular resistance (IMR). In all participants, RFR was estimated by endogenous creatinine clearance after oral protein load (cooked meal, 1.2 gr/kg). Normal RFR was defined as ≥30 ml/min/1.73 m2. Also, patients with INOCA were offered 24-hour Ambulatory Blood Pressure Monitoring (ABPM). Results A total of 22 participants have been enrolled so far in study: 10 without CMD—control group [7 female, mean age: 54.4 ± 8.1 years) and 12 with INOCA—CMD group (9 female, 75%, mean age: 53.5 ± 10.3 years). CMD patients were classified into 2 groups, structural and functional endotype (CFR&amp;lt;2.5 and an IMR≥25 were considered abnormal). The RFR value for CMD group is 7.4 ± 6.3 ml/min/1.73 m2, while for non-CMD group 36.3 ± 5.8 ml/min/1.73 m2 (p &amp;lt; 0.005), relationship that remained statistically significant after controlling for confounding factors. Regarding the two endotypes of MVD, it was found that RFR for the patients with the functional endotype is 3.5 ± 2.4 ml/min/1.73 m2, while for those with the structural endotype 9.3 ± 6.9 ml/min/1.73 m2 (p-value = 0.061). Furthermore, no statistically significant relationship emerged between RFR and IMR, CFR indices (p = 0.347, p = 0.263). According to data from 24 hr ABPM, there were no significant differences in ambulatory blood pressure (systolic and diastolic) between the two endotypes of CMD (p = 0.594, p = 0.243), as well as no relationship with RFR (p = 0.553, p = 0.594). However, the proportion of non-dippers (for both SBP and DBP) was significantly higher in functional CMD endotype (p &amp;lt; 0.05). It was not found correlation between RFR and non-dipping phenotype, both for SBP and DBP (p = 0.561, p = 0.238). Conclusion Abnormal RFR has been observed in all patients with microvascular dysfunction. In addition, patients with functional CMD show a lower RFR value compared to those with structural. RFR is not related to blood pressure or the non-dipping pattern. Given the hypothesis that the assessment of renal functional reserve is an early diagnostic tool for subclinical renal disease, the early identification of patients with specific phenotypes—such as INOCA and pathological RFR—could contribute to the individualization of therapeutic interventions.

#2508 Urinary [TIMP-2]*[IGFBP7] as the ultimate potential biomarker of subclinical Acute Kidney Injury after kidney surgery: a multicentric study

Abstract Background and Aims Nephron-sparing surgery (NSS) represents the preferred technique to treat localized renal lesions and better preserve kidney function. Still it is not exempted from the risk of postoperative acute kidney injury (AKI) to happen, with a reported incidence ranging from 5.5% to 34%. Patients experiencing postoperative AKI, either clinical or subclinical, are more susceptible to chronic kidney disease (CKD). The latter represents a difficult-to-identify subpopulation characterized by tubular damage biomarker's rising without changes in serum creatinine (scr), that after surgery is less likely to be included among the ones deserving a closer follow-up, but actually needing one, as this subpopulation's long term outcomes slightly differ from individuals recovered from clinical postoperative AKI. This is the reason why a standardized tool for early identification of patients suffering from subclinical AKI is required, to allow a customized postoperative surveillance, promote strategies of nephroprotection and reduce the incidence of CKD and end-stage kidney disease. Recent evidences show that by exclusively following outdated consensus criteria for AKI (changes in scr, urine output), 15-20% of patients undergoing through acute tubular injury and suffering from its adverse outcomes are likely to be missed. Only recently, FDA approved NephroCheck® biomarker, which combines two urinary markers, tissue inhibitor of metalloproteinases-2 (TIMP-2) and insulin-like growth factor-binding protein 7 (IGFBP7). It represents the first effective test for AKI's risk assessment. In a previous monocentric study [1], our group presented NephroCheck® as a biomarker able to efficiently identify subclinical AKI and predict long-term eGFR decline after robotic NSS. In order to confirm our previous results, we recruited a larger cohort and performed a multicentric study. Method We prospectively observed all patients scheduled for robotic NSS in suspected localized renal cell carcinoma in two different Centers from 2016 to 2018. Samples were collected preoperatively and postoperatively (4 h, 10 h, 24 h, 48 h), while kidney function was re-assessed up to 24 months. A multivariate logistic analysis was performed to evaluate the association between different parameters and eGFR decline at 24 months. Results A total number of 131 patients were included; 55/131 (42%) developed clinical AKI. A significant association between NephroCheck® at 4 h and clinical AKI, as stated by KDIGO Guidelines, is confirmed (p = 0.0055). In the overall cohort, the multivariate analysis shows that only clinical AKI appears as an independent factor for predicting eGFR decline at 24 months (p &amp;lt; 0.0003), while postoperative NephroCheck® alone did not (p = 0.92). Based on NephroCheck® measured 4 h after surgery and clinical AKI, patients can be divided in four groups with significantly different eGFR at 24 months (p = 0.0003) (Fig. 1). Not considering patients who experienced clinical AKI, the independent role of different parameters in predicting severe eGFR decline at 24 months was evaluated by multivariate logistic analysis; in this subgroup of patients, NephroCheck® evaluated at 4 h postoperatively appears as an independent factor able to predict a severe eGFR decline at 24 months (OR 3.76, p = 0.02) (Fig. 2). Conclusion NephroCheck®, in combination with scr, represents an accurate and easy-to-use test, likely able to early identify long-term eGFR decline in patients undergoing NSS surgery that don't develop a clinically evident postoperative AKI (subclinical AKI), making it possible to identify those in need of closer-up surveillance, reducing the incidence and progression of CKD. Still, clinical postoperative AKI is confirmed as the most important prognostic parameter and predictive factor for eGFR decline in the long-term. Further studies are needed, particularly focusing on application of NephroCheck® in setting other than NSS.

Clinical features and risk factors for pyogenic liver abscess caused by multidrug-resistant organisms: A retrospective study

ABSTRACT The incidence rate of pyogenic liver abscess caused by multidrug-resistant bacteria has increased in recent years. This study aimed to identify the clinical characteristics and risk factors for pyogenic liver abscess caused by multidrug-resistant bacteria. We conducted a retrospective analysis of the clinical features, laboratory test results, and causes of pyogenic liver abscesses in 239 patients admitted to a tertiary hospital. Multivariable logistic regression was used to identify risk factors for multidrug resistance. Among patients with pyogenic liver abscesses, the rate of infection caused by multidrug-resistant organisms was observed to be 23.0% (55/239), with a polymicrobial infection rate of 14.6% (35/239). Additionally, 71 cases (29.7%) were associated with biliary tract disease. Patients with pyogenic liver abscesses caused by multidrug-resistant organisms had a significantly higher likelihood of polymicrobial infection and increased mortality (7/44 [15.9%] vs. 3/131 [2.3%]; p = .003). The Charlson Comorbidity Index (adjusted odds ratio [aOR]: 1.32, 95% confidence interval [CI]: 1.06–1.68), hospitalization (aOR: 10.34, 95% CI: 1.86–60.3) or an invasive procedure (aOR: 9.62; 95% CI: 1.66–71.7) within the past 6 months, and gas in the liver on imaging (aOR: 26.0; 95% CI: 3.29–261.3) were independent risk factors for pyogenic liver abscess caused by multidrug-resistant bacteria. A nomogram was constructed based on the risk factors identified. The nomogram showed high diagnostic accuracy (specificity, 0.878; sensitivity 0.940). Multidrug-resistant organisms causing pyogenic liver abscesses have specific characteristics. Early identification of patients at high risk of infection with multidrug-resistant organisms could help improve their management and enable personalized treatment.

How Will Artificial Intelligence Shape the Future of Decision-Making in Congenital Heart Disease?

Improvements in medical technology have significantly changed the management of congenital heart disease (CHD), offering novel tools to predict outcomes and personalize follow-up care. By using sophisticated imaging modalities, computational models and machine learning algorithms, clinicians can experiment with unprecedented insights into the complex anatomy and physiology of CHD. These tools enable early identification of high-risk patients, thus allowing timely, tailored interventions and improved outcomes. Additionally, the integration of genetic testing offers valuable prognostic information, helping in risk stratification and treatment optimisation. The birth of telemedicine platforms and remote monitoring devices facilitates customised follow-up care, enhancing patient engagement and reducing healthcare disparities. Taking into consideration challenges and ethical issues, clinicians can make the most of the full potential of artificial intelligence (AI) to further refine prognostic models, personalize care and improve long-term outcomes for patients with CHD. This narrative review aims to provide a comprehensive illustration of how AI has been implemented as a new technological method for enhancing the management of CHD.

Evaluation of a proteomic signature coupled with the kidney failure risk equation in predicting end stage kidney disease in a chronic kidney disease cohort.

The early identification of patients at high-risk for end-stage renal disease (ESRD) is essential for providing optimal care and implementing targeted prevention strategies. While the Kidney Failure Risk Equation (KFRE) offers a more accurate prediction of ESRD risk compared to static eGFR-based thresholds, it does not provide insights into the patient-specific biological mechanisms that drive ESRD. This study focused on evaluating the effectiveness of KFRE in a UK-based advanced chronic kidney disease (CKD) cohort and investigating whether the integration of a proteomic signature could enhance 5-year ESRD prediction. Using the Salford Kidney Study biobank, a UK-based prospective cohort of over 3000 non-dialysis CKD patients, 433 patients met our inclusion criteria: a minimum of four eGFR measurements over a two-year period and a linear eGFR trajectory. Plasma samples were obtained and analysed for novel proteomic signals using SWATH-Mass-Spectrometry. The 4-variable UK-calibrated KFRE was calculated for each patient based on their baseline clinical characteristics. Boruta machine learning algorithm was used for the selection of proteins most contributing to differentiation between patient groups. Logistic regression was employed for estimation of ESRD prediction by (1) proteomic features; (2) KFRE; and (3) proteomic features alongside KFRE. SWATH maps with 943 quantified proteins were generated and investigated in tandem with available clinical data to identify potential progression biomarkers. We identified a set of proteins (SPTA1, MYL6 and C6) that, when used alongside the 4-variable UK-KFRE, improved the prediction of 5-year risk of ESRD (AUC = 0.75 vs AUC = 0.70). Functional enrichment analysis revealed Rho GTPases and regulation of the actin cytoskeleton pathways to be statistically significant, inferring their role in kidney function and the pathogenesis of renal disease. Proteins SPTA1, MYL6 and C6, when used alongside the 4-variable UK-KFRE achieve an improved performance when predicting a 5-year risk of ESRD. Specific pathways implicated in the pathogenesis of podocyte dysfunction were also identified, which could serve as potential therapeutic targets. The findings of our study carry implications for comprehending the involvement of the Rho family GTPases in the pathophysiology of kidney disease, advancing our understanding of the proteomic factors influencing susceptibility to renal damage.

Development and Validation of a Nomogram for Predicting Nutritional Risk Based on Frailty Scores in Older Stroke Patients

BackgroundIn older stroke patients with frailty, nutritional deficiencies can amplify their susceptibility, delay recovery, and deteriorate prognosis. A precise predictive model is crucial to assess their nutritional risk, enabling targeted interventions for improved clinical outcomes.ObjectiveTo develop and externally validate a nutritional risk prediction model integrating general demographics, physical parameters, psychological indicators, and biochemical markers. The aim is to facilitate the early identification of older stroke patients requiring nutritional intervention.MethodsThis was a multicenter cross-sectional study. A total of 570 stroke patients were included, 434 as the modeling set and 136 as the external validation set. The least absolute shrinkage selection operator (LASSO) regression analysis was used to select the predictor variables. Internal validation was performed using Bootstrap resampling (1000 iterations). The nomogram was constructed based on the results of logistic regression. The performance assessment relied on the receiver operating characteristic curve (ROC), Hosmer–-Lemeshow test, calibration curves, Brier score, and decision curve analysis (DCA).ResultsThe predictive nomogram encompassed seven pivotal variables: Activities of Daily Living (ADL), NIHSS score, diabetes, Body Mass Index (BMI), grip strength, serum albumin levels, and depression. Together, these variables comprehensively evaluate the overall health and nutritional status of elderly stroke patients, facilitating accurate assessment of their nutritional risk. The model exhibited excellent accuracy in both the development and external validation sets, evidenced by AUC values of 0.934 and 0.887, respectively. Such performance highlights its efficacy in pinpointing elderly stroke patients who require nutritional intervention. Moreover, the model showed robust goodness of fit and practical applicability, providing essential clinical insights to improve recovery and prognosis for patients prone to malnutrition.ConclusionsElderly individuals recovering from stroke often experience significant nutritional deficiencies. The nomogram we devised accurately assesses this risk by combining physiological, psychological, and biochemical metrics. It equips healthcare providers with the means to actively screen for and manage the nutritional care of these patients. This tool is instrumental in swiftly identifying those in urgent need of targeted nutritional support, which is essential for optimizing their recovery and managing their nutrition more effectively.

Abstract B004: Deep learning unveils molecular footprints in histology: predicting molecular subtypes from bladder cancer histology slides

Abstract Introduction: Transurethral resection followed by intravesical bacillus Calmette-Guerin (BCG) is the standard of care for high-risk non-muscle-invasive bladder cancer (HR-NMIBC) patients. However, ≈20% of HR-NMIBC patients progress to muscle-invasive or metastatic disease, which is associated with a high-risk of death. Early identification of patients who are unlikely to benefit from BCG treatment could benefit from an early radical cystectomy or bladder-sparing alternatives. Previously, we showed that molecular subtyping or HR-NMIBC identified BCG response subtypes (BRS 1/2/3). BRS3 tumors were associated with a poor response to BCG and a high-risk of progression. However, molecular subtyping relies on resource-intensive and costly sequencing methods such as next-generation sequencing, and microarray analysis. We employed deep learning (DL) to predict BRS3 vs BRS1/2 molecular subtypes from digitized histology slides. Methods: Haematoxylin and eosin (H&amp;E)-stained slides were digitized, and quality control was performed. The areas where the RNA was extracted were annotated pixel-wise by a trained pathology assistant, using QuPath. Image tiles of 512 × 512 pixels at 10X, 20X, and 40X magnifications were extracted with a 25% overlap. For classification, BRS1 and BRS2 images were grouped, while BRS3 images were categorized separately. After applying Macenko normalization, tiles were split based on individual patients into a 75/25 training/validation ratio via stratified 4-fold cross-validation. Four DL models (DenseNet, Inception, ShuffleNet, ResNet) were trained to classify tiles into BRS3 and BRS1/2, with tile labels based on the patient’s subtype. Patient-level classification was performed using majority voting from tile predictions. Model efficacy was gauged using the area under the ROC curve (AUC). Results: Out of 245 H&amp;E slides, 45 were discarded after quality control. From 200 patients – with a 70:30 distribution between BRS1&amp;2 and BRS3 The DenseNet model at 10x magnification was the best-performing model, achieving the highest AUC compared to all other models and magnifications. On the image tile level, the best DenseNet achieved an average AUC of 0.65 with a standard deviation of 0.03 across the four folds of the validation set. At the patient-level prediction, the best DenseNet reached an average AUC of 0.80 and a standard deviation of 0.05 on the validation set. Conclusion: Our study demonstrates that deep learning classifies BSR3 from BSR1 and 2 subtypes from H&amp;E slides. This method holds potential to identify BRS3 HR-NMIBC patients who may benefit from alternative treatments than BCG. With further refinement, this deep learning strategy can become a key tool in histology, aiding in swift, affordable, and efficient subtype identification. Hence, this method has the potential to bridge the gap between molecular techniques and clinical practice. Future research should prioritize evaluating the model on an external test cohort and consider predicting additional molecular markers to fine-tune prediction outcomes. Citation Format: Farbod Khoraminia, Flouros C de Jong, Farhan Akram, Geert Litjens, Maarten D.J. Jansen, Alberto Nakuama Gonzalez, Danique Lichtenburg, Andrew Stubbs, Nadieh Khalili, Tahlita C.M. Zuiverloon. Deep learning unveils molecular footprints in histology: predicting molecular subtypes from bladder cancer histology slides [abstract]. In: Proceedings of the AACR Special Conference on Bladder Cancer: Transforming the Field; 2024 May 17-20; Charlotte, NC. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(10_Suppl):Abstract nr B004.

Extracellular volume fraction derived from dual-energy CT: a potential predictor for acute pancreatitis after pancreatoduodenectomy.

To investigate the value of extracellular volume (ECV) fraction and fat fraction (FF) derived from dual- energy CT (DECT) for predicting postpancreatectomy acute pancreatitis (PPAP) after pancreatoduodenectomy (PD). This retrospective study included patients who underwent DECT and PD between April 2022 and September 2022. PPAP was determined according to the International Study Group for Pancreatic Surgery (ISGPS) definition. Iodine concentration (IC) and FF of the pancreatic parenchyma were measured on preoperative DECT. The ECV fraction was calculated from iodine map images of the equilibrium phase. The independent predictors for PPAP were assessed by univariate and multivariable logistic regression analysisand receiver operating characteristic (ROC) curve analysis. Sixty-nine patients were retrospectively enrolled (median age, 60 years; interquartile range, 55-70 years; 47 men). Of these, nine patients (13.0%) developed PPAP. These patients had lower portal venous phase IC, equilibrium phase IC, FF, and ECV fraction, and higher pancreatic parenchymal-to-portal venous phase IC ratio and pancreatic parenchymal-to-equilibrium phase IC ratio, compared with patients without PPAP. After multivariable analysis, ECV fraction was independently associated with PPAP (odd ratio [OR], 0.87; 95% confidence interval [CI]: 0.79, 0.96; p < 0.001), with an area under the curve (AUC) of 0.839 (sensitivity 100.0%, specificity 58.3%). A lower ECV fraction is independently associated with the occurrence of PPAP after PD. ECV fraction may serve as a potential predictor for PPAP after PD. DECT-derived ECV fraction of pancreatic parenchyma is a promising biomarker for surgeons to preoperatively identify patients with higher risk for postpancreatectomy acute pancreatitis after PD and offer selective perioperative management. PPAP is a complication of pancreatic surgery, early identification of higher-risk patients allows for risk mitigation. Lower DECT-derived ECV fraction was independently associated with the occurrence of PPAP after PD. DECT aids in preoperative PAPP risk stratification, allowing for appropriate treatment to minimize complications.

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

ObjectiveTo develop a robust machine learning prediction model for the automatic screening and diagnosis of obstructive sleep apnea (OSA) using five advanced algorithms, namely Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) to provide substantial support for early clinical diagnosis and intervention.MethodsWe conducted a retrospective analysis of clinical data from 439 patients who underwent polysomnography at the Affiliated Hospital of Xuzhou Medical University between October 2019 and October 2022. Predictor variables such as demographic information [age, sex, height, weight, body mass index (BMI)], medical history, and Epworth Sleepiness Scale (ESS) were used. Univariate analysis was used to identify variables with significant differences, and the dataset was then divided into training and validation sets in a 4:1 ratio. The training set was established to predict OSA severity grading. The validation set was used to assess model performance using the area under the curve (AUC). Additionally, a separate analysis was conducted, categorizing the normal population as one group and patients with moderate-to-severe OSA as another. The same univariate analysis was applied, and the dataset was divided into training and validation sets in a 4:1 ratio. The training set was used to build a prediction model for screening moderate-to-severe OSA, while the validation set was used to verify the model's performance.ResultsAmong the four groups, the LightGBM model outperformed others, with the top five feature importance rankings of ESS total score, BMI, sex, hypertension, and gastroesophageal reflux (GERD), where Age, ESS total score and BMI played the most significant roles. In the dichotomous model, RF is the best performer of the five models respectively. The top five ranked feature importance of the best-performing RF models were ESS total score, BMI, GERD, age and Dry mouth, with ESS total score and BMI being particularly pivotal.ConclusionMachine learning-based prediction models for OSA disease grading and screening prove instrumental in the early identification of patients with moderate-to-severe OSA, revealing pertinent risk factors and facilitating timely interventions to counter pathological changes induced by OSA. Notably, ESS total score and BMI emerge as the most critical features for predicting OSA, emphasizing their significance in clinical assessments. The dataset will be publicly available on my Github.

Hotspots and trends of risk factors in gastric cancer: A visualization and bibliometric analysis.

The lack of specific symptoms of gastric cancer (GC) causes great challenges in its early diagnosis. Thus it is essential to identify the risk factors for early diagnosis and treatment of GC and to improve the survival rates. To assist physicians in identifying changes in the output of publications and research hotspots related to risk factors for GC, constructing a list of key risk factors, and providing a reference for early identification of patients at high risk for GC. Research articles on risk factors for GC were searched in the Web of Science core collection, and relevant information was extracted after screening. The literature was analyzed using Microsoft Excel 2019, CiteSpace V, and VOSviewer 1.6.18. A total of 2514 papers from 72 countries and 2507 research institutions were retrieved. China (n = 1061), National Cancer Center (n = 138), and Shoichiro Tsugane (n = 36) were the most productive country, institution, or author, respectively. The research hotspots in the study of risk factors for GC are summarized in four areas, namely: Helicobacter pylori (H. pylori) infection, single nucleotide polymorphism, bio-diagnostic markers, and GC risk prediction models. In this study, we found that H. pylori infection is the most significant risk factor for GC; single-nucleotide polymorphism (SNP) is the most dominant genetic factor for GC; bio-diagnostic markers are the most promising diagnostic modality for GC. GC risk prediction models are the latest current research hotspot. We conclude that the most important risk factors for the development of GC are H. pylori infection, SNP, smoking, diet, and alcohol.

Efficacy of Bedside Index for Severity In Acute Pancreatitis (Bisap) Score As Predictor of In-Hospital Outcome in Acute Pancreatitis

Background: Acute pancreatitis is a potentially life-threatening condition characterized by inflammation of the pancreas. Early identification of patients at risk of severe disease is crucial for devising appropriate management strategies and improving outcomes. The aim of the study was to investigate the efficacy of BISAP score as predictor of in-hospital outcome in patients with acute pancreatitis. Methods: This was a longitudinal study conducted in Department of Medicine, Sir Salimullah Medical College Mitford Hospital, Dhaka from January 2023 to December 2023. After ethical approval, a total 107 subjects were included in this study based on inclusion and exclusion criteria. Severity of the disease was assessed by BISAP score. Theoutcome determinants were length of hospital stay, complete recovery, partial recovery with complication, transfer to ICU and mortality. Chi Square test, Binominal Regression analysis and Receiver operator characteristic (ROC) curve analysis were performed as applicable. p value &lt;0.05 was considered as the level of significance. Results: The mean BISAP score among 107 study participants was 2.00 ± 0.76. Patients with BISAP score ³3 had significantly increased odds of prolonged hospital stay (OR: 11.226; 95% CI: 2.985- 42.222; p&lt;0.001), higher rate of partial recovery with complications (OR: 7.302; 95.325% CI: -20.997; p&lt;0.001). &lt;0.001), and greater likelihood of intensive care unit (ICU) transfer (OR: 1.136; 95% CI: 0.968-1.333; p=0.004). A BISAP score cutoff value of ³3 was associated with increased length of hospital stay (sensitivity 91.3%, specificity 97.6%, AUC=0.945), partial recovery with complications (sensitivity 83.3%, specificity 96.4%, AUC=0.899), and ICU transfer (sensitivity 75%, specificity 80.6%, AUC=0.778).Conclusion: It can be concluded that increased BISAP score can be served as an independent predictor of in-hospital in patients with acute pancreatitis (AP). Bangladesh J Medicine 2024; 35: 88-92

Prevention of sickness absence through early identification and rehabilitation of at-risk patients with musculoskeletal disorders (PREVSAM): short term effects of a randomised controlled trial in primary care

Purpose To evaluate short-term effects of the PREVention of Sickness Absence for Musculoskeletal disorders (PREVSAM) model on sickness absence and patient-reported health outcomes. Methods Patients with musculoskeletal disorders were randomised to rehabilitation according to PREVSAM or treatment as usual (TAU) in primary care. Sickness absence and patient-reported health outcomes were evaluated after three months in 254 participants. Results The proportion of participants remaining in full- or part-time work were 86% in PREVSAM vs 78% in TAU (p = 0.097). The PREVSAM group had approximately four fewer sickness benefit days during three months from baseline (p range 0.078–0.126). No statistically significant difference was found in self-reported sickness absence days (PREVSAM 12.4 vs TAU 14.5; p = 0.634), nor were statistically significant differences between groups found in patient-reported health outcomes. Both groups showed significant improvements from baseline to three months, except for self-efficacy, and only the PREVSAM group showed significantly reduced depression symptoms. Conclusions The findings suggest that for sickness absence, the PREVSAM model may have an advantage over TAU, although the difference did not reach statistical significance at the p < 0.05 level, and similar positive effects on patient-reported health outcomes were found in both groups. Long-term effects must be evaluated before firm conclusions can be drawn.

Nursing assessment of mental health issues in the general clinical environment: A descriptive study.

To evaluate the effectiveness of a mental health screening form for early identification and care escalation of mental health issues in general settings. A secondary aim was to explore general nurses' use of the form and their confidence to discuss mental health issues with patients. A cross-sectional design comprising a review of clinical records to determine use of the form, instances of missed care and escalation to the mental health team. The survey focused on nurses' confidence in general settings to engage in discussions with patients about mental health. Data were collected from April to December 2022. The Strengthening the Reporting of Observational Studies in Epidemiology Statement guided this study. Of 400 patient records, 397 were analysed; 293 (73.8%) of those had mental health screening by nurses. Age was a significant factor, with younger patients more likely to be screened although concerns were typically recognized in older patients. Of the 20 patients identified with mental health concerns, 9 (45%) were referred for further evaluation by the Clinical Liaison Team. While nurses were proactive in assessing physical risks, assessing risk factors that required deeper conversations with patients, including psychiatric history, was lacking. The survey highlighted fewer than half of the respondents (46%, n = 10) felt competent to engage in discussions about mental health; however, most (59%, n = 13) knew when to seek a mental health referral. General nurses have a role in the early identification and referral of patients with mental health challenges. However, training is imperative to facilitate deeper patient interactions concerning mental health. Integrating mental health checks within general settings is crucial for early detection and intervention, aligning with global quality care standards. STROBE guidelines. We received feedback that shaped the research protocol from a consumer representative.

Deep-learning survival analysis for patients with calcific aortic valve disease undergoing valve replacement

Calcification of the aortic valve (CAVDS) is a major cause of aortic stenosis (AS) leading to loss of valve function which requires the substitution by surgical aortic valve replacement (SAVR) or transcatheter aortic valve intervention (TAVI). These procedures are associated with high post-intervention mortality, then the corresponding risk assessment is relevant from a clinical standpoint. This study compares the traditional Cox Proportional Hazard (CPH) against Machine Learning (ML) based methods, such as Deep Learning Survival (DeepSurv) and Random Survival Forest (RSF), to identify variables able to estimate the risk of death one year after the intervention, in patients undergoing either to SAVR or TAVI. We found that with all three approaches the combination of six variables, named albumin, age, BMI, glucose, hypertension, and clonal hemopoiesis of indeterminate potential (CHIP), allows for predicting mortality with a c-index of approximately 80%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$80\\%$$\\end{document}. Importantly, we found that the ML models have a better prediction capability, making them as effective for statistical analysis in medicine as most state-of-the-art approaches, with the additional advantage that they may expose non-linear relationships. This study aims to improve the early identification of patients at higher risk of death, who could then benefit from a more appropriate therapeutic intervention.

Acute heart failure and acute coronary syndrome: not uncommon duo and dangerous

Abstract Funding Acknowledgements None. Introduction Acute Heart Failure (AHF) is a common cause of hospitalisation. Its ethology and triggering factors influence the prognosis and evolution. Methods and purpose Retrospective analysis of 6330 patients admitted to our hospital's Coronary Care Unit (CCU) between 2012 and 2022. The main objective was to analyse the characteristics during hospital progress and follow-up of patients with AHF after an Acute Coronary Syndrome (ACS) in class Killip III or IV, comparing it with those admitted for AHF not secondary to ACS. Results 698 patients with AHF after ACS and 384 with AHF not secondary to ACS were included. 68.8% of patients presented Acute Coronary Syndrome with ST elevation (STEMI), with a higher prevalence in the anterior location (34,3%). Angioplasty was performed in 53.4% of patiens with STEMI and in 40.3% of patients with NSTEMI. The Cardiovascular risk factors (Figure 1) were similar in both groups, while patients with AHF not secondary to ACS had a history of Coronary Heart Disease (CHD) and atrial fibrilación (AF) more frequently. Patients with AHF after ACS more frequently required treatment with dobutamine and norepinephrine (63.6% and 57.6%, respectively) as well as orotracheal intubation. At the same time, levosimendan was administered more frequently to patients with AHF not secondary to ACS, with non-invasive mechanical ventilation being more frequent in this group. Both groups similarly received neurohormonal treatment, with beta-blockers being used the most. Events during follow-up (Figure 2) were higher in patients with AHF after ACS, except HF events. Cardiovascular mortality was 21.9% in patients with AHF after ACS. Conclusions Patients admitted for ACS complicated with AHF Killip III-IV represented 11.02%. The majority presented previously STEMI. During their admission, compared to patients admitted for AHF not secondary to ACS, they more frequently required vasoactive drugs and orotracheal intubation. Cardiovascular complications and mortality during follow-up were higher in patients with AHF after ACS. Therefore, early identification of patients with ACS at risk of developing AHF and establishing a specific and optimal treatment is crucial in the evolution of these patients.

Renal functional reserve assessment in patients with coronary microvascular dysfuntion and preserved renal function

Abstract Funding Acknowledgements None. Introduction Renal Functional Reserve (RFR) is a field of scientific debate and may be a valuable diagnostic tool for the early detection of subclinical renal disease. According to literature, chronic kidney disease is related to cardiovascular disease (CVD), however the available data on the association of early renal dysfunction and CVD are sparse. Aim The aim of the present study is to evaluate RFR in patients with coronary microvascular dysfunction (CMD) and preserved renal function [eGFR≥ 60 ml/min/1.73m2 (CKD-EPI) and proteinuria&amp;lt; 400mg/24h]. Methods This is a single-center, prospective study enrolling patients with CMD. We are presenting preliminary resuts. In the absence of significant coronary artery stenosis, functional coronary circulation assessment was performed for all patients. Coronary flow reserve (CFR) and index of microvascular resistance (IMR) were measured invasively. In all participants, RFR was estimated by endogenous creatinine clearance after oral protein load (cooked meal, 1.2gr/kg). Normal RFR was defined as ≥30 ml/min/1.73m2. Also, patients with CMD were offered 24-hour Ambulatory Blood Pressure Monitoring (ABPM). Results A total of 25 participants have been enrolled so far in study: 11 without CMD - non-CMD group [7 female, 64%, mean age: 52.9±8.8 years) and 14 with INOCA – CMD group (11 female, 79%, mean age : 53.5±10.3 years). CMD patients were classified into 2 groups, structural and functional endotype (CFR&amp;lt;2.5 and IMR≥25 were considered abnormal). The RFR value for CMD group is 7.4±6.3 ml/min/1.73m2, while for control group 36.3±5.8 ml/min/1.73m2 (p&amp;lt;0.005), This difference between groups was found to be statistically significant after controlling for confounding factors. It was found that RFR value for functional CMD endotype was 3.8±2.6 ml/min/1.73m2, while for patients with structural endotype 9.6±7,2 ml/min/1.73m2 (p=0.06). Furthermore, no statistical significance was found between RFR and IMR, CFR indices (p =0.35, p =0.23 respectively). According to data from 24hr ABPM , there were no significant differences in ambulatory blood pressure (systolic and diastolic) between the two endotypes of CMD (p=NS for all), as well as no relationship with RFR (p=0.6, p=0.6 respectively) was observed. However, the proportion of non-dippers (for both SBP and DBP) was significantly higher in functional CMD endotype (p&amp;lt;0.05). It was not found correlation between RFR and non-dipping phenotype, for both SBP and DBP (p=NS). Conclusion Abnormal RFR has been observed in all patients with microvascular dysfunction. In addition, patients with functional CMD show a lower RFR value compared to those with structural. RFR is not related to levels of BP or the non-dipping pattern. Given the hypothesis that the assessment of renal functional reserve is an early diagnostic tool for subclinical renal disease, the early identification of patients with specific phenotypes could contribute to the individualization of therapeutic interventions.

Interleukin-1β Polymorphisms Are Genetic Markers of Susceptibility to Periprosthetic Joint Infection in Total Hip and Knee Arthroplasty.

Periprosthetic joint infections (PJIs) are serious complications of prosthetic surgery. The criteria for the diagnosis of PJI integrate clinical and laboratory findings in a complex and sometimes inconclusive workflow. Host immune factors hold potential as diagnostic biomarkers in bone and joint infections. We reported that the humoral pattern-recognition molecule long pentraxin 3 (PTX3) predicts PJI in total hip and knee arthroplasty (THA and TKA, respectively). If and how genetic variation in PTX3 and inflammatory genes that affect its expression (IL-1β, IL-6, IL-10, and IL-17A) contributes to the risk of PJI is unknown. We conducted a case-control study on a Caucasian historic cohort of THA and TKA patients who had prosthesis explant due to PJI (cases) or aseptic complications (controls). Saliva was collected from 93 subjects and used to extract DNA and genotype PTX3, IL-1β, IL-6, IL-10, and IL-17A single-nucleotide polymorphisms (SNPs). Moreover, the concentration of IL-1β, IL-10, and IL-6 was measured in synovial fluid and plasma. No association was found between PTX3 polymorphisms and PJI; however, the AGG haplotype, encompassing rs2853550, rs1143634, and rs1143627 in IL-1β, was linked to the infection (p = 0.017). Also, synovial levels of all inflammatory markers were higher in cases than in controls, and a correlation emerged between synovial concentration of PTX3 and that of IL-1β in cases only (Spearman r = 0.67, p = 0.004). We identified a relationship between rs2853550 and the synovial concentration of IL-1β and PTX3. Our findings suggest that IL-1β SNPs could be used for the early identification of THA and TKA patients with a high risk of infection.