Tool For Prediction Of Outcome Research Articles

Improved survival prediction for kidney transplant outcomes using artificial intelligence-based models: development of the UK Deceased Donor Kidney Transplant Outcome Prediction (UK-DTOP) Tool

The UK Deceased Donor Kidney Transplant Outcome Prediction (UK-DTOP) Tool, developed using advanced artificial intelligence (AI), significantly enhances the prediction of outcomes for deceased-donor kidney transplants in the UK. This study analyzed data from the UK Transplant Registry (UKTR), including 29,713 transplant cases between 2008 and 2022, to assess the predictive performance of three machine learning models: XGBoost, Random Survival Forest, and Optimal Decision Tree. Among these, XGBoost demonstrated exceptional performance with the highest concordance index of 0.74 and an area under the curve (AUC) consistently above 0.73, indicating robust discriminative ability and calibration. In comparison to the traditional Kidney Donor Risk Index (KDRI), which achieved a lower concordance index of 0.57, the UK-DTOP model marked a significant improvement, underscoring its superior predictive accuracy. The advanced capabilities of the XGBoost model were further highlighted through calibration assessments using the Integrated Brier Score (IBS), showing a score of 0.14, indicative of precise survival probability predictions. Additionally, unsupervised learning via k-means clustering was employed to identify five distinct clusters based on donor and transplant characteristics, uncovering nuanced insights into graft survival outcomes. These clusters were further analyzed using Bayesian Cox regression, which confirmed significant survival outcome variations across the clusters, thereby validating the model’s effectiveness in enhancing risk stratification. The UK-DTOP tool offers a comprehensive decision-support system that significantly refines pre-transplant decision-making. The study’s findings advocate for the adoption of AI-enhanced tools in healthcare systems to optimize organ matching and transplant success, potentially guiding future developments in global transplant practices.

Utilizing artificial neural network system to predict the residual valve after endoscopic posterior urethral valve ablation.

To build, train, and assess the artificial neural network (ANN) system in estimatingthe residual valve rate after endoscopic valve ablationand compare the data obtained with conventional analysis. In a retrospective cross-sectional study between June 2010 and December 2020, 144 children with a history of posteriorurethral valve (PUV) who underwent endoscopic valve ablation were enrolled in the study. MATLAB software was used to design and train the network in a feed-forward backpropagationerror adjustment scheme. Preoperative and postoperative data from 101 patients (70%) (training set) were utilized to assessthe impact and relative significance of the necessity for repeatedablation. The validated suitably trained ANN was used to predict repeated ablation in the next 33 patients (22.9%) (test set)whose preoperative data were serially input into the system. To assess system accuracy in forecasting the requirement for repeatablation, projected values were compared to actual outcomes. The likelihood of predicting the residual valve was calculatedusing a three-layered backpropagating deep ANN using preoperativeand postoperative information. Of 144 operated cases, 33 (22.9%) had residual valvesand needs to repeated ablation. The ANN accuracy, sensitivity, and specificity for predicting the residual valve were 90.75%,92.73%, and 73.19%, respectively. Younger age at surgery, hyperechogenicity of the renal parenchyma, presence of vesicoureteralreflux (VUR), and grade of reflux before surgery were among the most significant characteristics that affectedpostoperative outcome variables, the need for repeated ablation, and were given the highest relative weight by the ANN system. Conclusions: The ANN is an integrated data-gathering tool for analyzing and finding relationships among variables as a complex non-linear statistical model. The results indicate that ANN is a valuable tool for outcome prediction of the residualvalveafter endoscopic valve ablation in patients with PUV.

New prognostic model for liver transplantation outcomes in hepatocellular carcinoma

Background. Liver transplantation remains a priority treatment option for hepatocellular carcinoma in the presence of liver cirrhosis; yet precise outcome prediction post-operation continues to be a complex challenge. Existing prognostic model often overlook patient age and donor type. Enhanced models that incorporate these parameters can improve prediction accuracy and treatment efficacy, which is critically important in the dynamically evolving field of transplantation.Objective. The aim of this study is to develop a prognostic model for liver transplantation outcomes in patients with hepatocellular carcinoma and liver cirrhosis.Material and methods. This retrospective study included 69 patients with hepatocellular carcinoma on the background of liver cirrhosis who underwent liver transplantation between May 2010 and December 2022. Of these, 42 patients (61%) received organs from living donors, and 27 (39%) from deceased donors. The study involved analysis of alpha-fetoprotein levels in blood, as well as assessment of radiological (maximum tumor nodule size, number of nodules) and histological parameters (maximum tumor nodule size, number of nodules, presence of vascular invasion). Cox regression model was used to predict recurrence-free survival, and the results for five-year recurrence-free survival, recipient age, and donor type were reused in the Cox model to predict overall survival.Results. Four models for predicting recurrence-free survival and overall survival based on histological and radiological data were developed, demonstrating high prognostic value with C-indexes on training/test data of 0.76/1; 0.73/1; 0.78/0.8; 0.6/0.8 respectively. All models showed recurrence-free survival prediction accuracy comparable to the Milan criteria. The model outcomes are available as a calculator on the website https://nadit.ru/calculate_HCC.Conclusion. The developed prognostic models are vital tools for personalized outcome prediction after liver transplantation for hepatocellular carcinoma. To enhance the accuracy of these models, further amalgamation and validation of data from various medical centers, as well as open scientific collaboration, are necessary.

341.5: Artificial intelligence assisted risk prediction in organ transplantation: A UK live-donor kidney transplant outcome prediction (UK-LTOP) tool.

341.5: Artificial intelligence assisted risk prediction in organ transplantation: A UK live-donor kidney transplant outcome prediction (UK-LTOP) tool.

300.5: Improved survival prediction for kidney transplant outcome prediction using artificial intelligence-based models: Development of a UK deceased donor kidney transplant outcome prediction (UK-DTOP) Tool.

300.5: Improved survival prediction for kidney transplant outcome prediction using artificial intelligence-based models: Development of a UK deceased donor kidney transplant outcome prediction (UK-DTOP) Tool.

Automated information extraction for behavioural interventions: evaluation and reflections on interdisciplinary AI development

Background The HBCP knowledge system identifies and extracts entities from randomised controlled trials of behaviour change interventions organised by a behaviour change intervention ontology (BCIO) to populate: 1) an outcome prediction tool; and 2) a research browser tool. This knowledge system requires automated information extraction algorithms to query and interpret evidence from behaviour change intervention (BCI) reports. This paper reports the results of an evaluation of the automated information extraction and reflects on the results in relation to the challenges of interdisciplinary working and collaboration. Methods The evaluation used a dataset of 117 previously unseen BCI reports to assess its performance. The automatically extracted information was compared to the full text PDF by trained annotators on essential BCIO entities required for the outcome prediction tool and research browser tool and whether the extracted information was assigned to the correct arm of the randomised trial. Essential entities were the outcome value, a selection of the most common Behaviour Change Techniques (BCTs), the mode of intervention delivery, and key population characteristics. Results The evaluation found an outcome value present in 53.85% (n=63) of the output from the information extraction system but it never extracted both the correct outcome values (interventions and control arms) and assigned them to the correct study arms (intervention and control). Although 84.62% (n=99) of the papers contained information relevant to Behaviour Change Techniques (BCTs), the information extraction algorithm correctly extracted only 58.59% (n=58) of BCTs. Conclusions The evaluation found that the information extraction algorithm did not extract the outcome values and key BCIO entities correctly against the correct arms in any of the papers in our sample, making it unsuitable for deployment in the outcome prediction and research browser tools. Several challenges with working in interdisciplinary teams were identified and discussed along with lessons learned for future work.

Using Machine Learning to Predict Outcomes Following Transfemoral Carotid Artery Stenting.

Transfemoral carotid artery stenting (TFCAS) carries important perioperative risks. Outcome prediction tools may help guide clinical decision-making but remain limited. We developed machine learning algorithms that predict 1-year stroke or death following TFCAS. The VQI (Vascular Quality Initiative) database was used to identify patients who underwent TFCAS for carotid artery stenosis between 2005 and 2024. We identified 112 features from the index hospitalization (82 preoperative [demographic/clinical], 13 intraoperative [procedural], and 17 postoperative [in-hospital course/complications]). The primary outcome was 1-year postprocedural stroke or death. The data were divided into training (70%) and test (30%) sets. Six machine learning models were trained using preoperative features with 10-fold cross-validation. The primary model evaluation metric was area under the receiver operating characteristic curve. The algorithm with the best performance was further trained using intra- and postoperative features. Model robustness was assessed using calibration plots and Brier scores. Overall, 35 214 patients underwent TFCAS during the study period and 3257 (9.2%) developed 1-year stroke or death. The best preoperative prediction model was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.93-0.95). In comparison, logistic regression had an AUROC of 0.65 (95% CI, 0.63-0.67). The extreme gradient boosting model maintained excellent performance at the intra- and postoperative stages, with area under the receiver operating characteristic curve values of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively. Calibration plots showed good agreement between predicted/observed event probabilities with Brier scores of 0.11 (preoperative), 0.11 (intraoperative), and 0.09 (postoperative). Machine learning can accurately predict 1-year stroke or death following TFCAS, performing better than logistic regression.

PanPIERS: A tool for risk prediction of adverse maternal outcomes for patients with pre-eclampsia using incomplete data

panPIERS: A tool for risk prediction of adverse maternal outcomes for patients with pre-eclampsia using incomplete data

Advancements in treatment strategies for periprosthetic joint infections: A comprehensive review

Periprosthetic joint infection (PJI) presents a critical challenge in orthopedic care, contributing to significant patient morbidity and healthcare costs. This burden is expected to increase secondary to growing demand for total joint arthroplasty (TJA). Despite the profound significance of PJI, there is currently no universally accepted “gold standard” diagnostic criteria using serum biomarker thresholds; latest criteria fail to differentiate acute infections from chronic or consider time since initial surgery. Furthermore, contemporary PJI treatment, which conventionally requires 2-stage revision surgery in conjunction with rigorous antibiotic treatment, can be particularly taxing on patients. Fortunately, recent years have seen marked evolution in both PJI diagnosis and treatment methods. Contemporary research supports time-dependent serum biomarker thresholds with greater sensitivity and specificity than previously reported, as well as alternative surgical options which may be more suitable for certain patients.The following narrative review aims to describe the significance and pathogenesis of PJI before characterizing current challenges, novel innovations, and the future landscape of PJI diagnosis and management. Here, we spotlight the emerging utility of novel biomarkers and metagenomic next-generation sequencing for diagnosis, advancements in patient-centered surgical outcome prediction tools for PJI risk assessment and prevention, and evolving surgical techniques including 1-stage and a “hybrid” 1.5-stage revision surgeries. Additionally, we explore cutting-edge therapeutic modalities including peptide and bacteriophage-based treatments, intraoperative anti-biofilm gel, the VT-X7 antibiotic pump, and promising immune-based interventions. Ultimately, these advancements hold the potential to revolutionize PJI management, offering hope for improved outcomes and reduced burdens on healthcare systems.

EVALUATION OF MATERNAL AND PERINATAL OUTCOME IN WOMEN WITH BORDERLINE AFI AND OLIGOHYDRAMNIOS IN THIRD TRIMESTER: A TERTIARY CARE HOSPITAL-BASED STUDY

Objectives: Objectives of our study were (1) to study and compare obstetric outcome in women with oligohydramnios, borderline amniotic fluid index (AFI), and normal AFI in terms of (a) type of labor (spontaneous/induced) and (b) mode of delivery-C-section or vaginal delivery and (2) to study and compare perinatal outcome in women with oligohydramnios, borderline AFI, and normal AFI in terms of (a) prematurity, (b) APGAR score at 1 and 5 min, (c) fetal distress, (d) low birth weight, (e) weight for gestational age, (f) neonatal intensive care unit (NICU) admission, (g) cause of NICU admission, and (h) neonatal deaths. Methods: This prospective and comparative study was conducted in Rajindra Hospital Patiala, over a period of 1 year. Women with ≥34 weeks POG were subjected to ultrasonography. They were then divided into following three groups of 50 women each depending upon AFI: Group A – oligohydramnios (AFI <5 cm), Group B – borderline AFI (AFI 5–8 cm), and Group C – normal AFI (AFI >8–25 cm). Patients were followed up to 40 weeks POG or till delivery occurred or decision for C-section was taken. Results: Perinatal outcome was adversely affected by decrease in AFI in terms of increase in rate of preterm delivery, small for gestational age babies, low birth weight babies, and neonatal deaths. Conclusion: Measurement of AFI is an important tool for prediction of adverse neonatal outcome

Percutaneous coronary intervention outcomes based on American College of Cardiology/American Heart Association coronary lesion classification over 14 years – Melbourne interventional group (MIG) registry

BackgroundThe American College of Cardiology / American Heart Association (ACC/AHA) introduced a coronary lesion classification in 1988 to stratify coronary lesions for probability of procedural success and complications after coronary angioplasty. Our aim is to assess the validity of the ACC/AHA lesion classification in predicting outcomes of percutaneous coronary intervention (PCI) in a contemporary cohort of patients. MethodsConsecutive PCI procedures performed between 2005 and 2018, were divided into three periods. At each period, the ACC/AHA lesion classification (A, B1, B2, C) was analysed with respect to procedural characteristics, in-hospital and 30-day outcomes, as well as long-term mortality by linkage to the National Death Index (NDI). ResultsIn total, 21,437 lesions were included with 7399 lesions (2005–2009), 6917 lesions (2010–2014) and 7121 lesions (2015–2018). There was a progressive increase in the number of complex lesions treated over time with ACC/AHA type C (15 %, 21 % and 26 %, p < 0.01). The rate of PCI procedural success decreased with increase in the complexity of lesions treated across all three periods (p < 0.01). Further, in-hospital and 30-day major adverse cardiovascular events (MACE), major adverse cardiac and cerebrovascular events (MACCE) increased across all three time periods (all p < 0.05). ConclusionsOur study validates the ACC/AHA lesion classification as a meaningful tool for prediction of PCI outcomes. Despite advances in PCI techniques and technology, complex lesion PCI defined by this classification continues to be associated with adverse outcomes.

Molecular characterization and biomarker identification in pediatric B-cell acute lymphoblastic leukemia.

6524 Background: B-cell acute lymphoblastic leukemia (B-ALL) is the most prevalent hematologic malignancy in children and a leading cause of mortality. Despite high cure rates, the management of B-ALL remains challenging due to its high heterogeneity and propensity for relapse. This study aimed to delineate molecular features of pediatric B-ALL and explore the clinical utility of circulating tumor DNA (ctDNA) as a biomarker in B-ALL. Methods: The study analyzed 146 primary pediatric B-ALL patients who were diagnosed from August 2020 to April 2023 and received systemic chemotherapy in Wuhan Children's Hospital. Baseline bone marrow (BM) and plasma samples were collected for next-generation sequencing (NGS) to profile the mutational landscape. BM samples collected on day 19 of the treatment were utilized for minimal residual disease (MRD) testing to assess treatment efficacy. Transcriptomic profiling of baseline BM samples was performed via bulk RNA sequencing. Fisher's exact test and the Wilcoxon rank sum test were utilized to compare categorical and continuous variables between groups, respectively. A two‐tailed P-value&lt;0.05 was considered statistically significant unless indicated otherwise. Results: Transcriptomic analysis revealed that 86.3% of patients (126 out of 146) could be categorized into 13 distinct molecular subtypes, with hyperdiploidy emerging as the predominant subtype. Baseline BM NGS identified gene fusions in 61% of patients, including 37 novel fusions previously unreported in B-ALL. Specifically, the KMT2A-TRIM29 novel fusion was detected and validated in a male child diagnosed with the KMT2A-rearranged subtype. Despite initially responding well to therapy, the patient experienced disease progression after a year, indicating a poor prognosis. We also found that elevated mutant counts and maximum-variant-allele-frequency (maxVAF) in baseline BM were associated with significantly poorer response to chemotherapy ( P=0.0012 and 0.028, respectively). Additionally, MRD-negative patients exhibited upregulated expression of immune-related pathways ( P&lt;0.01) and increased CD8+ T cell infiltration ( P=0.047), indicating a more active immune microenvironment in better responding tumors. Baseline plasma ctDNA, which exhibited high mutational concordance with paired baseline BM samples, also demonstrated significant associations with chemotherapy efficacy, highlighting its potential as a non-invasive tool for disease monitoring and treatment outcome prediction. Conclusions: This study elucidated novel gene fusions and potential biomarkers for treatment response in pediatric B-ALL. Importantly, both baseline plasma ctDNA and BM samples offer promising prognostic insights into chemotherapy responses, paving the way for non-invasive monitoring strategies in the management of pediatric B-ALL.

Incorporating a deep‐learning client outcome prediction tool as feedback in supported internet‐delivered cognitive behavioural therapy for depression and anxiety: A randomised controlled trial within routine clinical practice

AbstractIntroductionMachine learning techniques have been leveraged to predict client psychological treatment outcomes. Few studies, however, have tested whether providing such model predictions as feedback to therapists improves client outcomes. This randomised controlled trial examined (1) the effects of implementing therapist feedback via a deep‐learning model (DLM) tool that predicts client treatment response (i.e., reliable improvement on the Patient Health Questionnaire‐9 [PHQ‐9] or Generalized Anxiety Disorder‐7 [GAD‐7]) to internet‐delivered cognitive behavioural therapy (iCBT) in routine clinical care and (2) therapist acceptability of this prediction tool.MethodsFifty‐one therapists were randomly assigned to access the DLM tool (vs. treatment as usual [TAU]) and oversaw the care of 2394 clients who completed repeated PHQ‐9 and GAD‐7 assessments.ResultsMultilevel growth curve models revealed no overall differences between the DLM tool vs. TAU conditions in client clinical outcomes. However, clients of therapists with the DLM tool used more tools, completed more activities and visited more platform pages. In subgroup analyses, clients predicted to be ‘not‐on‐track’ were statistically significantly more likely to have reliable improvement on the PHQ‐9 in the DLM vs. TAU group. Therapists with access to the DLM tool reported that it was acceptable for use, they had positive attitudes towards it, and reported it prompted greater examination and discussion of clients, particularly those predicted not to improve.ConclusionAltogether, the DLM tool was acceptable for therapists, and clients engaged more with the platform, with clinical benefits specific to reliable improvement on the PHQ‐9 for not‐on‐track clients. Future applications and considerations for implementing machine learning predictions as feedback tools within iCBT are discussed.

Can 3D Multiparametric Ultrasound Imaging Predict Prostate Biopsy Outcome?

ObjectivesTo assess the value of 3D multiparametric ultrasound imaging, combining hemodynamic and tissue stiffness quantifications by machine learning, for the prediction of prostate biopsy outcomes. MethodsAfter signing informed consent, 54 biopsy-naïve patients underwent a 3D dynamic contrast-enhanced ultrasound (DCE-US) recording, a multi-plane 2D shear-wave elastography (SWE) scan with manual sweeping from base to apex of the prostate, and received 12-core systematic biopsies (SBx). 3D maps of 18 hemodynamic parameters were extracted from the 3D DCE-US quantification and a 3D SWE elasticity map was reconstructed based on the multi-plane 2D SWE acquisitions. Subsequently, all the 3D maps were segmented and subdivided into 12 regions corresponding to the SBx locations. Per region, the set of 19 computed parameters was further extended by derivation of eight radiomic features per parameter. Based on this feature set, a multiparametric ultrasound approach was implemented using five different classifiers together with a sequential floating forward selection method and hyperparameter tuning. The classification accuracy with respect to the biopsy reference was assessed by a group-k-fold cross-validation procedure, and the performance was evaluated by the Area Under the Receiver Operating Characteristics Curve (AUC). ResultsOf the 54 patients, 20 were found with clinically significant prostate cancer (csPCa) based on SBx. The 18 hemodynamic parameters showed mean AUC values varying from 0.63 to 0.75, and SWE elasticity showed an AUC of 0.66. The multiparametric approach using radiomic features derived from hemodynamic parameters only produced an AUC of 0.81, while the combination of hemodynamic and tissue-stiffness quantifications yielded a significantly improved AUC of 0.85 for csPCa detection (p-value < 0.05) using the Gradient Boosting classifier. ConclusionsOur results suggest 3D multiparametric ultrasound imaging combining hemodynamic and tissue-stiffness features to represent a promising diagnostic tool for biopsy outcome prediction, aiding in csPCa localization.

Validation of MELD 3.0 in patients with alcoholic liver cirrhosis using prospective KACLiF cohort.

The Model for End-Stage Liver Disease (MELD) is a reliable prognostic tool for short-term outcome prediction in patients with end-stage liver disease. MELD 3.0 was introduced to enhance the predictive accuracy. This study assessed the performance of MELD 3.0, in comparison to MELD and MELD-Na, in patients with alcoholic liver cirrhosis. This multicenter prospective cohort study comprised patients with alcoholic cirrhosis admitted for acute deterioration of liver function in the Republic of Korea between 2015 and 2019. This study compared the predictive abilities of MELD, MELD-Na, and MELD 3.0, for 30-day and 90-day outcomes, specifically death or liver transplantation, and explored the factors influencing these outcomes. A total of 1096 patients were included in the study, with a mean age of 53.3±10.4years, and 82.0% were male. The mean scores for MELD, MELD-Na, and MELD 3.0 at the time of admission were 18.7±7.2, 20.6±7.7, and 21.0±7.8, respectively. At 30 and 90days, 7.2% and 14.1% of patients experienced mortality or liver transplantation. The areas under the receiver operating characteristic curves for MELD, MELD-Na, and MELD 3.0 at 30days were 0.823, 0.820, and 0.828; and at 90days were 0.765, 0.772, and 0.776, respectively. Factors associated with the 90-day outcome included concomitant chronic viral hepatitis, prolonged prothrombin time, elevated levels of aspartate transaminase, bilirubin, and creatinine, and low albumin levels. MELD 3.0 demonstrated improved performance compared to previous models, although the differences were not statistically significant.

Predicting Outcomes Following Lower Extremity Endovascular Revascularization Using Machine Learning.

Lower extremity endovascular revascularization for peripheral artery disease carries nonnegligible perioperative risks; however, outcome prediction tools remain limited. Using machine learning, we developed automated algorithms that predict 30-day outcomes following lower extremity endovascular revascularization. The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity endovascular revascularization (angioplasty, stent, or atherectomy) for peripheral artery disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day postprocedural major adverse limb event (composite of major reintervention, untreated loss of patency, or major amputation) or death. Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Overall, 21 886 patients were included, and 30-day major adverse limb event/death occurred in 1964 (9.0%) individuals. The best performing model for predicting 30-day major adverse limb event/death was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.94). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.70-0.74). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.09. The top 3 predictive features in our algorithm were (1) chronic limb-threatening ischemia, (2) tibial intervention, and (3) congestive heart failure. Our machine learning models accurately predict 30-day outcomes following lower extremity endovascular revascularization using preoperative data with good discrimination and calibration. Prospective validation is warranted to assess for generalizability and external validity.

EEG connectivity and network analyses predict outcome in patients with disorders of consciousness – A systematic review and meta-analysis

Outcome prediction in prolonged disorders of consciousness (DOC) remains challenging. This can result in either inappropriate withdrawal of treatment or unnecessary prolongation of treatment. Electroencephalography (EEG) is a cheap, portable, and non-invasive device with various opportunities for complex signal analysis. Computational EEG measures, such as EEG connectivity and network metrics, might be ideal candidates for the investigation of DOC, but their capacity in prognostication is still undisclosed. We conducted a meta-analysis aiming to compare the prognostic power of the widely used clinical scale, Coma Recovery Scale-Revised - CRS-R and EEG connectivity and network metrics. We found that the prognostic power of the CRS-R scale was moderate (AUC: 0.67 (0.60–0.75)), but EEG connectivity and network metrics predicted outcome with significantly (p = 0.0071) higher accuracy (AUC:0.78 (0.70–0.86)). We also estimated the prognostic capacity of EEG spectral power, which was not significantly (p = 0.3943) inferior to that of the EEG connectivity and graph-theory measures (AUC:0.75 (0.70–0.80)). Multivariate automated outcome prediction tools seemed to outperform clinical and EEG markers.

Therapeutic Drug Monitoring as a Tool for the Clinical Outcome Prediction in Vedolizumab-Treated Patients: An Italian Pilot Study.

Over the years, vedolizumab (VDZ) has emerged as a more effective target therapy for inflammatory bowel disease. The aim of this work was to analyze a cohort of inflammatory bowel disease patients, evaluating the association between VDZ serum concentrations at 6 months from starting therapy and their clinical and biochemical indexes within one year of treatment, correlating drug levels with response and clinical remission. Forty patients treated with VDZ were enrolled. Drug concentrations were quantified through ELISA methods. VDZ levels correlated with hemoglobin levels at twelve months of therapy (p = 0.03) and with clinical remission at twelve months of therapy (p = 0.03); patients who reached clinical remission showed higher VDZ concentrations. A VDZ cut-off value of 43.1 μg/mL was suggested, predicting clinical remission at twelve months of therapy. A statistically significant association between VDZ levels at T6 and calprotectin <250 μg/g at T12 was found (p = 0.04). Furthermore, the optimal threshold value of VDZ levels at T6 associated with calprotectin <250 μg/g at T12 was identified: through levels higher than 45.2 µg/mL, we were able to predict remission one year after therapy. In the final regression multivariate model, no factor was retained as a predictor of clinical remission at one year of treatment. In conclusion, this is the first pilot study reporting a possible VDZ serum cut-off value able to predict not only the clinical remission at twelve months of therapy but also the calprotectin level, which is very important, as it is a surrogate marker of mucosal healing.

Development and validation of an intrinsic capacity score in the UK Biobank study

BackgroundIn 2015, the World Health Organization introduced the concept of intrinsic capacity (IC) to define the individual-level characteristics that enable an older person to be and do the things they value. This study developed an intrinsic capacity score for UK Biobank study participants and validated its use as a tool for health outcome prediction, understanding healthy aging trajectories, and genetic research. MethodsOur analysis included data from 45,208 UK biobank participants who had a complete record of the ten variables included in the analysis. Factor adequacy was tested using Kaiser–Meyer–Olkin, Barthelt's, and the determinant of matrix tests, and the number of factors was determined by the parallel analysis method. Exploratory and confirmatory factor analyses were employed to determine the structure and dimensionality of indicators. Finally, the intrinsic capacity score was generated, and its construct and predictive validities as well as reliability were assessed. ResultsThe factor analysis identified a multidimensional construct comprising one general factor (intrinsic capacity) and five specific factors (locomotor, vitality, cognitive, psychological, and sensory). The bifactor structure showed a better fit (comparative fit index = 0.995, Tucker Lewis index = 0.976, root mean square error of approximation = 0.025, root mean square residual = 0.009) than the conventional five-factor structure. The intrinsic capacity score generated using the bifactor confirmatory factor analysis has good construct validity, as demonstrated by an inverse association with age (lower intrinsic capacity in older age; (β) =−0.035 (95%CI: −0.036, −0.034)), frailty (lower intrinsic capacity score in prefrail participants, β = −0.104 (95%CI: (−0.114, −0.094)) and frail participants, β = −0.227 (95%CI: −0.267, −0.186) than robust participants), and comorbidity (a lower intrinsic capacity score associated with increased Charlson's comorbidity index, β =−0.019 (95%CI: −0.022, −0.015)). The intrinsic capacity score also predicted comorbidity (a one-unit increase in baseline intrinsic capacity score led to a lower Charlson's comorbidity index, β = 0.147 (95%CI: −0.173, −0.121)) and mortality (a one-unit increase in baseline intrinsic capacity score led to 25 % lower risk of death, odds ratio = 0.75(95%CI: 0.663, 0.848)). ConclusionThe bifactor structure showed a better fit in all goodness of fit tests. The intrinsic capacity construct has strong structural, construct, and predictive validities and is a promising tool for monitoring aging trajectories.

Machine Learning to Predict Outcomes of Endovascular Intervention for Patients With PAD

Endovascular intervention for peripheral artery disease (PAD) carries nonnegligible perioperative risks; however, outcome prediction tools are limited. To develop machine learning (ML) algorithms that can predict outcomes following endovascular intervention for PAD. This prognostic study included patients who underwent endovascular intervention for PAD between January 1, 2004, and July 5, 2023, with 1 year of follow-up. Data were obtained from the Vascular Quality Initiative (VQI), a multicenter registry containing data from vascular surgeons and interventionalists at more than 1000 academic and community hospitals. From an initial cohort of 262 242 patients, 26 565 were excluded due to treatment for acute limb ischemia (n = 14 642) or aneurysmal disease (n = 3456), unreported symptom status (n = 4401) or procedure type (n = 2319), or concurrent bypass (n = 1747). Data were split into training (70%) and test (30%) sets. A total of 112 predictive features (75 preoperative [demographic and clinical], 24 intraoperative [procedural], and 13 postoperative [in-hospital course and complications]) from the index hospitalization were identified. Using 10-fold cross-validation, 6 ML models were trained using preoperative features to predict 1-year major adverse limb event (MALE; composite of thrombectomy or thrombolysis, surgical reintervention, or major amputation) or death. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). After selecting the best performing algorithm, additional models were built using intraoperative and postoperative data. Overall, 235 677 patients who underwent endovascular intervention for PAD were included (mean [SD] age, 68.4 [11.1] years; 94 979 [40.3%] female) and 71 683 (30.4%) developed 1-year MALE or death. The best preoperative prediction model was extreme gradient boosting (XGBoost), achieving the following performance metrics: AUROC, 0.94 (95% CI, 0.93-0.95); accuracy, 0.86 (95% CI, 0.85-0.87); sensitivity, 0.87; specificity, 0.85; positive predictive value, 0.85; and negative predictive value, 0.87. In comparison, logistic regression had an AUROC of 0.67 (95% CI, 0.65-0.69). The XGBoost model maintained excellent performance at the intraoperative and postoperative stages, with AUROCs of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively. In this prognostic study, ML models were developed that accurately predicted outcomes following endovascular intervention for PAD, which performed better than logistic regression. These algorithms have potential for important utility in guiding perioperative risk-mitigation strategies to prevent adverse outcomes following endovascular intervention for PAD.