Area Under The Receiver Operating Characteristic Research Articles

In-hospital mortality, readmission, and prolonged length of stay risk prediction leveraging historical electronic patient records.

This study aimed to investigate the predictive capabilities of historical patient records to predict patient adverse outcomes such as mortality, readmission, and prolonged length of stay (PLOS). Leveraging a de-identified dataset from a tertiary care university hospital, we developed an eXplainable Artificial Intelligence (XAI) framework combining tree-based and traditional machine learning (ML) models with interpretations and statistical analysis of predictors of mortality, readmission, and PLOS. Our framework demonstrated exceptional predictive performance with a notable area under the receiver operating characteristic (AUROC) of 0.9625 and an area under the precision-recall curve (AUPRC) of 0.8575 for 30-day mortality at discharge and an AUROC of 0.9545 and AUPRC of 0.8419 at admission. For the readmission and PLOS risk, the highest AUROC achieved were 0.8198 and 0.9797, respectively. The tree-based models consistently outperformed the traditional ML models in all 4 prediction tasks. The key predictors were age, derived temporal features, routine laboratory tests, and diagnostic and procedural codes. The study underscores the potential of leveraging medical history for enhanced hospital predictive analytics. We present an accurate and intuitive framework for early warning models that can be easily implemented in the current and developing digital health platforms to predict adverse outcomes accurately.

Identifying clinical and proteomic markers for early diagnosis and prognosis prediction of major psychiatric disorders

BackgroundTo clarify if blood proteins can predict disease progression among individuals at clinical high-risk of severe mental illness (CHR-SMI), we developed a statistical model incorporating clinical and blood protein markers to distinguish the transition group (who developed severe mental illness) (CHR-SMI-T) and from non-transition group (CHR-SMI-NT) at baseline. MethodsNinety individuals (74 at CHR-SMI: 16 patients) were monitored for ≤4 years and were the focus of predictive models. Three predictive models (1 [100 clinical variables], 2 [158 peptides], and 3 [100 clinical variables +158 peptides]) were evaluated using area under the receiver operating characteristic (AUROC) values. Clinical and protein feature patterns were evaluated by linear mixed-effect analysis within the model at 12 and 24 months among patients who did (CHR-SMI-T) and did not transition (CHR-SMI-NT) and the entire group. ResultEighteen CHR-SMI individuals with major psychiatric disorders (first episode psychosis: 2; bipolar II disorder: 13; major depressive disorder; 3) developed disorders over an average of 17.7 months. The combined model showed the highest discriminatory performance (AUROC = 0.73). Cytosolic malate dehydrogenase and transgelin-2 levels were lower in the CHR-SMI-T than the CHR-SMI-NT group. Complement component C9, inter-alpha-trypsin inhibitor heavy chain H4, von Willebrand factor, and C-reactive protein were lower in the patient than the CHR-SMI-NT group. These differences were non-significant after FDR adjustment. LimitationsSmall sample, no control for medication use. ConclusionThis exploratory study identified clinical and proteomic markers that might predict severe mental illness early onset, which could aid in early detection and intervention. Future studies with larger samples and controlled variables are needed to validate these findings.

Ultrasound normalized local variance to assess metabolic dysfunction-associated steatotic liver disease

PurposeIncreased prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) highlights a desire for screening with liver ultrasound normalized local variance (NLV). We aimed to assess variations in NLV values measured at different sampling depths and discuss common technical considerations in measuring liver NLV. MethodsWe retrospectively measured liver NLVs at variable depths on ultrasound images pre-recorded in 116 participants who underwent liver magnetic resonance imaging-proton density fat fraction (MRI-PDFF) and ultrasound to screen for MASLD. Liver NLVs were measured and differences at variable depths were tested using one-way analysis of variance (ANOVA) and multiple paired comparisons using post hoc Tukey honestly significant difference (HSD), Scheffé, Bonferroni, and Holm multiple comparisons. Diagnostic performance of NLV values were analyzed by area under the receiver operating characteristics (AUROC) curve. ResultsThe NLV measured at a depth of 10 cm significantly differed from those measured near the liver capsule and at depths of 6 cm and 8 cm (p < 0.001) from the skin. There was no significant difference in NLV value in other paired groups (p > 0.05). The difference in the area under AUROCs for NLVs measured at variable depths was not significant (p > 0.05). ConclusionsThe best diagnostic performance of liver NLV was measured at depth of 8 cm from the skin, although NLV measured at variable depth showed similar diagnostic performance for assessing ≥ mild hepatic steatosis. The study results provide a reference that can be used in the development of standardized scanning protocols and technical considerations in measuring liver NLV.

The Trial Enrollment Diversity Dashboard for Acute Leukemia Clinical Research: Intervention Development and Cohort Analysis.

Participation in acute leukemia clinical trials is inequitable across multiple sociodemographic categories. Tools that provide researchers with performance feedback on the representativeness of the patients they enroll are limited. We aimed to develop an electronic health record (EHR)-based dashboard to provide such feedback and to describe any enrollment inequities uncovered. We created a visual dashboard linking leukemia clinical trial registration and EHR data at the Dana-Farber Cancer Institute. Accuracy of a patient inclusion and assignment algorithm was tested with a target area under the receiver-operator curve (AUROC) of >0.90 against manual review. Demographic metric identification, visualization construction, and dashboard refinement were performed through stakeholder cognitive testing. Analysis of a recent 5-year cohort generated by the final algorithm assessed bivariate associations between enrollment and demographic metrics. Multivariable logistic regression included significant bivariate results. The final algorithm assignment AUROC was 0.98. Metrics were identified and visualizations successfully constructed. Fourteen individuals participated in testing and identified areas for revision: category mergers, denominator filters, and data delivery preferences. In the initial cohort of 1,315 patients, 1,020 (77.6%) had enrolled in any study protocol: 553 (42.1%) in a treatment trial and 936 (71.2%) in a biobanking study. In a multivariable model, older age (odds ratio [OR], 0.83 [95% CI, 0.73 to 0.94]) and Non-Hispanic Black race-ethnicity (OR, 0.38 [95% CI, 0.18 to 0.82]) were associated with lower enrollment, and English primary language with higher enrollment (OR, 2.50 [95% CI, 1.30 to 4.79]). We developed a research participation equity performance feedback dashboard for clinical researchers, and we identified actionable inequities. Next steps include feasibility and efficacy testing as well as implementation.

Adverse Drug Reactions in an Ageing PopulaTion risk Prediction (ADAPTiP) tool: development of a prediction model related to hospital admissions

Abstract Background Older patients are at an increased risk of developing adverse drug reactions (ADRs). The aim of this study was to develop a risk prediction model (ADAPTiP) for ADR-related hospital admissions in older populations, based on predictors available at the time of hospital admission. Methods Using the Adverse Drg reactions in an Ageing PopulaTion (ADAPT) cohort (N=798; 361 ADR-related admissions; 437 non-ADR-related admissions), a cross-sectional and prospective cohort study designed to examine the prevalence of and risk factors for ADR-related hospital admissions in patients aged ≥ 65 years, twenty predictors (categorised as sociodemographic-related, functional ability-related, disease-related and medication-related) were considered in the development of the model. A multivariable logistic regression model was developed using statistically significant univariate associations and/or clinically relevant predictors to estimate adjusted odds ratios and 95% confidence intervals (CI). Calibration and discriminative performance of the model was assessed by the Hosmer-Lemeshow test and by calculating the area under the receiver operator characteristic (AUROC) curve. Results The multivariable model (ADAPTiP) included ten predictors; age, frailty, chronic lung disease, antithrombotic agents, diuretics, renin angiotensin aldosterone system (RAAS) drug classes, primary presenting complaints of respiratory, bleeding, gastrointestinal disorders and syncope on hospital admission. Antithrombotic agents, diuretics and RAAS drug classes and the primary presenting complaints of bleeding disorders, gastrointestinal disorders and syncope and frailty were significantly associated with an ADR-related hospital admission. Whereas, increasing age and presence of chronic lung disease were significantly associated with having a non-ADR-related hospital admission. The AUROC was 0.78 [95%CI:0.75;0.81] with sensitivity and specificity values of 59% and 83%, respectively. Conclusion ADAPTiP has the potential for use as a risk prediction model for ADR-related hospital admissions. Future research will validate this model in other settings.

The Silent Threat: A Retrospective Cohort Study on the Impact of Prediabetes on ST-Elevation Myocardial Infarction Survival-A Call to Action!

Background: Prediabetes is frequently underdiagnosed and undertreated, yet it poses significant cardiovascular risks. This study investigates the impact of prediabetes on short- and long-term survival outcomes in patients who experienced ST-elevation myocardial infarction (STEMI). Methods: In this retrospective, single-center cohort study, we evaluated 725 STEMI patients stratified into non-diabetic, prediabetic, and diabetic groups based on HbA1c levels at presentation. A Kaplan-Meier survival analysis was employed to compare long-term outcomes over a three-year follow-up period. Cardiovascular risk factors, including hypertension and dyslipidemia, were analyzed across the groups. The discriminatory power of HbA1c for predicting all-cause mortality was assessed using an Area Under the Receiver Operating Characteristic (AUROC) analysis. Results: Of the 725 patients, 407 (56.1%) were non-diabetic, 184 (25.4%) were prediabetic, and 134 (18.5%) were diabetic. Prediabetic patients exhibited significant additional cardiovascular risk factors, such as arterial hypertension (67.4%) and dyslipidemia (78.3%), with prevalence rates between those of non-diabetic and diabetic patients. The Kaplan-Meier analysis revealed that at a three-year follow-up, prediabetic patients faced a survival disadvantage, with a significant decrease in survival rates compared to non-diabetic patients (log-rank p = 0.016); their survival outcomes approached those of diabetic patients (p = 0.125). The AUROC analysis demonstrated that HbA1c was a significant predictor of short- and long-term mortality, with a cut-off value of 5.75% and an Area Under the Curve (AUC) of 0.580-0.617 (95% CI: 0.458-0.721), indicating a moderate ability to predict survival in patients with STEMI. Conclusions: Prediabetes significantly worsens survival outcomes following STEMI, nearly approaching the risk level of diabetes. Integrating rigorous cardiovascular risk management strategies for prediabetic individuals, including lifestyle interventions and potentially pharmacological treatments, could prevent the progression to diabetes and mitigate associated cardiovascular risks.

Pentraxin-3 (PTX-3) as a potential biomarker for predicting death in hospitalized patients with COVID-19

BackgroundPentraxin 3 (PTX3) is an acute-phase protein that belongs to the pentraxin family, which plays an important role in the body’s defense against pathogens. PTX3 levels have been associated with inflammatory processes, and it is a possible biomarker for the diagnosis and prognosis of different infectious diseases, including COVID-19. The objective of this study was to analyze the potential of PTX3 as a plasma biomarker for predicting death in patients hospitalized with COVID-19.MethodsThe study included a total of 312 patients with COVID-19, admitted from July 2020 to August 2021 to hospital ward and intensive care unit beds at two hospitals in the Northeast Region of Brazil. PTX3 was measured using ELISA in samples collected within 24 h after hospital admission. Maximally selected rank statistics were used to determine the PTX3 cutoff point that best distinguished patients who died from those who survived. A receiver operating characteristic (ROC) curve was used to determine the performance of the biomarker. Survival analysis was performed using a Kaplan-Meier curve, and a Cox regression model was used to determine predictors associated with death.ResultsOf the 312 patients included in the study, 233 recovered and 79 died. Patients who died had higher PTX3 levels at the time of admission, when compared to those who recovered (median: 52.84 versus 10.79 ng/mL; p < 0.001). PTX3 showed area under the ROC (AUC) = 0.834, higher than other markers used in clinical practice, such as C-reactive protein (AUC = 0.72) and D-dimer (AUC = 0.77). Furthermore, according to the Kaplan-Meier survival curve, patients with PTX3 concentrations above the cutoff point (27.3 ng/mL) had a lower survival rate (p = 0.014). In multivariate Cox regression, PTX3 > 27.3 ng/mL was an important predictor of death, regardless of other confounding factors (hazard ratio = 1.79; p = 0.027).ConclusionPTX3 can be considered as a potential biomarker for predicting death in patients hospitalized with COVID-19.

VesiMCNN: Using pre-trained protein language models and multiple window scanning convolutional neural networks to identify vesicular transport proteins

Vesicular transport is a critical cellular process responsible for the proper organization and functioning of eukaryotic cells. This mechanism relies on specialized vesicles that shuttle macromolecules, such as proteins, across the cellular landscape, a process pivotal to maintaining cellular homeostasis. Disruptions in vesicular transport have been linked to various disease mechanisms, including cancer and neurodegenerative disorders.In this study, we present vesiMCNN, a novel computational approach that integrates pre-trained protein language models with a multi-window scanning convolutional neural network architecture to accurately identify vesicular transport proteins. To the best of our knowledge, this is the first study to leverage the power of pre-trained language models in combination with the multi-window scanning technique for this task. Our method achieved a Matthews Correlation Coefficient (MCC) of 0.558 and an Area Under the Receiver Operating Characteristic (AUC-ROC) of 0.933, outperforming existing state-of-the-art approaches. Additionally, we have curated a comprehensive benchmark dataset for the study of vesicular transport proteins, which can facilitate further research in this field. The remarkable performance of our model, combined with the comprehensive dataset and novel deep learning model, marks a significant advancement in the field of vesicular transport protein research.

A data-driven approach for predicting cash flow performance of public owners in building projects: insights from Turkish cases

PurposeThe cash flow from government agencies to contractors, called progress payment, is a critical step in public projects. The delays in progress payments significantly affect the project performance of contractors and lead to conflicts between two parties in the Turkish construction industry. Although some previous studies focused on the issues in internal cash flows (e.g. inflows and outflows) of construction companies, the context of cash flows from public agencies to contractors in public projects is still unclear. Therefore, the primary objective of this study is to develop and test diverse machine learning-based predictive models on the progress payment performance of Turkish public agencies and improve the predictive performance of these models with two different optimization algorithms (e.g. first-order and second-order). In addition, this study explored the attributes that make the most significant contribution to predicting the payment performance of Turkish public agencies.Design/methodology/approachIn total, project information of 2,319 building projects tendered by the Turkish public agencies was collected. Six different machine learning algorithms were developed and two different optimization methods were applied to achieve the best machine learning (ML) model for Turkish public agencies' cash flow performance in this study. The current research tested the effectiveness of each optimization algorithm for each ML model developed. In addition, the effect size achieved in the ML models was evaluated and ranked for each attribute, so that it is possible to observe which attributes make significant contributions to predicting the cash flow performance of Turkish public agencies.FindingsThe results show that the attributes “inflation rate” (F5; 11.2%), “consumer price index” (F6; 10.55%) and “total project duration” (T1; 10.9%) are the most significant factors affecting the progress payment performance of government agencies. While decision tree (DT) shows the best performance among ML models before optimization process, the prediction performance of models support vector machine (SVM) and genetic algorithm (GA) has been significantly improved by Broyden–Fletcher–Goldfarb–Shanno (BFGS)-based Quasi-Newton optimization algorithm by 14.3% and 18.65%, respectively, based on accuracy, AUROC (Area Under the Receiver Operating Characteristics) and F1 values.Practical implicationsThe most effective ML model can be used and integrated into proactive systems in real Turkish public construction projects, which provides management of cash flow issues from public agencies to contractors and reduces conflicts between two parties.Originality/valueThe development and comparison of various predictive ML models on the progress payment performance of Turkish public owners in construction projects will be the first empirical attempt in the body of knowledge. This study has been carried out by using a high number of project information with diverse 27 attributes, which distinguishes this study in the body of knowledge. For the optimization process, a new hyper parameter tuning strategy, the Bayesian technique, was adopted for two different optimization methods. Thus, it is available to find the best predictive model to be integrated into real proactive systems in forecasting the cash flow performance of Turkish public agencies in public works projects. This study will also make novel contributions to the body of knowledge in understanding the key parameters that have a negative impact on the payment progress of public agencies.

External validation of the preHEART score and comparison with current clinical risk scores for prehospital risk assessment in patients with suspected NSTE-ACS

BackgroundEmergency Medical Services (EMS) studies have shown that prehospital risk stratification and triage decisions in patients with suspected non-ST-elevation acute coronary syndrome (NSTE-ACS) can be improved using clinical risk scores...

Development of a Surgery-Specific Comorbidity Score for Use in Administrative Data.

To create a novel comorbidity score tailored for surgical database research. Despite their use in surgical research, the Elixhauser (ECI) and Charlson Comorbidity Indices (CCI) were developed nearly four decades ago utilizing primarily non-surgical cohorts. Adults undergoing 62 operations across 14 specialties were queried from the 2019 National Inpatient Sample (NIS) using International Classification of Diseases, 10th Revision (ICD-10) codes. ICD-10 codes for chronic diseases were sorted into Clinical Classifications Software Refined (CCSR) groups. CCSR with non-zero feature importance across four machine learning algorithms predicting in-hospital mortality were used for logistic regression; resultant coefficients were used to calculate the Comorbid Operative Risk Evaluation (CORE) score based on previously validated methodology. Areas under the receiver operating characteristic (AUROC) with 95% Confidence Intervals (CI) were used to compare model performance in predicting in-hospital mortality for the CORE score, ECI, and CCI. Validation was performed using the 2016-2018 NIS, combined 2018-2019 Florida and New York State Inpatient Databases (SID), and 2016-2022 institutional data. 699,155 records from the 2019 NIS were used for model development. The CORE score better predicted in-hospital mortality compared to the ECI within the NIS (0.90, 95%CI:0.90-0.90 vs. 0.84, 95%CI:0.84-0.84), SID (0.91, 95%CI:0.90-0.91 vs. 0.86, 95%CI:0.86-0.87), and institutional (0.88, 95%CI:0.87-0.89 vs. 0.84, 95%CI:0.83-0.85) databases (all P<0.001). Likewise, it outperformed the CCI for the NIS (0.76, 95%CI:0.76-0.76), SID (0.78, 95%CI:0.77-0.78), and institutional (0.62, 95%CI:0.60-0.64) cohorts (all P<0.001). The CORE score may better predict in-hospital mortality after surgery due to comorbid diseases in outcome-based research.

Novel Quantitative Liver Steatosis Assessment Method With Ultrasound Harmonic Imaging.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most prevalent liver disorder in Western countries, with approximately 20%-30% of the MASLD patients progressing to severe stages. There is an urgent need for noninvasive, cost-effective, widely accessible, and precise biomarkers to evaluate liver steatosis. This study aims to assess and compare the diagnostic performance of a novel reference frequency method-based ultrasound attenuation coefficient estimation (ACE) in both fundamental (RFM-ACE-FI) and harmonic (RFM-ACE-HI) imaging for detecting and grading liver steatosis. An Institutional Review Board-approved prospective study was carried out between December 2018 and October 2022. A total number of 130 subjects were enrolled in the study. The correlation between RFM-ACE-HI values and magnetic resonance imaging proton density fat fraction (MRI-PDFF), as well as between RFM-ACE-FI values and MRI-PDFF were calculated. The diagnostic performance of RFM-ACE-FI and RFM-ACE-HI was evaluated using receiver operating characteristic (ROC) curve analysis, as compared to MRI-PDFF. The reproducibility of RFM-ACE-HI was assessed by interobserver agreement between two sonographers. A strong correlation was observed between RFM-ACE-HI and MRI-PDFF, with R = 0.88 (95% confidence interval [CI]: 0.83-0.92; P < .001), while the correlation between RFM-ACE-FI and MRI-PDFF was R = 0.65 (95% CI: 0.50-0.76; P < .001). The area under the ROC (AUROC) curve for RFM-ACE-HI in staging liver steatosis grades of S ≥ 1 and S ≥ 2 was 0.97 (95% CI: 0.91-0.99; P < .001) and 0.98 (95% CI: 0.93-1.00; P < .001), respectively, and 0.76 (95% CI: 0.65-0.85) and 0.80 (95% CI: 0.70-0.88) for RFM-ACE-FI, respectively. Great reproducibility was achieved for RFM-ACE-HI, with an interobserver agreement of R = 0.97 (95% CI: 0.94-0.99; P < .001). The novel RFM-ACE-HI method offered high liver steatosis diagnostic accuracy and reproducibility, which has important clinical implications for early disease intervention and treatment evaluation.

Crowd-sourced machine learning prediction of long COVID using data from the National COVID Cohort Collaborative

BackgroundWhile many patients seem to recover from SARS-CoV-2 infections, many patients report experiencing SARS-CoV-2 symptoms for weeks or months after their acute COVID-19 ends, even developing new symptoms weeks after infection. These long-term effects are called post-acute sequelae of SARS-CoV-2 (PASC) or, more commonly, Long COVID. The overall prevalence of Long COVID is currently unknown, and tools are needed to help identify patients at risk for developing long COVID. MethodsA working group of the Rapid Acceleration of Diagnostics-radical (RADx-rad) program, comprised of individuals from various NIH institutes and centers, in collaboration with REsearching COVID to Enhance Recovery (RECOVER) developed and organized the Long COVID Computational Challenge (L3C), a community challenge aimed at incentivizing the broader scientific community to develop interpretable and accurate methods for identifying patients at risk of developing Long COVID. From August 2022 to December 2022, participants developed Long COVID risk prediction algorithms using the National COVID Cohort Collaborative (N3C) data enclave, a harmonized data repository from over 75 healthcare institutions from across the United States (U.S.). FindingsOver the course of the challenge, 74 teams designed and built 35 Long COVID prediction models using the N3C data enclave. The top 10 teams all scored above a 0.80 Area Under the Receiver Operator Curve (AUROC) with the highest scoring model achieving a mean AUROC of 0.895. Included in the top submission was a visualization dashboard that built timelines for each patient, updating the risk of a patient developing Long COVID in response to clinical events. InterpretationAs a result of L3C, federal reviewers identified multiple machine learning models that can be used to identify patients at risk for developing Long COVID. Many of the teams used approaches in their submissions which can be applied to future clinical prediction questions. FundingResearch reported in this RADx® Rad publication was supported by the National Institutes of Health. Timothy Bergquist, Johanna Loomba, and Emily Pfaff were supported by Axle Subcontract: NCATS-STSS-P00438.

Retrieval-Augmented Generation for Extracting CHA2DS2-VASc Risk Factors from Unstructured Clinical Notes in Patients with Atrial Fibrillation.

Assessment of stroke risk in patients with atrial fibrillation (AF) is crucial for guiding anticoagulation therapy. CHA2DS2-VASc is a widely used score for defining this risk, but current assessments rely on manual calculation by clinicians or approximations from structured EHR data elements. Unstructured clinical notes contain rich information that could enhance risk assessment. We developed and validated a Retrieval-Augmented Generation (RAG) approach to extract CHA2DS2-VASc risk factors from unstructured notes in patients with AF. We employed a RAG architecture paired with the large language model, Llama3.1, to extract features relevant to CHA2DS2-VASc scores from unstructured notes. The model was deployed on a random set of 1,000 clinical notes (934 AF patients) from Yale New Haven Health System (YNHHS). To establish a gold standard, 2 clinicians manually reviewed and labeled CHA2DS2-VASc risk factors in a random subset of 200 notes. The CHA2DS2-VASc scores were calculated for each patient using structured data alone and by incorporating risk factors identified with RAG. We assessed performance across risk factors using macro-averaged area under the receiver operating characteristic (AUROC). For external validation, we utilized 100 manually labeled clinical notes from the MIMIC-IV database. The RAG model demonstrated robust performance in extracting risk factors from clinical notes. In the 1000 clinical notes, RAG identified several risk factors more frequently than structured elements, including hypertension (82.4% vs 26.2%), stroke/TIA (62.9% vs 45.5%), vascular disease (83.4% vs 56.6%), and diabetes (84.1% vs 47.2%). In the 200 expert-annotated notes, the RAG approach achieved high performance for various risk factors, with AUROCs ranging from 0.96 to 0.98 for hypertension, diabetes, and age ≥75 years. Incorporating risk factors identified by RAG increased CHA2DS2-VASc scores compared with using structured data alone. An LLM-optimized RAG can accurately extract CHA2DS2-VASc risk factors from unstructured clinical notes in AF patients. This approach can enable computable risk assessment and guide appropriate anticoagulation therapy.

Abstract A004: Validation of the PREDICT breast version 3.0 prognostic tool in the US breast cancer patients

Abstract PREDICT Breast v3 is the latest version of a prognostic tool designed to predict the treatment responses for early invasive breast cancer patients. It was developed using data from approximately 35,000 women diagnosed between 2000 and 2018 in the United Kingdom. However, its performance in the United States (US) population is unknown. This study aims to validate PREDICT Breast v3 using the newly released Surveillance, Epidemiology, and End Results (SEER) outcome data for US breast cancer patients and to address potential health disparities. We selected over 860,000 female patients diagnosed with primary breast cancer between 2000 and 2021 and followed for at least 5 years from the SEER database. The model’s performance was measured by calibration and discrimination; comparing predicted and observed 5-, 10- and 15-year breast cancer-specific survival outcomes and determining discrimination through the area under the receiver-operator curves (AUC). PREDICT Breast v3 demonstrated good calibration and discrimination for both short- and long-term up breast cancer-specific mortality in US populations. The predicted 10-year breast cancer-specific mortality differed from observed by 11% in ER-positive and 6 % in ER-negative patients. The AUCs for 15-year breast cancer-specific mortality were 0.81 for ER-positive patients and 0.76 for ER-negative patients. When stratified by race and ethnicity, the model showed strong performance in Non-Hispanic Asians ER-positive patients, despite being originally developed based on the UK population. These results are consistent with previous validations in Malaysia, Japan, and other Asian countries for PREDICT Breast v2. However, the model poorly estimated the number of deaths in Non-Hispanic Black individuals for both ER-positive and ER-negative. In conclusion, this study marks the first validation of PREDICT Breast v3 in the US and demonstrates that it is a reliable and generalizable tool, capable of providing longer term follow-up time up to 15 years for a wide and diverse population. Citation Format: Yi-Wen Hsiao, Paul Pharaoh, Pei-Chen Peng. Validation of the PREDICT breast version 3.0 prognostic tool in the US breast cancer patients [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A004.

Utility of the Neutrophil to Lymphocyte Ratio for Predicting Mortality in Pleural Empyema - A Retrospective Study

Purpose: The prognostic qualities of the hematological biomarker neutrophil to lymphocyte ratio (NLR) have not yet been evaluated in pleural empyema. Therefore, we aimed to find if NLR can predict adverse outcome in such clinical setting. Methods: Retrospectively we studied 84 patients with pleural empyema who were operated in emergency setting in a clinic of thoracic surgery of an academic hospital over a 34-month period (01.2021- 10.2023). To assess the prognostic performance of NLR we used the area under the receiver operating characteristics (AUROC) curves. Results: Of a total of 84 patients, nine (10.7%) died. Using ROC Curve analysis we found that NLR has an excellent prognostic ability and outperformed systemic immune inflammation index (SII), platelet to lymphocyte ratio (PLR), quick- sequential organ failure (qSOFA) score and systemic inflammation response syndrome (SIRS) (AUROC = 0.904 vs 0.782 vs 0.749 vs 0.747 vs 0.676, respectively) in outcome prediction. An optimal threshold NLR &gt; 9.88 x 109 /L for prognostication of death was identified with a sensitivity of 85.7% and a specificity of 83.6%. Conclusion: In pleural empyema the neutrophil to lymphocyte ratio demonstrates excellent ability to predict the unfavorable outcome.

Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography

PurposeTo develop a deep learning-based algorithm that automatically and accurately classifies patients as either having pulmonary emboli or not in CT pulmonary angiography (CTPA) examinations. Materials and methodsFor model development, 700 CTPA examinations from 652 patients performed at a single institution were used, of which 149 examinations contained 1497 PE traced by radiologists. The nnU-Net deep learning-based segmentation framework was trained using 5-fold cross-validation. To enhance classification, we applied logical rules based on PE volume and probability thresholds. External model evaluation was performed in 770 and 34 CTPAs from two independent datasets. ResultsA total of 1483 CTPA examinations were evaluated. In internal cross-validation and test set, the trained model correctly classified 123 of 128 examinations as positive for PE (sensitivity 96.1 %; 95 % C.I. 91–98 %; P < .05) and 521 of 551 as negative (specificity 94.6 %; 95 % C.I. 92–96 %; P < .05), achieving an area under the receiver operating characteristic (AUROC) of 96.4 % (95 % C.I. 79–99 %; P < .05). In the first external test dataset, the trained model correctly classified 31 of 32 examinations as positive (sensitivity 96.9 %; 95 % C.I. 84–99 %; P < .05) and 2 of 2 as negative (specificity 100 %; 95 % C.I. 34–100 %; P < .05), achieving an AUROC of 98.6 % (95 % C.I. 83–100 %; P < .05). In the second external test dataset, the trained model correctly classified 379 of 385 examinations as positive (sensitivity 98.4 %; 95 % C.I. 97–99 %; P < .05) and 346 of 385 as negative (specificity 89.9 %; 95 % C.I. 86–93 %; P < .05), achieving an AUROC of 98.5 % (95 % C.I. 83–100 %; P < .05). ConclusionOur automatic pipeline achieved beyond state-of-the-art diagnostic performance of PE in CTPA using nnU-Net for segmentation and volume- and probability-based post-processing for classification.

Peptide-Bound Glycative, AGE and Oxidative Modifications as Biomarkers for the Diagnosis of Alzheimer's Disease-A Feasibility Study.

Background: The diagnosis of Alzheimer's disease (AD) relies on core cerebrospinal fluid (CSF) biomarkers, amyloid beta (Aβ) and tau. As the brain is then already damaged, researchers still strive to discover earlier biomarkers of disease onset and the progression of AD. Glycation, advanced glycation end products (AGEs) and oxidative modifications on proteins in CSF mirror the underlying biological mechanisms that contribute to early AD pathology. However, analyzing free AGEs in the body fluids of AD patients has led to controversial results. Thus, this pilot study aimed to test the feasibility of detecting, identifying and quantifying differentially glycated, AGE or oxidatively modified peptides in CSF proteins of AD patients (n = 5) compared to a control group (n = 5). Methods: To this end, we utilized a data-dependent (DDA) nano liquid chromatography (LC) linear ion trap-Orbitrap tandem mass spectrometry (MS/MS) ) approach and database search that included over 30 glycative and oxidative modifications in four search nodes to analyze endogenous modifications on individual peptides. Furthermore, we quantified candidate peptide abundance using LC Quan. Results: We identified 299 sites of early and advanced glycation and 53 sites of oxidatively modified tryptophan. From those, we identified 17 promising candidates as putative biomarkers (receiver operating curve-area under the curve (ROC-AUC) > 0.8), albeit without statistical significance. Conclusions: The potential candidates with higher discrimination power showed correlations with established diagnostic markers, thus hinting toward the potential of those peptides as biomarkers.

Decoding machine learning in nursing research: A scoping review of effective algorithms.

The rapid evolution of artificial intelligence (AI) technology has revolutionized healthcare, particularly through the integration of AI into health information systems. This transformation has significantly impacted the roles of nurses and nurse practitioners, prompting extensive research to assess the effectiveness of AI-integrated systems. This scoping review focuses on machine learning (ML) used in nursing, specifically investigating ML algorithms, model evaluation methods, areas of focus related to nursing, and the most effective ML algorithms. The scoping review followed the Preferred Reporting Items for Systematic Review and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) guidelines. A structured search was performed across seven databases according to PRISMA-ScR: PubMed, EMBASE, CINAHL, Web of Science, OVID, PsycINFO, and ProQuest. The quality of the final reviewed studies was assessed using the Medical Education Research Study Quality Instrument (MERSQI). Twenty-six articles published between 2019 and 2023 met the inclusion and exclusion criteria, and 46% of studies were conducted in the US. The average MERSQI score was 12.2, indicative of moderate- to high-quality studies. The most used ML algorithm was Random Forest. The four second-most used were logistic regression, least absolute shrinkage and selection operator, decision tree, and support vector machine. Most ML models were evaluated by calculating sensitivity (recall)/specificity, accuracy, receiver operating characteristic (ROC), area under the ROC (AUROC), and positive/negative prediction value (precision). Half of the studies focused on nursing staff or students and hospital readmission or emergency department visits. Only 11 articles reported the most effective ML algorithm(s). The scoping review provides insights into the current status of ML research in nursing and recognition of its significance in nursing research, confirming the benefits of ML in healthcare. Recommendations include incorporating experimental designs in research studies to optimize the use of ML models across various nursing domains. The scoping review demonstrates substantial clinical relevance of ML applications for nurses, nurse practitioners, administrators, and researchers. The integration of ML into healthcare systems and its impact on nursing practices have important implications for patient care, resource management, and the evolution of nursing research.

Development and validation of machine learning models for predicting cancer-related fatigue in lymphoma survivors

BackgroundNew cases of lymphoma are rising, and the symptom burden, like cancer-related fatigue (CRF), severely impacts the quality of life of lymphoma survivors. However, clinical diagnosis and treatment of CRF are inadequate and require enhancement. ObjectiveThe main objective of this study is to construct machine learning-based CRF prediction models for lymphoma survivors to help healthcare professionals accurately identify the CRF population and better personalize treatment and care for patients. MethodsA cross-sectional study in China recruited lymphoma patients from June 2023 to March 2024, dividing them into two datasets for model construction and external validation. Six machine learning algorithms were used in this study: Logistic Regression (LR), Random Forest, Single Hidden Layer Neural Network, Support Vector Machine, eXtreme Gradient Boosting, and Light Gradient Boosting Machine (LightGBM). Performance metrics like the area under the receiver operating characteristic (AUROC) and calibration curves were compared. The clinical applicability was assessed by decision curve, and Shapley additive explanations was employed to explain variable significance. ResultsCRF incidence was 40.7 % (dataset I) and 44.8 % (dataset II). LightGBM showed strong performance in training and internal validation. LR excelled in external validation with the highest AUROC and best calibration. Pain, total protein, physical function, and sleep disturbance were important predictors of CRF. ConclusionThe study presents a machine learning-based CRF prediction model for lymphoma patients, offering dynamic, data-driven assessments that could enhance the development of automated CRF screening tools for personalized management in clinical practice.