Traditional Clinical Factors Research Articles

I-SIRch: AI-powered concept annotation tool for equitable extraction and analysis of safety insights from maternity investigations

BackgroundMaternity care is a complex system involving treatments and interactions between patients, healthcare providers, and the care environment. To enhance patient safety and outcomes, it is crucial to understand the human factors (e.g. individuals' decisions, local facilities) influencing healthcare. However, most current tools for analysing healthcare data focus only on biomedical concepts (e.g. health conditions, procedures and tests), overlooking the importance of human factors. MethodsWe developed a new approach called I-SIRch, using artificial intelligence to automatically identify and label human factors concepts in maternity investigation reports describing adverse maternity incidents produced by England's Healthcare Safety Investigation Branch (HSIB). These incident investigation reports aim to identify opportunities for learning and improving maternal safety across the entire healthcare system. Unlike existing clinical annotation tools that extract solely biomedical insights, I-SIRch is uniquely designed to capture the socio-technical dimensions of patient safety incidents. This innovation enables a more comprehensive analysis of the complex systemic issues underlying adverse events in maternity care, providing insights that were previously difficult to obtain at scale. Importantly, I-SIRch employs a hybrid approach, incorporating human expertise to validate and refine the AI-generated annotations, ensuring the highest quality of analysis. FindingsI-SIRch was trained using real data and tested on both real and synthetic data to evaluate its performance in identifying human factors concepts. When applied to real reports, the model achieved a high level of accuracy, correctly identifying relevant concepts in 90% of the sentences from 97 reports (Balanced Accuracy of 90% ± 18% (Recall 93% ± 18%, Precision 87% ± 34%, F-score 96% ± 10%). Applying I-SIRch to analyse these reports revealed that certain human factors disproportionately affected mothers from different ethnic groups. In particular, gaps in risk assessment were more prevalent for minority mothers, whilst communication issues were common across all groups but potentially more for minorities. InterpretationOur work demonstrates the potential of using automated tools to identify human factors concepts in maternity incident investigation reports, rather than focusing solely on biomedical concepts. This approach opens up new possibilities for understanding the complex interplay between social, technical and organisational factors influencing maternal safety and population health outcomes. By taking a more comprehensive view of maternal healthcare delivery, we can develop targeted interventions to address disparities and improve maternal outcomes. Targeted interventions to address these disparities could include culturally sensitive risk assessment protocols, enhanced language support, and specialised training for healthcare providers on recognising and mitigating biases. These findings highlight the need for tailored approaches to improve equitable care delivery and outcomes in maternity services. The I-SIRch framework thus represents a significant advancement in our ability to extract actionable intelligence from healthcare incident reports, moving beyond traditional clinical factors to encompass the broader systemic issues that impact patient safety.

Abstract 4114417: Polygenic Risk in Heart Failure – Evaluating the Ability of a Polygenic Risk Score to Identify Risk of Future Heart Failure Events in 60,000 Patients from 6 TIMI Randomized Trials

Background: The ability of polygenic risk scores (PRS) to predict heart failure (HF) beyond classic risk factors is unclear. Aims: To evaluate the risk of a HF PRS with incident hospitalization for HF (HHF) in patients with established cardiovascular disease. Methods: We analyzed a 59 SNP HF PRS (HERMES collaboration, Henry et al) in genotyped patients from six multinational TIMI randomized controlled trials (DECLARE, ENGAGE AF, FOURIER, PEGASUS, SAVOR, SOLID). Patients were stratified to low (quintile, Q1), intermediate (Q2-Q4), or high (Q5) genetic risk. We investigated the association of the HF PRS with incident HHF (median of 2.5 years) i) stratified by prior HF, and ii) across NTproBNP concentrations at baseline, using Cox-proportional hazard models. Results are reported as HR [95% CI], per 1-SD or with Q1 as a reference, and adjusted for ancestry (principal components 1-5), age, sex, trial, BMI, smoking, systolic BP, prior CAD, DM, AF, and eGFR. Results: In 59,906 pts (median age 66 years; 71% male; 26% prior HF), the HF PRS was associated with incident HHF (HR adj per 1-SD 1.08 [1.03, 1.13], p<0.001). Compared to low genetic risk pts, the HR adj for HHF was 1.12 [1.00, 1.26] in intermediate and 1.17 [1.02, 1.35] in high-risk pts. There were significant interactions between the HF PRS and prior HF (P int 0.001), and NTproBNP (P int 0.038), respectively. In pts without prior HF (Fig A), compared to low-risk pts, the risk was increased in high- (HR adj 1.56 [1.25, 1.94], p<0.001) and intermediate-risk pts (HR adj 1.27 [1.05, 1.54], p=0.013). In contrast, there was no significant association in pts with known HF at baseline ( Fig B ). Similarly, the HF PRS was significantly associated with HHF in pts with low but not elevated NTproBNP at baseline ( Fig C ). Conclusion: Our study confirms the role of polygenic risk for HF and demonstrates that a 59 SNP PRS can identify pts at increased risk of future HF events beyond traditional clinical factors, specifically in patients without established HF or elevated NTproBNP. These findings suggest a potential application of a HF PRS for screening and early identification of pts at increased risk for HF.

Yield of Coronary Assessment in Sustained Monomorphic Ventricular Tachycardia

Coronary assessment is frequently conducted in patients with sustained monomorphic ventricular tachycardia (SMVT); however, its yield and subsequent treatment implications remain unclear. This study aimed to determine the prevalence of coronary artery disease (CAD) in patients presenting with SMVT, factors influencing clinician referral for coronary assessment, and clinical outcomes based on revascularisation or medical management of CAD. Consecutive patients presenting with acute SMVT requiring inpatient admission between 2017 and 2022 were identified. A total of 249 individual patients with SMVT were identified, with 140 undergoing coronary assessment. Referral for coronary assessment was driven by chest pain (p<0.001) and increased troponin kinetics (p<0.001). No patient with SMVT had an acute coronary occlusion. Significant CAD was found in 48 (34%) patients, and traditional ischaemic features did not predict significant CAD. Nineteen (40%) patients with significant CAD underwent revascularisation (n=15 percutaneous coronary intervention, n=4 coronary artery bypass grafting). There was no significant difference in time to ventricular tachycardia (VT) recurrence between revascularised and medically managed CAD (hazard ratio 1.670; 95% confidence interval 0.756-3.687; p=0.199). A total of five of six patients who underwent a revascularisation-only strategy (no upfront antiarrhythmic therapy or ablation) had VT recurrence (median time to recurrence 8.9 months). Despite being frequently performed, coronary assessment in SMVT has only modest yield, with no patients having an acute coronary occlusion. Traditional clinical factors of ischaemia did not improve this yield. Revascularisation alone did not improve freedom from VT.

Incremental prognostic value of cardiovascular magnetic resonance imaging in patients with severe LV dysfunction undergoing coronary artery bypass grafting.

Coronary artery disease (CAD) remains a significant global health issue, particularly when complicated by left ventricular ejection fraction (LVEF) < 35%. Although coronary artery bypass grafting (CABG) is recommended for such cases, the unclear prognosis necessitates further investigation. This retrospective study aimed to determine whether cardiovascular magnetic resonance (CMR) imaging provides additional prognostic value in guiding effective clinical management. The study included patients with CAD and LVEF < 35% who underwent CABG surgery after enhanced CMR between March 2016 and March 2023. CMR was performed using a 3.0T scanner with steady-state free precession and phase-sensitive inversion recovery sequences. Prognostic analysis of clinical and CMR data was conducted, with the endpoint defined as cardiovascular death, revascularization, hospitalization for heart failure, or stroke. Statistical analysis included Student's t-test, chi-squared test, univariate and multivariate Cox regression analysis, receiver operating characteristic analysis, Harrell C statistical analysis, integrated discrimination improvement (IDI), and net reclassification improvement (NRI) analysis. The study included 152 patients (mean age 58.6 ± 9.7 years; 138 men). During a mean follow-up of 2.0 years, 8 patients experienced cardiovascular death, while 1 case had revascularization, 13 had hospitalization for heart failure, and 11 had a stroke. Left atrial diameter index (LADi) (hazard ratio [HR], 1.08 [95% confidence interval (CI): 1.02-1.15]; P = 0.04) and late gadolinium enhancement (LGE) mass (HR, 1.03 [95% CI: 1.01-1.06]; P < 0.001) were associated with the endpoint, even after adjusting for multiple clinical variables. Adding LADi and LGE mass improved risk prediction for adverse events, as indicated by the C-index (0.738, p < 0.01), IDI (0.36), and NRI (0.13). Left atrial diameter index (LADi) and scar burden are valuable prognostic indicators in patients with LVEF < 35% undergoing CABG. They offer enhanced risk stratification beyond traditional clinical factors, highlighting their importance in guiding clinical management.

Integration of Patient Reported Quality-of-life Data into Risk Assessment in Heart Failure

Optimal management of outpatients with heart failure (HF) requires serially updating the estimates of their risk for adverse clinical outcomes to guide treatment. Patient-reported outcomes (PROs) are becoming increasingly used in clinical care. The purpose of this study was to determine whether the inclusion of PROs can improve the risk prediction for HF hospitalization and death in ambulatory patients with HF. We included consecutive patients with HF with reduced ejection fraction (HFrEF) and HF with preserved EF (HFpEF) seen in a HF clinic between 2015 and 2019 who completed PROs as part of routine care. Cox regression with a least absolute shrinkage and selection operator regularization and gradient boosting machine analyses were used to estimate risk for a combined outcome of HF hospitalization, heart transplant, left ventricular assist device implantation, or death. The performance of the prediction models was evaluated with the time-dependent concordance index (Cτ). Among 1165 patients with HFrEF (mean age 59.1 ± 16.1, 68% male), the median follow-up was 487 days. Among 456 patients with HFpEF (mean age 64.2 ± 16.0 years, 55% male) the median follow-up was 494 days. Gradient boosting regression that included PROs had the best prediction performance - Cτ 0.73 for patients with HFrEF and 0.74 in patients with HFpEF, and showed very good stratification of risk by time to event analysis by quintile of risk. The Kansas City Cardiomyopathy Questionnaire overall summary score, visual analogue scale and Patient Reported Outcomes Measurement Information System dimensions of satisfaction with social roles and physical function had high variable importance measure in the models. PROs improve risk prediction in both HFrEF and HFpEF, independent of traditional clinical factors. Routine assessment of PROs and leveraging the comprehensive data in the electronic health record in routine clinical care could help more accurately assess risk and support the intensification of treatment in patients with HF.

T2DM/CKD genetic risk scores and the progression of diabetic kidney disease in T2DM subjects

This study aimed at understanding the predictive potential of genetic risk scores (GRS) for diabetic kidney disease (DKD) progression in patients with type 2 diabetes mellitus (T2DM) and Major Cardiovascular Events (MCVE) and All-Cause Mortality (ACM) as secondary outcomes. We evaluated 30 T2DM and CKD GWAS-derived single nucleotide polymorphisms (SNPs) and their association with clinical outcomes in a central European cohort (n = 400 patients). Our univariate Cox analysis revealed significant associations of age, duration of diabetes, diastolic blood pressure, total cholesterol and eGFR with progression of DKD (all P < 0.05). However, no single SNP was conclusively associated with progression to DKD, with only CERS2 and SHROOM3 approaching statistical significance. While a single SNP was associated with MCVE − WSF1 (P = 0.029), several variants were associated with ACM − specifically CANCAS1, CERS2 and C9 (all P < 0.02). Our GRS did not outperform classical clinical factors in predicting progression to DKD, MCVE or ACM. More precisely, we observed an increase only in the area under the curve (AUC) in the model combining genetic and clinical factors compared to the clinical model alone, with values of 0.582 (95 % CI 0.487–0.676) and 0.645 (95 % CI 0.556–0.735), respectively. However, this difference did not reach statistical significance (P = 0.06).This study highlights the complexity of genetic predictors and their interplay with clinical factors in DKD progression. Despite the promise of personalised medicine through genetic markers, our findings suggest that current clinical factors remain paramount in the prediction of DKD. In conclusion, our results indicate that GWAS-derived GRSs for T2DM and CKD do not offer improved predictive ability over traditional clinical factors in the studied Czech T2DM population.

Hepatic-associated vascular morphological assessment to predict overt hepatic encephalopathy before TIPS: a multicenter study

BackgroundTo provide patients the chance of accepting curative transjugular intrahepatic portosystemic shunt (TIPS) rather than palliative treatments for portal hypertension-related variceal bleeding and ascites, we aimed to assess hepatic-associated vascular morphological change to improve the predictive accuracy of overt hepatic encephalopathy (HE) risks.MethodsIn this multicenter study, 621 patients undergoing TIPS were subdivided into training (413 cases from 3 hospitals) and external validation datasets (208 cases from another 3 hospitals). In addition to traditional clinical factors, we assessed hepatic-associated vascular morphological changes using maximum diameter (including absolute and ratio values). Three predictive models (clinical, hepatic-associated vascular, and combined) were constructed using logistic regression. Their discrimination and calibration were compared to test the necessity of hepatic-associated vascular assessment and identify the optimal model. Furthermore, to verify the improved performance of ModelC−V, we compared it with four previous models, both in discrimination and calibration.ResultsThe combined model outperformed the clinical and hepatic-associated vascular models (training: 0.814, 0.754, 0.727; validation: 0.781, 0.679, 0.776; p < 0.050) and had the best calibration. Compared to previous models, ModelC−V showed superior performance in discrimination. The high-, middle-, and low-risk populations displayed significantly different overt HE incidence (p < 0.001). Despite the limited ability of pre-TIPS ammonia to predict overt HE risks, the combined model displayed a satisfactory ability to predict overt HE risks, both in the low- and high-ammonia subgroups.ConclusionHepatic-associated vascular assessment improved the predictive accuracy of overt HE, ensuring curative chances by TIPS for suitable patients and providing insights for cirrhosis-related studies.Graphical

Incremental value of high-risk CMR attributes to predict adverse remodeling after ST-segment elevation myocardial infarction across LVEF categories

BackgroundA couple of cardiac magnetic resonance (CMR) attributes strongly predict adverse remodeling after ST-segment elevation myocardial infarction (STEMI); however, the value of incorporating high-risk CMR attributes, particularly, in patients with non-reduced ejection fraction, remains undetermined. This study sought to evaluate the independent and incremental predictive value of a multiparametric CMR approach for adverse remodeling after STEMI across left ventricular ejection fraction (LVEF) categories. MethodsA total of 157 patients with STEMI undergoing primary percutaneous coronary intervention were prospectively enrolled. Adverse remodeling was defined as ≥20% enlargement in left ventricular end-diastolic volume from index admission to 3 months of follow-up. ResultsAdverse remodeling occurred in 23.6% of patients. After adjustment for clinical risk factors, a stroke volume index <29.6 mL/m2, a global longitudinal strain >−7.5%, an infarct size >39.2%, a microvascular obstruction >4.9%, and a myocardial salvage index <36.4 were independently associated with adverse remodeling. The incidence of adverse remodeling increased with the increasing number of high-risk CMR attributes, regardless of LVEF (LVEF ≤ 40%: P = 0.026; 40% < LVEF < 50%: P = 0.001; LVEF ≥ 50%: P < 0.001). The presence of ≥4 high-risk attributes was an independent predictor of LV adverse remodeling (70.0% vs. 16.8%, adjusted OR 9.68, 95 CI% 3.25–28.87, P < 0.001). Furthermore, the number of high-risk CMR attributes had an incremental predictive value over reduced LVEF and baseline clinical risk factors (AUC: 0.81 vs. 0.68; P = 0.002). ConclusionsHigh-risk CMR attributes showed a significant association with adverse remodeling after STEMI across LVEF categories. This imaging-based model provided incremental value for adverse remodeling over traditional clinical factors and LVEF.

Predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma using deep learning.

The aim of this study is to design a deep learning (DL) model to preoperatively predict the occurrence of central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC). This research collected preoperative ultrasound (US) images and clinical factors of 611 PTMC patients. The clinical factors were analyzed using multivariate regression. Then, a DL model based on US images and clinical factors was developed to preoperatively predict CLNM. The model's efficacy was evaluated using the receiver operating characteristic (ROC) curve, along with accuracy, sensitivity, specificity, and the F1 score. The multivariate analysis indicated an independent correlation factors including age ≥55 (OR = 0.309, p < 0.001), tumor diameter (OR = 2.551, p = 0.010), macrocalcifications (OR = 1.832, p = 0.002), and capsular invasion (OR = 1.977, p = 0.005). The suggested DL model utilized US images achieved an average area under the curve (AUC) of 0.65, slightly outperforming the model that employed traditional clinical factors (AUC = 0.64). Nevertheless, the model that incorporated both of them did not enhance prediction accuracy (AUC = 0.63). The suggested approach offers a reference for the treatment and supervision of PTMC. Among three models used in this study, the deep model relied generally more on image modalities than the data modality of clinic records when making the predictions.

P915 Multi-Omics Biomarkers for the Prediction of Response to Biologics in Patients with Inflammatory Bowel Disease

Abstract Background The treatment concept for inflammatory bowel disease (IBD) has been transformed with biologics now recommended as the first-line therapy for moderate-to-severe patients. However, the significant heterogeneity among IBD patients has limited the efficacy of selected biologics based on traditional clinical factors. Therefore, it is imperative to molecularly stratify patients to match them with the most appropriate biologics. In this study, we systematically reviewed baseline omics biomarkers that have the potential to predict response to biological therapies, aiming to facilitate precision medicine in IBD. Methods We conducted a comprehensive literature search using PubMed by which we included studies that explore the role of omics biomarkers in predicting the efficacy of various biologics including anti-TNFα, anti-integrin, anti-IL-12/23P40 and anti-IL-23 P19 in patients with IBD. Results Our review included 110 studies. Of these, 86 studies focused on anti-TNFα, 17 focused on anti-integrin and 7 focused on anti-IL-12/23P40 and/or anti-IL-23P19. These studies investigated multi-levels baseline biomarkers, including genomics, transcriptomics (bulk RNA and sc-RNA sequence), proteomics, microbiome, and metabolomics (derived from serum, urine, or stool). Furthermore, recent studies already focused on integrating multiple omics analysis and showed that the predictive model based on multi-omics data could significantly enhance their performance. Among the available biomarkers, mucosal transcription of OSM (AUROC = 0.83), IL-13RA2 (AUROC = 0.90), and TREM-1 transcription in mucosal biopsy (AUROC = 0.77) as well as in PBMC ( AUROC varies between 0.78 and 0.94) could accurately predict the response to anti-TNFα. The mucosal IL-23A transcription could discriminate responders from non-responders to anti-IL-12/23P40 with an AUROC of 0.90. OSM, biomarkers of intestinal collagen turnover like C4M, IL-17, IL-22, and TNFα in serum also showed significant potential in predicting the response to anti-TNFα, anti-integrin and anti-IL-12/23P40. In addition, single-cell molecular signatures with sc-RNA sequencing provided more profound insights into predicting the response to biologics. The lack of reproducibility in results across different groups may be due to the disparity in patient selection, methodology, and study designs among different investigations. Conclusion Numerous omics markers have shown great potential in predicting the efficacy of biologics. However, it is crucial to explore and validate these novel biomarkers in larger cohorts using harmonized protocols to facilitate their evaluation into actual clinical practice, especially for newer biologics like anti-IL-12/23P40 and anti-IL-23P19.

Comparative Analysis of Tumor Microbiome, Molecular Profile and Immune Cell Abundance by HPV Status in Head and Neck Cancers and Their Impact on Survival

Traditional clinical and molecular prognostic factors offer valuable insight into the heterogeneous natural history and treatment response of head and neck squamous cell carcinoma (HNSCC) yet fail to explain the full spectrum of observed variability. The tumor microenvironment (TME), comprising microbiome and immune cells can impact treatment response and prognosis. We analyzed The Cancer Genome Atlas (TCGA) to evaluate the association of specific microbes and genes in TME with survival and their differential expression in HPV positive (+) and HPV negative (-) HNSCC. HNSCC RNA sequencing (RNAseq) samples from TCGA were processed through the Exogenous sequencing in Tumors and Immune Cells (ExoTIC) pipeline to identify gene expression and microbial presence. HPV status was assessed by detection of papillomaviridae family of microbes. Clinical data from TCGA was extracted to compare overall survival (OS) and control for competing variables using Cox proportional hazards regression. Difference in immune cell abundance was evaluated by Kruskal-Wallis test. All statistical analysis was performed using R. A total of 498 RNAseq samples from TCGA were analyzed. Oral cavity, oropharynx, hypopharynx, and larynx tumors comprised 21.6%, 15%, 1.8%, and 22.2% of specimens, respectively. HPV was detected in 111 patients (22%), most commonly Alpha papillomavirus 9 (90.1%). Of the 5838 enriched microbes, 330 were significantly associated with OS after controlling for tumor stage, smoking, and age. Specifically, the presence of Alpha papillomavirus 9 was associated with significantly improved OS [adjusted HR = 0.60 (95% CI 0.40 - 0.89, p = 0.01)]. Microbial species found in more abundance in HPV- tumors included Citrobacter farmeri, Thermoanaerobacter kivui and Yersinia pestis which are gram negative anaerobes. Genes related to cellular transport and DNA repair were enriched while genes related to proliferation (e.g., SAGE1) were depleted in HPV+ samples. HPV- tumors had a significantly higher number of M0 (p < 0.001) and M2 macrophages (p = 0.035) while HPV+ tumors had more T regulatory cells (p < 0.001) and CD8+ T-cells (p < 0.001). Tumor microenvironment was significantly associated with survival for HNSCC patients, with particular microbes such as Alpha papillomavirus 9 correlating with improved OS. Greater abundance of certain anaerobic microbes was seen in HPV- tumors. These findings suggest TME can be used to predict patient outcomes and potentially guide personalized treatment approaches. We found an abundance of M0 and M2 macrophages in HPV- tumors, which are considered pro-tumorigenic, while anti-tumor M1 macrophages were similar in the two groups. This may help identify mechanism of resistance to immunotherapies and tailor novel immunotherapy combinations in specific patient subgroups. With further prospective research and external validation these findings have the potential to significantly impact the way we treat HNSCC in the future.

Association of hemoglobin glycation index with prognosis of coronary artery disease after percutaneous coronary intervention: A retrospective cohort study.

To analyze the association between hemoglobin glycation index (HGI) and the long-term prognosis of patients with coronary artery disease (CAD) after percutaneous coronary intervention (PCI). Predicted glycated hemoglobin (HbA1c) level was calculated using an established formula and HGI represented the difference between laboratory measured HbA1c and predicted HbA1c. A total of 1780 patients were stratified into three subgroups (HGI < -0.4, -0.4 ≦ HGI < 0.12 and HGI ≧ 0.12). The primary endpoints included all-cause mortality (ACM) and cardiac mortality (CM). The secondary endpoints were major adverse cardiac events (MACEs) and major adverse cardiac and cerebrovascular events (MACCEs). ACM occurred in 54 patients: 22 (3.7) in the low-HGI subgroup, 8 (1.3) in the moderate-HGI subgroup and 24 (4.1) in the high-HGI subgroup (p = .012). After adjusting for the traditional clinical prognostic factors, multivariate Cox regression analysis showed that patients in both the low and high HGI subgroups had significantly increased risk of ACM as compared with patients in the moderate HGI subgroup (hazard ratio [HR] = 4.979, 95% confidence interval [CI]: 1.865-13.297, p = .001 and HR = 2.918, 95% CI: 1.075-7.922, p = .036). However, we did not find significant differences in the incidence of CM, MACEs and MACCEs. HGI can predicts risk for long-term mortality in patients undergoing PCI. This index could be helpful for the effective clinical management of the CAD population.

Construction of Ovarian Cancer Prognostic Model Based on the Investigation of Ferroptosis-Related lncRNA.

(1) Background: Ovarian cancer (OV) has the high mortality rate among gynecological cancers worldwide. Inefficient early diagnosis and prognostic prediction of OV leads to poor survival in most patients. OV is associated with ferroptosis, an iron-dependent form of cell death. Ferroptosis, believed to be regulated by long non-coding RNAs (lncRNAs), may have potential applications in anti-cancer treatments. In this study, we aimed to identify ferroptosis-related lncRNA signatures and develop a novel model for predicting OV prognosis. (2) Methods: We downloaded data from The Cancer Genome Atlas (TCGA), Genotype-Tissue Expression, and Gene Expression Omnibus (GEO) databases. Prognostic lncRNAs were screened by least absolute shrinkage and selection operator (LASSO)-Cox regression analysis, and a prognostic model was constructed. The model's predictive ability was evaluated by Kaplan-Meier (KM) survival analysis and receiver operating characteristic (ROC) curves. The expression levels of these lncRNAs included in the model were examined in normal and OV cell lines using quantitative reverse transcriptase polymerase chain reaction. (3) Results: We constructed an 18 lncRNA prognostic prediction model for OV based on ferroptosis-related lncRNAs from TCGA patient samples. This model was validated using TCGA and GEO patient samples. KM analysis showed that the prognostic model was able to significantly distinguish between high- and low-risk groups, corresponding to worse and better prognoses. Based on the ROC curves, our model shows stronger prediction precision compared with other traditional clinical factors. Immune cell infiltration, immune checkpoint expression levels, and Tumor Immune Dysfunction and Exclusion analyses are also insightful for OV immunotherapy. (4) Conclusions: The prognostic model constructed in this study has potential for improving our understanding of ferroptosis-related lncRNAs and providing a new tool for prognosis and immune response prediction in patients with OV.

OBINUTUZUMAB FOR THE TREATMENT OF CHRONIC LYMPHOCYTIC LEUKEMIA PATIENTS: SINGLE CENTER EXPERIENCE

Monoclonal antibodies (mAbs) targeting CD20 molecule on B lymphocyte are of great importance in the treatment of B-cell malignancies. In recent years a great effort has been put in developing novel mAbs that can provide greater efficacy than the well-known rituximab. A second class of mAbs obinutuzumab has been presented as a more powerful tool in the treatment of this group of patients. In this retrospective study 70 patients with symptomatic CLL were included. CLL patients were diagnosed and treated at the University Clinic for Hematology between January 2018 and January 2022. All patients were evaluated for traditional clinical and laboratory prognostic factors and newer prognostic factors including IGHV mutation status and CLL prognostic and predictive genetic abnormalities. Most of the patients treated with obinutuzumab had Binet B stage (56%). Mutational status of the immunoglobulin variable region heavy chain (IGHV) in most of CLL patients treated with obinutuzumab was unmated IGHV gene. The most frequently encountered adverse events were tumor lysis syndrome and leukopenia. The analysis of the initial results of the application of obinutuzumab-based therapy allows us to conclude that this therapeutical modality is not associated with severe adverse events that would limit the administration of therapy.

Development and validation of a prognostic 9-gene signature for colorectal cancer.

Colorectal cancer (CRC) is one of the most prevalent cancers globally with a high mortality rate. Predicting prognosis using disease progression and cancer pathologic stage is insufficient, and a prognostic factor that can accurately evaluate patient prognosis needs to be developed. In this study, we aimed to infer a prognostic gene signature to identify a functional signature associated with the prognosis of CRC patients. First, we used univariate Cox regression, least absolute shrinkage and selection operator (lasso) regression, and multivariate Cox regression analyses to screen genes significantly associated with CRC patient prognosis, from colorectal cancer RNA sequencing data in The Cancer Genome Atlas (TCGA) database. We then calculated the risk score (RS) for each patient based on the expression of the nine candidate genes and developed a prognostic signature. Based on the optimal cut-off on the receiver operating characteristic (ROC) curve, patients were separated into high- and low-risk groups, and the difference in overall survival between the two groups was examined. Patients in the low-risk group had a better overall survival rate than those in the high-risk group. The results were validated using the GSE72970, GSE39582, and GSE17536 Gene Expression Omnibus (GEO) datasets, and the same conclusions were reached. ROC curve test of the RS signature also indicated that it had excellent accuracy. The RS signature was then compared with traditional clinical factors as a prognostic indicator, and we discovered that the RS signature had superior predictive ability. The RS signature developed in this study has excellent predictive power for the prognosis of patients with CRC and broad applicability as a prognostic indicator for patients.

Identification and validation of a lipid metabolism gene signature for predicting biochemical recurrence of prostate cancer after radical prostatectomy.

Pro5state cancer is one of the most commonly diagnosed cancers in men worldwide and biochemical recurrence occurs in approximately 25% of patients after radical prostatectomy. Current decisions regarding biochemical recurrence after radical prostatectomy are largely dependent on clinicopathological parameters, which are less accurate. A growing body of research suggests that lipid metabolism influences tumor development and treatment, and that prostate cancer is not only a malignancy but also a lipid metabolism disease. Therefore, this study aimed to identify the prognostic value of lipid metabolism-related gene signaling disease to better predict biochemical recurrence and contribute to clinical decision-making. Expression data and corresponding clinical information were obtained from The Cancer Genome Atlas (TCGA) database and the MSKCC database. Candidate modules closely associated with BCR were screened by univariate and LASSOcox regression analyses, and multivariate Cox regression analyses were performed to construct gene signatures. Kaplan-Meier (KM) survival analysis, time-dependent subject operating curves (ROC), independent prognostic analysis, and Nomogram were also used to assess the prognostic value of the signatures. In addition, Gene Ontology Analysis (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Gene Set Enrichment Analysis (GSEA) were used to explore potential biological pathways. A 6-gene lipid metabolism-related gene signature was successfully constructed and validated to predict biochemical recurrence in prostate cancer patients. In addition, we identified the 6-gene signature as an independent risk factor. Functional analysis showed that lipid metabolism-related genes were closely associated with arachidonic acid metabolism, PPAR transduction signaling pathway, fatty acid metabolism, peroxisome, and glycerophospholipid metabolism. Prognostic models were associated with immune cell infiltration. We have successfully developed a novel lipid metabolism-related gene signature that is highly effective in predicting BCR in patients with limited prostate cancer after RP and created a prognostic Nomogram. Furthermore, the signature may help clinicians to select high-risk subpopulations, predict patient survival, and facilitate more personalized treatment than traditional clinical factors.

Trimethyllysine, a trimethylamine N-oxide precursor, predicts the presence, severity, and prognosis of heart failure

Background and aimsIntestinal flora metabolites are associated with cardiovascular (CV) diseases including heart failure (HF). The carnitine precursor trimethyllysine (TML), which participates in the generation of the atherogenic-related metabolite trimethylamine N-oxide (TMAO), was found to be related to poor prognosis in patients with CV diseases. The aim of the present study was to examine the relationship between TML and stable chronic HF.Methods and resultsIn total, 956 subjects including 471 stable chronic HF and 485 non-HF patients were enrolled in the present cohort study and subjects with stable HF were followed up for 2.0 ± 1.1 years. Serum levels of TML and TMAO were measured by liquid chromatography mass spectrometry in tandem. TML levels were significantly elevated in patients with HF compared with non-HF patients and were positively correlated with N-terminal pro-brain natriuretic peptide (NTproBNP) levels (r = 0.448, P < 0.001). TML was associated with the presence of HF after adjusting for age, sex, complications, traditional clinical factors, and TMAO (tertile 3 (T3), adjusted odds ratio (OR) 1.93, 95% confidence interval (CI) 1.19–3.13, and P = 0.007). In patients with HF, increased TML levels were associated with a composite endpoint of CV death and HF hospitalization during follow-up (T3, adjusted hazard ratio (HR) 1.93, 95% CI 1.27–2.93, and P = 0.002). Increased TML levels indicated a higher risk of CV death, re-hospitalization, and all-cause mortality.ConclusionSerum TML levels were associated with the presence and severity of HF in all subjects. High levels of TML can indicate complications and poor prognosis in HF patients.

163P Development and validation of the prognostic HER2RI assay for predicting recurrence and survival in early HER2-positive breast cancer

HER2-positive accounts for 15-20% of breast cancers. Today the decision to escalate or de-escalate systemic therapy for early HER2-positive breast cancer is based primarily on traditional clinical factors, which are insufficient to reflect the molecular complexity and heterogeneity of HER2-positive breast cancer. Here we describe the development and validation of a new HER2RI assay, a model that combines expression data of 16 genes and clinical features to obtain risk values to predict the prognosis of early HER2-positive breast cancer.

DeepThy‐Net: A Multimodal Deep Learning Method for Predicting Cervical Lymph Node Metastasis in Papillary Thyroid Cancer

Papillary thyroid cancer (PTC) accounts for more than 80% of thyroid cancers, and ultrasound (US) imaging is the preferred method for the diagnosis of PTC. However, accurate prediction of different patterns of cervical lymph node metastasis (CLNM) in PTC continues to be a challenge. Herein, US images and clinical factors of PTC patients from three hospitals for more than 11 years are collected, and a multimodal deep learning model called DeepThy‐Net is then developed to predict different CLNM patterns. The proposed model not only uses the convolutional features extracted by deep learning but also integrates traditional clinical factors that are highly related to lymph node metastasis. Finally, the model is tested in two independent test sets, and the experimental results show that the area under curve (AUC) is between 0.870 and 0.905, indicating clinical applicability. The proposed method provides an important reference for the treatment and management of PTC. Moreover, for PTC cases involving an active surveillance strategy, the proposed method can serve as an important CLNM early warning tool.

Development and validation of a hypoxia-stemness-based prognostic signature in pancreatic adenocarcinoma.

Background: Pancreatic adenocarcinoma (PAAD) is one of the most aggressive and fatal gastrointestinal malignancies with high morbidity and mortality worldwide. Accumulating evidence has revealed the clinical significance of the interaction between the hypoxic microenvironment and cancer stemness in pancreatic cancer progression and therapies. This study aims to identify a hypoxia-stemness index-related gene signature for risk stratification and prognosis prediction in PAAD. Methods: The mRNA expression-based stemness index (mRNAsi) data of PAAD samples from The Cancer Genome Atlas (TCGA) database were calculated based on the one-class logistic regression (OCLR) machine learning algorithm. Univariate Cox regression and LASSO regression analyses were then performed to establish a hypoxia-mRNAsi-related gene signature, and its prognostic performance was verified in both the TCGA-PAAD and GSE62452 corhorts by Kaplan-Meier and receiver operating characteristic (ROC) analyses. Additionally, we further validated the expression levels of signature genes using the TCGA, GTEx and HPA databases as well as qPCR experiments. Moreover, we constructed a prognostic nomogram incorporating the eight-gene signature and traditional clinical factors and analyzed the correlations of the risk score with immune infiltrates and immune checkpoint genes. Results: The mRNAsi values of PAAD samples were significantly higher than those of normal samples (p < 0.001), and PAAD patients with high mRNAsi values exhibited worse overall survival (OS). A novel prognostic risk model was successfully constructed based on the eight-gene signature comprising JMJD6, NDST1, ENO3, LDHA, TES, ANKZF1, CITED, and SIAH2, which could accurately predict the 1-, 3-, and 5-year OS of PAAD patients in both the training and external validation datasets. Additionally, the eight-gene signature could distinguish PAAD samples from normal samples and stratify PAAD patients into low- and high-risk groups with distinct OS. The risk score was closely correlated with immune cell infiltration patterns and immune checkpoint molecules. Moreover, calibration analysis showed the excellent predictive ability of the nomogram incorporating the eight-gene signature and traditional clinical factors. Conclusion: We developed a hypoxia-stemness-related prognostic signature that reliably predicts the OS of PAAD. Our findings may aid in the risk stratification and individual treatment of PAAD patients.